Generally, people do various things while walking. For example, people frequently walk while looking at their smartphones. Sometimes we walk differently than usual; for example, when walking on ice or snow, we tend to waddle. Understanding walking patterns could provide users with contextual information tailored to the current situation. To formulate this as a machine-learning problem, we defined 18 different everyday walking styles. Noting that walking strategies significantly affect the spatiotemporal features of hand motions, e.g., the speed and intensity of the swinging arm, we propose a smartwatch-based wearable system that can recognize these predefined walking styles. We developed a wearable system, suitable for use with a commercial smartwatch, that can capture hand motions in the form of multivariate timeseries (MTS) signals. Then, we employed a set of machine learning algorithms, including feature-based and recent deep learning algorithms, to learn the MTS data in a supervised fashion. Experimental results demonstrated that, with recent deep learning algorithms, the proposed approach successfully recognized a variety of walking patterns, using the smartwatch measurements. We analyzed the results with recent attention-based recurrent neural networks to understand the relative contributions of the MTS signals in the classification process.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Gait quality is generally considered a critical health indicator, especially for older adults. Assessing gait quality in an unobtrusive manner is essential for the seamless monitoring of these populations. However, precise evaluation of gait often requires dedicated sensor systems, which may not be feasible or practical for monitoring in everyday life. Gait quality is generally considered a critical health indicator, especially for older adults. Assessing gait quality in an unobtrusive manner is essential for the seamless monitoring of these populations. However, precise evaluation of gait often requires dedicated sensor systems, which may not be feasible or practical for monitoring in everyday life. We first defined four typical gait patterns of older adults: gait with disturbances, gait without disturbances, gait with cane, and gait with walker. Thereafter, we formulated the classification task of these gait patterns as a supervised machine learning problem in which multivariate time series signals of inertial motions captured while walking were learned and tested using deep neural network architectures in a supervised learning fashion. To demonstrate the feasibility of the proposed approach, we recruited 38 older adult participants (age: 80.4 +- 6.5; 73.7 % women). We also examined the internal representations and computational attention vectors learned by deep neural networks tailored to learn gait features from complex time series gait-related data. The experimental results validated the feasibility of the proposed approach, revealing that 1) gait patterns of older adults were recognized using smartwatch measurements from both-hands with high accuracies (mean F_1-score of 97.4 %) and 2) either left- or right-hand measurement is sufficient for the proposed recognition task (mean F_1-score of 97.1 %). The proposed wearable recognition system demonstrated acceptable performance (i.e., both accuracy and F_m were higher than 0.95), in predicting the gait patterns of the older adult population.

The squat is a multi-joint exercise widely used for everyday at-home fitness. Focusing on the fine-grained classification of squat motions, we propose a smartwatch-based wearable system that can recognize subtle motion differences. For data collection, 52 participants were asked to perform one correct squat and five incorrect squats with three different arm postures (straight arm, crossed arm, and hands on waist). We utilized deep neural network-based models and adopted a conventional machine learning method (random forest) as a baseline. Experimental results revealed that the bidirectional GRU/LSTMs with an attention mechanism and the arm posture of hands on waist achieved the best test accuracy (F1-score) of 0.854 (0.856). High-dimensional embeddings in the latent space learned by attention-based models exhibit more clustered distributions than those by other DNN models, indicating that attention-based models learned features from the complex multivariate time-series motion signals more efficiently. To understand the underlying decision-making process of the machine-learning system, we analyzed the result of attention-based RNN models. The bidirectional GRU/LSTMs show a consistent pattern of attention for defined squat classes, but these models weigh the attention to the different kinematic events of the squat motion (e.g., descending and ascending). However, there was no significant difference found in classification performance.

BACKGROUND Gait quality is generally considered a critical health indicator, especially for older adults. Assessing gait quality in an unobtrusive manner is essential for the seamless monitoring of these populations. However, precise evaluation of gait often requires dedicated sensor systems, which may not be feasible or practical for monitoring in everyday life. OBJECTIVE Gait quality is generally considered a critical health indicator, especially for older adults. Assessing gait quality in an unobtrusive manner is essential for the seamless monitoring of these populations. However, precise evaluation of gait often requires dedicated sensor systems, which may not be feasible or practical for monitoring in everyday life. METHODS We first defined four typical gait patterns of older adults: gait with disturbances, gait without disturbances, gait with cane, and gait with walker. Thereafter, we formulated the classification task of these gait patterns as a supervised machine learning problem in which multivariate time series signals of inertial motions captured while walking were learned and tested using deep neural network architectures in a supervised learning fashion. To demonstrate the feasibility of the proposed approach, we recruited 38 older adult participants (age: 80.4 +- 6.5; 73.7 % women). We also examined the internal representations and computational attention vectors learned by deep neural networks tailored to learn gait features from complex time series gait-related data. RESULTS The experimental results validated the feasibility of the proposed approach, revealing that 1) gait patterns of older adults were recognized using smartwatch measurements from both-hands with high accuracies (mean F_1-score of 97.4 %) and 2) either left- or right-hand measurement is sufficient for the proposed recognition task (mean F_1-score of 97.1 %). CONCLUSIONS The proposed wearable recognition system demonstrated acceptable performance (i.e., both accuracy and F_m were higher than 0.95), in predicting the gait patterns of the older adult population.