Machine Learning for Human Activity Recognition: State-of-the-Art Techniques and Emerging Trends
Journal of Imaging · 20.03.2025 · 11 (3) · 91
DOI: 10.3390/jimaging11030091 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Imaging, online erschienen am 20.03.2025. Verfasst von Md Amran Hossen und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Integrated Technologies, Universiti Brunei Darussalam, Bandar Seri Begawan BE 1410, Brunei. Die Arbeit wurde bisher 62-mal zitiert (Crossref) und nennt 319 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universiti Brunei Darussalam.
Abstract (Originalsprache)
Human activity recognition (HAR) has emerged as a transformative field with widespread applications, leveraging diverse sensor modalities to accurately identify and classify human activities. This paper provides a comprehensive review of HAR techniques, focusing on the integration of sensor-based, vision-based, and hybrid methodologies. It explores the strengths and limitations of commonly used modalities, such as RGB images/videos, depth sensors, motion capture systems, wearable devices, and emerging technologies like radar and Wi-Fi channel state information. The review also discusses traditional machine learning approaches, including supervised and unsupervised learning, alongside cutting-edge advancements in deep learning, such as convolutional and recurrent neural networks, attention mechanisms, and reinforcement learning frameworks. Despite significant progress, HAR still faces critical challenges, including handling environmental variability, ensuring model interpretability, and achieving high recognition accuracy in complex, real-world scenarios. Future research directions emphasise the need for improved multimodal sensor fusion, adaptive and personalised models, and the integration of edge computing for real-time analysis. Additionally, addressing ethical considerations, such as privacy and algorithmic fairness, remains a priority as HAR systems become more pervasive. This study highlights the evolving landscape of HAR and outlines strategies for future advancements that can enhance the reliability and applicability of HAR technologies in diverse domains.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Integrated Technologies, Universiti Brunei Darussalam, Bandar Seri Begawan BE 1410, Brunei.
ORCID-Profile: Md Amran Hossen, Pg Emeroylariffion Abas
Förderung
- Universiti Brunei Darussalam
Zitieren
APA
Hossen, M. A., & Abas, P. E. (2025). Machine Learning for Human Activity Recognition: State-of-the-Art Techniques and Emerging Trends. Journal of Imaging, 11(3), 91. https://doi.org/10.3390/jimaging11030091
Vancouver
Hossen MA, Abas PE. Machine Learning for Human Activity Recognition: State-of-the-Art Techniques and Emerging Trends. Journal of Imaging. 2025;11(3):91. doi:10.3390/jimaging11030091
BibTeX
@article{Hossen2025,
author = {Hossen, Md Amran and Abas, Pg Emeroylariffion},
title = {Machine Learning for Human Activity Recognition: State-of-the-Art Techniques and Emerging Trends},
journal = {Journal of Imaging},
year = {2025},
volume = {11},
number = {3},
pages = {91},
doi = {10.3390/jimaging11030091}
}
EUVIMED