Deep Learning-Based Classification of Cognitive Workload Using Functional Connectivity Features

Authors

  • Vineeta Khemchandani Galgotias University
  • Alok Singh Chauhan Galgotias University
  • Shahnaz Fatima Amity University
  • Jalauk Singh Maurya JSS Academy of Technical Education
  • Abhay Singh Rathaur JSS Academy of Technical Education
  • Narendra Kumar Sharma Pranveer Singh Institute of Technology
  • Daya Shankar Srivastava Greater Noida Institute of Technology
  • Vugar Abdullayev Azerbaijan University of Architecture and Construction

DOI:

https://doi.org/10.26877/asset.v8i1.2833

Keywords:

Cognitive workload, Deep Learning, CNN, EEG, Functional Connectivity, Connectivity Metrics

Abstract

Cognitive workload plays a vital role in tasks that demand dynamic decision-making, especially under high-risk and time-sensitive conditions. An excessive workload can lead to unexpected and disproportionate risks, whereas insufficient workload may cause disengagement, undermining task performance. This underscores the importance of maintaining an optimal level of mental focus in high-pressure situations to ensure successful task execution. This study leverages deep learning methods alongside functional connectivity measures to classify cognitive workload levels. Using the N-back EEG dataset, functional connectivity metrics such as Phase Locking Value (PLV), Phase Lagging Index (PLI), and Coherency are extracted after data pre-processing. These metrics, characterized as directed or non-directed, enable efficient computational analysis. A convolutional neural network (CNN) classifier is employed to categorize cognitive workload into three levels: low (0-back), medium (2-back), and high (3-back). The CNN-A architecture achieves peak performance with an accuracy of 93.75% using PLV, 87.5% using Coherency, and 68.75% using PLI.

Author Biographies

  • Vineeta Khemchandani, Galgotias University

    School of Computer Applications and Technology, Galgotias University, Greater Noida 203201, India

  • Alok Singh Chauhan, Galgotias University

    School of Computer Applications and Technology, Galgotias University, Greater Noida 203201, India

  • Shahnaz Fatima, Amity University

    Amity Institute of Information Technology, Amity University, Lucknow, India

  • Jalauk Singh Maurya, JSS Academy of Technical Education

    Department of Information Technology, JSS Academy of Technical Education, Noida, India

  • Abhay Singh Rathaur, JSS Academy of Technical Education

    Department of Information Technology, JSS Academy of Technical Education, Noida, India

  • Narendra Kumar Sharma, Pranveer Singh Institute of Technology

    Department of Computer Application, Pranveer Singh Institute of Technology, Kanpur, India

  • Daya Shankar Srivastava, Greater Noida Institute of Technology

    Department of Computer Science and Engineering, Greater Noida Institute of Technology, Greater Noida, India

  • Vugar Abdullayev, Azerbaijan University of Architecture and Construction

    Azerbaijan University of Architecture and Construction, Azerbaijan

    Azerbaijan State Oil and Industry University, Azerbaijan

References

[1] Hart, S.G. NASA-task load index (NASA-TLX); 20 years later. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting; Sage Publications: Los Angeles, CA, USA, 2006; Volume 50, pp. 904–908. https://doi.org/10.1177/154193120605000909

[2] Nikhil Panwar, Vishal Pandey, Partha Pratim Roy, EEG-CogNet: A deep learning framework for cognitive state assessment using EEG brain connectivity, Biomedical Signal Processing and Control, Volume 98, 2024, 106770, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2024.106770.

[3] Borhani, S.; Abiri, R.; Jiang, Y.; Berger, T.; Zhao, X. Brain connectivity evaluation during selective attention using EEG-based brain-computer interface. Brain Comput. Interfaces (Abingdon), 2019, 6(1–2), 25–35. https://doi.org/10.1080/2326263X.2019.1651186

[4] Zafar, R.; Dass, S.C.; Malik, A.S. Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio-based score fusion. PLoS One 2017, 12(5), e0178410. https://doi.org/10.1371/journal.pone.0178410

[5] Matthews, G.; Reinerman-Jones, L.E.; Barber, D.J.; Abich, J., IV. The psychometrics of mental workload: Multiple measures are sensitive but divergent. Hum. Factors 2015, 57, 125–143. https://doi.org/10.1177/0018720814539505

[6] Hopstaken, J.F.; Van Der Linden, D.; Bakker, A.B.; Kompier, M.A. A multifaceted investigation of the link between mental fatigue and task disengagement. Psychophysiology 2015, 52, 305– https://doi.org/315. 10.1111/psyp.12339

[7] Wascher, E.; Rasch, B.; Sänger, J.; Hoffmann, S.; Schneider, D.; Rinkenauer, G.; Heuer, H.; Gutberlet, I. Frontal theta activity reflects distinct aspects of mental fatigue. Biol. Psychol. 2014, 96, 57–65. https://doi.org/10.1016/j.biopsycho.2013.11.010

[8] Dehais, F.; Duprès, A.; Blum, S.; Drougard, N.; Scannella, S.; Roy, R.N.; Lotte, F. Monitoring Pilot's Mental Workload Using ERPs and Spectral Power with a Six-Dry-Electrode EEG System in Real Flight Conditions. Sensors (Basel) 2019, 19(6), 1324. https://doi.org/10.3390/s19061324

[9] Zhang, L.; Wade, J.; Bian, D.; Fan, J.; Swanson, A.; Weitlauf, A.; Warren, Z.; Sarkar, N. Cognitive Load Measurement in a Virtual Reality-Based Driving System for Autism Intervention. IEEE Trans. Affect. Comput. 2017, 8, 176–189. https://doi.org/10.1109/TAFFC.2016.2582490

[10] Luo C, Li F, Li P, Yi C, Li C, Tao Q, Zhang X, Si Y, Yao D, Yin G, Song P, Wang H, Xu P. A survey of brain network analysis by electroencephalographic signals. Cogn Neurodyn. 2022 Feb;16(1):17-41. https://doi.org/10.1007/s11571-021-09689-8

[11] Motamedi-Fakhr, S.; Moshrefi-Torbati, M.; Hill, M.; Hill, C.M.; White, P.R. Signal processing techniques applied to human sleep EEG signals—A review. Biomed. Signal Process. Control. 2014, 10, 21–33. https://doi.org/10.1016/j.bspc.2013.12.003

[12] Rashid, M.; Sulaiman, N.; Majeed, A.P.P.A.; Musa, R.M.; Nasir, A.F.A.; Bari, B.S.; Khatun, S. Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review. Front. Neurorobot. 2020, 14. https://doi.org/10.3389/fnbot.2020.00025

[13] Zhang, P.; Wang, X.; Zhang, W.; Chen, J. Learning Spatial-Spectral-Temporal EEG Features With Recurrent 3D Convolutional Neural Networks for Cross-Task Mental Workload Assessment. IEEE Trans. Neural Syst. Rehabil. Eng. 2019. https://doi.org/10.1109/TNSRE.2018.2884641

[14] Zhang, P.; Wang, X.; Chen, J.; You, W.; Zhang, W. Spectral and temporal feature learning with two-stream neural networks for mental workload assessment. IEEE Trans. Neural Syst. Rehabil. Eng. 2019. https://doi.org/10.1109/TNSRE.2019.2913400

[15] Dimitrakopoulos, G.N.; Kakkos, I.; Dai, Z.; Lim, J.; deSouza, J.J.; Bezerianos, A.; Sun, Y. Task-independent mental workload classification based upon common multiband EEG cortical connectivity. IEEE Trans. Neural Syst. Rehabil. Eng. 2017. https://doi.org/10.1109/TNSRE.2017.2701002

[16] Stam, C.J.; Nolte, G.; Daffertshofer, A. Phase lag index: Assessment of functional connectivity from multi-channel EEG and MEG with diminished bias from common sources. Hum. Brain Mapp. 2007, 28(11), 1178–1193. https://doi.org/10.1002/hbm.20346

[17] Gupta, A.; Siddhad, G.; Pandey, V.; Roy, P.P.; Kim, B.G. Subject-Specific Cognitive Workload Classification Using EEG-Based Functional Connectivity and Deep Learning. Sensors 2021. https://doi.org/10.3390/s21206710

[18] Cohen, M.X. Effects of time lag and frequency matching on phase-based connectivity. Journal of Neuroscience Methods 2015, 250, 137-146. https://doi.org/10.1016/j.jneumeth.2014.09.005

[19] Shin, J.; von Lühmann, A.; Kim, D.W.; et al. Simultaneous acquisition of EEG and NIRS during cognitive tasks for an open-access dataset. Sci Data 2018, 5, 180003. https://doi.org/10.1038/sdata.2018.3

[20] Barua, S.; Ahmed, M.U.; Begum, S. Towards Intelligent Data Analytics: A Case Study in Driver Cognitive Load Classification. Brain Sci. 2020, 10(8), 526. https://doi.org/10.3390/brainsci10080526

[21] Xiong, R.; Kong, F.; Yang, X.; Liu, G.; Wen, W. Pattern Recognition of Cognitive Load Using EEG and ECG Signals. Sensors 2020, 20, 5122. https://doi.org/10.3390/s20185122

[22] Zarjam, P.; Epps, J.; Chen, F.; Lovell, N.H. Estimating cognitive workload using wavelet entropy-based features during an arithmetic task. Computers in Biology and Medicine 2013, 43(12), 2186–2195. https://doi.org/10.1016/j.compbiomed.2013.08.021

[23] Shen, M.; Wen, P.; Song, B.; Li, Y. Automatic identification of schizophrenia based on EEG signals using dynamic functional connectivity analysis and 3D convolutional neural network. https://doi.org/10.1016/j.compbiomed.2023.107022

[24] Yang, S.; Yin, Z.; Wang, Y.; Zhang, W.; Wang, Y.; Zhang, J. Assessing cognitive mental workload via EEG signals and an ensemble deep learning classifier based on denoising autoencoders. Computers in Biology and Medicine 2019. https://doi.org/10.1016/j.compbiomed.2019.04.034

[25] Safari, M., Shalbaf, R., Bagherzadeh, S. et al. Classification of mental workload using brain connectivity and machine learning on electroencephalogram data. Sci Rep 14, 9153 (2024). https://doi.org/10.1038/s41598-024-59652-w

Downloads

Published

2026-01-22

Issue

Vol. 8 No. 1 (2026): November - January

Section

Articles

License

Copyright (c) 2025 Advance Sustainable Science Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.