Privacy-Preserving Sensor-Based Human Activity Recognition for Low-Resource Healthcare Using Classical Machine Learning
Ramakant Kumar, Pravin Kumar
TL;DR
This work addresses privacy-preserving HAR for low-resource healthcare by deploying wearable IMU sensors and evaluating classical classifiers alongside a tensor-based Support Tensor Machine (STM). The STM leverages Tucker-decomposed tensor representations to capture spatiotemporal dependencies, and is complemented by a federated learning framework to enable on-device training while protecting data privacy. Empirically, STM achieves the highest test accuracy of 96.67% and cross-validation accuracy of 98.50%, outperforming Logistic Regression, Random Forest, SVM, and k-NN. The approach demonstrates strong potential for remote eldercare, rehabilitation monitoring, and smart-home wellness in resource-constrained settings, with real-time mobile prototype validation and privacy-preserving deployment. Overall, the combination of tensor-based HAR and federated learning advances robust, private activity recognition suitable for home-based healthcare.
Abstract
Limited access to medical infrastructure forces elderly and vulnerable patients to rely on home-based care, often leading to neglect and poor adherence to therapeutic exercises such as yoga or physiotherapy. To address this gap, we propose a low-cost and automated human activity recognition (HAR) framework based on wearable inertial sensors and machine learning. Activity data, including walking, walking upstairs, walking downstairs, sitting, standing, and lying, were collected using accelerometer and gyroscope measurements. Four classical classifiers, Logistic Regression, Random Forest, Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN), were evaluated and compared with the proposed Support Tensor Machine (STM). Experimental results show that SVM achieved an accuracy of 93.33 percent, while Logistic Regression, Random Forest, and k-NN achieved 91.11 percent. In contrast, STM significantly outperformed these models, achieving a test accuracy of 96.67 percent and the highest cross-validation accuracy of 98.50 percent. Unlike conventional methods, STM leverages tensor representations to preserve spatio-temporal motion dynamics, resulting in robust classification across diverse activities. The proposed framework demonstrates strong potential for remote healthcare, elderly assistance, child activity monitoring, yoga feedback, and smart home wellness, offering a scalable solution for low-resource and rural healthcare settings.