Explainable stress detection system using hybrid CNN-Transformer and uncertainty quantification with copula GAN-based data

S. Janifer Jabin Jui; Ravinesh C. Deo; Rajendra Acharya; Prabal Datta Barua; Jeffrey Soar; Aruna Devi

doi:10.1016/j.bspc.2026.109934

Back

Explainable stress detection system using hybrid CNN-Transformer and uncertainty quantification with copula GAN-based data

Journal article

Open access

Peer reviewed

Explainable stress detection system using hybrid CNN-Transformer and uncertainty quantification with copula GAN-based data

S. Janifer Jabin Jui, Ravinesh C. Deo, Rajendra Acharya, Prabal Datta Barua, Jeffrey Soar and Aruna Devi

Biomedical Signal Processing and Control, Vol.120(Part A), pp.1-20

2026

DOI: https://doi.org/10.1016/j.bspc.2026.109934

Files and links (1)

pdf

1-s2.0-S174680942600488X-main4.98 MBDownload View

Published VersionCC BY V4.0, Open Access

Abstract

stress detection

uncertainty quantification

data augmentation

explainable AI

interpretable model

CNN-transformer

Stress is a widespread concern that impacts human health with its silent progression, causing significant public health burdens and economic loss globally. Non-invasive wearable technology empowered by physiological signal monitoring can enable early warning systems for stress, alleviating some of the burdens, allowing on-time interventions, and thus significantly improving quality of life. This study used the heart rate and respiratory rate data from 34 participants. It evaluated the performance of the hybrid deep learning CNN-Transformer model and benchmarked it against deep learning convolutional neural networks (CNNs) and Transformer models, extreme gradient boosting (XGBoost) and random forest (RF) machine learning models, comprising a total of five AI models. To mitigate data imbalance and observe the efficacy of deep learning data augmentation techniques in physiological signals for stress monitoring, two generative adversarial network (GAN) models: conditional tabular GAN (CTGAN), copula GAN (CopGAN) and variational autoencoder (VAE) based model tabular VAE synthesiser (TVAES) had been employed. The modelling performance significantly improved when applying CTGAN and CopGAN, demonstrating the usefulness of synthetic data. The CNN-Transformer achieved an average accuracy of 77%, a precision of 87% and an AUC of 83%. The study applied leave-one- subject- out (LOSO CV) to prove the CNN-Transformer hybrid’s robustness for generalizability to perform well for unseen subjects. The study integrated explainable AI models, Shapley values (SHAP), and local interpretable model-agnostic explanations (LIME), as well as Monte Carlo Dropout for uncertainty quantification to bring confidence, trust and transparency to AI systems, taking a step closer to real-world deployment. Similar studies can also help in the detection of other disorders, such as anxiety and depression.

Details

Title: Explainable stress detection system using hybrid CNN-Transformer and uncertainty quantification with copula GAN-based data
Authors: S. Janifer Jabin Jui (Corresponding Author) - University of Southern Queensland
Ravinesh C. Deo - University of Southern Queensland
Rajendra Acharya - University of Southern Queensland
Prabal Datta Barua - University of Southern Queensland
Jeffrey Soar - University of Southern Queensland
Aruna Devi - University of the Sunshine Coast
Publication details: Biomedical Signal Processing and Control, Vol.120(Part A), pp.1-20
Publisher: Elsevier BV
Date published: 2026
DOI: 10.1016/j.bspc.2026.109934
ISSN: 1746-8108; 1746-8094
Data Availability: The authors are unable or have chosen not to specify which data has been used.
Grant note: This work was supported by the University of Southern Queensland International PhD Fee Scholarship (2022–2025) and an International PhD Stipend Scholarship from Cogninet Australia Pty Ltd., under the Industry Research Scholarship Agreement .
Organisation Unit: School of Education and Tertiary Access
Language: English
Record Identifier: 991212772402621
Output Type: Journal article

Metrics

1 Record Views