Work

A Cost-Effective Real-Time Human Activity Recognition System Using Supervised Learning Algorithms and Wearable Acceleration Sensors

Year: 2025

Type: article

Abstract: Human activity recognition (HAR) plays a vital role in health monitoring by providing detailed insights into daily movements. This study aims to enhance HAR by developing a lightweight and efficient machine learning model that balances accuracy, real-time performance, and affordability. Using acceleration data from a wearable inertial sensor, we extracted a novel feature set optimized for computational efficiency. The proposed model was evaluated on a benchmark dataset, achieving an accuracy of 98.9%, in classifying six essential daily activities: walking, walking upstairs, walking downstairs, laying, sitting, and standing. These results demonstrate the model’s potential for real-time health monitoring applications, offering a cost-effective and deployable solution for wearable-based activity recognition.

Source: Journal of Applied Engineering and Technological Science (JAETS)

DOI: 10.37385/jaets.v6i2.6830

Authors: Nguyen Thi Thu, Phung Cong Phi Khanh, Trong-Minh Hoang, Duc-Tan Tran, Nguyen Ngoc Linh, Nguyen Canh Minh

Institutions: Hanoi University of Industry, Hanoi National University of Education, Posts and Telecommunications Institute of Technology, Phenikaa University, University of Transport and Communications

Language: English

Topic: Context-Aware Activity Recognition Systems

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $16

OpenAlex ID: W4411123195

FWCI:

Cites:

Cited by:

Related to: 10