Micro-Doppler Radar Gait Measurement to Detect Age- and Fall Risk-Related Differences in Gait: A Simulation Study on Comparison of Deep Learning and Gait Parameter-Based Approaches

Abstract

This paper describes the application of micro-Doppler radar (MDR) to gait classification based on fall risk-related differences using deep learning and gait parameter-based approaches. Two classification problems were considered in this study: elderly non-fallers and multiple fallers were classified to investigate the detection of fall risk-related gait differences, and middle-aged (50s) and elderly (70s) adults were classified to detect aging-related gait differences. The MDR signal data of the participants were simulated using an open motion capture gait dataset. The classification results obtained using the deep learning and gait parameter-based approaches showed that the classification accuracy achieved using a support vector machine with the gait parameters extracted from the MDR signals was better than that resulting from the deep learning of spectrogram (time-velocity distribution) images of the MDR signals for both classification problems. The gait parameter-based approach achieved the classification rates of 79 % for faller/non-faller classification and 82 % for 50s/70s classification, whereas the corresponding accuracies were 73 % and 76 %, respectively, using the deep learning approach. These results reveal that the gait parameters extracted via MDR measurements include sufficient information on gait to detect individuals with a high risk of falls and the gait parameter-based approaches are thus effective for both classification problems.

Experimental Verification of Micro-Doppler Radar Measurements of Fall-Risk-Related Gait Differences for Community-Dwelling Elderly Adults

“…In our previous study, we developed a method for detecting fall risk without the direct measurement of fall events. We utilized the MDR-based gait classification of healthy young and elderly adults based on the gait parameters related to their fall-risk-related gait differences [31][32][33], indicating the possibility of remotely measuring gait differences. In [31], we demonstrated the gait classification of young (aged in their 20s) and elderly (65 years and older) groups with over 90% accuracy using a recurrent neural network with time-velocity signals extracted from MDR data.…”

“…However, the detection of elderly fallers is more important for fall prevention. We presented the classification of elderly fallers using only simulated MDR data [32,33]. To our best knowledge, our previous paper [32] is the first report on the radar-based faller classification (not the detection of fall events) and there are no other studies except for the authors' recent work [33] that deal with this classification problem.…”

“…We presented the classification of elderly fallers using only simulated MDR data [32,33]. To our best knowledge, our previous paper [32] is the first report on the radar-based faller classification (not the detection of fall events) and there are no other studies except for the authors' recent work [33] that deal with this classification problem. We constructed a support vector machine (SVM) model using the kinematic gait parameters to classify elderly fallers and non-fallers [33].…”

“…To our best knowledge, our previous paper [32] is the first report on the radar-based faller classification (not the detection of fall events) and there are no other studies except for the authors' recent work [33] that deal with this classification problem. We constructed a support vector machine (SVM) model using the kinematic gait parameters to classify elderly fallers and non-fallers [33]. We achieved a classification accuracy of 78%, which was better than that of a deep-learning-based model.…”

“…Furthermore, the efficient gait parameters for faller classification were clarified (e.g., leg velocity in leg swinging motion during walking). In [33], simulated MDR data were generated using the AIST Gait Database 2019 [34], which is composed of the optical motion capture data of various participants including fallers. These data were used for model construction, validation, and the clarification of efficient gait parameters.…”