Complex Human Activities Recognition Using Smartphone Sensors: A Deep Learning Approach
International Journal of Innovations in Science and Technology · 25.10.2024 · 172
DOI: 10.33411/ijist/1076 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 25.10.2024. Verfasst von Mubashar Saeed und 2 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Saeed, M., Awan, A., & Hameed, S. (2024). Complex Human Activities Recognition Using Smartphone Sensors: A Deep Learning Approach. International Journal of Innovations in Science and Technology, 172. https://doi.org/10.33411/ijist/1076
Vancouver
Saeed M, Awan A, Hameed S. Complex Human Activities Recognition Using Smartphone Sensors: A Deep Learning Approach. International Journal of Innovations in Science and Technology. 2024:172. doi:10.33411/ijist/1076
BibTeX
@article{Saeed2024,
author = {Saeed, Mubashar and Awan, Arshad and Hameed, Saira},
title = {Complex Human Activities Recognition Using Smartphone Sensors: A Deep Learning Approach},
journal = {International Journal of Innovations in Science and Technology},
year = {2024},
pages = {172},
doi = {10.33411/ijist/1076}
}
EUVIMED