Dr. Harold H. Szu Profile

Dr. Harold H. Szu

Senior Scientist at DEVCOM C5ISR

SPIE Involvement:

Track Chair | Author | Editor | Instructor

Area of Expertise:

Artificial Neural Networks , Dual Infrared Spectral Cancer Screening , Statistical Physics , Unsupervised Learning , Wavelets, ICA, Compressive Sampling , Image Video Processing

Profile Summary

Army NVESD MS/Human Signature Exploitation Ft. Belvoir, VA 22060 703-704-0532
• Fellow of American. Institute Medicine & BioEngineering 2004 for breast cancer passive spectrogram diagnoses.
• Fellow of IEEE (1997) for bi-sensor fusion;
• Foreign Academician, Russian Academy of Nonlinear Sciences, 1999, for unsupervised learning.
• Fellow of Optical Society America (1996) for adaptive wavelet
• Fellow of International Optical Engineering (SPIE since 1995) for neural nets.
• Fellow of INNS (2010) for a founding governor and former president of INNS
Dr. Szu has been a champion of brain-style computing for 2 decades; a founder, former president, and a current governor of International Neural Network Society (INNS), he received the INNS D. Gabor Award in 1997 “for outstanding contribution to neural network applications in information sciences and pioneer implementations of fast simulated annealing search,” and the Eduardo R. Caianiello Award in 1999 from the Italy Academy for “elucidating and implementing a chaotic neural net as a dynamic realization for fuzzy logic membership function.” Recently, he contributed to the unsupervised learning theory of the thermodynamic free energy of sensory pair for fusion. Because of this contribution, Dr. Szu is a foreign academician of Russian Academy of Nonlinear Sciences in 1999 for the unsupervised learning based on a homeostasis constant Cybernetic brain temperature. Recently, SPIE awarded him with the Nanoengineering Award and the Biomedical Wellness Engineering Award.
Besides 300 publications, a dozen patents, numerous books & journals, Dr. Szu taught students “how to be creative in interdisciplinary sciences” according to the Uhlenbeck’s Royal Dutch tradition and guided a dozen PhD students. His practice of the creativity is itemized as follows:
• Initiate Biomedical Wellness Engineering for the quality of life of aging societies.
• Promote Nano-Robot for high-yield Nanoengineering based on Nanosciences and Na

Publications (222)

Proceedings Article | 3 June 2016 Paper

Paper

Smart sensing surveillance video system

Charles Hsu, Harold Szu

Proceedings Volume 9871, 98710W (2016) https://doi.org/10.1117/12.2239982

KEYWORDS: Surveillance, Sensor networks, Sensing systems, Sensors, Image processing, Video, Feature extraction, Algorithm development, Smart sensors, Image sensors

Read Abstract +

Proceedings Article | 3 June 2016 Paper

Paper

3D MEMS sensor for application on earthquakes early detection and Nowcast

Jerry Wu, Jing Liang, Harold Szu

Proceedings Volume 9871, 98710X (2016) https://doi.org/10.1117/12.2239983

KEYWORDS: Earthquakes, Microelectromechanical systems, Sensors, Digital signal processing, Signal processing, Data processing, Filtering (signal processing), Gyroscopes, Seismic sensors, Electronic filtering

Read Abstract +

Proceedings Article | 3 June 2015 Paper

Paper

Optical display for radar sensing

Harold Szu, Charles Hsu, Jefferson Willey, Joseph Landa, Minder Hsieh, Louis Larsen, Alan Krzywicki, Binh Tran, Philip Hoekstra, John Dillard, Keith Krapels, Michael Wardlaw, Kai-Dee Chu

Proceedings Volume 9496, 94960G (2015) https://doi.org/10.1117/12.2176082

KEYWORDS: Microwave radiation, Radar, RGB color model, Scattering, Thermodynamics, Surveillance, Signal to noise ratio, Backscatter, Sensors, Neural networks

Read Abstract +

Proceedings Article | 3 June 2015 Paper

Paper

Spatially revolved high density electroencephalography

Jerry Wu, Harold Szu, Yuechen Chen, Ran Guo, Xixi Gu

Proceedings Volume 9496, 94960S (2015) https://doi.org/10.1117/12.2184655

KEYWORDS: Electroencephalography, Brain, Field programmable gate arrays, Digital signal processing, Signal to noise ratio, Electrodes, Neurons, Fourier transforms, Data processing, Magnetoencephalography

Read Abstract +

Proceedings Article | 2 June 2015 Paper

Paper

A new EEG measure using the 1D cluster variation method

Alianna Maren, Harold Szu

Proceedings Volume 9496, 949609 (2015) https://doi.org/10.1117/12.2184651

KEYWORDS: Electroencephalography, Thermodynamics, Sensors, Neural networks, Interfaces, Brain-machine interfaces, Data modeling, Neurons, Electrodes, Systems modeling

Read Abstract +

Proceedings Article | 2 June 2015 Paper

Paper

Hardware enhance of brain computer interfaces

Jerry Wu, Harold Szu, Yuechen Chen, Ran Guo, Xixi Gu

Proceedings Volume 9496, 94960T (2015) https://doi.org/10.1117/12.2184654

KEYWORDS: Electroencephalography, Brain, Field programmable gate arrays, Human-machine interfaces, Digital signal processing, Brain-machine interfaces, Image enhancement, Data processing, Head, Data analysis

Read Abstract +

Proceedings Article | 2 June 2015 Paper

Paper

Selective-imaging camera

Harold Szu, Charles Hsu, Joseph Landa, Jae H. Cha, Keith Krapels

Proceedings Volume 9496, 94960H (2015) https://doi.org/10.1117/12.2176093

KEYWORDS: Cameras, Black bodies, Brain, Neurons, Visualization, Thermodynamics, Sensing systems, RGB color model, Neural networks, Surveillance

Read Abstract +

Proceedings Article | 20 May 2015 Paper

Paper

Hypothesis on human eye perceiving optical spectrum rather than an image

Yufeng Zheng, Harold Szu

Proceedings Volume 9496, 94960F (2015) https://doi.org/10.1117/12.2180827

KEYWORDS: Cones, Retina, Eye, Neurons, Visualization, Retinal scanning, Rods, Fourier transforms, Visual process modeling, Nerve

Read Abstract +

Proceedings Article | 20 May 2015 Paper

Paper

Simulated annealing model of acupuncture

Charles Shang, Harold Szu

Proceedings Volume 9496, 94960U (2015) https://doi.org/10.1117/12.2185052

KEYWORDS: Algorithms, Annealing, Control systems, Clinical trials, Data modeling, Medicine, Lead, Clinical research, Systems modeling, Surgery

Read Abstract +

Proceedings Article | 20 May 2015 Paper

Paper

Bio-mining for biomarkers with a multi-resolution block chain

Jeffrey Jenkins, Jarad Kopf, Binh Tran, Christopher Frenchi, Harold Szu

Proceedings Volume 9496, 94960N (2015) https://doi.org/10.1117/12.2180648

KEYWORDS: Biometrics, Biomedical optics, Computer security, Sensors, Electroencephalography, Diagnostics, Databases, Data analysis, Data mining, Gold

Read Abstract +

In this paper, we discuss a framework for bridging the gap between security and medical Large Data Analysis (LDA) with functional- biomarkers. Unsupervised Learning for individual e-IQ & IQ relying on memory eliciting (i.e. scent, grandmother images) and IQ baseline profiles could further enhance the ability to uniquely identify and properly diagnose individuals. Sub-threshold changes in a common/probable biomedical biomarker (disorders) means that an individual remains healthy, while a martingale would require further investigation and more measurements taken to determine credibility. Empirical measurements of human actions can discover anomalies hidden in data, which point to biomarkers revealed through stimulus response. We review the approach for forming a single-user baseline having 1-d devices and a scale-invariant representation for N users each (i) having N*d(i) total devices. Such a fractal representation of human-centric data provides self-similar levels information and relationships which are useful for diagnosis and identification causality anywhere from a mental disorder to a DNA match. Biomarkers from biomedical devices offer a robust way to collect data. Biometrics could be envisioned as enhanced and personalized biomedical devices (e.g. typing fist), but used for security. As long as the devices have a shared context origin, useful information can be found by coupling the sensors. In the case of the electroencephalogram (EEG), known patterns have emerged in low frequency Delta Theta Alpha Beta-Gamma (DTAB-G) waves when an individual views a familiar picture in the visual cortex which is shown on EEGs as a sharp peak. Using brainwaves as a functional biomarker for security can lead the industry to create more secure sessions by allowing not only passwords but also visual stimuli and/or keystrokes coupled with EEG to capture and stay informed about real time user e-IQ/IQ data changes. This holistic Computer Science (CS) Knowledge Discovery in Databases, Data Mining (KDD, DM) approach seeks to merge the fields having a shared data origin - biomarkers revealed through stimulus response.

Proceedings Article | 20 May 2015 Paper

Paper

e-IQ and IQ knowledge mining for generalized LDA

Jeffrey Jenkins, Rutger van Bergem, Charles Sweet, Eveline Vietsch, Harold Szu

Proceedings Volume 9496, 94960C (2015) https://doi.org/10.1117/12.2180649

KEYWORDS: Data analysis, Computing systems, Machine learning, Binary data, Data processing, Nose, Mining, Databases, Social networks, Mouth

Read Abstract +

How can the human brain uncover patterns, associations and features in real-time, real-world data? There must be a general strategy used to transform raw signals into useful features, but representing this generalization in the context of our information extraction tool set is lacking. In contrast to Big Data (BD), Large Data Analysis (LDA) has become a reachable multi-disciplinary goal in recent years due in part to high performance computers and algorithm development, as well as the availability of large data sets. However, the experience of Machine Learning (ML) and information communities has not been generalized into an intuitive framework that is useful to researchers across disciplines. The data exploration phase of data mining is a prime example of this unspoken, ad-hoc nature of ML – the Computer Scientist works with a Subject Matter Expert (SME) to understand the data, and then build tools (i.e. classifiers, etc.) which can benefit the SME and the rest of the researchers in that field. We ask, why is there not a tool to represent information in a meaningful way to the researcher asking the question? Meaning is subjective and contextual across disciplines, so to ensure robustness, we draw examples from several disciplines and propose a generalized LDA framework for independent data understanding of heterogeneous sources which contribute to Knowledge Discovery in Databases (KDD). Then, we explore the concept of adaptive Information resolution through a 6W unsupervised learning methodology feedback system. In this paper, we will describe the general process of man-machine interaction in terms of an asymmetric directed graph theory (digging for embedded knowledge), and model the inverse machine-man feedback (digging for tacit knowledge) as an ANN unsupervised learning methodology. Finally, we propose a collective learning framework which utilizes a 6W semantic topology to organize heterogeneous knowledge and diffuse information to entities within a society in a personalized way.

Proceedings Article | 24 June 2014 Paper

Paper

Neo-angiogenesis metabolic biomarker of tumor-genesis tracking by infrared joystick contact imaging in personalized homecare system

Harold Szu, Philip Hoekstra, Joseph Landa, Nadarajen Vydelingum

Proceedings Volume 9118, 91180T (2014) https://doi.org/10.1117/12.2049598

KEYWORDS: Cancer, Infrared imaging, Tumors, Breast cancer, Breast, Cameras, Infrared cameras, Thermography, Capillaries, Proteins

Read Abstract +

We describe an affordable, harmless, and administrative (AHA) metabolic biomarker (MBM) for homecare cancer screening. It may save hundreds of thousands of women’s and thousands of men’s lives every year from breast cancer and melanoma. The goal is to increase the specificity of infrared (IR) imagery to reduce the false alarm rate (FAR). The patient’s hands are immersed in icy cold water, about 11oC, for 30 seconds. We then compare two IR images, taken before and after the cold stimulus, and the difference reveals an enhanced signal and noise ratio (SNR) at tumorigenesis sites since the contraction of capillaries under cold challenge is natural to healthy capillaries, except those newly built capillaries during angiogenesis (Folkman, Nature 1995). Concomitant with the genome and the phenome (molecular signaling by phosphor-mediate protein causing inflammation by platelet activating factor (PAF) that transform cells from benign to malignant is the amplification of nitric oxide (NO) syntheses, a short-lived reactive oxygen species (ROS) that dilates regional blood vessels; superseding normal autonomic nervous system regulation. A rapidly growing tumor site might implicate accumulation of ROS, for which NO can rapidly stretch the capillary bed system usually having thinning muscular lining known as Neo-Angiogenesis (NA) that could behave like Leaky In-situ Faucet Effect (LIFE) in response to cold challenge. To emphasize the state of art knowledge of NA, we mentioned in passing the first generation of an anticapillary growth drug, Avastin by Genetech; it is an antibody protein that is injected for metastasis, while the second generation drug; Sorafenib by Bayers (2001) and Sutent by Pfizer (2000) both target molecular signaling loci to block receptor associated tyrosine kinase induced protein phosphorylation in order to reverse the angiogenesis. Differentiating benign from malignant in a straightforward manner is required to achieve the wellness protocol, yet would become prohibitively expensive and impossible to follow through. For example, given the probability of detection (PD) about 0.1% over unspecified number of years (e.g. menopause years for breast cancer), one might need hundred thousand volunteers. We suggested a Time Reversal Invariant Paradigm (TRIP) (a private communication with Vatican) for gathering equivalent cancer symptom imagery from recovery histories of dozens of patients. We further mixed it with few % of recovered/non-sick cases for negative controls. Creating Virtual images and running videos of these, frame by frame, in two directions (forward and backward in time) resulted in identical Receiver Operation Characteristics (ROC) for both the computer Aided Target Recognition (AiTR) algorithm and the human radiological experts; namely PD versus FAR within the standard deviation; even though the physiology could be entirely different. Such a TRIP would be true taken by any memory-less instantaneous imagery devices (IR, ultrasound, X-rays, MRI excluding magnetic hysteresis memory). In summary, such an affordable, harmless, and administrative, neo-angiogenesis metabolic biomarker can help monitor the transitioning from benign to malignant states of high-risk home alone seniors and also monitor the progress of home alone seniors treatment at home. Therefore, Smartphone equipped with a day camera having IR spectral filtering for a contact self imaging called joystick, when augmented with AHA NA MBM, may be suited for HAS homecare.

Proceedings Article | 24 June 2014 Paper

Paper

Large data analysis of different sensory modalities

Ming-Kai Hsu, Harold Szu

Proceedings Volume 9118, 911803 (2014) https://doi.org/10.1117/12.2054581

KEYWORDS: Data analysis, Video, Video surveillance, Data mining, Sensors, Acoustics, Analog electronics, Surveillance, Cameras, Nonlinear image processing

Read Abstract +

Proceedings Article | 24 June 2014 Paper

Paper

Brain order disorder 2nd group report of f-EEG

Francois Lalonde, Nitin Gogtay, Jay Giedd, Nadarajen Vydelingum, David Brown, Binh Tran, Charles Hsu, Ming-Kai Hsu, Jae Cha, Jeffrey Jenkins, Lien Ma, Jefferson Willey, Jerry Wu, Kenneth Oh, Joseph Landa, C. Lin, T. Jung, Scott Makeig, Carlo Francesco Morabito, Qyu Moon, Takeshi Yamakawa, Soo-Young Lee, Jong-Hwan Lee, Harold Szu, Balvinder Kaur, Kenneth Byrd, Karen Dang, Alan Krzywicki, Babajide Familoni, Louis Larson, Susan Harkrider, Keith Krapels, Liyi Dai

Proceedings Volume 9118, 91180J (2014) https://doi.org/10.1117/12.2051706

KEYWORDS: Brain, Electroencephalography, Head, Correlation function, Ions, Electrodes, Neuroimaging, Thermodynamics, Feedback loops, Diffusion

Read Abstract +

Since the Brain Order Disorder (BOD) group reported on a high density Electroencephalogram (EEG) to capture the neuronal information using EEG to wirelessly interface with a Smartphone [1,2], a larger BOD group has been assembled, including the Obama BRAIN program, CUA Brain Computer Interface Lab and the UCSD Swartz Computational Neuroscience Center. We can implement the pair-electrodes correlation functions in order to operate in a real time daily environment, which is of the computation complexity of O(N³) for N=10^2~3 known as functional f-EEG. The daily monitoring requires two areas of focus. Area #(1) to quantify the neuronal information flow under arbitrary daily stimuli-response sources. Approach to #1: (i) We have asserted that the sources contained in the EEG signals may be discovered by an unsupervised learning neural network called blind sources separation (BSS) of independent entropy components, based on the irreversible Boltzmann cellular thermodynamics(ΔS < 0), where the entropy is a degree of uniformity. What is the entropy? Loosely speaking, sand on the beach is more uniform at a higher entropy value than the rocks composing a mountain – the internal binding energy tells the paleontologists the existence of information. To a politician, landside voting results has only the winning information but more entropy, while a non-uniform voting distribution record has more information. For the human’s effortless brain at constant temperature, we can solve the minimum of Helmholtz free energy (H = E − TS) by computing BSS, and then their pairwise-entropy source correlation function. (i) Although the entropy itself is not the information per se, but the concurrence of the entropy sources is the information flow as a functional-EEG, sketched in this 2^nd BOD report. Area #(2) applying EEG bio-feedback will improve collective decision making (TBD). Approach to #2: We introduce a novel performance quality metrics, in terms of the throughput rate of faster (Δt) & more accurate (ΔA) decision making, which applies to individual, as well as team brain dynamics. Following Nobel Laureate Daniel Kahnmen’s novel “Thinking fast and slow”, through the brainwave biofeedback we can first identify an individual’s “anchored cognitive bias sources”. This is done in order to remove the biases by means of individually tailored pre-processing. Then the training effectiveness can be maximized by the collective product Δt * ΔA. For Area #1, we compute a spatiotemporally windowed EEG in vitro average using adaptive time-window sampling. The sampling rate depends on the type of neuronal responses, which is what we seek. The averaged traditional EEG measurements and are further improved by BSS decomposition into finer stimulus-response source mixing matrix [A] having finer & faster spatial grids with rapid temporal updates. Then, the functional EEG is the second order co-variance matrix defined as the electrode-pair fluctuation correlation function C(s~, s~’) of independent thermodynamic source components. (1) We define a 1-D Space filling curve as a spiral curve without origin. This pattern is historically known as the Peano-Hilbert arc length a. By taking the most significant bits of the Cartesian product a≡ O(x * y * z), it represents the arc length in the numerical size with values that map the 3-D neighborhood proximity into a 1-D neighborhood arc length representation. (2) 1-D Fourier coefficients spectrum have no spurious high frequency contents, which typically arise in lexicographical (zig-zag scanning) discontinuity [Hsu & Szu, “Peano-Hilbert curve,” SPIE 2014]. A simple Fourier spectrum histogram fits nicely with the Compressive Sensing CRDT Mathematics. (3) Stationary power spectral density is a reasonable approximation of EEG responses in striate layers in resonance feedback loops capable of producing a 100, 000 neuronal collective Impulse Response Function (IRF). The striate brain layer architecture represents an ensemble <IRF< e.g. at V1-V4 of Brodmann areas 17-19 of the Cortex, i.e. stationary Wiener-Kintchine-Einstein Theorem. Goal#1: functional-EEG: After taking the 1-D space-filling curve, we compute the ensemble averaged 1-D Power Spectral Density (PSD) and then make use of the inverse FFT to generate f-EEG. (ii) Goal#2 individual wellness baseline (IWB): We need novel change detection, so we derive the ubiquitous fat-tail distributions for healthy brains PSD in outdoor environments (Signal=310°C; Noise=27°C: SNR=310/300; 300°K=(1/40)eV). The departure from IWB might imply stress, fever, a sports injury, an unexpected fall, or numerous midnight excursions which may signal an onset of dementia in Home Alone Senior (HAS), discovered by telemedicine care-giver networks. Aging global villagers need mental healthcare devices that are affordable, harmless, administrable (AHA) and user-friendly, situated in a clothing article such as a baseball hat and able to interface with pervasive Smartphones in daily environment.

Proceedings Article | 24 June 2014 Paper

Paper

Low-discrepancy sampling of parametric surface using adaptive space-filling curves (SFC)

Charles Hsu, Harold Szu

Proceedings Volume 9118, 91180P (2014) https://doi.org/10.1117/12.2053306

KEYWORDS: Electroencephalography, Image processing, Partial differential equations, Palladium, Associative arrays, Fourier transforms, Image resolution, Signal processing, Computer engineering, Computer science

Read Abstract +

Proceedings Article | 24 June 2014 Paper

Paper

Overcoming shadowing and occlusion in imagery with error-resilient processing

Charles Hsu, Todd DuBosq, Steven Moyer, Eric Flug, Jeffrey Jenkins, Joseph Landa, Kenneth Byrd, Harold Szu

Proceedings Volume 9118, 91180K (2014) https://doi.org/10.1117/12.2054409

KEYWORDS: Fourier transforms, Phase retrieval, Iris, Image processing, 3D acquisition, 3D image processing, LIDAR, Image acquisition, Target acquisition, Target recognition

Read Abstract +

Proceedings Article | 24 June 2014 Paper

Paper

Future enhancements to 3D printing and real time production

Joseph Landa, Jeffery Jenkins, Jerry Wu, Harold Szu

Proceedings Volume 9118, 91180C (2014) https://doi.org/10.1117/12.2051256

KEYWORDS: Printing, 3D printing, Prototyping, Head, Manufacturing, Computer aided design, Cell phones, Augmented reality, Bone, Semiconductors

Read Abstract +

Proceedings Article | 19 June 2014 Paper

Paper

Surface surveillance for ground moving targets indicators

Charles Hsu, Harold Szu

Proceedings Volume 9118, 91180Q (2014) https://doi.org/10.1117/12.2053285

KEYWORDS: Radar, Doppler effect, Synthetic aperture radar, Target detection, Image processing, Surveillance, Scattering, Antennas, Electromagnetism, Signal processing

Read Abstract +

Proceedings Article | 19 June 2014 Paper

Paper

Telescopic multi-resolution augmented reality

Jeffrey Jenkins, Christopher Frenchi, Harold Szu

Proceedings Volume 9118, 911811 (2014) https://doi.org/10.1117/12.2051255

KEYWORDS: Visualization, Augmented reality, Physics, Virtual reality, Chemistry, Autoregressive models, Photons, Analog electronics, Sensors, Molecules

Read Abstract +

Proceedings Article | 19 June 2014 Paper

Paper

Authentication, privacy, security can exploit brainwave by biomarker

Jeffrey Jenkins, Charles Sweet, James Sweet, Steven Noel, Harold Szu

Proceedings Volume 9118, 91180U (2014) https://doi.org/10.1117/12.2051323

KEYWORDS: Electroencephalography, Brain, Biometrics, Visualization, Sensors, Information security, Head, Iris recognition, Biomedical optics, Eye

Read Abstract +

We seek to augment the current Common Access Control (CAC) card and Personal Identification Number (PIN) verification systems with an additional layer of classified access biometrics. Among proven devices such as fingerprint readers and cameras that can sense the human eye's iris pattern, we introduced a number of users to a sequence of 'grandmother images', or emotionally evoked stimuli response images from other users, as well as one of their own, for the purpose of authentication. We performed testing and evaluation of the Authenticity Privacy and Security (APS) brainwave biometrics, similar to the internal organ of the human eye’s iris which cannot easily be altered. ‘Aha’ recognition through stimulus-response habituation can serve as a biomarker, similar to keystroke dynamics analysis for inter and intra key fluctuation time of a memorized PIN number (FIST). Using a non-tethered Electroencephalogram (EEG) wireless smartphone/pc monitor interface, we explore the appropriate stimuli-response biomarker present in DTAB low frequency group waves. Prior to login, the user is shown a series of images on a computer display. They have been primed to click their mouse when the image is presented. DTAB waves are collected with a wireless EEG and are sent via Smartphone to a cloud based processing infrastructure. There, we measure fluctuations in DTAB waves from a wireless, non-tethered, single node EEG device between the Personal Graphic Image Number (PGIN) stimulus image and the response time from an individual’s mental performance baseline. Towards that goal, we describe an infrastructure that supports distributed verification for web-based EEG authentication. The performance of machine learning on the relative Power Spectral Density EEG data may uncover features required for subsequent access to web or media content. Our approach provides a scalable framework wrapped into a robust Neuro-Informatics toolkit, viable for use in the Biomedical and mental health communities, as well as numerous consumer applications.

Proceedings Article | 19 June 2014 Paper

Paper

Non-equilibrium thermodynamics theory of econometric source discovery for large data analysis

Rutger van Bergem, Jeffrey Jenkins, Dalila Benachenhou, Harold Szu

Proceedings Volume 9118, 911804 (2014) https://doi.org/10.1117/12.2054927

KEYWORDS: Thermodynamics, Data modeling, Data analysis, Data mining, Analytical research, Machine learning, Visual process modeling, Signal to noise ratio, Databases, Data acquisition

Read Abstract +

Almost all consumer and firm transactions are achieved using computers and as a result gives rise to increasingly large amounts of data available for analysts. The gold standard in Economic data manipulation techniques matured during a period of limited data access, and the new Large Data Analysis (LDA) paradigm we all face may quickly obfuscate most tools used by Economists. When coupled with an increased availability of numerous unstructured, multi-modal data sets, the impending 'data tsunami' could have serious detrimental effects for Economic forecasting, analysis, and research in general. Given this reality we propose a decision-aid framework for Augmented-LDA (A-LDA) – a synergistic approach to LDA which combines traditional supervised, rule-based Machine Learning (ML) strategies to iteratively uncover hidden sources in large data, the artificial neural network (ANN) Unsupervised Learning (USL) at the minimum Helmholtz free energy for isothermal dynamic equilibrium strategies, and the Economic intuitions required to handle problems encountered when interpreting large amounts of Financial or Economic data. To make the ANN USL framework applicable to economics we define the temperature, entropy, and energy concepts in Economics from non-equilibrium molecular thermodynamics of Boltzmann viewpoint, as well as defining an information geometry, on which the ANN can operate using USL to reduce information saturation. An exemplar of such a system representation is given for firm industry equilibrium. We demonstrate the traditional ML methodology in the economics context and leverage firm financial data to explore a frontier concept known as behavioral heterogeneity. Behavioral heterogeneity on the firm level can be imagined as a firm's interactions with different types of Economic entities over time. These interactions could impose varying degrees of institutional constraints on a firm's business behavior. We specifically look at behavioral heterogeneity for firms that are operating with the label of ‘Going-Concern’ and firms labeled according to institutional influence they may be experiencing, such as constraints on firm hiring/spending while in a Bankruptcy or a Merger procedure. Uncovering invariant features, or behavioral data metrics from observable firm data in an economy can greatly benefit the FED, World Bank, etc. We find that the ML/LDA communities can benefit from Economic intuitions just as much as Economists can benefit from generic data exploration tools. The future of successful Economic data understanding, modeling, simulation, and visualization can be amplified by new A-LDA models and approaches for new and analogous models of Economic system dynamics. The potential benefits of improved economic data analysis and real time decision aid tools are numerous for researchers, analysts, and federal agencies who all deal with increasingly large amounts of complex data to support their decision making.

Proceedings Article | 19 June 2014 Paper

Paper

Neuromorphic implementation of a software-defined camera that can see through fire and smoke in real-time

Jae Cha, A. Lynn Abbott, Harold Szu, Jefferson Willey, Joseph Landa, Keith Krapels

Proceedings Volume 9118, 911809 (2014) https://doi.org/10.1117/12.2052021

KEYWORDS: Cameras, Thermodynamics, Visible radiation, Machine learning, Sensors, Thermography, Visualization, Infrared radiation, Fiber optic gyroscopes, Independent component analysis

Read Abstract +

Proceedings Article | 19 June 2014 Paper

Paper

Theory of enhancing thermal imaging through fire

Jae Cha, A. Lynn Abbott, Keith Krapels, Harold Szu

Proceedings Volume 9118, 91180A (2014) https://doi.org/10.1117/12.2052654

KEYWORDS: Temperature metrology, Cameras, Visual system, Image quality, Algorithms, Particles, Image enhancement, Sensors, Thermodynamics, Thermography

Read Abstract +

Proceedings Article | 29 May 2013 Paper

Paper

Monitoring and diagnosis of Alzheimer's disease using noninvasive compressive sensing EEG

F. Morabito, D. Labate, G. Morabito, I. Palamara, H. Szu

Proceedings Volume 8750, 87500Y (2013) https://doi.org/10.1117/12.2020886

KEYWORDS: Electroencephalography, Oxygen, Electrodes, Compressed sensing, Databases, Alzheimer's disease, Brain, Signal processing, Sensors, Medicine

Read Abstract +

Proceedings Article | 29 May 2013 Paper

Paper

Adaptive compressive sensing camera

Charles Hsu, Ming Hsu, Jae Cha, Tomo Iwamura, Joseph Landa, Charles Nguyen, Harold Szu

Proceedings Volume 8750, 87500W (2013) https://doi.org/10.1117/12.2017881

KEYWORDS: Image quality, Databases, Sensors, Analog electronics, Charge-coupled devices, Surveillance, CCD cameras, Image restoration, Cameras, Compressed sensing

Read Abstract +

Proceedings Article | 29 May 2013 Paper

Paper

Passive ranging redundancy reduction in diurnal weather conditions

Jae Cha, A. Lynn Abbott, Harold Szu

Proceedings Volume 8750, 87500F (2013) https://doi.org/10.1117/12.2018433

KEYWORDS: Head, Neural networks, Modulation transfer functions, Signal to noise ratio, Roads, Cameras, Compressed sensing, Reflectivity, Ranging, Data modeling

Read Abstract +

Proceedings Article | 29 May 2013 Paper

Paper

Theory of compressive modeling and simulation

Harold Szu, Jae Cha, Richard Espinola, Keith Krapels

Proceedings Volume 8750, 875011 (2013) https://doi.org/10.1117/12.2032322

KEYWORDS: Long wavelength infrared, Passive millimeter wave sensors, Reflectivity, Rayleigh scattering, Atmospheric modeling, Picosecond phenomena, Atmospheric propagation, Scattering, Thermodynamics, Data modeling

Read Abstract +

Proceedings Article | 29 May 2013 Paper

Paper

Augmented reality for biomedical wellness sensor systems

Jeffrey Jenkins, Harold Szu

Proceedings Volume 8750, 875017 (2013) https://doi.org/10.1117/12.2018409

KEYWORDS: Sensors, Augmented reality, Autoregressive models, Biomedical optics, 3D modeling, Visualization, Cameras, Video, Medicine, Heart

Read Abstract +

Due to the commercial move and gaming industries, Augmented Reality (AR) technology has matured. By definition of AR, both artificial and real humans can be simultaneously present and realistically interact among one another. With the help of physics and physiology, we can build in the AR tool together with real human day-night webcam inputs through a simple interaction of heat transfer –getting hot, action and reaction –walking or falling, as well as the physiology –sweating due to activity. Knowing the person age, weight and 3D coordinates of joints in the body, we deduce the force, the torque, and the energy expenditure during real human movements and apply to an AR human model. We wish to support the physics-physiology AR version, PPAR, as a BMW surveillance tool for senior home alone (SHA). The functionality is to record senior walking and hand movements inside a home environment. Besides the fringe benefit of enabling more visits from grand children through AR video games, the PP-AR surveillance tool may serve as a means to screen patients in the home for potential falls at points around in house. Moreover, we anticipate PP-AR may help analyze the behavior history of SHA, e.g. enhancing the Smartphone SHA Ubiquitous Care Program, by discovering early symptoms of candidate Alzheimer-like midnight excursions, or Parkinson-like trembling motion for when performing challenging muscular joint movements. Using a set of coordinates corresponding to a set of 3D positions representing human joint locations, we compute the Kinetic Energy (KE) generated by each body segment over time. The Work is then calculated, and converted into calories. Using common graphics rendering pipelines, one could invoke AR technology to provide more information about patients to caretakers. Alerts to caretakers can be prompted by a patient’s departure from their personal baseline, and the patient’s time ordered joint information can be loaded to a graphics viewer allowing for high-definition digital reconstruction. Then an entire scene can be viewed from any position in virtual space, and AR can display certain measurements values which either constituted an alert, or otherwise indicate signs of the transition from wellness to illness.

Proceedings Article | 15 May 2012 Paper

Paper

Smartphone home monitoring of ECG

Harold Szu, Charles Hsu, Gyu Moon, Joseph Landa, Hiroshi Nakajima, Yutaka Hata

Proceedings Volume 8401, 84010L (2012) https://doi.org/10.1117/12.923579

KEYWORDS: Electrocardiography, Lead, Heart, Electrodes, Compressed sensing, Blood, Databases, Tomography, Biomedical optics, Independent component analysis

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Artificial neural network does better spatiotemporal compressive sampling

Soo-Young Lee, Charles Hsu, Harold Szu

Proceedings Volume 8401, 84010G (2012) https://doi.org/10.1117/12.923619

KEYWORDS: Optical flow, Artificial neural networks, Computer vision technology, Visual process modeling, Machine vision, Wavelets, Neurons, Visual system, Mathematics, Sensors

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

A NANO enhancement to Moore's law

Jerry Wu, Yin-Lin Shen, Kitt Reinhardt, Harold Szu

Proceedings Volume 8401, 84010P (2012) https://doi.org/10.1117/12.921203

KEYWORDS: Transistors, Semiconductors, Electrons, Nanotechnology, Carbon nanotubes, Mobile devices, Spintronics, Quantum computing, Manufacturing, Magnetic semiconductors

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Face recognition from a moving platform via sparse representation

Ming Kai Hsu, Charles Hsu, Ting Lee, Harold Szu

Proceedings Volume 8401, 840106 (2012) https://doi.org/10.1117/12.923591

KEYWORDS: Facial recognition systems, Video surveillance, Video, Detection and tracking algorithms, Surveillance systems, Sensors, Machine vision, Surveillance, Algorithm development, Reconstruction algorithms

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Household wireless electroencephalogram hat

Harold Szu, Charles Hsu, Gyu Moon, Takeshi Yamakawa, Binh Tran

Proceedings Volume 8401, 84010K (2012) https://doi.org/10.1117/12.923669

KEYWORDS: Electroencephalography, Electrodes, Signal to noise ratio, Sensors, Independent component analysis, Compressed sensing, Brain, Video, Data acquisition, Analog electronics

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Elucidating compressive sensing from Nyquist critical sampling

Harold Szu, Charles Hsu, Charles Nguyen

Proceedings Volume 8401, 84010I (2012) https://doi.org/10.1117/12.923587

KEYWORDS: Oscillators, Receivers, Compressed sensing, Modulation, Analog electronics, Signal to noise ratio, Antennas, Amplifiers, Signal processing, Interference (communication)

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Enhanced decision making through neuroscience

Harold Szu, TP Jung, Scott Makeig

Proceedings Volume 8401, 840112 (2012) https://doi.org/10.1117/12.926424

KEYWORDS: Electroencephalography, Electrodes, Independent component analysis, Brain, Compressed sensing, Head, Signal to noise ratio, Neuroscience, Neuroimaging, Video

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Interdisciplinary education approach to the human science

Harold Szu, Yufeng Zheng, Nian Zhang

Proceedings Volume 8401, 840103 (2012) https://doi.org/10.1117/12.923440

KEYWORDS: Wavelets, Independent component analysis, Nanoengineering, Biomedical optics, Biology, Machine learning, Sensing systems, Ear, Neural networks, Iron

Read Abstract +

Proceedings Article | 15 May 2012 Paper

Paper

Video image cliff notes

Harold Szu, Charles Hsu

Proceedings Volume 8401, 84010H (2012) https://doi.org/10.1117/12.923593

KEYWORDS: Video, Nose, Visualization, Eye, Video compression, Brain, Content addressable memory, Molybdenum, Neurons, Mouth

Read Abstract +

Proceedings Article | 10 May 2012 Paper

Paper

Under-dermal emulator of vascular identification

Joseph Landa, Robert Blake, Alex Rich, Harold Szu

Proceedings Volume 8401, 840116 (2012) https://doi.org/10.1117/12.923670

KEYWORDS: Tumors, Infrared imaging, Thermography, Algorithm development, Sensors, Cancer, Infrared cameras, Skin, Standards development, Oncology

Read Abstract +

The goal of this paper and research effort is to develop a simple and clear apparatus and approach to quantify the effectiveness of sensor systems as it relates to their ability to penetrate camouflage and resolve skin depth. Over the last decade, several attempts have been made to leverage advances in Infrared (IR) imaging, made by the military, into medical sensing [1]. Several promising technologies have been evaluated and thus far determined to be lacking when compared to the current standards of care based on x-ray imaging [2]. While progress has been made this general class of technology has not generated wide spread interest from the medical community. This lack of interest is discouraging, especially when considering the great potential for good that would result in successfully demonstrating a truly passive tumor detection system based on thermal signatures. Recently, this team participated as part of a larger group in the development and testing of a novel class of algorithms using images from two separate IR spectra. This area of spectral fusing algorithms is called the Single Pixel-Blind Source Separation (SP-BSS). While the goal of experiment is not new, our results showed this approach provided potential improvements over more traditional thermography, particularly in the area of overcoming environmental noise. These promising results have motivated us to develop a method for running controlled experiments so that the equipment and algorithms can be optimized and the significant engineering challenges of frame registration, data standardization, and sensor optimization for wellness screening can be accomplished. Conducting these efforts using data from human subjects is both impractical and unwarranted at this time. We have developed a physics-physiological under-dermal model of internal vascular circulation that approximates not only a healthy human body (angiogenesis effect) but also a human body developing a tumor (neo-angiogenesis effect). This physical model also provides useful insight into the detection of objects concealed on a person. We call this dual use target an Under-Dermal Emulator.

Proceedings Article | 9 June 2011 Paper

Paper

Non-cryogenic cooled MWIR with swap-limited carbon nanotubes

H. Szu, Y. L. Shen, J. Wu, K. Reinhardt

Proceedings Volume 8058, 80580P (2011) https://doi.org/10.1117/12.887539

KEYWORDS: Semiconductors, Mid-IR, Carbon nanotubes, Electrons, Sensors, Graphene, Carbon, Compressed sensing, Fermions, Field effect transistors

Read Abstract +

Proceedings Article | 9 June 2011 Paper

Paper

Lossless divide and conquer for time-order sorting of N facial poses

Ming Kai Hsu, Harold Szu

Proceedings Volume 8058, 80580W (2011) https://doi.org/10.1117/12.887551

KEYWORDS: Sensors, Video, Facial recognition systems, Surveillance, Video surveillance, Diffusion, Head, Cameras, Compressed sensing, Data storage

Read Abstract +

Proceedings Article | 9 June 2011 Paper

Paper

Compressive sampling by artificial neural networks for video

Harold Szu, Charles Hsu, Jeffrey Jenkins, Kitt Reinhardt

Proceedings Volume 8058, 805803 (2011) https://doi.org/10.1117/12.887596

KEYWORDS: Video, Video compression, Video surveillance, Compressed sensing, Content addressable memory, Image restoration, Sensors, Cameras, Independent component analysis, Binary data

Read Abstract +

Proceedings Article | 8 June 2011 Paper

Paper

Ubiquitous-health (U-Health) monitoring systems for elders and caregivers

Gyu Moon, Kyung-won Lim, Young-min Yoo, Hye-min An, Ki Seop Lee, Harold Szu

Proceedings Volume 8058, 80581J (2011) https://doi.org/10.1117/12.887532

KEYWORDS: Databases, Sensors, Sensing systems, Biomedical optics, Magnetic sensors, Medicine, Signal detection, Data acquisition, Microcontrollers, Infrared sensors

Read Abstract +

Proceedings Article | 8 June 2011 Paper

Paper

Sequential principal component analysis

Charles Hsu, Harold Szu

Proceedings Volume 8058, 80580S (2011) https://doi.org/10.1117/12.887509

KEYWORDS: Principal component analysis, Facial recognition systems, Image processing, Machine vision, Computer vision technology, Object recognition, Data processing, Databases, Glasses, Denoising

Read Abstract +

Proceedings Article | 8 June 2011 Paper

Paper

The physiology of keystroke dynamics

Jeffrey Jenkins, Quang Nguyen, Joseph Reynolds, William Horner, Harold Szu

Proceedings Volume 8058, 80581N (2011) https://doi.org/10.1117/12.887419

KEYWORDS: Sensors, Biometrics, Behavioral biometrics, Brain, Eye, Neurons, Physiology, Nervous system, Retina, Cones

Read Abstract +

Proceedings Article | 8 June 2011 Paper

Paper

What is a missing link among wireless persistent surveillance?

Charles Hsu, Harold Szu

Proceedings Volume 8058, 80580R (2011) https://doi.org/10.1117/12.887533

KEYWORDS: Wavelets, Surveillance, Orthogonal frequency division multiplexing, Sensors, Modulation, Wireless communications, Telecommunications, Radar, Receivers, Sensor networks

Read Abstract +

Proceedings Article | 8 June 2011 Paper

Paper

Spotting and tracking good biometrics with the human visual system

Harold Szu, Jeffrey Jenkins, Charles Hsu

Proceedings Volume 8058, 80580T (2011) https://doi.org/10.1117/12.887520

KEYWORDS: Iris, Iris recognition, Biometrics, Wavelets, Fourier transforms, Visual system, Eye models, Mathematical modeling, Brain, 3D metrology

Read Abstract +

Proceedings Article | 4 June 2011 Paper

Paper

Dynamic range compensation in non-linear sensors

Harold Szu, Michael Wardlaw, Jeff Willey

Proceedings Volume 8058, 80580H (2011) https://doi.org/10.1117/12.887405

KEYWORDS: Analog electronics, Signal detection, Receivers, Sensors, Feedback signals, Nulling interferometry, Optical spheres, Interference (communication), Magnetic sensors, Doppler effect

Read Abstract +

SPIE Journal Paper | 1 April 2011 Open Access

Open Access

Re-establish the time-order across sensors of different modalities

Ming-Kai Hsu, Ting Lee, Harold Szu

OE, Vol. 50, Issue 04, 047002, (April 2011) https://doi.org/10.1117/12.10.1117/1.3562322

KEYWORDS: Video, Video surveillance, Sensors, Surveillance, Cameras, Reconstruction algorithms, Algorithm development, Optical engineering, Facial recognition systems, Nose

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Asymmetric GT of social networks

Harold Szu

Proceedings Volume 7703, 770304 (2010) https://doi.org/10.1117/12.853682

KEYWORDS: Social networks, Probability theory, Databases, Video, Vector spaces, Particles, Diffusion, Transform theory, Principal component analysis, Linear algebra

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Recognizing foreground-background interaction

Jeffrey Jenkins, Harold Szu

Proceedings Volume 7703, 770312 (2010) https://doi.org/10.1117/12.853601

KEYWORDS: Brain, Visualization, Rods, Cones, Wavelets, Neodymium, Eye, Ions, Electroencephalography, Sensors

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Can we detect influenza?

Patrick Dolan, Harold Szu

Proceedings Volume 7703, 77030T (2010) https://doi.org/10.1117/12.853652

KEYWORDS: Surface enhanced Raman spectroscopy, Molecules, Proteins, Raman scattering, Viruses, Silver, Raman spectroscopy, Nanotechnology, Nanoparticles, Nanorods

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Optical determination of cardiovascular health at a distance

Matthew Farley, Harold Szu, Joseph Reynolds

Proceedings Volume 7703, 77030R (2010) https://doi.org/10.1117/12.853314

KEYWORDS: Speckle, Sensors, Blood, Blood pressure, Pulsed laser operation, Blood circulation, Heart, Arteries, Skin, Signal detection

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Biomimetic novelty detection

Lein Ma, Harold Szu

Proceedings Volume 7703, 770316 (2010) https://doi.org/10.1117/12.855789

KEYWORDS: Sensors, Environmental sensing, Independent component analysis, Climate change, Detection and tracking algorithms, Surveillance, Methane, Biomimetics, Machine learning, Autoregressive models

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Exploiting iris dynamics

Charles Hsu, Harold Szu

Proceedings Volume 7703, 770307 (2010) https://doi.org/10.1117/12.855185

KEYWORDS: Iris, Iris recognition, Eye, Retina, Fractal analysis, Biometrics, Image processing, Cameras, Rods, Sensors

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

A subspace learning approach to evaluating the performance of image fusion algorithms

Kenneth Byrd, Harold Szu, Mohamed Chouikha

Proceedings Volume 7703, 770310 (2010) https://doi.org/10.1117/12.855787

KEYWORDS: Image fusion, Discrete wavelet transforms, Detection and tracking algorithms, Principal component analysis, Visualization, Algorithm development, Information fusion, Diffusion, Image enhancement, Wavelets

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Video surveillance of passengers with mug shots

Ming Kai Hsu, Ting Lee, Harold Szu

Proceedings Volume 7703, 770305 (2010) https://doi.org/10.1117/12.850546

KEYWORDS: Video, Facial recognition systems, Video surveillance, Cameras, Inspection, Image resolution, Filtering (signal processing), Databases, Algorithm development, Photography

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Nano-photonics: past and present

Harold Szu

Proceedings Volume 7703, 77030J (2010) https://doi.org/10.1117/12.855069

KEYWORDS: Single walled carbon nanotubes, Graphene, Nanotechnology, Semiconductors, Nanophotonics, Chemical species, Photons, Carbon, Fermions, Computer aided design

Read Abstract +

Proceedings Article | 13 April 2010 Paper

Paper

Electronic tongue system for remote multi-ion sensing using blind source separation and wireless sensor network

Wen-Yan Chung, Febus Reidj Cruz, Harold Szu, Dorota Pijanowska, Marek Dawgul, Wladyslaw Torbicz, Piotr Grabiec, Bohdan Jarosewicz, Jung-Lung Chiang, Cheanyeh Cheng, Kuo-Chung Chang, Le Thanh Truc, Wei-Chiang Lin

Proceedings Volume 7703, 77030A (2010) https://doi.org/10.1117/12.850128

KEYWORDS: Ions, Field effect transistors, Sensors, Hydrogen, Sodium, Tongue, Independent component analysis, Sensor networks, Remote sensing, Sensing systems

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Modular biometric system

Charles Hsu, Michael Viazanko, Jimmy O'Looney, Harold Szu

Proceedings Volume 7343, 734317 (2009) https://doi.org/10.1117/12.820297

KEYWORDS: Biometrics, Veins, Field programmable gate arrays, Sensors, Facial recognition systems, Feature extraction, Detection and tracking algorithms, Digital signal processing, Principal component analysis, Speaker recognition

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Con_A-carbone nanotube conjugate with short wave near-infrared laser ablation for tumor therapy

Huan-Yao Lei, Ching-An Peng, Ming-Jer Tang, Kit Reindhart, Harold Szu

Proceedings Volume 7343, 73430Q (2009) https://doi.org/10.1117/12.820838

KEYWORDS: Tumors, Near infrared, Cell death, Laser ablation, Short wave infrared radiation, Carbon nanotubes, Liver, Chemical lasers, Laser therapeutics, Proteins

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Towards non-cooperative standoff biometrics using extremely low frequency (ELF) processing

Kenneth Byrd, Harold Szu, Michael Wardlaw

Proceedings Volume 7343, 734314 (2009) https://doi.org/10.1117/12.820829

KEYWORDS: Magnetism, Biometrics, Signal detection, Magnetic resonance imaging, Independent component analysis, Sensors, Signal to noise ratio, Digital signal processing, Positron emission tomography, Spectroscopy

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

ISFET electronic tongue system for environmental multi-ion sensing with independent component analysis signal processing

Wen-Yaw Chung, Febus Reidj Cruz, Harold Szu, Dorota Pijanowska, Marek Dawgul, Wladislaw Torbicz, Piotr Grabiec, Bohdan Jarosewicz, Jung-Lung Chiang, Kuo-Chung Chang, Cheanyeh Cheng, Wei-Po Ho

Proceedings Volume 7343, 73431D (2009) https://doi.org/10.1117/12.821635

KEYWORDS: Field effect transistors, Ions, Independent component analysis, Tongue, Signal processing, Hydrogen, Sodium, Sensing systems, Electronic components, Sensors

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Wavelets and impulse radar

Harold Szu, Charles Hsu, Kim Scheff, Peter Hansen, Jeff Willey

Proceedings Volume 7343, 734305 (2009) https://doi.org/10.1117/12.821900

KEYWORDS: Wavelets, Radar, Antennas, Signal generators, Optical circuits, Cameras, Doppler effect, Fourier transforms, Wavelet transforms, Floods

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Implications of the advanced mini-max (AMM) classifier on non-cooperative standoff biometrics

Kenneth Byrd, Harold Szu, Mohamed Chouikha

Proceedings Volume 7343, 734315 (2009) https://doi.org/10.1117/12.820832

KEYWORDS: Biometrics, Sensors, Surveillance, Data acquisition, Robotics, Databases, Facial recognition systems, Feature extraction, Detection and tracking algorithms, Cameras

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Digging for knowledge

Harold Szu, Jeffrey Jenkins, Charles Hsu, Steve Goehl, Liden Miao, Masud Cader, Dalila Benachenhou

Proceedings Volume 7343, 734304 (2009) https://doi.org/10.1117/12.822736

KEYWORDS: Principal component analysis, Wavelet transforms, Internet, Databases, Mining, Independent component analysis, Visualization, Feature extraction, Data storage, Sensors

Read Abstract +

The "smile of a mother" is always recognized, whenever and wherever. But why is my PC always dumb and unable to recognize me or my needs, whoever or whatever? This paper postulates that such a 6 W's query and search system needs matching storage. Such a lament will soon be mended with a smarter PC, or a smarter Google engine, a network computer, working in the field of data retrieval, feature extraction, reduction, and knowledge precipitation. Specifically, the strategy of modern information storage and retrieval shall work like our brains, which are constantly overwhelmed by 5 pairs of identical tapes taken by eyes, ears, etc. 5 high fidelity sensors generate 5 pairs of high definition tapes which produce the seeing and hearing etc. in our perception. This amounts to 10 tapes recorded in a non-abridged fashion. How can we store and retrieve them when we need to? We must reduce the redundancy, enhancing the signal noise ratio, and fusing invariant features using a simple set of mathematical operations to write according to the union and read by the intersection in the higher dimensional vector space. For example, (see paper for equation) where the query must be phrased in terms of the union of imprecise or partial set of 6w's denoted by the union of lower case w's. The upper case W's are the archival storage of a primer tree. A simplified humanistic representation may be called the 6W space (who, what, where, when, why, how), also referred to as the Newspaper geometry. It seems like mapping the 6W to the 3W (World Wide Web) is becoming relatively easier. It may thus become efficient and robust by rapidly digging for knowledge through the set operations of union, writing, and intersection, reading, upon the design of 6 W query searching engine matched efficiently by the 6W vector index databases. In fact, Newspaper 6D geometry may be reduced furthermore by PCA (Principal Component Analysis) eigenvector mathematics and mapped into the 2D causality space comprised of the causes (What, How, Why) and the effects (Where, When and Who). If this hypothesis of brain strategy were true, one must then develop a 6W query language to support a 6Wordered set storage of linkage pointers in high D space. In other words, one can easily map the basic 1st Gen. Google Web, 1-D statistical PageRanking databases, to a nested 6W tree where each branch of sub-6-W is stemming from the prime 6 W tree, using a system of automated text mining assisted by syntactic semantics to discern the properties of the 6W for that query. Goehl et al. has demonstrated previously that such is doable, but one may need more tools to support the knowledge extraction and automated feature reduction. In this paper, we have set out to demonstrate lossless down sampling using the 2nd Gen wavelet transform, the so-called "1-D Cartesian lifting processing of Swelden" adopted by JPEG 2000. "The loss of statistics, if any (including PageRanking and 1-D lifting), is the loss of geometry insights," such as 2-D vector time series, video, whose 1-D lifting Cartesian product will loss the diagonal changes insights.

Proceedings Article | 19 March 2009 Paper

Paper

The semantic problem of science and its implications

John Gray, Harold Szu

Proceedings Volume 7343, 73430D (2009) https://doi.org/10.1117/12.818156

KEYWORDS: Mathematics, Brain, Signal processing, Data modeling, Communication engineering, Fuzzy logic, Sensors, Visualization, Physics, Communication theory

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Biomedical wellness standoff screening by unsupervised learning

Harold Szu, Charles Hsu, Philip Hoekstra, Jerry Beeney

Proceedings Volume 7343, 734319 (2009) https://doi.org/10.1117/12.821206

KEYWORDS: Breast, Cameras, Forward looking infrared, Breast cancer, Image processing, 3D image processing, 3D modeling, Skin, Infrared imaging, Mid-IR

Read Abstract +

Biomedical Wellness (BMW) surveillance system may become indispensible in public health riding on four confluent trends: (i) The surge of retirement waves of WWII baby boomers; (ii) The longevity of the seniors, thanks to 3 decades steady NIH budgets~$23B per year; (iii) The economic melting down is exasperating resources for entitlements; (iv) The emergent Next Gen Internet having the last mile challenges solved entirely and friendly with IT wired and wireless delivery system, thanks to DoD/DARPA pioneer and numerous entrepreneurs visionary efforts. To be effective in job recreation in current economic slag, BMW needs a jump start, WH/HHS should establish a balanced investment policy in health care, not just to illness but to wellness, and a BMW blue ribbon panel (BMWbrp), which must be, however, independent of NIHbrp, recommending additional resources, say $5B budget for BMW infrastructure building that will surely create new jobs to prepare badly needed geriatric caretakers. Being governmental investment, the BMWbrp must come back with a upward-conversion compatible infrastructure Blue-Print, version#1, an open architecture of standard interfaces, workable with distributed data bases and programming languages. The infrastructure must be simple, transparent, scalable, to leverage with a win-win-win(senior) CRADA from the private investments worldwide, e.g. from the insurance companies and home security companies, etc. that can further attract senior community center BOT. To start whenever the rubber meets the road, we shall enlist the military infrastructure, their sensors suite located in DoD & DHS labs supported with their affiliated contractors and universities. However, the down selections should be done under open bids, oversight by BMWbrp, under HHS $5B budget, to translate their sophisticated military persistent and precision surveillance know-how technology to watch out, no longer the enemy of USA but also, the enemy of mankind, the malicious microorganisms and disorders. The degree of friendliness must be demanded and measured by the standoff methodology such as 4 nones: noninvasive, noncontact, and none-stop-to-measure, in this order.

Proceedings Article | 19 March 2009 Paper

Paper

Aided infrared target classifier pre-processing by adaptive local contrast enhancement

Ming Kai Hsu, Harold Szu, Ting N. Lee

Proceedings Volume 7343, 73431F (2009) https://doi.org/10.1117/12.822203

KEYWORDS: Infrared imaging, Infrared cameras, Thermography, Image processing, Infrared radiation, Cameras, Image segmentation, Signal to noise ratio, Image enhancement, Image restoration

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Earthquake calamity warning from space station: orbital dynamics coupling geology mantle convection

Harold Szu, Han-Shou Liu

Proceedings Volume 7343, 73430W (2009) https://doi.org/10.1117/12.820902

KEYWORDS: Earthquakes, Satellites, Convection, Independent component analysis, Solids, Tumors, Liquids, Metals, Neurons, Data modeling

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Nanomaterials for sensor applications

Francisco Santiago, Kevin Boulais, Alfredo Rayms-Kelleran, Victor Gehman, Karen Long, Harold Szu

Proceedings Volume 7343, 73430P (2009) https://doi.org/10.1117/12.822602

KEYWORDS: Sensors, Nanomaterials, Infrared sensors, Nanoparticles, Sensor technology, Chemical elements, Detector development, Absorption, Magnetism, Nanotechnology

Read Abstract +

Proceedings Article | 19 March 2009 Paper

Paper

Designs of solar voltaic cells based on carbon nano-tubes II

Yin-Lin Shen, Jong-Horng Dai, Kenneth Ou, Kit Reinhardt, Harold Szu

Proceedings Volume 7343, 73430V (2009) https://doi.org/10.1117/12.821903

KEYWORDS: Near infrared, Solar energy, Solar cells, Visible radiation, Quantum efficiency, Scalable video coding, Glasses, Carbon, Carbon nanotubes, Diffraction

Read Abstract +

Inspired by Asian rice-paddy and Firefighter spiraling steps staircase, we employ a nano-manipulator augmented with CAD as a nano-robot water-buffalo, promised to improve by an order of the magnitude the pioneer work of GE Solar voltaic cell (SVC) made of one Carbon NanoTube (CNT) enjoyed QE_CNT~5%. Our CNT was made of the semiconductor at NIR wavelength E_BG= 1.107 eV which can absorb any photon whose wavelength λ ≤ λ_NIR =1.11 μm. This EBG is chosen due to the cutoff of Pb-Crown glass which happened put us in the equal amount of solar energy spectrum as silicon p-n junction SVC. Nevertheless, the exceeding of the Shockley and Queisser efficiency limit 30% might be due to the fact that we have much compact one-dimensional building block CNT of a tiny diameter 0.66 nm. It allows us to construct 3D structure, called volume pixel, "voxel," in a much efficient spiraling steps staircase fashion to capture the solar spectral energy spreading naturally by a simple focusing lens without occlusion. For real-estate premium applications, in Space or Ocean, we designed a volume pixel (Voxel) housing a stack of 16 CNTs steps spiraling 22° each like the fire house staircase occupying the height of 16 x d_CNT =16 x 0.66nm= 10.56 nm and covering over 360°. The total SVC had the size 2x2 meter², consisting of 100×100 lenslet array. Each lens was made of Pb-Crown glass which was inexpensive simple spherical lens having the diameter of D_lens=2 cm and F#=0.7. It can focus the sunlight a millionth times stronger in a smallest possible focal spot size, λ_Yellow=0.635 μm< λ_{Max photons} <λ_Red=0.73 μm, where the largest number of solar photons, 68%, according to the Plank radiation spectrum at 6000°K and the Lord Rayleigh diffraction limit. The solar panel seals individually such an array of 3D cavities of SVC enjoying theoretically from the UV 12% (wasted in passing through) visible 68% to the infrared 20% at a total of 16x5%~80% total QECNT per cell. The solar panel is made of light-weight carbon composite tolerating about 20% inactive fill factor and 10% dead pixels.

Proceedings Article | 3 April 2008 Paper

Paper

A non-cooperative long-range biometric image tracking and recognition (BITAR) method for maritime surveillance

Xiaokun Li, Genshe Chen, Erik Blasch, Harold Szu, Thomas McKenna

Proceedings Volume 6979, 697905 (2008) https://doi.org/10.1117/12.777443

KEYWORDS: Iris recognition, Cameras, Facial recognition systems, Biometrics, Video, Imaging systems, Image quality, Image processing, Target detection, Infrared cameras

Read Abstract +

Proceedings Article | 3 April 2008 Paper

Paper

Spatiotemporal sharpening of sub-pixel super-resolution by means of two infrared spectrum cameras for early cancer detection

Chia-Yen Lee, Hsin-Yu Hsieh, Si-Chen Lee, Chiun-Sheng Huang, Yeun-Chung Chang, Chung-Ming Chen, Harold Szu

Proceedings Volume 6979, 69790R (2008) https://doi.org/10.1117/12.793385

KEYWORDS: Infrared imaging, Infrared cameras, Cameras, Infrared spectroscopy, Cancer, Image registration, Breast cancer, Super resolution, Imaging systems, Breast

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Paper

Unsupervised learning with mini free energy

Harold Szu, Lidan Miao, Hairong Qi

Proceedings Volume 6576, 657605 (2007) https://doi.org/10.1117/12.725198

KEYWORDS: Infrared imaging, Breast cancer, Tumors, Mammography, Breast, Tissues, Thermography, Infrared cameras, Independent component analysis, Infrared radiation

Read Abstract +

In this paper, we present an unsupervised learning with mini free energy for early breast cancer detection. Although an early malignant tumor must be small in size, the abnormal cells reveal themselves physiologically by emitting spontaneously thermal radiation due to the rapid cell growth, the so-called angiogenesis effect. This forms the underlying principle of Thermal Infrared (TIR) imaging in breast cancer study. Thermal breast scanning has been employed for a number of years, which however is limited to a single infrared band. In this research, we deploy two satellite-grade dual-color (at middle wavelength IR (3 - 5&mgr;m) and long wavelength IR (8 - 12&mgr;m)) IR imaging cameras equipped with smart subpixel automatic target detection algorithms. According to physics, the radiation of high/low temperature bodies will shift toward a shorter/longer IR wavelength band. Thus, the measured vector data x per pixel can be used to invert the matrix-vector equation x=As pixel-by-pixel independently, known as a single pixel blind sources separation (BSS). We impose the universal constraint of equilibrium physics governing the blackbody Planck radiation distribution, i.e., the minimum Helmholtz free energy, H = E - T_oS. To stabilize the solution of Lagrange constrained neural network (LCNN) proposed by Szu et al., we incorporate the second order approximation of free energy, which corresponds to the second order constraint in the method of multipliers. For the subpixel target, we assume the constant ground state energy E_o can be determined by those normal neighborhood tissue, and then the excited state can be computed by means of Taylor series expansion in terms of the pixel I/O data. We propose an adaptive method to determine the neighborhood to find the free energy locally. The proposed methods enhance both the sensitivity and the accuracy of traditional breast cancer diagnosis techniques. It can be used as a first line supplement to traditional mammography to reduce the unwanted X-rays during the chemotherapy recovery. More important, the single pixel BSS method renders information on the tumor stage and tumor degree during the recovery process, which is not available using the popular independent component analysis (ICA) techniques.

Proceedings Article | 9 April 2007 Paper

Paper

Nanorobot assembly of carbon nanotubes for mid-IR sensor

Ning Xi, Jiangbo Zhang, Harold Szu, Guangyong Li

Proceedings Volume 6576, 65760K (2007) https://doi.org/10.1117/12.725188

KEYWORDS: Electrodes, Carbon nanotubes, Atomic force microscopy, Infrared detectors, Single walled carbon nanotubes, Augmented reality, Nanolithography, Infrared sensors, Infrared radiation, Sensors

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Paper

Implicit differential analysis for cortical models

Frank McFadden, Harold Szu

Proceedings Volume 6576, 657617 (2007) https://doi.org/10.1117/12.725209

KEYWORDS: Neurons, Neural networks, Systems modeling, Fusion energy, Differential equations, Biological research, Sensors, Scanning tunneling microscopy, Brain, Visual cortex

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Paper

Learning, entropy, free energy, an underlying commonality?

John Gray, Harold Szu

Proceedings Volume 6576, 657606 (2007) https://doi.org/10.1117/12.725208

KEYWORDS: Mechanics, Inverse problems, Complex systems, Independent component analysis, Wavelets, Sensors, Neural networks, Statistical modeling, Bayesian inference, Systems modeling

Read Abstract +

Statistical Mechanics, which is due primarily to Maxwell, Gibbs, and Boltzmann in the ninetieth century, has proven to be useful model for drawing inferences about the collective behavior of individual objects that interact according to a known force law (which for more general usage is referred to as interacting units.). Collective behavior is determined not by computing F = ma for each interacting unit because the problem is mathematically intractable. Instead, one computes the partition function for the collection of interacting units and predicts statistical behavior from the partition function. Statistical mechanics was united with Bayesian inference by Jaynes [4]. As a continuation, Shannon [7] demonstrated that the partition function assignment of probabilities via the interaction Hamiltonian is the solution to Bayesian assignment of probabilities (based on the maximum entropy method with known means and standard deviations). Once this technique has been applied to a variety of problems and obtained a solution, one can, of course, solve the inverse problem of to determine the solution to an inverse problem to determine what interaction model gives rise to a given probability assignment [1] and [8]. The usage of statistical mechanics allows one can draw general inferences about any complex system including networks [5] by defining "energy", "heat capacity", "temperature", and other thermodynamic characteristics of most complex systems based on the common standard of the Helmholtz free energy. Principle has noted that the aspect of entropy used in reasoning with uncertainty may not be the most appropriate entropy for learning mechanisms [6]. Instead he has explored using Renyi entropy and derived a form of information learning dynamics that has some promising features [2]. To fully realize the potential of the usage of a more generalized entropy to the three aspects of survival, we suggest some connections to the free energy and learning. We also connect some aspects of sensing to probability distributions that suggest why certain search strategies perform better than others. In making these connections, we suggest a fundamental connection waits to be discovered between inference, learning, and related to the manner in which sensing mechanisms perform.

Proceedings Article | 9 April 2007 Paper

Paper

Design of a cylindrical fiber-optic lens focusing passive dual-color IR spectra and readout

Kenneth Byrd, Harold Szu

Proceedings Volume 6576, 657607 (2007) https://doi.org/10.1117/12.731175

KEYWORDS: Fiber optics, Mid-IR, Tissues, Fusion energy, Infrared imaging, Infrared radiation, Tumors, Rectum, Refraction, Endoscopes

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Paper

Next gen wavelets down-sampling preserving statistics

Harold Szu, Lidan Miao, Pornchai Chanyagon, Masud Cader

Proceedings Volume 6576, 65760D (2007) https://doi.org/10.1117/12.725201

KEYWORDS: Wavelets, Discrete wavelet transforms, Wavelet transforms, Neodymium, Data compression, Surveillance, Infrared cameras, Sensors, Medicine, Computer graphics

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Paper

Noninvasive methodology for wellness baseline profiling

Danny Wen-Yaw Chung, Yuh-Show Tsai, Shaou-Gang Miaou, Walter Chang, Yaw-Jen Chang, Shia-Chung Chen, Y. Y. Hong, C. S. Chyang, Quan-Shong Chang, Hon-Yen Hsu, James Hsu, Wei-Cheng Yao, Ming-Sin Hsu, Ming-Chung Chen, Shi-Chen Lee, Charles Hsu, Lidan Miao, Kenny Byrd, Mohamed Chouikha, Xin-Bin Gu, Paul Wang, Harold Szu

Proceedings Volume 6576, 65760R (2007) https://doi.org/10.1117/12.724306

KEYWORDS: Glucose, Blood, Sensors, Thermography, Infrared imaging, Neurons, Tumors, System on a chip, Infrared cameras, Infrared radiation

Read Abstract +

We develop an accumulatively effective and affordable set of smart pair devices to save the exuberant expenditure for the healthcare of aging population, which will not be sustainable when all the post-war baby boomers retire (78 millions will cost 1/5~1/4 GDP in US alone). To design an accessible test-bed for distributed points of homecare, we choose two exemplars of the set to demonstrate the possibility of translation of modern military and clinical know-how, because two exemplars share identically the noninvasive algorithm adapted to the Smart Sensor-pairs for the real world persistent surveillance. Currently, the standard diagnoses for malignant tumors and diabetes disorders are blood serum tests, X-ray CAT scan, and biopsy used sometime in the physical checkup by physicians as cohort-average wellness baselines. The loss of the quality of life in making second careers productive may be caused by the missing of timeliness for correct diagnoses and easier treatments, which contributes to the one quarter of human errors generating the lawsuits against physicians and hospitals, which further escalates the insurance cost and wasteful healthcare expenditure. Such a vicious cycle should be entirely eliminated by building an "individual diagnostic aids (IDA)," similar to the trend of personalized drug, developed from daily noninvasive intelligent databases of the "wellness baseline profiling (WBP)". Since our physiology state undulates diurnally, the Nyquist anti-aliasing theory dictates a minimum twice-a-day sampling of the WBP for the IDA, which must be made affordable by means of noninvasive, unsupervised and unbiased methodology at the convenience of homes. Thus, a pair of military infrared (IR) spectral cameras has been demonstrated for the noninvasive spectrogram ratio test of the spontaneously emitted thermal radiation from a normal human body at 37°C temperature. This invisible self-emission spreads from 3 microns to 12 microns of the radiation wavelengths. This pair of cameras are used in the military satellite surveillance imaging operated at 3~5 mid IR band and 8~12 long IR band accompanied by several other UV and visible bands cameras. We can thereby measure accurately both the thermal emission bands at the mid IR and the long IR (X₁ X₂). The spectral ratio will be independent of the depth and imaging environment. Similarly, we will take six times per pair saliva samples (X₁ X₂) inside the upper jaw for three meals daily, of which the dynamics is shown as a delayed mirror image of "blood glucose level". And for which we must design a portable lab "system on chip (SOC)," and the micro-fluidity of pair channels per chemical reactions. According to the same biochemical principle of spontaneity, we apply the identical algorithm to determine both the ratio of hidden malignant and benign heat sources (s₁, s₂) and the blood glucose & other sources (s₁, s₂) leaking into the saliva. This is possible because of the Gibbs isothermal spontaneous process, in which the Helmholtz free energy must be minimized for the spontaneous thermal radiation from unknown mixing of malign and benign sources or the diffusion mixing of glucose s₁ * and other sources s₂ *. We have derived a general formula relating two equilibrium values, before and after, in order to design our devices. Daily tracking the spectrogram ratio and saliva glucose levels are, nevertheless, needed for a reliable prediction of individual malignant angiogenesis and blood glucose level in real time.

Proceedings Article | 9 April 2007 Paper

Paper

Wellness engineering for better quality of life of aging baby boomer

Harold Szu

Proceedings Volume 6576, 65760O (2007) https://doi.org/10.1117/12.725191

KEYWORDS: Surgery, Smart sensors, Profiling, Sensors, Automatic target recognition, Heart, Cancer, Independent component analysis, Surveillance, Medicine

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Paper

Autonomous unmanned air vehicles (UAV) techniques

Ming-Kai Hsu, Ting Lee

Proceedings Volume 6576, 657614 (2007) https://doi.org/10.1117/12.723182

KEYWORDS: Unmanned aerial vehicles, Optical flow, Image processing, Cameras, Stereo vision systems, Safety, Image resolution, Optical components, Surveillance, Roads

Read Abstract +

Proceedings Article | 20 May 2006 Paper

Paper

Interaction field modeling of mini-UAV swarm

William Liou, Kapseong Ro, Harold Szu

Proceedings Volume 6228, 62280N (2006) https://doi.org/10.1117/12.666555

KEYWORDS: Bismuth, Motion models, Aerodynamics, Solids, Molecular interactions, Unmanned aerial vehicles, Telecommunications, Molecules, Kinematics, Safety

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Designs of solar voltaic cells based on carbon nano-tubes

Hsu-Cheng Ou, Harold Szu

Proceedings Volume 6247, 62470F (2006) https://doi.org/10.1117/12.668995

KEYWORDS: Solar energy, Carbon nanotubes, Electrons, Solar cells, Photovoltaics, Silicon, Nanorobotics, Electrodes, Diodes, Semiconductors

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Light-weight cyptography for resource constrained environments

Patrick Baier, Harold Szu

Proceedings Volume 6247, 624711 (2006) https://doi.org/10.1117/12.668779

KEYWORDS: Computer security, Cryptanalysis, Detection and tracking algorithms, Computing systems, Data storage, Standards development, Algorithm development, Cryptography, Biometrics, Cell phones

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Authenticated, private, and secured smart cards (APS-SC)

Harold Szu, Amir Mehmood

Proceedings Volume 6247, 62470L (2006) https://doi.org/10.1117/12.684205

KEYWORDS: Computer security, Magnetism, Near field, Antennas, Radar, Information security, Receivers, Global Positioning System, Digital signal processing, Modulation

Read Abstract +

From historical perspective, the recent advancements in better antenna designs, low power circuitry integrations and inexpensive fabrication materials have made possible a miniature counter-measure against Radar, a clutter behaving like a fake target return called Digital Reflection Frequency Modulation (DRFM). Such a military counter-measure have found its way in the commerce as a near field communication known as Radio Frequency Identification (RFID), a passive or active item tag T attached to every readable-writable Smart Card (SC): Passports ID, medical patient ID, biometric ID, driver licenses, book ID, library ID, etc. These avalanche phenomena may be due to the 3^rd Gen phones seeking much more versatile & inexpensive interfaces, than the line-of-sight bar-code optical scan. Despite of the popularity of RFID, the lacking of Authenticity, Privacy and Security (APS) protection restricted somewhat the wide spread commercial, financial, medical, legal, and militarily applications. Conventional APS approach can obfuscate a private passkey K of SC with the tag number T or the reader number R, or both, i.e. only T*K or R*K or both will appear on them, where * denotes an invertible operation, e.g. EXOR, but not limited to it. Then, only the authentic owner, knowing all, can inverse the operation, e.g. EXOR*EXOR= I to find K. However, such an encryption could be easily compromised by a hacker seeking exhaustively by comparison based on those frequently used words. Nevertheless, knowing biological wetware lesson for power of pairs sensors and Radar hardware counter-measure history, we can counter the counter-measure DRFM, instead using one RFID tag per SD, we follow the Nature adopting two ears/tags, e.g. each one holding portions of the ID or simply two different ID's readable only by different modes of the interrogating reader, followed by brain central processor in terms of nonlinear invertible shufflers mixing two ID bits. We prefer to adopt such a hardware-software combined hybrid approach because of a too limited phase space of a single RFID for any meaningful encryption approach. Furthermore, a useful biological lesson is not to put all eggs in one basket, "if you don't get it all, you can't hack it". According to the Radar physics, we can choose the amplitude, the frequency, the phase, the polarization, and two radiation energy supply principles, the capacitance coupling (~6m) and the inductance coupling (<1m), to code the pair of tags differently. A casual skimmer equipped with single-mode reader can not read all. We consider near-field and mid-field applications each in this paper. The near-field is at check-out counters or the convey-belt inventory involving sensitive and invariant data. The mid-field search & rescue involves not only item/person identification, but also the geo-location. If more RF power becomes cheaper & portable for longer propagation distance in the near future, then a triangulation with pair of secured readers, located at known geo-locations, could interrogate and identify items/persons and their locations in a GPS-blind environment.

Proceedings Article | 17 April 2006 Paper

Paper

Hearing loss treatment through stem cell therapy

Nazanin Azizian, Harold Szu

Proceedings Volume 6247, 62470G (2006) https://doi.org/10.1117/12.669021

KEYWORDS: Ear, Stem cells, Nerve, Brain, Bone, Sensors, Injuries, Head, Tissues, Acoustics

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Real-time fusion of two polarization images overcoming hazy or misty days

Mehmet Kurum, Harold Szu

Proceedings Volume 6247, 62470O (2006) https://doi.org/10.1117/12.669568

KEYWORDS: Polarization, Dielectric polarization, Light scattering, Scattering, Radio propagation, Visualization, Water, Reflection, Particles, Electromagnetic radiation

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

A bio-nanorobot design for drosophila therapeutic cloning

Chia-Pin Chang, Harold Szu

Proceedings Volume 6247, 62470U (2006) https://doi.org/10.1117/12.674725

KEYWORDS: Microfluidics, Artificial intelligence, Genetics, Nanorobotics, Control systems, Stem cells, Atomic force microscopy, In vitro testing, Biology, Organisms

Read Abstract +

To investigate Somatic Cell Nuclear Transfer (SCNT), we choose the Drosophila cloning based on a recent experiment (Haigh, MacDonald, Lioyd, Gen. V.169,1165, 2005) to be improving the adulthood rate in 2-week turn-around time. Original 1% success rate might be due to three less certain key steps: (i) The double membranes of a nucleus has at its pore led to the attached Rough Endoplasmic Reticulum (ER), passing the genetic instruction to assemble amino acids, proteins and lipid at its smooth end. Also, any mismatch of nucleus with mitochondria (MT) having own small genome for energy production had led to reprogramming failure. (D. Wallace, UC Irvine, Nature,Vol. 439, pp.653). We ask "whether a guest DNA shall come with its servants, ER, MT, etc or not." It seemed to be logical to have a whole package replaced the embryonic host cell, equipped with all housekeeping, energy production and mitosis functionalities except the genetic information. To answer this hypothesis, we design a bio-NanoRobot having a surgical precision in removing the desired nucleus with or without its attached ER and MT material. The design is based on a real-time multiplexing principle of combining both the soft-contact-vision of the Nobel Laureate Binning called Atomic Force Microscope (AFM) and the hard-grasp-action called NanoRobot^TM by Xi and Szu, 2004. However, applying it, we must re-design a new bio-NanoRobot, consisting of two parts: (a) multiple resolution analysis (MRA) using AI to control a dual-resolution vision system: the soft-contact-vision AFM co-registered with a on-contact high resolution imaging; and (b) two cantilever arms capable to hold and enucleate a cell. The calibration and automation are controlled by AI Case-Based reasoning (CBR) together with AI Blackboard (BB) of the taxonomy, necessary for integrating different tool's tolerance and resolution at the same location. Moreover, keeping the biological sample in one place, while a set of tools rotates upon it similar to a set of microscopic lenses, we can avoid the non-real-time re-imaging, and inadvertent contamination. Applying an imposing electrical field, we can take the advantage of structure differences in smooth nuclear membranes inducing Van der Waal's forces versus random cytoplasm. (ii) The re-programming of transplanted cells to the ground state is unclear and usually relies on electrochemical means tested systematically in a modified 3D Caltech micro-fluidics. (iii) Our real-time MRA video-manipulator can elucidate the mitosis's tread-mill assembly mechanism in the development course of pluripotent stem cell differentiation into specialized tissue cell engineering. Such a combination bio-NanoRobot and micro-fluidic massive parallel assembly-line approach might not only replace the aspirating pipette with a self- enucleating Drosophila embryonic eggs, but also genetically reproduce a large amount of cloning embryonic eggs repeatedly for various re-programming hypotheses.

Proceedings Article | 17 April 2006 Paper

Paper

Authenticity and privacy of a team of mini-UAVs by means of nonlinear recursive shuffling

Ming-Kai Hsu, Patrick Baier, Ting Lee, James Buss, Rabinder Madan

Proceedings Volume 6247, 62470T (2006) https://doi.org/10.1117/12.670659

KEYWORDS: Chaos, Neural networks, Logic, Image encryption, Content addressable memory, Algorithm development, Artificial intelligence, Evolutionary algorithms, Neurons, Computer security

Read Abstract +

We have developed a real-time EOIR video counter-jittering sub-pixel image correction algorithm for a single mini- Unmanned Air Vehicle (m-UAV) for surveillance and communication (Szu et al. SPIE Proc. V 5439 5439, pp.183-197, April 12, 2004). In this paper, we wish to plan and execute the next challenge---- a team of m-UAVs. The minimum unit for a robust chain saw communication must have the connectivity of five second-nearest-neighbor members with a sliding, arbitrary center. The team members require an authenticity check (AC) among a unit of five, in order to carry out a jittering mosaic image processing (JMIP) on-board for every m-UAV without gimbals. The JMIP does not use any NSA security protocol ("cardinal rule: no-man, no-NSA codec"). Besides team flight dynamics (Szu et al "Nanotech applied to aerospace and aeronautics: swarming,' AIAA 2005-6933 Sept 26-29 2005), several new modules: AOA, AAM, DSK, AC, FPGA are designed, and the JMIP must develop their own control, command and communication system, safeguarded by the authenticity and privacy checks presented in this paper. We propose a Nonlinear Invertible (deck of card) Shuffler (NIS) algorithm, which has a Feistel structure similar to the Data Encryption Standard (DES) developed by Feistel et. al. at IBM in the 1970's; but DES is modified here by a set of chaotic dynamical shuffler Key (DSK), as re-computable lookup tables generated by every on-board Chaotic Neural Network (CNN). The initializations of CNN are periodically provided by the private version of RSA from the ground control to team members to avoid any inadvertent failure of broken chain among m-UAVs. Efficient utilization of communication bandwidth is necessary for a constantly moving and jittering m-UAV platform, e.g. the wireless LAN protocol wastes the bandwidth due to a constant need of hand-shaking procedures (as demonstrated by NRL; though sensible for PCs and 3^rd gen. mobile phones). Thus, the chaotic DSK must be embedded in a fault-tolerant Neural Network Associative Memory for the error-resilientconcealment mosaic image chip re-sent. However, the RSA public and private keys, chaos typing and initial value are given on set or sent to each m-UAV so that each platform knows only its private key. AC among 5 team members are possible using a reverse RSA protocol. A hashed image chip is coded by the sender's private key and nobody else knows in order to send to it to neighbors and the receiver can check the content by using the senders public key and compared the decrypted result with on-board image chips. We discover a fundamental problem of digital chaos approach in a finite state machine, of which a fallacy test of a discrete version is needed for a finite number of bits, as James Yorke advocated early. Thus, our proposed chaotic NIS for bits stream protection becomes desirable to further mixing the digital CNN outputs. The fault tolerance and the parallelism of Artificial Neural Network Associative Memory are necessary attributes for the neighborhood smoothness image restoration. The associated computational cost of O(N²) deems to be worthy, because the Chaotic version CNN of N-D can further provide the privacy only for the lost image chip (N=8x8) re-sent requested by its neighbors and the result is better performed than a simple 1-D logistic map. We gave a preliminary design of low end of FPGA firmware that to compute all on board seemed to be possible.

Proceedings Article | 17 April 2006 Paper

Paper

Reducing blocking artifacts in JPEG with Mill's Cross technique

Daniel Schneider, Harold Szu

Proceedings Volume 6247, 62470H (2006) https://doi.org/10.1117/12.669594

KEYWORDS: Image compression, Quantization, Internet, Computer programming, Image quality, Photography, Image storage, Electrochemical etching, Eye, Image quality standards

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Carbon nanotube noise characterization

Harold Szu, Bassam Noaman

Proceedings Volume 6247, 62470S (2006) https://doi.org/10.1117/12.670047

KEYWORDS: Single walled carbon nanotubes, Infrared cameras, Carbon nanotubes, Fourier transforms, Mid-IR, Thermography, Diffusion, Correlation function, Infrared radiation, Particles

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

4D time-frequency representation for binaural speech signal processing

Raed Mikhael, Harold Szu

Proceedings Volume 6247, 62470V (2006) https://doi.org/10.1117/12.668690

KEYWORDS: Ear, Time-frequency analysis, Signal processing, Wavelets, Independent component analysis, Personal digital assistants, Acoustics, Interference (communication), Signal to noise ratio, Doppler effect

Read Abstract +

Hearing is the ability to detect and process auditory information produced by the vibrating hair cilia residing in the corti of the ears to the auditory cortex of the brain via the auditory nerve. The primary and secondary corti of the brain interact with one another to distinguish and correlate the received information by distinguishing the varying spectrum of arriving frequencies. Binaural hearing is nature's way of employing the power inherent in working in pairs to process information, enhance sound perception, and reduce undesired noise. One ear might play a prominent role in sound recognition, while the other reinforces their perceived mutual information. Developing binaural hearing aid devices can be crucial in emulating the working powers of two ears and may be a step closer to significantly alleviating hearing loss of the inner ear. This can be accomplished by combining current speech research to already existing technologies such as RF communication between PDAs and Bluetooth. Ear Level Instrument (ELI) developed by Micro-tech Hearing Instruments and Starkey Laboratories is a good example of a digital bi-directional signal communicating between a PDA/mobile phone and Bluetooth. The agreement and disagreement of arriving auditory information to the Bluetooth device can be classified as sound and noise, respectively. Finding common features of arriving sound using a four coordinate system for sound analysis (four dimensional time-frequency representation), noise can be greatly reduced and hearing aids would become more efficient. Techniques developed by Szu within an Artificial Neural Network (ANN), Blind Source Separation (BSS), Adaptive Wavelets Transform (AWT), and Independent Component Analysis (ICA) hold many possibilities to the improvement of acoustic segmentation of phoneme, all of which will be discussed in this paper. Transmitted and perceived acoustic speech signal will improve, as the binaural hearing aid will emulate two ears in sound localization, speech understanding in noisy environment, and loudness differentiation.

Proceedings Article | 17 April 2006 Paper

Paper

Smart internet search engine through 6W

Stephen Goehler, Masud Cader, Harold Szu

Proceedings Volume 6247, 62470W (2006) https://doi.org/10.1117/12.669053

KEYWORDS: Internet, Lithium, Genetic algorithms, Medicine, Data conversion, Visualization, Analytical research, Internet technology, Stem cells, Matrices

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Interference and noise adjusted principal components analysis for hyperspectral remote sensing image compression

Qian Du, Harold Szu

Proceedings Volume 6247, 62470A (2006) https://doi.org/10.1117/12.665088

KEYWORDS: Principal component analysis, Image compression, Signal to noise ratio, Hyperspectral imaging, Data compression, Chromium, Remote sensing, Image quality, Image classification, Data analysis

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Passive IR flexi-scope with two spectral colors for household screening of gastrointestinal disorders

Kenneth Byrd, Harold Szu

Proceedings Volume 6247, 62470E (2006) https://doi.org/10.1117/12.668656

KEYWORDS: Prostate cancer, Prostate, Cancer, Tumors, Artificial neural networks, Infrared radiation, Infrared imaging, Biopsy, Sensors, Machine learning

Read Abstract +

Proceedings Article | 17 April 2006 Paper

Paper

Thermodynamic free-energy minimization for unsupervised fusion of dual-color infrared breast images

Harold Szu, Lidan Miao, Hairong Qi

Proceedings Volume 6247, 62470P (2006) https://doi.org/10.1117/12.670684

KEYWORDS: Infrared cameras, Infrared imaging, Tumors, Thermography, Cameras, Infrared radiation, Breast, Breast cancer, Independent component analysis, Tissues

Read Abstract +

This paper presents algorithmic details of an unsupervised neural network and unbiased diagnostic methodology, that is, no lookup table is needed that labels the input training data with desired outputs. We deploy the smart algorithm on two satellite-grade infrared (IR) cameras. Although an early malignant tumor must be small in size and cannot be resolved by a single pixel that images about hundreds cells, these cells reveal themselves physiologically by emitting spontaneously thermal radiation due to the rapid cell growth angiogenesis effect (In Greek: vessels generation for increasing tumor blood supply), shifting toward, according to physics, a shorter IR wavelengths emission band. If we use those exceedingly sensitive IR spectral band cameras, we can in principle detect whether or not the breast tumor is perhaps malignant through a thin blouse in a close-up dark room. If this protocol turns out to be reliable in a large scale follow-on Vatican experiment in 2006, which might generate business investment interests of nano-engineering manufacture of nano-camera made of 1-D Carbon Nano-Tubes without traditional liquid Nitrogen coolant for Mid IR camera, then one can accumulate the probability of any type of malignant tumor at every pixel over time in the comfort of privacy without religious or other concerns. Such a non-intrusive protocol alone may not have enough information to make the decision, but the changes tracked over time will be surely becoming significant. Such an ill-posed inverse heat source transfer problem can be solved because of the universal constraint of equilibrium physics governing the blackbody Planck radiation distribution, to be spatio-temporally sampled. Thus, we must gather two snapshots with two IR cameras to form a vector data X(t) per pixel to invert the matrix-vector equation X=[A]S pixel-by-pixel independently, known as a single-pixel blind sources separation (BSS). Because the unknown heat transfer matrix or the impulse response function [A] may vary from the point tumor to its neighborhood, we could not rely on neighborhood statistics as did in a popular unsupervised independent component analysis (ICA) mathematical statistical method, we instead impose the physics equilibrium condition of the minimum of Helmholtz free-energy, H = E - T_oS. In case of the point breast cancer, we can assume the constant ground state energy E_o to be normalized by those benign neighborhood tissue, and then the excited state can be computed by means of Taylor series expansion in terms of the pixel I/O data. We can augment the X-ray mammogram technique with passive IR imaging to reduce the unwanted X-rays during the chemotherapy recovery. When the sequence is animated into a movie, and the recovery dynamics is played backward in time, the movie simulates the cameras' potential for early detection without suffering the PD=0.1 search uncertainty. In summary, we applied two satellite-grade dual-color IR imaging cameras and advanced military (automatic target recognition) ATR spectrum fusion algorithm at the middle wavelength IR (3 - 5μm) and long wavelength IR (8 - 12μm), which are capable to screen malignant tumors proved by the time-reverse fashion of the animated movie experiments. On the contrary, the traditional thermal breast scanning/imaging, known as thermograms over decades, was IR spectrum-blind, and limited to a single night-vision camera and the necessary waiting for the cool down period for taking a second look for change detection suffers too many environmental and personnel variabilities.

SPIE Journal Paper | 1 January 2006

Independent-component analysis for hyperspectral remote sensing imagery classification

Qian Du, Ivica Kopriva, Harold Szu

OE, Vol. 45, Issue 01, 017008, (January 2006) https://doi.org/10.1117/12.10.1117/1.2151172

KEYWORDS: Independent component analysis, Principal component analysis, Image classification, Hyperspectral imaging, Optical engineering, Remote sensing, Signal to noise ratio, Scene classification, Minerals, Dimension reduction

Read Abstract +

Proceedings Article | 12 October 2005 Paper

Paper

Carbon nanotube-based spectrum infrared detectors

Ning Xi, Harold Szu, James Buss, Ingham Mack

Proceedings Volume 5987, 59870M (2005) https://doi.org/10.1117/12.631219

KEYWORDS: Electrodes, Infrared detectors, Atomic force microscopy, Nanomanipulation, Carbon nanotubes, Infrared radiation, Sensors, Infrared sensors, Photodetectors, Quantum well infrared photodetectors

Read Abstract +

Proceedings Article | 28 March 2005 Paper

Paper

Synthesis of blind source separation algorithms on reconfigurable FPGA platforms

Hongtao Du, Hairong Qi, Harold Szu

Proceedings Volume 5818, (2005) https://doi.org/10.1117/12.604839

KEYWORDS: Field programmable gate arrays, Independent component analysis, Data modeling, Algorithm development, Clocks, Computing systems, Machine learning, Transistors, C++, Autoregressive models

Read Abstract +

Recent advances in intelligence technology have boosted the development of micro- Unmanned Air Vehicles (UAVs) including Sliver Fox, Shadow, and Scan Eagle for various surveillance and reconnaissance applications. These affordable and reusable devices have to fit a series of size, weight, and power constraints. Cameras used on such micro-UAVs are therefore mounted directly at a fixed angle without any motion-compensated gimbals. This mounting scheme has resulted in the so-called jitter effect in which jitter is defined as sub-pixel or small amplitude vibrations. The jitter blur caused by the jitter effect needs to be corrected before any other processing algorithms can be practically applied. Jitter restoration has been solved by various optimization techniques, including Wiener approximation, maximum a-posteriori probability (MAP), etc. However, these algorithms normally assume a spatial-invariant blur model that is not the case with jitter blur. Szu et al. developed a smart real-time algorithm based on auto-regression (AR) with its natural generalization of unsupervised artificial neural network (ANN) learning to achieve restoration accuracy at the sub-pixel level. This algorithm resembles the capability of the human visual system, in which an agreement between the pair of eyes indicates "signal", otherwise, the jitter noise. Using this non-statistical method, for each single pixel, a deterministic blind sources separation (BSS) process can then be carried out independently based on a deterministic minimum of the Helmholtz free energy with a generalization of Shannon's information theory applied to open dynamic systems. From a hardware implementation point of view, the process of jitter restoration of an image using Szu's algorithm can be optimized by pixel-based parallelization. In our previous work, a parallelly structured independent component analysis (ICA) algorithm has been implemented on both Field Programmable Gate Array (FPGA) and Application-Specific Integrated Circuit (ASIC) using standard-height cells. ICA is an algorithm that can solve BSS problems by carrying out the all-order statistical, decorrelation-based transforms, in which an assumption that neighborhood pixels share the same but unknown mixing matrix A is made. In this paper, we continue our investigation on the design challenges of firmware approaches to smart algorithms. We think two levels of parallelization can be explored, including pixel-based parallelization and the parallelization of the restoration algorithm performed at each pixel. This paper focuses on the latter and we use ICA as an example to explain the design and implementation methods. It is well known that the capacity constraints of single FPGA have limited the implementation of many complex algorithms including ICA. Using the reconfigurability of FPGA, we show, in this paper, how to manipulate the FPGA-based system to provide extra computing power for the parallelized ICA algorithm with limited FPGA resources. The synthesis aiming at the pilchard re-configurable FPGA platform is reported. The pilchard board is embedded with single Xilinx VIRTEX 1000E FPGA and transfers data directly to CPU on the 64-bit memory bus at the maximum frequency of 133MHz. Both the feasibility performance evaluations and experimental results validate the effectiveness and practicality of this synthesis, which can be extended to the spatial-variant jitter restoration for micro-UAV deployment.

Proceedings Article | 28 March 2005 Paper

Paper

Classifying hyperspectral remote sensing imagery with independent component analysis

Qian Du, Ivica Kopriva, Harold Szu

Proceedings Volume 5818, (2005) https://doi.org/10.1117/12.603189

KEYWORDS: Independent component analysis, Principal component analysis, Hyperspectral imaging, Image classification, Remote sensing, Signal to noise ratio, Data modeling, Image processing, Signal processing, Dimension reduction

Read Abstract +

Proceedings Article | 28 March 2005 Paper

Paper

Hybrid information privacy system: integration of chaotic neural network and RSA coding

Ming-Kai Hsu, Jeff Willey, Ting Lee, Harold Szu

Proceedings Volume 5818, (2005) https://doi.org/10.1117/12.610802

KEYWORDS: Chaos, Neural networks, Image encryption, Telecommunications, Neurons, Digital watermarking, Logic, Computer security, Network security, Convolution

Read Abstract +

Proceedings Article | 12 April 2004 Paper

Paper

Image sharpening using image sequence and independent component analysis

Ivica Kopriva, Qian Du, Harold Szu

Proceedings Volume 5439, (2004) https://doi.org/10.1117/12.542122

KEYWORDS: Independent component analysis, Video, Image analysis, Image sensors, Sensors, Atmospheric turbulence, Image registration, Turbulence

Read Abstract +

Proceedings Article | 12 April 2004 Paper

Paper

Early breast tumor and late SARS detections using space-variant multispectral infrared imaging at a single pixel

Harold Szu, James Buss, Ivica Kopriva

Proceedings Volume 5439, (2004) https://doi.org/10.1117/12.548916

KEYWORDS: Tumors, Synthetic aperture radar, Breast, Multispectral imaging, Infrared imaging, Inverse problems, Physics, Independent component analysis, Image processing, Remote sensing

Read Abstract +

Proceedings Article | 12 April 2004 Paper

Paper

Subpixel jitter video restoration on board of micro-UAV

Harold Szu, James Buss, Joseph Garcia, Nancy Breaux, Ivica Kopriva, Nicholas Karangelen, M. Hsu, Ting Lee, Jeff Willey, Gary Shield, Steve Brown, R. Robbins, John Hobday

Proceedings Volume 5439, (2004) https://doi.org/10.1117/12.563654

KEYWORDS: Video, Silver, Data storage, Image processing, Aerodynamics, Unmanned aerial vehicles

Read Abstract +

Proceedings Article | 12 April 2004 Paper

Paper

Independent component analysis for remotely sensed image classification with limited data dimensionality

Qian Du, Ivica Kopriva, Harold Szu, James Buss

Proceedings Volume 5439, (2004) https://doi.org/10.1117/12.541924

KEYWORDS: Independent component analysis, Image classification, Scene classification, Photography, Landsat, Earth observing sensors

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Postprocessing technique for Lagrangian artificial neural network approach to hyperspectral image classification

Qian Du, Harold Szu, Hsuan Ren

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.485964

KEYWORDS: Hyperspectral imaging, Artificial neural networks, Image classification, Image analysis, Image processing, Interference (communication), Vegetation, Sensors, Visualization, Independent component analysis

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Units of video compression

Ming-Kai Hsu, Charles Hsu, Harold Szu, Ting Lee

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.513444

KEYWORDS: Video compression, Video, Image compression, Image segmentation, Optical flow, Spatial frequencies, Wavelets, Distortion, Contrast sensitivity, Space operations

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Chaotic neural network for learnable associative memory recall

Charles Hsu, Harold Szu

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.502480

KEYWORDS: Neurons, Neural networks, Content addressable memory, Fuzzy logic, Resistors, Image processing, Device simulation, Nose, Artificial neural networks, Chaos

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Rectification of nonlinearity in pre-amplifier and A/D converter of biomedical instruments

Jun Yang, Seong-Bin Yim, Ivica Kopriva, Harold Szu

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.501740

KEYWORDS: Independent component analysis, Electrocardiography, Complex systems, Amplifiers, Biomedical optics, Signal processing, Statistical analysis, Data acquisition, Diagnostics, Fetus

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Blind inversion in nonlinear space-variant imaging by using Cauchy machine

Ivica Kopriva, Harold Szu

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.501498

KEYWORDS: Independent component analysis, Algorithms, Error analysis, Neural networks, Thermodynamics, Sensors, Stochastic processes, Optimization (mathematics), Evolutionary algorithms, Remote sensing

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Gene expression signature discovery with independent component analysis

Harold Szu, David Portnoy

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.501628

KEYWORDS: Independent component analysis, Melanoma, Signal processing, Tissues, Statistical analysis, Tumors, Sensors, Biological research, Distance measurement, Control systems

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Independent component analysis (ICA) and self-organizing map (SOM) approach to multidetection system for network intruders

Abdi Abdi, Harold Szu

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.502262

KEYWORDS: Computer intrusion detection, Independent component analysis, Data modeling, Telecommunications, Computing systems, Machine learning, Neural networks, Network security, Rule based systems, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 1 April 2003 Paper

Paper

Live biometric authenticity check

Harold Szu, Charles Hsu, Clifford Szu, Shoujue Wang

Proceedings Volume 5102, (2003) https://doi.org/10.1117/12.502477

KEYWORDS: Computer security, Biometrics, Wavelets, Computing systems, Video, Image compression, Modulation transfer functions, Neural networks, Video compression, Algorithm development

Read Abstract +

Proceedings Article | 8 March 2002 Paper

Paper

Lagrange constraint neural network for fully constrained subpixel classification in hyperspectral imagery

Hsuan Ren, Harold Szu, James Buss

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458766

KEYWORDS: Neural networks, Image classification, Hyperspectral imaging, Vegetation, Neurons, Remote sensing, Biological research, Chemical analysis, Image processing, Independent component analysis

Read Abstract +

Proceedings Article | 8 March 2002 Paper

Paper

Lagrange constraint neural network for audio varying BSS

Harold Szu, Charles Hsu

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458767

KEYWORDS: Independent component analysis, Acoustics, Wavelets, Neural networks, Neurons, Remote sensing, Reflectivity, Statistical modeling, Image information entropy, Phonons

Read Abstract +

Proceedings Article | 8 March 2002 Paper

Paper

Fast LCNN ICA for unsupervised hyperspectral image classifier

Ivica Kopriva, Harold Szu

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458765

KEYWORDS: Independent component analysis, Hyperspectral imaging, Reflectivity, Data modeling, Remote sensing, Image information entropy, Evolutionary algorithms, Field programmable gate arrays, Physics, Photons

Read Abstract +

Proceedings Article | 8 March 2002 Paper

Paper

Video via radio testbed

Harold Szu, Charles Hsu

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458761

KEYWORDS: Wavelets, Video compression, Video, Image compression, Visualization, Convolution, Diffusion, Video processing, Neurons, Signal detection

Read Abstract +

In this paper, an efficient video compression (CR, compression ratio,approximately equals 1000:1) mechanism is presented, and that preserves not only the visual acuity but also the perception fidelity. This is possible because we have made novel utilization of the Human Vision System (HVS). It is well known that our eyes do not pay attention to image pixels rather to intensity changes. Thus the traditional compression based on pixels' dynamic range reduction at all pixel level could be overkill. We furthermore label the discontinuity of the intensity with the derivative jump value across the boundary as the finger print of the edge, and that label together with its actual gray scale value are called the singularity map (SM) that enable us uniquely identify those corresponding control points among neighbor- hood frames without the usual exhaustive search at all image pixels level. The proposed video compression consists of two parallel operations: (1) sending the lossy compression of full image by the HVS wavelets without, however, the block artifact of DCT of JPEG or MPEG, and (2) inserting the original gray scale edge preserved by the SM before the lossy compression operation. Although we know how HVS can extract the SM without the convolution broadening, effectively if we could separate the address from the actual value, we can derive the address by taking into consideration the usual convolution broadening using the Sobel and Canny or any edge operator. Once the address of SM is sharpened without the broadening by inverse diffusion or other tricks, we can straightforwardly look up the actual image value at the gray scale edge from the original image. Since the correspondence among neighborhood frames of the singularity maps is followed in time, we need only send the change of the address without the need of sending the next frame and that fact further compress the redundancy in time from K bytes per frame to K bits on the average. This is the essential principle to enable us to transmit live video via the SINGARS radio at a narrow bandwidth of 16 K bps.

Proceedings Article | 8 March 2002 Paper

Paper

Power-line communication testbed through underdetermined blind source separation

Pornchai Chanyagorn, Ivica Kopriva, Harold Szu

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458760

KEYWORDS: Data modeling, Sensors, Signal to noise ratio, Transformers, Binary data, Interference (communication), Data communications, Receivers, Signal attenuation, Broadband telecommunications

Read Abstract +

Proceedings Article | 8 March 2002 Paper

Paper

Lagrange constraint neural networks for massive pixel parallel image demixing

Harold Szu, Charles Hsu

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458764

KEYWORDS: Landsat, Satellites, Earth observing sensors, Sensors, Remote sensing, Independent component analysis, Neural networks, Reflectivity, Neurons, Photons

Read Abstract +

We have shown that the remote sensing optical imaging to achieve detailed sub-pixel decomposition is a unique application of blind source separation (BSS) that is truly linear of far away weak signal, instantaneous speed of light without delay, and along the line of sight without multiple paths. In early papers, we have presented a direct application of statistical mechanical de-mixing method called Lagrange Constraint Neural Network (LCNN). While the BSAO algorithm (using a posteriori MaxEnt ANN and neighborhood pixel average) is not acceptable for remote sensing, a mirror symmetric LCNN approach is all right assuming a priori MaxEnt for unknown sources to be averaged over the source statistics (not neighborhood pixel data) in a pixel-by-pixel independent fashion. LCNN reduces the computation complexity, save a great number of memory devices, and cut the cost of implementation. The Landsat system is designed to measure the radiation to deduce surface conditions and materials. For any given material, the amount of emitted and reflected radiation varies by the wavelength. In practice, a single pixel of a Landsat image has seven channels receiving 0.1 to 12 microns of radiation from the ground within a 20x20 meter footprint containing a variety of radiation materials. A-priori LCNN algorithm provides the spatial-temporal variation of mixture that is hardly de-mixable by other a-posteriori BSS or ICA methods. We have already compared the Landsat remote sensing using both methods in WCCI 2002 Hawaii. Unfortunately the absolute benchmark is not possible because of lacking of the ground truth. We will arbitrarily mix two incoherent sampled images as the ground truth. However, the constant total probability of co-located sources within the pixel footprint is necessary for the remote sensing constraint (since on a clear day the total reflecting energy is constant in neighborhood receiving pixel sensors), we have to normalized two image pixel-by-pixel as well. Then, the result is indeed as expected.

Proceedings Article | 8 March 2002 Paper

Paper

Matched low-pass filter design for orthogonal IIR filter banks

Larry Wilkinson, Ajit Bopardikar, Raghuveer Rao, Harold Szu

Proceedings Volume 4738, (2002) https://doi.org/10.1117/12.458732

KEYWORDS: Linear filtering, Optical filters, Infinite impulse response filters, Filtering (signal processing), Wavelets, Finite impulse response filters, Optimal filtering, Electronic filtering, Image compression, Image filtering

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Ultraspectral: hyperspectral and rf features registered by IFSAR

Harold Szu, Charles Hsu

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421207

KEYWORDS: Synthetic aperture radar, Interferometric synthetic aperture radar, Hyperspectral imaging, Independent component analysis, Polarization, Imaging systems, Radar, Landsat, Image processing, Earth observing sensors

Read Abstract +

Hyperspectral remote sensing by air platforms can passively generate over two hundred channels of images of terabyte data the ground surface reflectance/eminence simultaneously, with wavelength ranging from 0.4 to 2.5 micrometers and to include a full infrared spectrum. We have extended the hyperspectral to include RF spectral for both the foliage penetration (from L band 1 GHz to UHF band 0.5 GHz,) using the polarization RF features and the terrain location ID for automatic navigation registration. These generalizations are possible because we have based our design of the foliage penetration (FOPEN) Interferometric Synthetic Aperture Radar (IFSAR) on all digital transceiver array and Field Programmable Gate Arrays (FPGA). We are able to do that, since we have leveraged the ONR 100 dB Digital Array Radar (DAR) for shipboard volume search radar (VSR) using the matured & rugged GaAs cellular phone technology. We study whether the high dynamic range DAR VSR approach can overcome the long baseline terran curvature (that might otherwise not be suited for the FOLPEN low frequency IFSAR). We show the standard deviation of the phase digital resolution better then 1o might overcome the terrain curvature due to low frequency, and long time integration. The applications of this technology include environmental monitoring and mineral exploration and mining, communication and Aided Target Recognition (ATR). The hyperspectral imagery takes the advantage of more unique spectral signature in terms of the massively parallel artificial neural network computation using the unsupervised learning Independent Component Analyses (ICA) algorithm introduced to the Landsat by Szu. The supervised classification is based on the library of spectral signals of known object material characteristics using various constrained versions of the orthogonal subspace projections (OSP) by. In this paper, we combine both the supervised OSP and the unsupervised ICA hyperspectral imaging algorithms. Then, we present all digital version of FOPEN SAR, considered as one of RF channels in ultraspectral image processing. Taking the advantage of the high dynamic range ONR DAR VSR technology, we can measure both RF signatures and 3D terrain by means of Interferometric (IF) FOPEN SAR. We prefer a real-time one-path fly over using bi-static Interferometric SAR equipped with a Stokes polarization vector information that can provide us with not only the RF signatures but also terrain height for location ID (knowing terran contour map stored in the flight data basis). Such an ultraspectral imaging feature-fusion system can manage Forrest search and rescue when it is complement IFSAR FOPEN with high-resolution EO/IR signatures. Conclusion and discussion are given in the final section.

Proceedings Article | 26 March 2001 Paper

Paper

Adaptive independent component analysis to analyze electrocardiograms

Seong-Bin Yim, Harold Szu

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421224

KEYWORDS: Independent component analysis, Electrocardiography, Heart, Signal detection, Sensors, Neural networks, Interference (communication), Nonlinear optics, Signal processing, Databases

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Video compression transmission via FM radio

Chat Do, Harold Szu

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421226

KEYWORDS: Video, Video compression, Televisions, Frequency modulation, Fermium, Modulation, Receivers, Amplitude modulation, FM band, RF communications

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Independent component analysis for multiple access interference noise cancellation

Ming Ye, Harold Szu

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421223

KEYWORDS: Independent component analysis, Antennas, Wavelets, Interference (communication), Neural networks, Telecommunications, Receivers, Signal processing, Binary data, Data communications

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Unified Lagrangian neural network method for subpixel classification in hyperspectral imagery

Harold Szu, Hsuan Ren

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421228

KEYWORDS: Hyperspectral imaging, Neurons, Image classification, Neural networks, Independent component analysis, Remote sensing, Landsat, Vegetation, Multispectral imaging, Earth observing sensors

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Phonocardiography nonlinear multiple measurements in discovering the abnormalities in the bioprosthetic heart valves

Hussam Mustafa, Harold Szu, Nicholas Kyriakopoulos, Mohammed Ameen

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421229

KEYWORDS: Independent component analysis, Heart, Electrocardiography, Signal detection, Acoustics, Feature extraction, Ear, Fourier transforms, Nonlinear optics, Machine learning

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Design of FPGA ICA for hyperspectral imaging processing

Anis Nordin, Charles Hsu, Harold Szu

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421225

KEYWORDS: Independent component analysis, Field programmable gate arrays, MATLAB, Hyperspectral imaging, Neural networks, Logic, Remote sensing, Image resolution, Computer programming, Data processing

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Noisy image superresolution by artificial neural networks

Harold Szu, Ivica Kopriva

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421186

KEYWORDS: Imaging systems, Artificial neural networks, Super resolution, Independent component analysis, Lithium, Diffraction, Wavelets, Dysprosium, Quantum wells, Geometrical optics

Read Abstract +

Proceedings Article | 26 March 2001 Paper

Paper

Fully digital foliage-penetrating synthetic aperture radar processor

Stephen Arnold, Charles Hsu, Mona Zaghloul, Harold Szu, Nicholas Karangelen, James Buss

Proceedings Volume 4391, (2001) https://doi.org/10.1117/12.421208

KEYWORDS: Synthetic aperture radar, Digital filtering, MATLAB, Detection and tracking algorithms, Image processing, Reconstruction algorithms, Signal processing, Computer simulations, Algorithm development, Device simulation

Read Abstract +

Proceedings Article | 15 December 2000 Paper

Paper

Independent component analysis approach to resolve the multisource limitation of the reticle-based optical trackers

Ivica Kopriva, Harold Szu

Proceedings Volume 4130, (2000) https://doi.org/10.1117/12.409910

KEYWORDS: Reticles, Independent component analysis, Optical tracking, Sensors, Frequency modulation, Fermium, Modulation, Detection theory, Detection and tracking algorithms, Optical design

Read Abstract +

Proceedings Article | 16 June 2000 Open Access

Open Access

Paper

Current progress in multiple-image blind demixing algorithms

Harold Szu

Proceedings Volume 3831, (2000) https://doi.org/10.1117/12.388716

KEYWORDS: Independent component analysis, Sensors, Cameras, Machine learning, Neurons, Image sensors, Fourier transforms, Wavelets, Visual system, Artificial neural networks

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Human visual system singularity map analyses

Harold Szu, Hongye Wang, Pornchai Chanyagorn

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381715

KEYWORDS: Visualization, Neurons, Filtering (signal processing), Signal processing, Neural networks, Visual system, Diffusion, Convolution, Signal detection, Wavelets

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Local ICA for the Most Wanted face recognition

Xin Guan, Harold Szu, Zvi Markowitz

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381716

KEYWORDS: Independent component analysis, Principal component analysis, Facial recognition systems, Databases, Mouth, Nose, Feature extraction, Data modeling, Machine learning, Visual process modeling

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Unsupervised ICA neural networks applied to reticle optical trackers

Ivica Kopriva, Harold Szu

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381677

KEYWORDS: Reticles, Independent component analysis, Optical tracking, Frequency modulation, Fermium, Sensors, Modulation, Amplitude modulation, Detection theory, Nonlinear optics

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Multimedia authenticity with ICA watermarks

Steven Noel, Harold Szu

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381712

KEYWORDS: Multimedia, Digital watermarking, Independent component analysis, Neural networks, Sensors, Signal processing, Image compression, Data hiding, Internet, Video

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

ICA neural net to refine remote sensing with multiple labels

Harold Szu, James Buss

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381669

KEYWORDS: Independent component analysis, Remote sensing, Neurons, Sensors, Machine learning, Landsat, Reflectivity, Neural networks, Image sensors, Earth observing sensors

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Ranking ICA bases by associative memory recalls of training texture samples

Mohammed Ameen, Pornchai Chanyagorn, Harold Szu

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381714

KEYWORDS: Independent component analysis, Principal component analysis, Feature extraction, Content addressable memory, Analytical research, Remote sensing, Statistical analysis, Algorithm development, Image information entropy, Artificial neural networks

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Real world analysis of electromagnetic pulses using adaptive wavelet transforms

Nancy Breaux, Harold Szu

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381689

KEYWORDS: Wavelet transforms, Wavelets, Continuous wavelet transforms, Fourier transforms, Electromagnetism, Physics, Discrete wavelet transforms, Analytical research, Modulation, Statistical modeling

Read Abstract +

Proceedings Article | 5 April 2000 Paper

Paper

Causal stable matched IIR wavelets and perfect reconstruction filter banks

Raghuveer Rao, Alex Lopez-Estrada, Ajit Bopardikar, Harold Szu

Proceedings Volume 4056, (2000) https://doi.org/10.1117/12.381684

KEYWORDS: Wavelets, Optical filters, Linear filtering, Filtering (signal processing), Finite impulse response filters, Electronic filtering, Image compression, Infinite impulse response filters, Signal processing, Image understanding

Read Abstract +

Proceedings Article | 22 March 1999 Paper

Paper

Recent progresses of neural network unsupervised learning: part IIreal world applications

Harold Szu

Proceedings Volume 3723, (1999) https://doi.org/10.1117/12.342954

KEYWORDS: Independent component analysis, Sensors, Remote sensing, Reflectivity, Neurons, Robots, Cameras, Landsat, Machine learning, Earth observing sensors

Read Abstract +

Proceedings Article | 22 March 1999 Paper

Paper

Recent development using H.263 and wavelets for digital video/image compression and implementation

Charles Hsu, Paul Cox, Harold Szu

Proceedings Volume 3723, (1999) https://doi.org/10.1117/12.342932

KEYWORDS: Image compression, Image processing, Video, Video compression, Discrete wavelet transforms, Image enhancement, Image filtering, Wavelets, Video processing, Signal processing

Read Abstract +

Proceedings Article | 22 March 1999 Paper

Paper

Video compression with embedded wavelet coding and singularity maps

Steven Noel, Harold Szu, Nian-Feng Tzeng, Chee-Hung Chu, Santipong Tanchatchawal

Proceedings Volume 3723, (1999) https://doi.org/10.1117/12.342947

KEYWORDS: Video compression, Wavelets, Video, Wavelet transforms, Defense technologies, Computer programming, Visual compression, Visualization, Motion estimation, Multimedia

Read Abstract +

Proceedings Article | 22 March 1999 Paper

Paper

Landsat PNN classifier using PCA of wavelet texture-edge features

Harold Szu, Jacqueline Le Moigne, Nathan Netanyahu, Charles Hsu

Proceedings Volume 3723, (1999) https://doi.org/10.1117/12.342922

KEYWORDS: Wavelets, Image classification, Neural networks, Wavelet transforms, Composites, Remote sensing, Landsat, Principal component analysis, Satellites, Earth observing sensors

Read Abstract +

Proceedings Article | 22 March 1999 Paper

Paper

Recent progresses of neural network unsupervised learning: I. Independent component analyses generalizing PCA

Harold Szu

Proceedings Volume 3722, (1999) https://doi.org/10.1117/12.342876

KEYWORDS: Sensors, Machine learning, Independent component analysis, Principal component analysis, Neurons, Neural networks, Wavelets, Positron emission tomography, Robots, Fourier transforms

Read Abstract +

The early vision principle of redundancy reduction of 10⁸ sensor excitations is understandable from computer vision viewpoint toward sparse edge maps. It is only recently derived using a truly unsupervised learning paradigm of artificial neural networks (ANN). In fact, the biological vision, Hubel- Wiesel edge maps, is reproduced seeking the underlying independent components analyses (ICA) among 10² image samples by maximizing the ANN output entropy (partial)H(V)/(partial)[W] equals (partial)[W]/(partial)t. When a pair of newborn eyes or ears meet the bustling and hustling world without supervision, they seek ICA by comparing 2 sensory measurements (x₁(t), x₂(t))^T equalsV X(t). Assuming a linear and instantaneous mixture model of the external world X(t) equals [A] S(t), where both the mixing matrix ([A] equalsV [a₁, a₂] of ICA vectors and the source percentages (s₁(t), s₂(t))^T equalsV S(t) are unknown, we seek the independent sources <S(t) S^T(t)> approximately equals [I] where the approximated sign indicates that higher order statistics (HOS) may not be trivial. Without a teacher, the ANN weight matrix [W] equalsV [w₁, w₂] adjusts the outputs V(t) equals tanh([W]X(t)) approximately equals [W]X(t) until no desired outputs except the (Gaussian) 'garbage' (neither YES '1' nor NO '-1' but at linear may-be range 'origin 0') defined by Gaussian covariance <V(t) V(t)^T>_G equals [I] equals [W][A] <S(t) S^T(t)greater than [A]^T[W]^T. Thus, ANN obtains [W][A] approximately equals [I] without an explicit teacher, and discovers the internal knowledge representation [W], as the inverse of the external world matrix [A]^-1. To unify IC, PCA, ANN & HOS theories since 1991 (advanced by Jutten & Herault, Comon, Oja, Bell-Sejnowski, Amari-Cichocki, Cardoso), the LYAPONOV function L(v₁,...,v_n, w₁,...w_n,) equals E(v₁,...,v_n) - H(w₁,...w_n) is constructed as the HELMHOTZ free energy to prove both convergences of supervised energy E and unsupervised entropy H learning. Consequently, rather using the faithful but dumb computer: 'GARBAGE-IN, GARBAGE-OUT,' the smarter neurocomputer will be equipped with an unsupervised learning that extracts 'RAW INFO-IN, (until) GARBAGE-OUT' for sensory knowledge acquisition in enhancing Machine IQ. We must go beyond the LMS error energy, and apply HOS To ANN. We begin with the Auto- Regression (AR) which extrapolates from the past X(t) to the future u_i(t+1) equals w_i^TX(t) by varying the weight vector in minimizing LMS error energy E equals <[x(t+1) - u_i(t+1)]²> at the fixed point (partial)E/(partial)w_i equals 0 resulted in an exact Toplitz matrix inversion for a stationary covariance assumption. We generalize AR by a nonlinear output v_i(t+1) equals tanh(w_i^TX(t)) within E equals <[x(t+1) - v_i(t+1)]²>, and the gradient descent (partial)E/(partial)w_i equals - (partial)w_i/(partial)t. Further generalization is possible because of specific image/speech having a specific histogram whose gray scale statistics departs from that of Gaussian random variable and can be measured by the fourth order cumulant, Kurtosis K(v_i) equals <v_i⁴> - 3 <v_i²>² (K greater than or equal to 0 super-G for speeches, K less than or equal to 0 sub-G for images). Thus, the stationary value at (partial)K/(partial)w_i equals plus or minus 4 PTLw_i/(partial)t can de-mix unknown mixtures of noisy images/speeches without a teacher. This stationary statistics may be parallel implemented using the 'factorized pdf code: (rho) (v₁, v₂) equals (rho) (v₁) (rho) (v₂)' occurred at a maximal entropy algorithm improved by the natural gradient of Amari. Real world applications are given in Part II, (Wavelet Appl-VI, SPIE Proc. Vol. 3723) such as remote sensing subpixel composition, speech segmentation by means of ICA de-hyphenation, and cable TV bandwidth enhancement by simultaneously mixing sport and movie entertainment events.

SPIE Journal Paper | 1 October 1998

WaveNet Processing Brassboards for Live Video via Radio

Charles Hsu, Harold Szu

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482662

KEYWORDS: Image compression, Video, Discrete wavelet transforms, Video compression, Digital signal processing, Image processing, Image filtering, Image enhancement, Wavelets, Filtering (signal processing)

SPIE Journal Paper | 1 October 1998

Video Johnson-like criterion for moving vehicle identification

Harold Szu, Paul Cox, Charles Hsu

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482657

KEYWORDS: Video, Video compression, Sensors, Wavelets, Contrast sensitivity, Modulation transfer functions, Image processing, Target recognition, Electro optical sensors, Target detection

SPIE Journal Paper | 1 October 1998

Proximity sensing with wavelet-generated video

Steven Noel, Harold Szu

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482656

KEYWORDS: Doppler effect, Wavelets, Video, Sensors, Pattern recognition, Neural networks, Continuous wavelet transforms, Wavelet transforms, Signal processing, Neurons

SPIE Journal Paper | 1 October 1998

Image error resilient and video error concealment codes for wavelet compression and noisy channel communication

Harold Szu, Duc Hai Do

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482664

KEYWORDS: Image compression, Wavelets, Quantization, Video, Error analysis, Video compression, Computer programming, Motion estimation, Wavelet transforms, Data communications

SPIE Journal Paper | 1 October 1998

Video compression quality metrics correlation with aided target recognition (ATR) applications

Michael Grim, Harold Szu

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482663

KEYWORDS: Video, Video processing, Video compression, Video surveillance, Automatic target recognition, Target recognition, Telecommunications, Quality measurement, Discrete wavelet transforms, Target detection

SPIE Journal Paper | 1 October 1998 Open Access

Open Access

Guest Editorial: Special Section on Wavelet Applications

Harold Szu

JEI, Vol. 7, Issue 04, (October 1998) https://doi.org/10.1117/12.10.1117/1.482658

Proceedings Article | 6 July 1998 Paper

Paper

Perceptual image compression for data transmission on the battlefield

Jose Gonzalez, Mark Smith, Ingo Hontsch, Lina Karam, Kameswara Namuduri, Harold Szu

Proceedings Volume 3387, (1998) https://doi.org/10.1117/12.316432

KEYWORDS: Image compression, Synthetic aperture radar, Image quality, Autoregressive models, Speckle, Quantization, Visualization, Model-based design, Computer programming, Distortion

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Statistical mechanics demixing approach to selection of independent wavelet basis

Harold Szu, Paul Cox, Charles Hsu

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304869

KEYWORDS: Wavelets, Principal component analysis, Neural networks, Independent component analysis, Algorithm development, Signal processing, Mechanics, Associative arrays, Feature extraction, Evolutionary algorithms

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Independent component analysis (ICA) using wavelet subband orthogonality

Harold Szu, Charles Hsu, Takeshi Yamakawa

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304868

KEYWORDS: Independent component analysis, Discrete wavelet transforms, Image compression, Linear filtering, Fourier transforms, Image filtering, Wavelets, Wavelet transforms, Principal component analysis, Image processing

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Continuous speech segmentation determined by blind source separation

Harold Szu, Charles Hsu, Da-Hong Xie

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304890

KEYWORDS: Wavelets, Acoustics, Independent component analysis, Superposition, Neural networks, Neurons, Wavelet transforms, Feature extraction, Signal processing, Speech recognition

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Video compression quality metrics for moving scenes

Michael Grim, Gerald Royce, Harold Szu, Charles Hsu

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304873

KEYWORDS: Video, Video processing, Video compression, Video surveillance, Telecommunications, Image processing, Image compression, Wavelets, Target detection, Discrete wavelet transforms

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Three-scale wavelet transforms

Raghuveer Rao, J. Scott Bundonis, Harold Szu

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304883

KEYWORDS: Wavelets, Fourier transforms, Linear filtering, Wavelet transforms, Imaging systems, Optical filters, Electrical engineering, Computing systems, Chemical elements, Vector spaces

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Adding wavelet image technology and adaptive resonance theory to a common control system for unmanned aerial vehicles

Tai-Ching Chu, Harold Szu

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304911

KEYWORDS: Unmanned aerial vehicles, Control systems, Wavelets, Image classification, Neural networks, Data modeling, Image analysis, Classification systems, Systems modeling, Sensors

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Doppler frequency estimation with wavelets and neural networks

Steven Noel, Harold Szu, Yogesh Gohel

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304865

KEYWORDS: Doppler effect, Wavelets, Neural networks, Wavelet transforms, Radar, Neurons, Continuous wavelet transforms, Denoising, Signal to noise ratio, Signal processing

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Characterization of polynomials satisfying the super-Haar condition

Addison Jump, Harold Szu, Steven Noel

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304861

KEYWORDS: Wavelets, Denoising, Signal processing, Interference (communication), Fourier transforms, Lithium, Mirrors, Applied research, Warfare, Electroluminescence

Read Abstract +

Proceedings Article | 26 March 1998 Paper

Paper

Application of the principal wavelet component in pattern classification

Pirawat Watanapongse, Harold Szu

Proceedings Volume 3391, (1998) https://doi.org/10.1117/12.304903

KEYWORDS: Principal component analysis, Wavelets, Image classification, Quantization, Image enhancement, Image processing, Data modeling, Image resolution, Classification systems, Data centers

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Integration of local texture information in the automatic classification of Landsat images

Harold Szu, Jacqueline Le Moigne, Nathan Netanyahu, Charles Hsu

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271708

KEYWORDS: Image classification, Landsat, Statistical analysis, Information fusion, Wavelet transforms, Wavelets, Data mining, Principal component analysis, Spatial frequencies, Earth observing sensors

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Landsat spectral demixing a la superresolution of blind matrix inversion by constraint MaxEnt neural nets

Harold Szu, Charles Hsu

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271711

KEYWORDS: Landsat, Super resolution, Neural networks, Reflectivity, Earth observing sensors

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Hermitian hat wavelet design for singularity detection in the Paraguay river-level data analyses

Harold Szu, Charles Hsu, Leonardo Sa, Weigang Li

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271774

KEYWORDS: Wavelets, Convolution, Data analysis, Wavelet transforms

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Symmetric codec video compressions for N-to-N teleconferences using biorthogonal subband wavelets

Harold Szu, Charles Hsu

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271717

KEYWORDS: Wavelets, Video compression, Data compression, Image compression, Motion estimation, Network architectures, Visual communications

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Wavelet-based image compression scheme with the error-resilient entropy coding (EREC) for noisy channels

Duc Hai Do, Terry Jones, David Ii, Harold Szu, Victor Stievenart, Tracey Beauchat

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271769

KEYWORDS: Image compression, Wavelets, Quantization, Computer programming, Discrete wavelet transforms, Data compression, Wavelet transforms, Image transmission, Image processing, Image filtering

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Image compression quality metrics

Harold Szu, Charles Hsu, Joseph Landa, Terry Jones, Barbara O'Kane, John O'Connor, Romain Murenzi, Mark Smith

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271768

KEYWORDS: Image compression, Image quality, Discrete wavelet transforms, Image transmission, Target recognition, Target detection, Wavelets, Automatic target recognition, X-ray imaging, X-rays

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Edge-texture wavelet features for automated x-ray inspection

Harold Szu, Charles Hsu

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271738

KEYWORDS: Wavelets, X-rays, Composites, Fractal analysis, X-ray imaging, Backscatter, Wavelet transforms, Inspection, Image filtering, Reflectivity

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Multiple-resolution clustering for recursive divide and conquer

Steven Noel, Harold Szu

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271725

KEYWORDS: Wavelets, Fractal analysis

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Performance comparison among nonparametric probability density estimator, radial basis function, and adaptive wavelet transform neural networks

Weigang Li, Harold Szu, Joao Marar, Leonardo Sa, Edson Carvalho Filho

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271709

KEYWORDS: Wavelet transforms, Neural networks, Wavelets

Read Abstract +

Proceedings Article | 3 April 1997 Paper

Paper

Wavelet detection of singularities in the presence of fractal noise

Steven Noel, Yogesh Gohel, Harold Szu

Proceedings Volume 3078, (1997) https://doi.org/10.1117/12.271770

KEYWORDS: Wavelets, Fractal analysis, Signal detection, Radar, Interference (communication), Target detection, Discrete wavelet transforms, Electronic filtering, Fourier transforms, Signal to noise ratio

Read Abstract +

Proceedings Article | 26 February 1997 Paper

Paper

Wavelet index of texture for artificial neural network classification of Landsat images

Harold Szu, Jacqueline Le Moigne, Nathan Netanyahu, Charles Hsu, Margaret Francis

Proceedings Volume 2962, (1997) https://doi.org/10.1117/12.267837

KEYWORDS: Wavelets, Image classification, Composites, Wavelet transforms, Neural networks, Earth observing sensors, Artificial neural networks, Vegetation, Remote sensing, Landsat

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Sensor fusion for wide-area surveillance

Harold Szu, Joseph Garcia

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236023

KEYWORDS: Fourier transforms, Radar, Staring arrays, Signal to noise ratio, Super resolution, Infrared radiation, Surveillance, Wavelets, Sensor fusion, Infrared imaging

Read Abstract +

Proceedings Article | 22 March 1996 Open Access

Open Access

Paper

Review of wavelet transforms for pattern recognitions

Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236044

KEYWORDS: Wavelets, Neural networks, Wavelet transforms, Sensors, Fourier transforms, Neurons, Signal detection, Pattern recognition, Fast wavelet transforms, Visualization

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Application of adaptive subband coding for noisy bandlimited ECG signal processing

Krishna Aditya, Chee-Hung Chu, Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236040

KEYWORDS: Wavelets, Electrocardiography, Interference (communication), Signal processing, Linear filtering, Electronic filtering, Digital filtering, Filtering (signal processing), Data modeling, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Entries in the continuous wavelet transform table

Joseph DeWitte, Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236041

KEYWORDS: Continuous wavelet transforms, Transform theory, Wavelets, Wavelet transforms, Fourier transforms, Tungsten, Discrete wavelet transforms, Digital signal processing, Data processing, Nomenclature

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Fast algo-tectures for discrete wavelet transforms

Krishna Aditya, Chee-Hung Chu, Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236037

KEYWORDS: Discrete wavelet transforms, Convolution, Computer architecture, Wavelets, Linear filtering, Digital filtering, Multiplexing, Filtering (signal processing), Network architectures, Wavelet transforms

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Chords in wavelet projection transform space applied to aspect invariant pattern recognition

Joseph Garcia, Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.235995

KEYWORDS: Wavelets, Image segmentation, Discrete wavelet transforms, Pattern recognition, Continuous wavelet transforms, Superposition, Automatic target recognition, Brain, Edge detection, Information fusion

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Novel biorthogonal MRAs using compact wavelet and bandlimited dual pairing

Raghuveer Rao, Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236011

KEYWORDS: Wavelets, Fourier transforms, Electrical engineering, Wavelet transforms, Digital filtering, Linear filtering, Warfare, Surveillance

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Progress toward three-scale biorthogonal decomposition

Raghuveer Rao, Harold Szu

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.235982

KEYWORDS: Wavelets, Reconstruction algorithms, Optical filters, Nonlinear filtering, Algorithm development, Finite impulse response filters, Linear filtering, Fourier transforms, Electrical engineering, Wavelet transforms

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Constraints in the wavelet transform domain for stereo vision correspondence matching

Sheng Zhong, Harold Szu, Francis Chin, Qing-Yun Shi

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.236029

KEYWORDS: Linear filtering, Cameras, Wavelets, Information visualization, Image filtering, Wavelet transforms, Stereo vision systems, Visualization, Image analysis, Visual system

Read Abstract +

Proceedings Article | 22 March 1996 Paper

Paper

Super-Haar designs of wavelet transforms

Harold Szu, Joseph Garcia, Brian Telfer, Raghuveer Rao

Proceedings Volume 2762, (1996) https://doi.org/10.1117/12.235989

KEYWORDS: Image compression, Superposition, Wavelets, Image filtering, Wavelet transforms, Linear filtering, Digital filtering, Optical filters, Infrared imaging, Infrared radiation

Read Abstract +

Proceedings Article | 20 June 1995 Paper

Paper

Integrated image compression and detection for minelike objects

Harold Szu, Brian Telfer, Joseph Garcia, Abinash Dubey, Ned Witherspoon

Proceedings Volume 2496, (1995) https://doi.org/10.1117/12.211367

KEYWORDS: Image compression, Discrete wavelet transforms, Wavelets, Linear filtering, Quantization, Neural networks, Warfare, Image quality, Data compression, Wavelet transforms

Read Abstract +

Proceedings Article | 6 April 1995 Paper

Paper

Wavelet transform for local tomography reconstruction

Harold Szu, Joseph DeWitte, Joseph Garcia, Brian Telfer, Tim Olson, Dennis Healy, Rui de Figueiredo

Proceedings Volume 2491, (1995) https://doi.org/10.1117/12.205442

KEYWORDS: Tomography, Fourier transforms, Wavelets, X-rays, Wavelet transforms, Tumors, Reconstruction algorithms, Optical filters, Computed tomography, Image restoration

Read Abstract +

Proceedings Article | 6 April 1995 Paper

Paper

Fingerprint data acquisition, desmearing, wavelet feature extraction, and identification

Harold Szu, Charles Hsu, Joseph Garcia, Brian Telfer

Proceedings Volume 2491, (1995) https://doi.org/10.1117/12.205376

KEYWORDS: Wavelets, Discrete wavelet transforms, Linear filtering, Stars, Data compression, Neural networks, Image filtering, Convolution, Feature extraction, Data acquisition

Read Abstract +

Proceedings Article | 6 April 1995 Paper

Paper

Compression of the electrocardiogram (ECG) using an adaptive orthonomal wavelet basis architecture

Janavikulam Anandkumar, Harold Szu

Proceedings Volume 2491, (1995) https://doi.org/10.1117/12.205378

KEYWORDS: Wavelets, Electrocardiography, Wavelet transforms, Distortion, Lead, Optical filters, Signal processing, Fourier transforms, Electronic filtering, Computer architecture

Read Abstract +

Proceedings Article | 6 April 1995 Paper

Paper

Novel identification of intercepted signals from unknown radio transmitters

Howard Choe, Clark Poole, Andrea Yu, Harold Szu

Proceedings Volume 2491, (1995) https://doi.org/10.1117/12.205415

KEYWORDS: Transmitters, Wavelets, Feature extraction, Antennas, Receivers, Signal analyzers, Neural networks, Neurons, Signal processing, Signal detection

Read Abstract +

Proceedings Article | 6 April 1995 Paper

Paper

Adaptive time-frequency classification of acoustic backscatter

Brian Telfer, Harold Szu, Gerald Dobeck

Proceedings Volume 2491, (1995) https://doi.org/10.1117/12.205411

KEYWORDS: Time-frequency analysis, Chemical species, Wavelet transforms, Fourier transforms, Acoustics, Backscatter, Wavelets, Associative arrays, Receivers, Algorithm development

Read Abstract +

Proceedings Article | 6 April 1995 Paper

Paper

Multiresolution wavelet techniques for noisy inverse-sensing problems

Harold Szu, Sheng Zhong, Lei Xu, Qing-Yun Shi, Min-Teh Cheng, Ke Chen, Huisheng Chi, Che Li

Proceedings Volume 2491, (1995) https://doi.org/10.1117/12.205375

KEYWORDS: Wavelets, Inverse problems, Sensors, Wavelet transforms, Reconstruction algorithms, Signal to noise ratio, Remote sensing, Image processing, Machine vision, Image resolution

Read Abstract +

SPIE Journal Paper | 1 July 1994

Symmetrical wavelet transforms for edge localization

Mingui Sun, Robert Sclabassi, Ching-Chung Li, Yingping Zhang, Harold Szu

OE, Vol. 33, Issue 07, (July 1994) https://doi.org/10.1117/12.10.1117/12.172245

KEYWORDS: Wavelet transforms, Wavelets, Fourier transforms, Information technology, Sensors, Linear filtering, Image processing, Digital filtering, Edge detection, Signal processing

Read Abstract +

SPIE Journal Paper | 1 July 1994

Fractional Fourier transforms, wavelet transforms, and adaptive neural networks

Soo-Young Lee, Harold Szu

OE, Vol. 33, Issue 07, (July 1994) https://doi.org/10.1117/12.10.1117/12.172793

KEYWORDS: Neural networks, Fractional fourier transform, Wavelet transforms, Optical filters, Wigner distribution functions, Digital filtering, Algorithm development, Evolutionary algorithms, Adaptive optics, Fourier transforms

Read Abstract +

SPIE Journal Paper | 1 July 1994

Adaptive wavelet classification of acoustic backscatter and imagery

Brian Telfer, Harold Szu, Gerald Dobeck, Joseph Garcia, Hanseok Ko, Abinash Dubey, Ned Witherspoon

OE, Vol. 33, Issue 07, (July 1994) https://doi.org/10.1117/12.10.1117/12.172257

KEYWORDS: Wavelets, Acoustics, Neural networks, Backscatter, Wavelet transforms, Databases, Image classification, Multispectral imaging, Warfare, Data modeling

Read Abstract +

SPIE Journal Paper | 1 July 1994 Open Access

Open Access

Guest Editorial: Adaptive Wavelet Transforms

Harold Szu

OE, Vol. 33, Issue 07, (July 1994) https://doi.org/10.1117/12.10.1117/12.189530

KEYWORDS: Wavelet transforms, Wavelets, Warfare, Adaptive optics, Neural networks, Indium nitride, Optical computing, Silver, Holography, Signal processing

SPIE Journal Paper | 1 July 1994

Mathematics of adaptive wavelet transforms: relating continuous with discrete transforms

Harold Szu, Brian Telfer

OE, Vol. 33, Issue 07, (July 1994) https://doi.org/10.1117/12.10.1117/12.173205

KEYWORDS: Wavelets, Fourier transforms, Superposition, Wavelet transforms, Signal to noise ratio, Transform theory, Interference (communication), Discrete wavelet transforms, Optical filtering, Linear filtering

Read Abstract +

SPIE Journal Paper | 1 July 1994

Image wavelet transforms implemented by discrete wavelet chips

Harold Szu, Charles Hsu, Pradip Thaker, Mona Zaghloul

OE, Vol. 33, Issue 07, (July 1994) https://doi.org/10.1117/12.10.1117/12.173210

KEYWORDS: Discrete wavelet transforms, Wavelets, Image processing, Image filtering, Optical filters, Wavelet transforms, Optical filtering, Fourier transforms, Image compression, Clocks

Read Abstract +

Proceedings Article | 15 March 1994 Paper

Paper

Analyses of long-term solar irradiance data with wavelet transforms

Richard Kiang, H. Lee Kyle, Brian Telfer, Harold Szu

Proceedings Volume 2242, (1994) https://doi.org/10.1117/12.170047

KEYWORDS: Wavelets, Wavelet transforms, Sun, Sensors, Solar energy, Transform theory, Solar radiation, Climatology, Fourier transforms, Satellites

Read Abstract +

Proceedings Article | 15 March 1994 Paper

Paper

Mathematical theorems of adaptive wavelet transform

Harold Szu, Brian Telfer

Proceedings Volume 2242, (1994) https://doi.org/10.1117/12.170061

KEYWORDS: Wavelets, Signal to noise ratio, Fourier transforms, Linear filtering, Superposition, Wavelet transforms, Interference (communication), Digital filtering, Discrete wavelet transforms, Neural networks

Read Abstract +

Proceedings Article | 15 March 1994 Paper

Paper

Neural network adaptive digital image screen halftoning (DISH) based on wavelet transform preprocessing

Harold Szu, Yingping Zhang, Mingui Sun, Ching-Chung Li

Proceedings Volume 2242, (1994) https://doi.org/10.1117/12.170080

KEYWORDS: Wavelet transforms, Image filtering, Linear filtering, Digital image processing, Image processing, Printing, Wavelets, Digital imaging, Image compression, Neural networks

Read Abstract +

Proceedings Article | 15 March 1994 Paper

Paper

Adaptive wavelet classification of acoustic backscatter

Brian Telfer, Harold Szu, Gerald Dobeck

Proceedings Volume 2242, (1994) https://doi.org/10.1117/12.170065

KEYWORDS: Warfare, Silver, Classification systems, Active sonar, Evolutionary algorithms, Neural networks, Wavelet transforms, Backscatter, Acoustics, Wavelets

Read Abstract +

Proceedings Article | 15 March 1994 Paper

Paper

Combining wavelet features for image recognition

Joseph Garcia, Brian Telfer, Hanseok Ko, Harold Szu

Proceedings Volume 2242, (1994) https://doi.org/10.1117/12.170094

KEYWORDS: Wavelets, Neural networks, Image processing, Image filtering, Sensors, Composites, Image compression, Signal detection, Target recognition, Image enhancement

Read Abstract +

Proceedings Article | 1 March 1994 Paper

Paper

Chaotic neurochips for fuzzy computing

Harold Szu, Lotfi Zadeh, Charles Hsu, Joseph DeWitte, Gyu Moon, Desa Gobovic, Mona Zaghloul

Proceedings Volume 2037, (1994) https://doi.org/10.1117/12.167517

KEYWORDS: Fuzzy logic, Chaos, Neurons, Logic, Neural networks, Pattern recognition, Tolerancing, Data processing, Artificial neural networks, Mathematical modeling

Read Abstract +

SPIE Journal Paper | 1 January 1994 Open Access

Open Access

Letter: Invariant analog wavelets [see 33(1)307-308(Jan1994)]

Harold Szu, H. John Caulfield

OE, Vol. 33, Issue 01, (January 1994) https://doi.org/10.1117/12.10.1117/1.OE.33.1.response1

Proceedings Article | 14 September 1993 Paper

Paper

Medical image diagnoses by artificial neural networks with image correlation, wavelet transform, simulated annealing

Harold Szu

Proceedings Volume 1898, (1993) https://doi.org/10.1117/12.154494

KEYWORDS: Image processing, Neurons, Medical imaging, Neural networks, Algorithms, Image filtering, Artificial neural networks, Feature extraction, Annealing, Inspection

Read Abstract +

Proceedings Article | 3 September 1993 Paper

Paper

Determination of viewing aspect by maximization of image symmetry

Joseph Garcia, Harold Szu, Thomas Tsao, John Libert

Proceedings Volume 1955, (1993) https://doi.org/10.1117/12.154991

KEYWORDS: Image sensors, Sensors, Optical correlators, Image processing, Image compression, Data modeling, 3D modeling, Spatial filters, Pattern recognition, Warfare

Read Abstract +

Proceedings Article | 27 August 1993 Paper

Paper

Representation and classification of unvoiced sounds using adaptive wavelets

Shubha Kadambe, Pramila Srinivasan, Brian Telfer, Harold Szu

Proceedings Volume 1961, (1993) https://doi.org/10.1117/12.150961

KEYWORDS: Wavelets, Neural networks, Acoustics, Fast wavelet transforms, Visual information processing, Sensors, Statistical analysis, Feature extraction, Error analysis, Signal to noise ratio

Read Abstract +

Proceedings Article | 27 August 1993 Paper

Paper

Detecting blobs in multispectral electro-optical imagery using wavelet techniques

Brian Telfer, Harold Szu, Abinash Dubey, Ned Witherspoon

Proceedings Volume 1961, (1993) https://doi.org/10.1117/12.150975

KEYWORDS: Wavelets, Blob detection, Neural networks, Image segmentation, Sensors, Multispectral imaging, Cameras, Visual information processing, Electro optics, Sensor fusion

Read Abstract +

Proceedings Article | 27 August 1993 Paper

Paper

Why adaptive wavelet transform?

Harold Szu

Proceedings Volume 1961, (1993) https://doi.org/10.1117/12.150972

KEYWORDS: Wavelets, Wavelet transforms, Neural networks, Neurons, Visual information processing, Sensors, Fourier transforms, Turbulence, Signal detection, Fast wavelet transforms

Read Abstract +

Proceedings Article | 27 August 1993 Paper

Paper

Speaker recognition using neural network and adaptive wavelet transform

Mohammad Bodruzzaman, Xingkang Li, Kah Kuah, Lamar Crowder, Mohan Malkani, Harold Szu, Brian Telfer

Proceedings Volume 1961, (1993) https://doi.org/10.1117/12.150976

KEYWORDS: Wavelets, Neural networks, Speaker recognition, Wavelet transforms, Visual information processing, Classification systems, Acoustics, Binary data, Digital filtering, Electronic filtering

Read Abstract +

Proceedings Article | 1 October 1992 Paper

Paper

Why the soliton wavelet transform is useful for nonlinear dynamic phenomena

Harold Szu

Proceedings Volume 1705, (1992) https://doi.org/10.1117/12.138462

KEYWORDS: Wavelets, Solitons, Fourier transforms, Nonlinear dynamics, Wavelet transforms, Superposition, Visualization, Interference (communication), Neural networks, Active sonar

Read Abstract +

Proceedings Article | 1 October 1992 Paper

Paper

Continuous wavelet transform of 1D signals by Fourier filtering

H. John Caulfield, Harold Szu

Proceedings Volume 1705, (1992) https://doi.org/10.1117/12.138466

KEYWORDS: Warfare, Spatial light modulators, Discrete wavelet transforms, Holography, Image processing, Image filtering, Fourier transforms, Optical filters, Electronic filtering, Continuous wavelet transforms

Read Abstract +

Proceedings Article | 1 October 1992 Paper

Paper

Modified wavelets that accommodate causality

Harold Szu, Brian Telfer, Adolf Lohmann

Proceedings Volume 1705, (1992) https://doi.org/10.1117/12.138463

KEYWORDS: Wavelets, Wavelet transforms, Signal to noise ratio, Fourier transforms, Signal detection, Visualization, Signal processing, Interference (communication), Modulation, Terbium

Read Abstract +

Proceedings Article | 1 October 1992 Paper

Paper

Modified wavelet transform for unbiased frequency representation

Brian Telfer, Harold Szu

Proceedings Volume 1705, (1992) https://doi.org/10.1117/12.138464

KEYWORDS: Wavelets, Wavelet transforms, Visualization, Signal processing, Neural networks, Optical filters, Fourier transforms, Sodium, Silver, Visual system

Read Abstract +

Proceedings Article | 1 October 1992 Paper

Paper

Wavelet transform and its optical implementations

Yunlong Sheng, Jing Chen, Harold Szu

Proceedings Volume 1705, (1992) https://doi.org/10.1117/12.138467

KEYWORDS: Wavelets, Wavelet transforms, Fourier transforms, Optical filters, Optical correlators, Visualization, Electronic filtering, Signal processing, Visual information processing, Transmittance

Read Abstract +

SPIE Journal Paper | 1 September 1992

Causal analytical wavelet transform

Harold Szu, Brian Telfer, Adolf Lohmann

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59911

KEYWORDS: Wavelets, Wavelet transforms, Signal to noise ratio, Signal analyzers, Fourier transforms, Signal detection, Acousto-optics, Signal processing, Image processing, Interference (communication)

Read Abstract +

SPIE Journal Paper | 1 September 1992

Optical wavelet transform

Yunlong Sheng, Danny Roberge, Harold Szu

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59916

KEYWORDS: Wavelets, Wavelet transforms, Fourier transforms, Optical filters, Optical correlators, Signal processing, Radon, Reconstruction algorithms, Transmittance, Filtering (signal processing)

Read Abstract +

SPIE Journal Paper | 1 September 1992

Optoelectronic computation of waveletlike-based features

George Rogers, Jeffrey Solka, Carey Priebe, Harold Szu

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59981

KEYWORDS: Wavelets, Image segmentation, Optoelectronics, Retina, Analog electronics, Nonlinear optics, Image processing, Feature extraction, Silicon, Chlorine

Read Abstract +

SPIE Journal Paper | 1 September 1992

Texture analysis by space-filling curves and one-dimensional Haar wavelets

Sonlinh Phuvan, Tae Kwan Oh, Nicholas Caviris, Yao Li, Harold Szu

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59957

KEYWORDS: Fractal analysis, Wavelets, Wavelet transforms, Artificial neural networks, Optoelectronics, Neural networks, Image processing, Pattern recognition, Signal processing, Raster graphics

Read Abstract +

SPIE Journal Paper | 1 September 1992

Neural network adaptive wavelets for signal representation and classification

Harold Szu, Brian Telfer, Shubha Kadambe

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59918

KEYWORDS: Wavelets, Neural networks, Speaker recognition, Feature extraction, Calcium, Tongue, Library classification systems, Solids, Signal to noise ratio, Lung

Read Abstract +

SPIE Journal Paper | 1 September 1992 Open Access

Open Access

Editorial: Special Issues, Special Sections, and Related Topics

Harold Szu, H. John Caulfield

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.61000

KEYWORDS: Wavelet transforms, Wavelets, Discrete wavelet transforms, Transform theory, Continuous wavelet transforms, Warfare, Holography, Optical computing, Fourier transforms, Neural networks

SPIE Journal Paper | 1 September 1992

Parallel discrete and continuous wavelet transforms

H. John Caulfield, Harold Szu

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59915

KEYWORDS: Discrete wavelet transforms, Wavelets, Continuous wavelet transforms, Fourier transforms, Holograms, Spatial light modulators, Optical filters, Holography, Electronic filtering, Wavelet transforms

Read Abstract +

SPIE Journal Paper | 1 September 1992

Optical Haar wavelet transforms of binary images

Xiangyang Yang, Harold Szu, Yunlong Sheng, H. John Caulfield

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59914

KEYWORDS: Wavelets, Lithium, Wavelet transforms, Polarization, Optical filters, Binary data, Computer simulations, Light, Light sources, Holography

Read Abstract +

SPIE Journal Paper | 1 September 1992

New wavelet transform normalization to remove frequency bias

Brian Telfer, Harold Szu

OE, Vol. 31, Issue 09, (September 1992) https://doi.org/10.1117/12.10.1117/12.59912

KEYWORDS: Wavelets, Wavelet transforms, Optical filters, Image filtering, Fourier transforms, Signal to noise ratio, Warfare, Optical correlators, Interference (communication), Silver

Read Abstract +

Showing 5 of 222 publications

Proceedings Volume Editor (24)

SPIE Conference Volume | 19 June 2015

Independent Component Analyses, Compressive Sampling, Large Data Analyses (LDA), Neural Networks, Biosystems, and Nanoengineering XIII

SPIE Conference Volume | 24 June 2014

Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII

SPIE Conference Volume | 10 June 2013

Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI

SPIE Conference Volume | 3 May 2012

Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X

SPIE Conference Volume | 9 June 2011

Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX

Showing 5 of 24 publications

Conference Committee Involvement (25)

Independent Component Analyses, Compressive Sampling, Large Data Analyses (LDA), Neural Networks, Biosystems, and Nanoengineering XIII

23 April 2015 | Baltimore, MD, United States

Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII

7 May 2014 | Baltimore, MD, United States

Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI

1 May 2013 | Baltimore, Maryland, United States

Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X

25 April 2012 | Baltimore, Maryland, United States

Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX

27 April 2011 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering VIII

7 April 2010 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering VII

13 April 2009 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, Unsupervised Nano-Biomimetic Sensors and Neural Networks VI

17 March 2008 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, Unsupervised Nano-Biomimetic Sensors and Neural Networks V

10 April 2007 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks IV

19 April 2006 | Orlando (Kissimmee), Florida, United States

Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks III

30 March 2005 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks II

14 April 2004 | Orlando, Florida, United States

Independent Component Analyses, Wavelets, and Neural Networks

22 April 2003 | Orlando, Florida, United States

Wavelet and Independent Component Analysis Applications IX

3 April 2002 | Orlando, FL, United States

Wavelet Applications VIII

18 April 2001 | Orlando, FL, United States

Optical Processing and Computing: A Tribute to Adolf Lohmann

17 April 2001 | Orlando, FL, United States

Wavelet Applications VII

26 April 2000 | Orlando, FL, United States

Wavelet Applications VI

6 April 1999 | Orlando, FL, United States

Wavelet Applications V

14 April 1998 | Orlando, FL, United States

Multidimensional Spectroscopy: Acquisition, Interpretation, and Automation

27 January 1998 | San Jose, CA, United States

Wavelet Applications IV

22 April 1997 | Orlando, FL, United States

Wavelet Applications III

8 April 1996 | Orlando, FL, United States

Wavelet Applications II

17 April 1995 | Orlando, FL, United States

Wavelet Applications

5 April 1994 | Orlando, FL, United States

Optical and Hybrid Computing

24 March 1986 | Leesburg, United States

Showing 5 of 25 Conference Committees

Course Instructor

SC715: Independent Component Analysis and Beyond: Blind Signal Processing and its Applications

Blind Signal Processing (BSP) is an emerging area of research and technology with solid theoretical foundations and many potential applications. The problems of separating or extracting of the source signals from sensor arrays, without knowledge of the transmission channel characteristics and the real sources, can be expressed briefly as a number of blind source separation (BSS) or related generalized component analysis (GCA) methods: Independent Component Analysis (ICA) (and its extensions), Sparse Component Analysis (SCA), Sparse Principal Component Analysis (SPCA), Non-negative Matrix Factorization (NMF), Time-Frequency Component Analyzer (TFCA) and Multichannel Blind Deconvolution (MBD). BSP is not limited to ICA or BSS. With BSP we aim to discover and validate principles or laws which govern relationships between inputs (hidden components) and outputs (observations) when the information about the propagation Multi-Input Multi-Output (MIMO) system and its inputs are limited or hindered. BSP incorporates many problems, like blind identification of channels of unknown systems or a problem of suitable decomposition of signals into basic latent (hidden) components which do not necessary represent true sources but rather some of their features or sub-components. This four-hour course presents the fundamentals of blind signal processing, especially blind source separation and extraction, and in the remaining time discusses their applications in several important signal processing areas including estimation of sources, novel enhancement, denoising, artifact removal, filtering, detection, classification of multi-sensory signals and data, especially in biomedical applications and Brain Computer Interface (BCI).

Expand Description +

SIGN IN TO:

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Advertisement

Advertisement