Open Access

ARTICLE

Enhancing Fall Detection in Alzheimer’s Patients Using Unsupervised Domain Adaptation

Nadhmi A. Gazem¹, Sultan Noman Qasem^2,3, Umair Naeem⁴, Shahid Latif⁵, Ibtehal Nafea⁶, Faisal Saeed⁷, Mujeeb Ur Rehman^8,*

1 Department of Information Systems, College of Business Administration-Yanbu, Taibah University, Medina, 42353, Saudi Arabia
2 Computer Science Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, 11432, Saudi Arabia
3 King Salman Center for Disability Research, Riyadh, 11614, Saudi Arabia
4 Department of Mechanical, Manufacturing and Mechatronics Engineering, RMIT University, Melbourne, VIC 3001, Australia
5 School of Computing and Creative Technologies, University of the West of England, Bristol, BS16 1QY, UK
6 College of Computer Science and Engineering, Taibah University, Medina, 41477, Saudi Arabia
7 College of Computing, Birmingham City University, Birmingham, B4 7XG, UK
8 School of Computer Science and Informatics, Institute of Artificial Intelligence, De Montfort University, Leicester, LE1 9BH, UK

* Corresponding Author: Mujeeb Ur Rehman. Email:

Computer Modeling in Engineering & Sciences 2025, 144(1), 407-427. https://doi.org/10.32604/cmes.2025.066517

Received 10 April 2025; Accepted 23 June 2025; Issue published 31 July 2025

Abstract

Falls are a leading cause of injury and morbidity among older adults, especially those with Alzheimer’s disease (AD), who face increased risks due to cognitive decline, gait instability, and impaired spatial awareness. While wearable sensor-based fall detection systems offer promising solutions, their effectiveness is often hindered by domain shifts resulting from variations in sensor placement, sampling frequencies, and discrepancies in dataset distributions. To address these challenges, this paper proposes a novel unsupervised domain adaptation (UDA) framework specifically designed for cross-dataset fall detection in Alzheimer’s disease (AD) patients, utilizing advanced transfer learning to enhance generalizability. The proposed method incorporates a ResNet-Transformer Network (ResT) as a feature extractor, along with a novel DualAlign Loss formulation that aims to align feature distributions while maintaining class separability. Experiments on the preprocessed KFall and SisFall datasets demonstrate significant improvements in F1-score and recall, crucial metrics for reliable fall detection, outperforming existing UDA methods, including a convolutional neural network (CNN), DeepCORAL, DANN, and CDAN. By addressing domain shifts, the proposed approach enhances the practical viability of fall detection systems for AD patients, providing a scalable solution to minimize injury risks and improve caregiving outcomes in real-world environments.

---

Keywords

---