TY - JOUR
T1 - STRIDE
T2 - Systematic Radar Intelligence Analysis for ADRD Risk Evaluation With Gait Signature Simulation and Deep Learning
AU - Cai, Fulin
AU - Patharkar, Abhidnya
AU - Wu, Teresa
AU - Lure, Fleming Y.M.
AU - Chen, Harry
AU - Chen, Victor C.
N1 - Publisher Copyright:
© 2001-2012 IEEE.
PY - 2023/5/15
Y1 - 2023/5/15
N2 - Abnormal gait is a significant noncognitive biomarker for Alzheimer's disease (AD) and AD-related dementia (ADRD). Micro-Doppler radar (MDR), a nonwearable technology, can capture human gait movements for potential early ADRD risk assessment. In this article, we propose to design a systematic radar intelligence analysis for ARDR risk evaluation (STRIDE) integrating MDR sensors with advanced artificial intelligence (AI) technologies. STRIDE embeds a new deep learning (DL) classification framework. As a proof of concept, we develop a 'digital twin' of STRIDE, consisting of a human walking simulation model and an MDR simulation model, to generate a gait signature dataset. Taking established human walking parameters, the walking model simulates individuals with ADRD under various conditions. The radar model based on electromagnetic scattering and the Doppler frequency shift model is employed to generate micro-Doppler signatures from different moving body parts (e.g., foot, limb, joint, torso, and shoulder). A band-dependent DL framework is developed to predict ADRD risks. The experimental results demonstrate the effectiveness and feasibility of STRIDE for evaluating ADRD risk.
AB - Abnormal gait is a significant noncognitive biomarker for Alzheimer's disease (AD) and AD-related dementia (ADRD). Micro-Doppler radar (MDR), a nonwearable technology, can capture human gait movements for potential early ADRD risk assessment. In this article, we propose to design a systematic radar intelligence analysis for ARDR risk evaluation (STRIDE) integrating MDR sensors with advanced artificial intelligence (AI) technologies. STRIDE embeds a new deep learning (DL) classification framework. As a proof of concept, we develop a 'digital twin' of STRIDE, consisting of a human walking simulation model and an MDR simulation model, to generate a gait signature dataset. Taking established human walking parameters, the walking model simulates individuals with ADRD under various conditions. The radar model based on electromagnetic scattering and the Doppler frequency shift model is employed to generate micro-Doppler signatures from different moving body parts (e.g., foot, limb, joint, torso, and shoulder). A band-dependent DL framework is developed to predict ADRD risks. The experimental results demonstrate the effectiveness and feasibility of STRIDE for evaluating ADRD risk.
KW - Alzheimer's disease and related dementia (ADRD)
KW - deep learning (DL)
KW - gait analysis
KW - micro-Doppler radar (MDR)
UR - http://www.scopus.com/inward/record.url?scp=85153342569&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153342569&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2023.3263071
DO - 10.1109/JSEN.2023.3263071
M3 - Article
AN - SCOPUS:85153342569
SN - 1530-437X
VL - 23
SP - 10998
EP - 11006
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 10
ER -