BrainNet: an automated approach for brain stress prediction utilizing electrodermal activity signal with XLNet model

Liao Xuanzhi; Abeer Hakeem; Linda Mohaisen; Muhammad Umer; Muhammad Attique Khan; Shrooq Alsenan; Shtwai Alsubai; Nisreen Innab

doi:10.3389/fncom.2024.1482994

BrainNet: an automated approach for brain stress prediction utilizing electrodermal activity signal with XLNet model

Front Comput Neurosci. 2024 Oct 24:18:1482994. doi: 10.3389/fncom.2024.1482994. eCollection 2024.

Authors

Liao Xuanzhi¹, Abeer Hakeem², Linda Mohaisen², Muhammad Umer³, Muhammad Attique Khan⁴, Shrooq Alsenan⁵, Shtwai Alsubai⁶, Nisreen Innab⁷

Affiliations

¹ College of Electronic and Information Engineering, Beibu Gulf University, Qinzhou, China.
² Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia.
³ Department of Computer Science & Information Technology, The Islamia University of Bahawalpur, Bahawalpur, Pakistan.
⁴ Department of AI, College of Computer Engineering and Science, Prince Mohammad Bin Fahd University, Al Khobar, Saudi Arabia.
⁵ Information Systems Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
⁶ Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia.
⁷ Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Diriyah, Saudi Arabia.

Abstract

Brain stress monitoring has emerged as a critical research area for understanding and managing stress and neurological health issues. This burgeoning field aims to provide accurate information and prediction about individuals' stress levels by analyzing behavioral data and physiological signals. To address this emerging problem, this research study proposes an innovative approach that uses an attention mechanism-based XLNet model (called BrainNet) for continuous stress monitoring and stress level prediction. The proposed model analyzes streams of brain data, including behavioral and physiological signal patterns using Swell and WESAD datasets. Testing on the Swell multi-class dataset, the model achieves an impressive accuracy of 95.76%. Furthermore, when evaluated on the WESAD dataset, it demonstrates even higher accuracy, reaching 98.32%. When applied to the binary classification of stress and no stress using the Swell dataset, the model achieves an outstanding accuracy of 97.19%. Comparative analysis with other previously published research studies underscores the superior performance of the proposed approach. In addition, cross-validation confirms the significance, efficacy, and robustness of the model in brain stress level prediction and aligns with the goals of smart diagnostics for understanding neurological behaviors.

Keywords: EEG monitoring; Swell; WESAD; XLNet; artificial intelligence; brain stress monitoring; smart healthcare.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This study was supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project (PNURSP2024R506), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia. Nisreen Innab would like to express sincere gratitude to AlMaarefa University, Riyadh, Saudi Arabia, for supporting this research.