Hybrid attention-based temporal convolutional networks for driver fatigue detection using physiological signal

Julakha Jahan Jui; Imali T. Hettiarachchi; Thanh Thi Nguyen

doi:10.1016/j.bspc.2025.109125

Back

Hybrid attention-based temporal convolutional networks for driver fatigue detection using physiological signal

Journal article

Open access

Peer reviewed

Hybrid attention-based temporal convolutional networks for driver fatigue detection using physiological signal

Julakha Jahan Jui, Imali T. Hettiarachchi and Thanh Thi Nguyen

Biomedical Signal Processing and Control, Vol.113, pp.1-20

2026

DOI: https://doi.org/10.1016/j.bspc.2025.109125

Files and links (1)

pdf

1-s2.0-S1746809425016362-main5.35 MBDownload View

Published Version Open Access CC BY V4.0

Abstract

Automatic and tunable artifact removal

Deep learning

Electroencephalography signals

Fatigue detection

Machine learning

Temporal convolutional networks

Fatigue detection remains a major challenge in safety-critical domains such as transportation and aviation, where timely and reliable monitoring is essential to prevent accidents and performance degradation. This study introduces a novel dual-architecture hybrid framework that leverages deep temporal modelling and attention mechanisms for real-time EEG-based fatigue classification. Specifically, two enhanced Temporal Convolutional Network (TCN) variants, TCN with Self-Attention (TCN-SA) and TCN integrated with Transformer Encoders (TTCN), are developed to capture both short- and long-range dependencies in EEG signals. To enhance decision-making robustness, high-level features extracted by these deep models are further classified using traditional machine learning algorithms, including Support Vector Machines (SVM), k-Nearest Neighbours (KNN), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Experimental results demonstrate that the hybrid TTCN+RF model achieves superior performance, reaching 98.47% accuracy in participant-wise evaluation and 93.25% in aggregated analysis. The proposed models are rigorously validated using 10-fold cross-validation repeated over 10 runs and leave-one-subject-out (LOSO) analysis. Furthermore, comprehensive statistical evaluations, including Friedman and Wilcoxon signed-rank tests, confirm the significant performance advantage of the proposed hybrid models across datasets. These findings underscore the potential of hybrid deep learning frameworks for real-time cognitive monitoring in high-stakes environments.

Details

Title: Hybrid attention-based temporal convolutional networks for driver fatigue detection using physiological signal
Authors: Julakha Jahan Jui (Corresponding Author) - Deakin University
Imali T. Hettiarachchi - Deakin University
Thanh Thi Nguyen - Monash University
Publication details: Biomedical Signal Processing and Control, Vol.113, pp.1-20
Publisher: Elsevier BV
Date published: 2026
DOI: 10.1016/j.bspc.2025.109125
ISSN: 1746-8108
Data Availability: Data will be made available on request.
Grant note: This research is fully funded by the Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia.
Organisation Unit: School of Science, Technology and Engineering
Language: English
Record Identifier: 991228430302621
Output Type: Journal article

Metrics

1 Record Views