ARCHIVES
Original Article
A Multimodal Machine Learning Framework for Class- Imbalanced Cognitive State Classification from High-Density EEG and Physiological Signals
Swapnil Wanjare1
Dr. Vishwas Gaikwad2
1 2 Department of Electronics and Telecommunications, Sipna College of Engineering and Technology, Maharashtra, India.
Published Online: September-December 2025
Pages: 230-238
Cite this article
↗ https://www.doi.org/10.59256/indjcst.20250403036
References
1. R. S. Abdulsadig and E. Rodriguez-Villegas, "A comparative study in class imbalance mitigation when working with physiological signals,"
Front. Digit. Health, vol. 6, p. 1377165, Mar. 2024, doi: 10.3389/fdgth.2024.1377165.
2. P. Kashyap, "Understanding precision, recall, and F1 score metrics," Medium, Dec. 2024. [Online]. Available:
https://medium.com/@piyushkashyap045/understanding-precision-recall-and-f1-score-metrics-ea219b908093. [Accessed: Nov. 8, 2025].
3. A. Ajit et al., "Eye state classification using ensemble machine learning models and SMOTE on EEG data," ResearchGate. [Online].
Available:
https://www.researchgate.net/publication/385414504_Eye_State_Classification_Using_Ensemble_Machine_Learning_Models_and_SMOT
E_on_EEG_Data. [Accessed: Nov. 8, 2025].
4. J. Singh, C. Beeche, Z. Shi, O. Beale, B. Rosin, J. Leader, and J. Pu, "Batch-balanced focal loss: A hybrid solution to class imbalance in deep
learning," J. Med. Imag., vol. 10, no. 5, p. 051809, Jun. 2023, doi: 10.1117/1.JMI.10.5.051809.
5. U. Niyaz, "Focal loss for handling the issue of class imbalance," Medium, Data Science @ Ecom Express, Nov. 2025. [Online]. Available:
https://medium.com/data-science-ecom-express/focal-loss-for-handling-the-issue-of-class-imbalance-be7addebd856. [Accessed: Nov. 8,
2025].
6. "Improving minority class recall through a novel cluster-based oversampling technique," MDPI Appl., vol. 11, no. 2, p. 35, 2025, doi:
10.3390/app11020035.
7. "Genetic algorithms for feature selection for brain-computer interface," Int. J. Pattern Recognit. Artif. Intell., World Scientific Publishing,
2015. [Online]. Available: https://www.worldscientific.com/doi/10.1142/S0218001415590089. [Accessed: Nov. 8, 2025].
8. V. Müller, V. Dirlich, M. Brandeis, H. Fallgatter, and A. J. Fallgatter, "Reproducible machine learning research in mental workload
classification using EEG," Front. Neuroergon., vol. 5, p. 1346794, 2024, doi: 10.3389/fnrgo.2024.1346794.
9. M. D'Alessandro, R. Mackie, T. Berger, C. Ott, C. Sullivan, and I. Curry, "Real-time neurophysiological and subjective indices of cognitive
engagement in high-speed flight," Aerosp. Med. Hum. Perform., vol. 95, no. 12, pp. 885–896, Dec. 2024, doi: 10.3357/AMHP.6489.2024.10. S. Jeunet, E. N. N'Kaoua, P. Subramanian, M. Hachet, and F. Lotte, "Enhanced pilot attention monitoring: A time-frequency EEG analysis
using CNN-LSTM networks for aviation safety," Information, vol. 16, no. 6, p. 503, Jun. 2025, doi: 10.3390/info16060503.
11. S. Jahangiri, A. Zaki, J. Parviz, and D. Marcus, "Measuring pilot physiology during in-flight training and implications for real-time
monitoring," Aerosp. Med. Hum. Perform., vol. 95, no. 10, pp. 712–725, Oct. 2024, doi: 10.3357/AMHP.6234.2024.
12. R. Puttige and M. Mohan, "Machine learning-based approach for identifying mental workload of pilots," ResearchGate. [Online]. Available:
https://www.researchgate.net/publication/359424930_Machine_learning-based_approach_for_identifying_mental_workload_of_pilots.
[Accessed: Nov. 8, 2025].
13. R. Jebari, M. Karim, P. S. Tofail, and Y. Gabbas, "PRISMA systematic review of electroencephalographic (EEG) microstates as biomarkers:
Secondary findings in memory functions," Neuroimage Reports, vol. 4, no. 2, p. 100307, 2024, doi: 10.1016/j.ynirp.2024.100307.
14. G. P. Navalkar and J. Kumar, "AI perspectives within computational neuroscience: EEG integrations and the human brain," ResearchGate.
[Online]. Available:
https://www.researchgate.net/publication/390042877_AI_Perspectives_Within_Computational_Neuroscience_EEG_Integrations_and_the_
Human_Brain. [Accessed: Nov. 8, 2025].
15. D. Mahajan, N. Tyagi, and H. Singh, "Neural decoding of EEG signals with machine learning: A systematic review," IEEE Trans. Biomed.
Eng., vol. 69, no. 12, pp. 3517–3530, Dec. 2022, doi: 10.1109/TBME.2022.3191075.
16. F. Mirza, M. Hasanzadeh, and S. Nazari, "From neural networks to emotional networks: A systematic review of EEG-based emotion
recognition in cognitive neuroscience and real-world applications," Brain Sci., vol. 15, no. 3, p. 220, Mar. 2024, doi:
10.3390/brainsci15030220.
17. A. Chen, M. Thorp, and B. Kandel, "Human-centric cognitive state recognition using physiological signals: A systematic review of machine
learning strategies across application domains," Sensors, vol. 25, no. 13, p. 4207, 2025, doi: 10.3390/s25134207.
18. [18] M. Koelstra, C. Mühl, E. Soleymani, J.-S. Lee, A. Nijholt, T. Pun, D. Ramsay, and M. Sap, "Human-centric cognitive state recognition
using physiological signals: A systematic review of machine learning strategies," PLoS ONE, vol. 19, no. 8, p. e0301947, Aug. 2024, doi:
10.1371/journal.pone.0301947.
19. [19] Y. Khalili, M. R. Begian, and M. Mozayan, "Emotion recognition based on multimodal physiological electrical signals," Front.
Neurosci., vol. 19, p. 1512799, Mar. 2025, doi: 10.3389/fnins.2025.1512799.
20. O. Aamir, M. Roslan, and S. Zamri, "Machine learning-based signal processing by physiological signals detection of stress," Turcomat.org,
vol. 12, no. 2, pp. 1–16, 2023. [Online]. Available: https://turcomat.org/index.php/turkbilmat/article/view/6659. [Accessed: Nov. 8, 2025].
21. A. K. Singh, K. Yadav, N. Kumar, and P. Verma, "Machine learning approaches to evaluate EEG correlates of relaxation between supine
and sitting postures in eyes-closed condition," Front. Hum. Neurosci., vol. 15, p. 756088, 2021, doi: 10.3389/fnhum.2021.756088.
22. Y. Roy, H. Banville, I. Albuquerque, A. Gramfort, T. H. Falk, and J. Feydy, "Deep learning-based electroencephalography analysis," IEEE
Trans. Biomed. Eng., vol. 69, no. 12, pp. 3521–3540, Dec. 2022, doi: 10.1109/TBME.2022.3195187.
23. H. Jahangiri, S. Javadi, and H. Soheilifar, "Cognitive state classification using convolutional neural networks on gamma-band EEG signals,"
Appl. Sci., vol. 14, no. 18, p. 8380, Sep. 2023, doi: 10.3390/app14188380.
24. I. Tuncer and A. Onan, "A hybrid CNN-Bi-LSTM model with feature fusion for accurate epilepsy seizure detection," Biomed. Signal Process.
Control, vol. 80, p. 104260, Dec. 2023, doi: 10.1016/j.bspc.2022.104260.
25. S. Mahmud, S. Fathema, M. Hasan, A. H. Rashid, and M. A. Rahman, "Automatic classification of EEG signals based on image interpretation
of spatio-temporal information," medRxiv, Feb. 2025, doi: 10.1101/2025.02.10.25322019.
Front. Digit. Health, vol. 6, p. 1377165, Mar. 2024, doi: 10.3389/fdgth.2024.1377165.
2. P. Kashyap, "Understanding precision, recall, and F1 score metrics," Medium, Dec. 2024. [Online]. Available:
https://medium.com/@piyushkashyap045/understanding-precision-recall-and-f1-score-metrics-ea219b908093. [Accessed: Nov. 8, 2025].
3. A. Ajit et al., "Eye state classification using ensemble machine learning models and SMOTE on EEG data," ResearchGate. [Online].
Available:
https://www.researchgate.net/publication/385414504_Eye_State_Classification_Using_Ensemble_Machine_Learning_Models_and_SMOT
E_on_EEG_Data. [Accessed: Nov. 8, 2025].
4. J. Singh, C. Beeche, Z. Shi, O. Beale, B. Rosin, J. Leader, and J. Pu, "Batch-balanced focal loss: A hybrid solution to class imbalance in deep
learning," J. Med. Imag., vol. 10, no. 5, p. 051809, Jun. 2023, doi: 10.1117/1.JMI.10.5.051809.
5. U. Niyaz, "Focal loss for handling the issue of class imbalance," Medium, Data Science @ Ecom Express, Nov. 2025. [Online]. Available:
https://medium.com/data-science-ecom-express/focal-loss-for-handling-the-issue-of-class-imbalance-be7addebd856. [Accessed: Nov. 8,
2025].
6. "Improving minority class recall through a novel cluster-based oversampling technique," MDPI Appl., vol. 11, no. 2, p. 35, 2025, doi:
10.3390/app11020035.
7. "Genetic algorithms for feature selection for brain-computer interface," Int. J. Pattern Recognit. Artif. Intell., World Scientific Publishing,
2015. [Online]. Available: https://www.worldscientific.com/doi/10.1142/S0218001415590089. [Accessed: Nov. 8, 2025].
8. V. Müller, V. Dirlich, M. Brandeis, H. Fallgatter, and A. J. Fallgatter, "Reproducible machine learning research in mental workload
classification using EEG," Front. Neuroergon., vol. 5, p. 1346794, 2024, doi: 10.3389/fnrgo.2024.1346794.
9. M. D'Alessandro, R. Mackie, T. Berger, C. Ott, C. Sullivan, and I. Curry, "Real-time neurophysiological and subjective indices of cognitive
engagement in high-speed flight," Aerosp. Med. Hum. Perform., vol. 95, no. 12, pp. 885–896, Dec. 2024, doi: 10.3357/AMHP.6489.2024.10. S. Jeunet, E. N. N'Kaoua, P. Subramanian, M. Hachet, and F. Lotte, "Enhanced pilot attention monitoring: A time-frequency EEG analysis
using CNN-LSTM networks for aviation safety," Information, vol. 16, no. 6, p. 503, Jun. 2025, doi: 10.3390/info16060503.
11. S. Jahangiri, A. Zaki, J. Parviz, and D. Marcus, "Measuring pilot physiology during in-flight training and implications for real-time
monitoring," Aerosp. Med. Hum. Perform., vol. 95, no. 10, pp. 712–725, Oct. 2024, doi: 10.3357/AMHP.6234.2024.
12. R. Puttige and M. Mohan, "Machine learning-based approach for identifying mental workload of pilots," ResearchGate. [Online]. Available:
https://www.researchgate.net/publication/359424930_Machine_learning-based_approach_for_identifying_mental_workload_of_pilots.
[Accessed: Nov. 8, 2025].
13. R. Jebari, M. Karim, P. S. Tofail, and Y. Gabbas, "PRISMA systematic review of electroencephalographic (EEG) microstates as biomarkers:
Secondary findings in memory functions," Neuroimage Reports, vol. 4, no. 2, p. 100307, 2024, doi: 10.1016/j.ynirp.2024.100307.
14. G. P. Navalkar and J. Kumar, "AI perspectives within computational neuroscience: EEG integrations and the human brain," ResearchGate.
[Online]. Available:
https://www.researchgate.net/publication/390042877_AI_Perspectives_Within_Computational_Neuroscience_EEG_Integrations_and_the_
Human_Brain. [Accessed: Nov. 8, 2025].
15. D. Mahajan, N. Tyagi, and H. Singh, "Neural decoding of EEG signals with machine learning: A systematic review," IEEE Trans. Biomed.
Eng., vol. 69, no. 12, pp. 3517–3530, Dec. 2022, doi: 10.1109/TBME.2022.3191075.
16. F. Mirza, M. Hasanzadeh, and S. Nazari, "From neural networks to emotional networks: A systematic review of EEG-based emotion
recognition in cognitive neuroscience and real-world applications," Brain Sci., vol. 15, no. 3, p. 220, Mar. 2024, doi:
10.3390/brainsci15030220.
17. A. Chen, M. Thorp, and B. Kandel, "Human-centric cognitive state recognition using physiological signals: A systematic review of machine
learning strategies across application domains," Sensors, vol. 25, no. 13, p. 4207, 2025, doi: 10.3390/s25134207.
18. [18] M. Koelstra, C. Mühl, E. Soleymani, J.-S. Lee, A. Nijholt, T. Pun, D. Ramsay, and M. Sap, "Human-centric cognitive state recognition
using physiological signals: A systematic review of machine learning strategies," PLoS ONE, vol. 19, no. 8, p. e0301947, Aug. 2024, doi:
10.1371/journal.pone.0301947.
19. [19] Y. Khalili, M. R. Begian, and M. Mozayan, "Emotion recognition based on multimodal physiological electrical signals," Front.
Neurosci., vol. 19, p. 1512799, Mar. 2025, doi: 10.3389/fnins.2025.1512799.
20. O. Aamir, M. Roslan, and S. Zamri, "Machine learning-based signal processing by physiological signals detection of stress," Turcomat.org,
vol. 12, no. 2, pp. 1–16, 2023. [Online]. Available: https://turcomat.org/index.php/turkbilmat/article/view/6659. [Accessed: Nov. 8, 2025].
21. A. K. Singh, K. Yadav, N. Kumar, and P. Verma, "Machine learning approaches to evaluate EEG correlates of relaxation between supine
and sitting postures in eyes-closed condition," Front. Hum. Neurosci., vol. 15, p. 756088, 2021, doi: 10.3389/fnhum.2021.756088.
22. Y. Roy, H. Banville, I. Albuquerque, A. Gramfort, T. H. Falk, and J. Feydy, "Deep learning-based electroencephalography analysis," IEEE
Trans. Biomed. Eng., vol. 69, no. 12, pp. 3521–3540, Dec. 2022, doi: 10.1109/TBME.2022.3195187.
23. H. Jahangiri, S. Javadi, and H. Soheilifar, "Cognitive state classification using convolutional neural networks on gamma-band EEG signals,"
Appl. Sci., vol. 14, no. 18, p. 8380, Sep. 2023, doi: 10.3390/app14188380.
24. I. Tuncer and A. Onan, "A hybrid CNN-Bi-LSTM model with feature fusion for accurate epilepsy seizure detection," Biomed. Signal Process.
Control, vol. 80, p. 104260, Dec. 2023, doi: 10.1016/j.bspc.2022.104260.
25. S. Mahmud, S. Fathema, M. Hasan, A. H. Rashid, and M. A. Rahman, "Automatic classification of EEG signals based on image interpretation
of spatio-temporal information," medRxiv, Feb. 2025, doi: 10.1101/2025.02.10.25322019.
Related Articles
2025
Transforming Cyber-Physical Systems: Machine Learning for Secure and Efficient Solutions
2025
Exploring AI Techniques for Quantum Threat Detection and Prevention
2025
Maturity Models for Business Intelligence: An Overview
2025
INSPIRO: An AI Driven Institution Auditor
2025
Adaptive AI Framework for Anomaly Detection and DDoS Mitigation in Distributed Systems
2025
