Open Access

ARTICLE

Efficient Real-Time Devices Based on Accelerometer Using Machine Learning for HAR on Low-Performance Microcontrollers

by Manh-Tuyen Vi¹, Duc-Nghia Tran², Vu Thi Thuong^3,4, Nguyen Ngoc Linh^5,*, Duc-Tan Tran^1,*

1 Faculty of Electrical and Electronic Engineering, Phenikaa University, Hanoi City, 100000, Vietnam
2 Institute of Information Technology, Vietnam Academy of Science and Technology, Hanoi City, 100000, Vietnam
3 Faculty of Information Technology and Communication, Phuong Dong University, Hanoi City, 100000, Vietnam
4 Graduate University of Sciences and Technology, Vietnam Academy of Science and Technology, Hanoi City, 100000, Vietnam
5 International School–Vietnam National University, Hanoi City, 100000, Vietnam

* Corresponding Authors: Nguyen Ngoc Linh. Email: ; Duc-Tan Tran. Email:

Computers, Materials & Continua 2024, 81(1), 1729-1756. https://doi.org/10.32604/cmc.2024.055511

Received 28 June 2024; Accepted 14 September 2024; Issue published 15 October 2024

Abstract

Analyzing physical activities through wearable devices is a promising research area for improving health assessment. This research focuses on the development of an affordable and real-time Human Activity Recognition (HAR) system designed to operate on low-performance microcontrollers. The system utilizes data from a body-worn accelerometer to recognize and classify human activities, providing a cost-effective, easy-to-use, and highly accurate solution. A key challenge addressed in this study is the execution of efficient motion recognition within a resource-constrained environment. The system employs a Random Forest (RF) classifier, which outperforms Gradient Boosting Decision Trees (GBDT), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) in terms of accuracy and computational efficiency. The proposed features Average absolute deviation (AAD), Standard deviation (STD), Interquartile range (IQR), Range, and Root mean square (RMS). The research has conducted numerous experiments and comparisons to establish optimal parameters for ensuring system effectiveness, including setting a sampling frequency of 50 Hz and selecting an 8-s window size with a 40% overlap between windows. Validation was conducted on both the WISDM public dataset and a self-collected dataset, focusing on five fundamental daily activities: Standing, Sitting, Jogging, Walking, and Walking the stairs. The results demonstrated high recognition accuracy, with the system achieving 96.7% on the WISDM dataset and 97.13% on the collected dataset. This research confirms the feasibility of deploying HAR systems on low-performance microcontrollers and highlights the system’s potential applications in patient support, rehabilitation, and elderly care.

---

Keywords

---