Paper
16 May 2011 Detecting gait alterations due to concussion impairment with radar using information-theoretic techniques
Jennifer Palmer, Kristin Bing, Amy Sharma, Eugene Greneker, Teresa Selee
Author Affiliations +
Abstract
Several studies have shown that measuring changes in gait could provide an easier method of diagnosing and monitoring concussions. The purpose of this study was to measure radar signal returns to explore if differences in gait patterns between normal and "concussed" individuals could be identified from radar spectrogram data. Access to concussed individuals was not available during this feasibility study. Instead, based on research that demonstrated concussion impairment is equivalent to a blood alcohol content (BAC) of 0.05%, BAC impairment goggles were used to visually simulate a concussion. Both "impaired" and "not impaired" individuals were asked to complete only a motor skill task (walking) and then complete motor skill and cognitive skill (saying the months of the year in reverse order) tasks simultaneously. Results from the tests were analyzed using informationtheoretic (IT) techniques. IT algorithms were selected because of their potential to identify similarities and differences without having the requirement of a priori knowledge on an individual. To quantify results, two methods were incorporated: decision index, D(Q), analysis with receiver operating characteristic (ROC) curves and object-feature matrix clustering. Both techniques showed acceptable percent correctness in discriminating between normal and "impaired" individuals.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jennifer Palmer, Kristin Bing, Amy Sharma, Eugene Greneker, and Teresa Selee "Detecting gait alterations due to concussion impairment with radar using information-theoretic techniques", Proc. SPIE 8029, Sensing Technologies for Global Health, Military Medicine, Disaster Response, and Environmental Monitoring; and Biometric Technology for Human Identification VIII, 80290U (16 May 2011); https://doi.org/10.1117/12.883278
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Goggles

Gait analysis

Information technology

Radar

Traumatic brain injury

Matrices

Statistical analysis

Back to Top