Keitaro Shioiri

Bio: Keitaro Shioiri is an academic researcher from Toyama Prefectural University. The author has contributed to research in topics: Doppler radar & Gait (human). The author has an hindex of 2, co-authored 7 publications receiving 7 citations.

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.

Accurate Person Identification Based on Combined Sit-to-Stand and Stand-to-Sit Movements Measured Using Doppler Radars

Abstract: This article demonstrates the identification of 10 persons with 99% accuracy achieved by combining micro-Doppler signatures of sit-to-stand and stand-to-sit movements. Data from these movements are measured using two radars installed above and behind the person. Images of Doppler spectrograms generated using the measured data are combined and input to a convolutional neural network. Experimental results show the significantly better accuracy of the proposed method compared with conventional methods that do not perform data combination. The accuracy of identifying 10 participants having similar ages and physical features was 96–99%, despite the relatively small training set (number of training samples: 50–90 Doppler radar images per person). These results suggest that combining sit-to-stand and stand-to-sit movements provides sufficient information for accurate person identification and such information can be remotely acquired using Doppler radar measurements.

Person Identification Based on Micro-Doppler Signatures of Sit-to-Stand and Stand-to-Sit Movements Using a Convolutional Neural Network

Abstract: This letter presents a method for person identification based on sit-to-stand and stand-to-sit movements using micro-Doppler radar measurements and a convolutional neural network (CNN). Two 24-GHz micro-Doppler radar systems placed directly above or behind participants will be used to measure the sit-to-stand and stand-to-sit movements of 10 participants. Images of the micro-Doppler signatures will be generated by subjecting the signals received by the radar to short-time Fourier transform. The generated images will then be used as input for the CNNs for training and evaluation purposes. The experiments verified the ability of the method to accurately identify people by measuring both their sit-to-stand and stand-to-sit movements. The identification accuracies for the sit-to-stand and stand-to-sit measurements were 93.6% and 94.9%, respectively, using the data of the radar placed above the participant, whereas the accuracy when placing the radar behind the participant was 92.9% for the sit-to-stand and 93.9% for the stand-to-sit movements. The obtained results will prove that both the horizontal and vertical directions of the velocities of both movements include information that can be used to identify individuals, and this information can be obtained with micro-Doppler radar systems.

Utilization of Micro-Doppler Radar to Classify Gait Patterns of Young and Elderly Adults: An Approach Using a Long Short-Term Memory Network

Abstract: To develop a daily monitoring system for early detection of fall risk of elderly people during walking, this study presents a highly accurate micro-Doppler radar (MDR)-based gait classification method for the young and elderly adults. Our method utilizes a time-series of velocity corresponding to leg motion during walking extracted from the MDR spectrogram (time-velocity distribution) in an experimental study involving 300 participants. The extracted time-series was inputted to a long short-term memory recurrent neural network to classify the gaits of young and elderly participant groups. We achieved a classification accuracy of 94.9%, which is significantly higher than that of a previously presented velocity-parameter-based classification method.

Simulation study of deep-learning-based gait classification of young/elderly adults using Doppler radar

Abstract: Deep-learning-based gait classification of young and elderly adults using micro-Doppler radar (MDR) is presented in this paper. The MDR signal data were accurately simulated using an open motion-capture gait dataset, and deep-learning classification of the time-velocity distribution (i.e., spectrogram) images calculated with the generated data are presented. Utilizing a simulation, we also investigated the body parts deemed most efficient for classification based on their generation of good MDR data. As a result, the classification rate using whole-body data was 74%. However, this classification rate of using only leg data showed an accuracy of 91%, which indicates that the thighs and shanks are efficient target body parts for the gait classification of both young and elderly adults.

Activity Classification Based on Feature Fusion of FMCW Radar Human Motion Micro-Doppler Signatures

Abstract: Fall is a challenging task that poses a great danger to the elderly person’s health as they carry out their daily routines and activities and could lead to serious injuries, long hospitalization, or even death. One of the key solutions to this important problem is the prompt and automatic detection of their fall motion, among other activities, so that immediate help can be rendered to avoid further complications. Cameras and other wearable sensors are the conventional means employed to monitor the daily activities performed by elderly people. However, recently radar sensing technology has been favored largely due to its short-range and velocity estimation. And most importantly, their ability to remotely capture the human activity motion electromagnetic wave signal without infringing on the user’s privacy. To this end, we present an elderly people fall detection system that integrates the radar signal micro-Doppler features extracted with the convolutional neural networks (CNNs). The features were extracted using Alex-Net, VGG-16-Net, and VGG-19-Net pre-trained models. We adapted the canonical correlation analysis (CCA) algorithm by proposing a channel attention network to fuse the extracted features effectively. The channel attention module employed a series of convolutional filters to determine the most discriminative features to focus on and discard the redundant ones. The fused features are classified using an SVM classifier. Our proposed method achieved the best performance against the state-of-the-art approaches. Specifically, our approach attained 99.77% test accuracy, which is about a 2% to 4 % increase compared to the recent state-of-the-art approaches.

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.

Machine Learning-Based Classification of Human Behaviors and Falls in Restroom via Dual Doppler Radar Measurements

Abstract: This study presents a radar-based remote measurement system for classification of human behaviors and falls in restrooms without privacy invasion. Our system uses a dual Doppler radar mounted onto a restroom ceiling and wall. Machine learning methods, including the convolutional neural network (CNN), long short-term memory, support vector machine, and random forest methods, are applied to the Doppler radar data to verify the model’s efficiency and features. Experimental results from 21 participants demonstrated the accurate classification of eight realistic behaviors, including falling. Using the Doppler spectrograms (time–velocity distribution) as the inputs, CNN showed the best results with an overall classification accuracy of 95.6% and 100% fall classification accuracy. We confirmed that these accuracies were better than those achieved by conventional restroom monitoring techniques using thermal sensors and radars. Furthermore, the comparison results of various machine learning methods and cases using each radar’s data show that the higher-order derivative parameters of acceleration and jerk, and the motion information in the horizontal direction are the efficient features for behavior classification in a restroom. These findings indicate that daily restroom monitoring using the proposed radar system accurately recognizes human behaviors and allows early detection of fall accidents.

Accurate Person Identification Based on Combined Sit-to-Stand and Stand-to-Sit Movements Measured Using Doppler Radars

Abstract: This article demonstrates the identification of 10 persons with 99% accuracy achieved by combining micro-Doppler signatures of sit-to-stand and stand-to-sit movements. Data from these movements are measured using two radars installed above and behind the person. Images of Doppler spectrograms generated using the measured data are combined and input to a convolutional neural network. Experimental results show the significantly better accuracy of the proposed method compared with conventional methods that do not perform data combination. The accuracy of identifying 10 participants having similar ages and physical features was 96–99%, despite the relatively small training set (number of training samples: 50–90 Doppler radar images per person). These results suggest that combining sit-to-stand and stand-to-sit movements provides sufficient information for accurate person identification and such information can be remotely acquired using Doppler radar measurements.

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

Abstract: In a previous study, we developed a classification model to detect fall risk for elderly adults with a history of falls (fallers) using micro-Doppler radar (MDR) gait measurements via simulation. The objective was to create daily monitoring systems that can identify elderly people with a high risk of falls. This study aimed to verify the effectiveness of our model by collecting actual MDR data from community-dwelling elderly people. First, MDR gait measurements were performed in a community setting, and the efficient gait parameters for the classification of fallers were extracted. Then, a support vector machine model that was trained and validated using the simulated MDR data was tested for the gait parameters extracted from the actual MDR data. A classification accuracy of 78.8% was achieved for the actual MDR data. The validity of the experimental results was confirmed based on a comparison with the results of our previous simulation study. Thus, the practicality of the faller classification model constructed using the simulated MDR data was verified for the actual MDR data.