EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Machine Learning in Ambient Assisted Living for Enhanced Elderly Healthcare: A Systematic Literature Review

Aabid A. Mir, Ahmad S. Khalid, Shahrulniza Musa, Mohammad Faizal Ahmad Fauzi, Normy Norfiza Abdul Razak, Tong Boon Tang

IEEE Access · 2025 · 13 · 110508-110527

DOI: 10.1109/access.2025.3580961 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift IEEE Access, 2025. Verfasst von Aabid A. Mir und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Government Linked University (GLU) Research Collaborative Fund (GRCF) 2023, managed by the Center for Research and Innovation (CoRI), Universiti Kuala Lumpur.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the global population ages, Ambient Assisted Living (AAL) systems have become essential in supporting the elderly to maintain independence and quality of life. Such systems integrate advanced technologies such as machine learning (ML), internet of things (IoT), and sensors to enhance safety and healthcare delivery. However, deploying such technologies raises significant challenges, especially in managing privacy, ensuring ethical compliance, and gaining user acceptance. This systematic literature review (SLR) explores the current state and advancements in AAL technologies, with a specific focus on their applications in elderly care. It synthesizes current methodologies, including predictive analytics, Explainable AI (XAI), and Generative AI (GenAI), while also evaluating the role of vision-based systems and multi-modal data fusion. It examines how such technologies are implemented to improve lives while also highlighting critical areas requiring attention, particularly privacy and ethical considerations. The review methodically analyzes articles and papers from the year 2020, selected based on their relevance to AAL technologies, their use of ML algorithms, and their focus on elderly care. The findings reveal the need for interpretability in AI-driven decisions and the role of GenAI in synthetic data generation and personalized conversational assistants. While ML and IoT significantly enhance AAL systems through predictive healthcare and personalized interventions, they also pose substantial privacy risks. The review identifies privacy as a critical concern due to the sensitive nature of the data collected and the vulnerabilities inherent in digital systems. Issues around data privacy, security breaches, and the need for robust privacy-preserving mechanisms are recurrent themes. This SLR illustrates the potential of AAL systems in elderly care and emphasizes the crucial requirement of addressing privacy and ethical issues to ensure such technologies are both beneficial and secure. The findings serve as a foundation for understanding the current state of AAL technologies and guide future advancements in elderly healthcare.

Förderung

  • Government Linked University (GLU) Research Collaborative Fund (GRCF) 2023, managed by the Center for Research and Innovation (CoRI), Universiti Kuala Lumpur

Zitieren

APA

Mir, A. A., Khalid, A. S., Musa, S., Fauzi, M. F. A., Razak, N. N. A., & Tang, T. B. (2025). Machine Learning in Ambient Assisted Living for Enhanced Elderly Healthcare: A Systematic Literature Review. IEEE Access, 13, 110508-110527. https://doi.org/10.1109/access.2025.3580961

Vancouver

Mir AA, Khalid AS, Musa S, Fauzi MFA, Razak NNA, Tang TB. Machine Learning in Ambient Assisted Living for Enhanced Elderly Healthcare: A Systematic Literature Review. IEEE Access. 2025;13:110508-110527. doi:10.1109/access.2025.3580961

BibTeX
@article{Mir2025,
  author = {Mir, Aabid A. and Khalid, Ahmad S. and Musa, Shahrulniza and Fauzi, Mohammad Faizal Ahmad and Razak, Normy Norfiza Abdul and Tang, Tong Boon},
  title = {Machine Learning in Ambient Assisted Living for Enhanced Elderly Healthcare: A Systematic Literature Review},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {110508--110527},
  doi = {10.1109/access.2025.3580961}
}
Kostenlos starten →