Complex Human Activities Recognition Using Smartphone Sensors: A Deep Learning Approach

Mubashar Saeed ()
Additional contact information
Mubashar Saeed: Allama Iqbal Open University

International Journal of Innovations in Science & Technology, 2024, vol. 6 Special Issue: 7, issue 7, 172-184

Abstract: Human Activity Recognition (HAR) plays a critical role in understanding human behavior, with mobile phone sensors offering a promising approach for practical applications. This research uniquely addresses the challenge of Complex Human Activity Recognition (CHAR) using Long Short-Term Memory (LSTM) networks, advancing beyond basic activity recognition. LSTM was applied to three publicly available datasets—PAMAP2, Complex Human Activities, and WISDM—using accelerometer, gyroscope, and magnetometer sensor data. The research evaluated the effectiveness of both single-sensor (accelerometer) and multi-sensor combinations for recognizing complex activities. The study achieved 94-98% accuracy across datasets, showing that a single accelerometer sensor provides reasonable accuracy, while adding more sensors, like gyroscope and magnetometer, further boosts performance at a resource cost. The LSTM-based approach consistently outperformed traditional methods, including CNNs, in complex activity recognition, demonstrating its robustness in simplifying sensor requirements without compromising accuracy. LSTM networks offer an efficient and accurate solution for complex human activity recognition, balancing performance and resource optimization

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journal.50sea.com/index.php/IJIST/article/view/1076/1642 (application/pdf)
https://journal.50sea.com/index.php/IJIST/article/view/1076 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abq:ijist1:v:6:y:2024:i:7:p:172-184

Access Statistics for this article

International Journal of Innovations in Science & Technology is currently edited by Prof. Dr. Syed Amer Mahmood

More articles in International Journal of Innovations in Science & Technology from 50sea
Bibliographic data for series maintained by Iqra Nazeer ().