Abstract

Physiological-state classification requires models that can represent dependencies among sensor channels while preserving temporal variation. This study presents a dataset-specific evaluation of an Adaptive Komodo Mlipir Algorithm-optimized spatiotemporal graph neural network (AKMA-ST-GNN) using four public physiological datasets with different modalities and target definitions: STEW for cognitive workload, SEED for emotion, DEAP for affect, and WESAD for stress and amusement. The datasets were analyzed independently. No EEG signal from one dataset was combined with EMG or peripheral signals from another dataset, and workload, emotion, affect, and stress labels were not collapsed into a common target. The proposed workflow included signal filtering, training-set standardization, frequency-domain characterization where physiologically appropriate, within-dataset channel graph construction, spatiotemporal graph learning, and dataset-specific classification. AKMA was used as a hyperparameter-search wrapper rather than as an additional predictive layer. Under the preliminary 80% training and 20% testing protocol preserved in the source manuscript, the reported accuracies were 98.60% for STEW, 98.31% for WESAD, 98.06% for DEAP, and 98.12% for SEED. Precision, F1-score, specificity, and sensitivity were available only for selected datasets. Prediction-level outputs, class supports, confusion matrices, and decision scores were not retained, therefore, macro F1, weighted F1, balanced accuracy, Matthews correlation coefficient, Cohen's kappa, and ROC/AUC could not be reconstructed. Repeated-seed results and fold- or participant-level scores were also unavailable, preventing calculation of standard deviations, confidence intervals, and statistical significance tests. The reported values are consequently interpreted as preliminary evidence of technical feasibility rather than proof of stable or subject-independent generalization.

Keywords

Cognitive Workload, Stress Recognition, Spatiotemporal Graph Neural Network, Komodo Mlipir Optimization, Multimodal Bio Signals,

Downloads

Download data is not yet available.

References

  1. M. Bonanno, D. Papa, A. Cerasa, M.G. Maggio, R.S. Calabrò, Psycho-neuroendocrinology in the rehabilitation field: Focus on the complex interplay between stress and pain. Medicina, 60(2), (2024) 285. https://doi.org/10.3390/medicina60020285
  2. Y. Liu, M.I. Palacio, T. Bikki, C. Toledo, Y. Ouyang, Z. Li, Z. Wang, F. Toledo, H. Zeng, M.T. Herrero Machine learning, physiological signals, and emotional stress/anxiety: Pitfalls and challenges. Applied Sciences, 15(21), (2025) 11777. https://doi.org/10.3390/app152111777
  3. C. Su, M. Zangeneh Soroush, N. Torkamanrahmani, A. Ruiz-Segura, L. Yang, X. Li, Y. Zeng Measurement and quantification of stress in the decision process: A model-based systematic review. Intelligent Computing, 3, (2024) 0090. https://doi.org/10.34133/icomputing.0090
  4. R. Pillalamarri, U. Shanmugam, A review on EEG-based multimodal learning for emotion recognition. Artificial Intelligence Review, 58(5), (2025) 131. https://doi.org/10.1007/s10462-025-11126-9
  5. C. Chatzaki, M. Tsiknakis, An overview of stress analysis based on physiological signals: Systematic review of open datasets and current trends. Sensors, 25(23), (2025) 7108. https://doi.org/10.3390/s25237108
  6. K. Jin, A. Rubio-Solis, R. Naik, D. Leff, J. Kinross, G. Mylonas, Human-centric cognitive state recognition using physiological signals: A systematic review of machine learning strategies across application domains. Sensors, 25(13), (2025) 4207. https://doi.org/10.3390/s25134207
  7. J.Y. Wu, C.T.S. Ching, H.M.D. Wang, L.D. Liao, Emerging wearable biosensor technologies for stress monitoring and their real-world applications. Biosensors, 12(12), (2022). 1097. https://doi.org/10.3390/bios12121097
  8. J. Su, J. Zhu, T. Song, H. Chang, Subject-independent EEG emotion recognition based on genetically optimized projection dictionary pair learning. Brain Sciences, 13(7), (2023) 977. https://doi.org/10.3390/brainsci13070977
  9. G. Vos, K. Trinh, Z. Sarnyai, M. Rahimi Azghadi, Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review. International Journal of Medical Informatics, 173, (2023) 105026. https://doi.org/10.1016/j.ijmedinf.2023.105026
  10. D. Klepl, M. Wu, F. He, Graph neural network-based EEG classification: A survey. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32, (2024) 493–503. https://doi.org/10.1109/TNSRE.2024.3355750
  11. J. Zhu, X. Jin, Y. Ming, W. Kong, EEG-DGRN: Dynamic graph representation network for subject-independent ERP detection. Brain-Apparatus Communication: A Journal of Bacomics, 4(1), (2025) 2447576. https://doi.org/10.1080/27706710.2024.2447576
  12. A. Morales-Hernández, I. Van Nieuwenhuyse, S. Rojas Gonzalez (2023). A survey on multi-objective hyperparameter optimization algorithms for machine learning. Artificial Intelligence Review, 56(8), 8043–8093. https://doi.org/10.1007/s10462-022-10359-2
  13. S. Suyanto, A.A. Ariyanto, A.F. Ariyanto Komodo Mlipir Algorithm. Applied Soft Computing, 114, (2022) 108043. https://doi.org/10.1016/j.asoc.2021.108043
  14. H.M. Afify, K.K. Mohammed, A.E. Hassanien, Stress detection based EEG under varying cognitive tasks using convolution neural network. Neural Computing and Applications, 37(7), (2025) 5381–5395. https://doi.org/10.1007/s00521-024-10737-7
  15. T.G. Troyee, M.H. Chowdhury, M.F.K. Khondakar, M. Hasan, M.A. Hossain, Q.D. Hossain, M.A.A. Dewan, Stress detection and audio-visual stimuli classification from electroencephalogram. IEEE Access, 12, (2024) 145417–145427. https://doi.org/10.1109/ACCESS.2024.3471590
  16. N. Phutela, D. Relan, G. Gabrani, P. Kumaraguru, M. Samuel, Stress classification using brain signals based on LSTM network. Computational Intelligence and Neuroscience, 2022, (2022) 7607592. https://doi.org/10.1155/2022/7607592
  17. R. Gupta, M.A. Alam, P. Agarwal, Modified support vector machine for detecting stress level using EEG signals. Computational Intelligence and Neuroscience, 2020, (2020) 8860841. https://doi.org/10.1155/2020/8860841
  18. B. Roy, L. Malviya, R. Kumar, S. Mal, A. Kumar, T. Bhowmik, J.W. Hu, Hybrid deep learning approach for stress detection using decomposed EEG signals. Diagnostics, 13(11), (2023) 1936. https://doi.org/10.3390/diagnostics13111936
  19. T. Wang, X. Huang, Z. Xiao, W. Cai, Y. Tai, EEG emotion recognition based on differential entropy feature matrix through 2D-CNN-LSTM network. EURASIP Journal on Advances in Signal Processing, 2024(1), (2024) 49. https://doi.org/10.1186/s13634-024-01146-y
  20. M.S. Andhare, T. Vijayan, B. Karthik, S. Urooj, A novel optimized hybrid deep learning framework for mental stress detection using electroencephalography. Brain Sciences, 15(8), (2025) 835. https://doi.org/10.3390/brainsci15080835
  21. O. AlShorman, M. Masadeh, M.B.B. Heyat, F. Akhtar, H. Almahasneh, G.M. Ashraf, A. Alexiou, Frontal lobe real-time EEG analysis using machine learning techniques for mental stress detection. Journal of Integrative Neuroscience, 21(1), (2022) 20. https://doi.org/10.31083/j.jin2101020
  22. D. Kamińska, K. Smółka, G. Zwoliński, Detection of mental stress through EEG signal in virtual reality environment. Electronics, 10(22), (2021) 2840. https://doi.org/10.3390/electronics10222840
  23. K. Kamakshi, A. Rengaraj, Early detection of stress and anxiety based seizures in position data augmented EEG signal using hybrid deep learning algorithms. IEEE Access, 12, (2024) 35351–35365. https://doi.org/10.1109/ACCESS.2024.3365192
  24. S. Jose, S.T. George, M.S.P. Subathra, V.S. Handiru, P.K. Jeevanandam, U. Amato, E.S. Suviseshamuthu Robust classification of intramuscular EMG signals to aid the diagnosis of neuromuscular disorders. IEEE Open Journal of Engineering in Medicine and Biology, 1, (2020) 235–242. https://doi.org/10.1109/OJEMB.2020.3017130
  25. H. Li, H. Ji, J. Yu, J. Li, L. Jin, L. Liu, Z. Bai, C. Ye, A sequential learning model with GNN for EEG–EMG-based stroke rehabilitation BCI. Frontiers in Neuroscience, 17, (2023) 1125230. https://doi.org/10.3389/fnins.2023.1125230
  26. N. Modi, Y. Kumar, K. Mehta, N. Chaplot, Physiological signal-based mental stress detection using hybrid deep learning models. Discover Artificial Intelligence, 5(1), (2025) 166. https://doi.org/10.1007/s44163-025-00412-8
  27. J.Z. Xiang, Q.Y. Wang, Z.B. Fang, J.A. Esquivel, Z.X. Su, A multi-modal deep learning approach for stress detection using physiological signals: Integrating time- and frequency-domain features. Frontiers in Physiology, 16, (2025) 1584299. https://doi.org/10.3389/fphys.2025.1584299