Spatio-Temporal Graph Neural Network Based on Nonlinear Time–Frequency Features for Mu-ERD Classification in Multi-Session EEG Motor Imagery

Firman Aziz; Jeffry Jeffry; Syahrul Usman; Rahmat Fuadi Syam; Muhammad Nur Arafah; Nurul Fathanah Mustamin

doi:10.37385/jaets.v7i2.8679

Authors

Firman Aziz Universitas Pancasakti Makassar
Jeffry Jeffry Institut Teknologi Bacharuddin Jusuf Habibie
Syahrul Usman Universitas Pancasakti Makassar
Rahmat Fuadi Syam Universitas Pancasakti Makassar
Muhammad Nur Arafah IRMEX Digital Akademika
Nurul Fathanah Mustamin University of Lambung Mangkurat

DOI:

https://doi.org/10.37385/jaets.v7i2.8679

Keywords:

Classification, EEG, Motor Imagery, ERD, ST-GNN

Abstract

Mu rhythm event-related desynchronization (ERD) is a key indicator of motor imagery activity based on EEG signals. However, accurate classification of ERD remains challenging due to the nonlinear nature of EEG signals and inter-session variability. This study proposes a motor imagery classification approach using a Spatio-Temporal Graph Neural Network (ST-GNN) model that leverages nonlinear time-frequency features extracted via Variational Mode Decomposition (VMD) and Synchrosqueezing Transform (SST). The dataset was collected from a single healthy subject across five separate sessions, each consisting of two conditions: relaxation and motor imagery. After preprocessing and segmentation, features were extracted and represented as spatio-temporal graphs to be processed by the ST-GNN. The model was evaluated using metrics such as accuracy, F1-score, AUC-ROC, and the Session Stability Index (SSI). The results show that the ST-GNN achieved an accuracy of 94.2%, F1-score of 94.1%, and AUC-ROC of 96.1%, along with high prediction stability across sessions. This performance outperformed baseline models including CNN, CSP+SVM, and STFT+MLP.These findings support the hypothesis that ERD is a distributed brain network phenomenon and demonstrate that the ST-GNN approach with VMD/SST-derived features is a promising strategy for developing adaptive and accurate BCI systems.

Downloads

Download data is not yet available.

References

Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., & Adeli, H. (2018). Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine, 100, 270–278. https://doi.org/10.1016/J.COMPBIOMED.2017.09.017

Atoar Rahman, S. M., Ibrahim Khalil, M., Zhou, H., Guo, Y., Ding, Z., Gao, X., & Zhang, D. (2025). Advancement in Graph Neural Networks for EEG Signal Analysis and Application: A Review. IEEE Access, 13, 50167–50187. https://doi.org/10.1109/ACCESS.2025.3549120

Azizi, T. (2024). Comparative Analysis of Statistical, Time–Frequency, and SVM Techniques for Change Detection in Nonlinear Biomedical Signals. Signals 2024, Vol. 5, Pages 736-755, 5(4), 736–755. https://doi.org/10.3390/SIGNALS5040041

Chatterjee, R., & Bandyopadhyay, T. (2016). EEG Based Motor Imagery Classification Using SVM and MLP. Proceedings - International Conference on Computational Intelligence and Networks, 2016-January, 84–89. https://doi.org/10.1109/CINE.2016.22

Démas, J., Bourguignon, M., Périvier, M., De Tiège, X., Dinomais, M., & Van Bogaert, P. (2020). Mu rhythm: State of the art with special focus on cerebral palsy. Annals of Physical and Rehabilitation Medicine, 63(5), 439–446. https://doi.org/10.1016/J.REHAB.2019.06.007

Graña, M., & Morais-Quilez, I. (2023). A review of Graph Neural Networks for Electroencephalography data analysis. Neurocomputing, 562, 126901. https://doi.org/10.1016/J.NEUCOM.2023.126901

Hou, Y., Jia, S., Lun, X., Hao, Z., Shi, Y., Li, Y., Zeng, R., & Lv, J. (2024). GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-Resolved EEG Motor Imagery Signals. IEEE Transactions on Neural Networks and Learning Systems, 35(6), 7312–7323. https://doi.org/10.1109/TNNLS.2022.3202569

Hsu, W. Y. (2010). EEG-based motor imagery classification using neuro-fuzzy prediction and wavelet fractal features. Journal of Neuroscience Methods, 189(2), 295–302. https://doi.org/10.1016/J.JNEUMETH.2010.03.030

Inamoto, T., Ueda, M., Ueno, K., Shiroma, C., Morita, R., Naito, Y., & Ishii, R. (2023). Motor-Related Mu/Beta Rhythm in Older Adults: A Comprehensive Review. Brain Sciences 2023, Vol. 13, Page 751, 13(5), 751. https://doi.org/10.3390/BRAINSCI13050751

Klepl, D., Wu, M., & He, F. (2024). Graph Neural Network-Based EEG Classification: A Survey. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32, 493–503. https://doi.org/10.1109/TNSRE.2024.3355750

Kumar, S., & Sharma, A. (2025). Advances in non-invasive EEG-based brain-computer interfaces: Signal acquisition, processing, emerging approaches, and applications. Signal Processing Strategies: Advances in Neural Engineering, 281–310. https://doi.org/10.1016/B978-0-323-95437-2.00014-8

Kumar, V. T., Siri Sanjana, S., Arun, S., Menon, A., Sreshtamol, K. G., & Satheesh, R. (2025). Enhanced Time-Frequency Analysis of Power Quality Disturbances Using Fourier Synchro-Squeezing Transform. ETIS International Conference on Emerging Technologies for Intelligent Systems, ETIS 2025. https://doi.org/10.1109/ETIS64005.2025.10961578

Li, Y., Yang, H., Li, J., Chen, D., & Du, M. (2020). EEG-based intention recognition with deep recurrent-convolution neural network: Performance and channel selection by Grad-CAM. Neurocomputing, 415, 225–233. https://doi.org/10.1016/J.NEUCOM.2020.07.072

Lou, H., Ye, Z., Yao, L., & Zhang, Y. (2023). Less Is More: Brain Functional Connectivity Empowered Generalizable Intention Classification With Task-Relevant Channel Selection. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 1888–1899. https://doi.org/10.1109/TNSRE.2023.3252610

Medvedeva, A. S., Syrov, N. V., Yakovlev, L. V., Alieva, Y. A., Petrova, D. A., Ivanova, G. E., Lebedev, M. A., & Kaplan, A. Y. (2024). Event-Related Desynchronization of EEG Sensorimotor Rhythms in Hemiparesis Post-Stroke Patients. Journal of Evolutionary Biochemistry and Physiology 2024 60:5, 60(5), 2058–2071. https://doi.org/10.1134/S0022093024050302

Müller-Gerking, J., & Pfurtscheller, G, H. F. (1999). Designing optimal spatial filters for single-trial EEG classification in a movement task. Clinical Neurophysiology. https://www.sciencedirect.com/science/article/pii/S1388245798000388

Nacharova, M. A., Makhin, S. A., & Pavlenko, V. B. (2020). Assessment of the Reactivity and Localization of EEG α-Rhythm Frequency Components on Execution and Observation of Movements. Neuroscience and Behavioral Physiology, 50(4), 468–478. https://doi.org/10.1007/S11055-020-00922-1/METRICS

Nikouei, M., & Abdali-Mohammadi, F. (2024). A novel method for modeling effective connections between brain regions based on EEG signals and graph neural networks for motor imagery detection. Computer Methods in Biomechanics and Biomedical Engineering, 27(11), 1430–1447. https://doi.org/10.1080/10255842.2023.2244110

Park, S., Ha, J., & Kim, L. (2023). Improving Performance of Motor Imagery-Based Brain-Computer Interface in Poorly Performing Subjects Using a Hybrid-Imagery Method Utilizing Combined Motor and Somatosensory Activity. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 1064–1074. https://doi.org/10.1109/TNSRE.2023.3237583

Proserpio, P., Cordani, R., & Nobili, L. (2025). Electroencephalogram (EEG) and Sleep Disorders. Chinese Journal of Contemporary Neurology and Neurosurgery, 8(4), 225–256. https://doi.org/10.1007/978-3-031-86878-8_17

Rakhmatulin, I., Dao, M. S., Nassibi, A., & Mandic, D. (2024). Exploring Convolutional Neural Network Architectures for EEG Feature Extraction. Sensors 2024, Vol. 24, Page 877, 24(3), 877. https://doi.org/10.3390/S24030877

Reuter, E. M., Booms, A., & Leow, L. A. (2022). Using EEG to study sensorimotor adaptation. Neuroscience & Biobehavioral Reviews, 134, 104520. https://doi.org/10.1016/J.NEUBIOREV.2021.104520

Rhif, M., Abbes, A. Ben, Farah, I. R., Martínez, B., & Sang, Y. (2019). Wavelet Transform Application for/in Non-Stationary Time-Series Analysis: A Review. Applied Sciences 2019, Vol. 9, Page 1345, 9(7), 1345. https://doi.org/10.3390/APP9071345

Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., & Faubert, J. (2019). Deep learning-based electroencephalography analysis: a systematic review. Journal of Neural Engineering, 16(5), 051001. https://doi.org/10.1088/1741-2552/AB260C

Saibene, A., Caglioni, M., Corchs, S., & Gasparini, F. (2023). EEG-Based BCIs on Motor Imagery Paradigm Using Wearable Technologies: A Systematic Review. Sensors, 23(5), 2798. https://doi.org/10.3390/S23052798/S1

Schirrmeister, R., Gemein, L., Eggensperger, K., Hutter, F., & Ball, T. (2017). Deep learning with convolutional neural networks for decoding and visualization of EEG pathology. 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings, 2018-January, 1–7. https://doi.org/10.1109/SPMB.2017.8257015

Sharma, N., Sharma, M., Singhal, A., Vyas, R., Malik, H., Afthanorhan, A., & Hossaini, M. A. (2023). Recent Trends in EEG-Based Motor Imagery Signal Analysis and Recognition: A Comprehensive Review. IEEE Access, 11, 80518–80542. https://doi.org/10.1109/ACCESS.2023.3299497

Sharma, R., & Meena, H. K. (2024). Emerging Trends in EEG Signal Processing: A Systematic Review. SN Computer Science, 5(4), 1–14. https://doi.org/10.1007/S42979-024-02773-W/METRICS

Shi, J., Tang, J., Lu, Z., Zhang, R., Yang, J., Guo, Q., & Zhang, D. (2024). A brain topography graph embedded convolutional neural network for EEG-based motor imagery classification. Biomedical Signal Processing and Control, 95, 106401. https://doi.org/10.1016/J.BSPC.2024.106401

Song, T., Zheng, W., Song, P., & Cui, Z. (2020). EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks. IEEE Transactions on Affective Computing, 11(3), 532–541. https://doi.org/10.1109/TAFFC.2018.2817622

Thangarajoo, R. G., Reaz, M. B. I., Srivastava, G., Haque, F., Ali, S. H. M., Bakar, A. A. A., & Bhuiyan, M. A. S. (2021). Machine Learning-Based Epileptic Seizure Detection Methods Using Wavelet and EMD-Based Decomposition Techniques: A Review. Sensors 2021, Vol. 21, Page 8485, 21(24), 8485. https://doi.org/10.3390/S21248485

Wen, T., & Zhang, Z. (2018). Deep Convolution Neural Network and Autoencoders-Based Unsupervised Feature Learning of EEG Signals. IEEE Access, 6, 25399–25410. https://doi.org/10.1109/ACCESS.2018.2833746

Xue, Q., Song, Y., Wu, H., Cheng, Y., & Pan, H. (2024). Graph neural network based on brain inspired forward-forward mechanism for motor imagery classification in brain-computer interfaces. Frontiers in Neuroscience, 18, 1309594. https://doi.org/10.3389/FNINS.2024.1309594/TEXT

Xue, Y. J., Cao, J. X., Wang, D. X., Du, H. K., & Yao, Y. (2016). Application of the Variational-Mode Decomposition for Seismic Time-frequency Analysis. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8), 3821–3831. https://doi.org/10.1109/JSTARS.2016.2529702

Yakovlev, L., Syrov, N., Miroshnikov, A., Morozova, M., Berkmush-Antipova, A., Petrova, D., & Kaplan, A. (2024). EEG Source Localization of μ-Rhythm Event-Related Desynchronization during Tactile Imagery. Moscow University Biological Sciences Bulletin, 79(Suppl 1), S100–S106. https://doi.org/10.3103/S0096392524600832/METRICS

Yan, H. T., Wu, L. H., Jiang, L. H., & Wu, N. (2026). Variational Mode Synchrosqueezing Transform: A Novel High-Resolution Time-Frequency Analysis Approach for Seismic Signal Processing. Applied Geophysics 2026, 1–14. https://doi.org/10.1007/S11770-026-1423-0

Yousif, M. A. A., & Ozturk, M. (2023a). Motor Imagery BCI Classification Using Synchrosqueezing Transform. 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023. https://doi.org/10.1109/SIU59756.2023.10223986

Yousif, M. A. A., & Ozturk, M. (2023b). Deep Learning-Based Classification of Epileptic Electroencephalography Signals Using a Concentrated Time-Frequency Approach. International Journal of Neural Systems, 33(12). https://doi.org/10.1142/S0129065723500648

Yu, G. (2021). A multisynchrosqueezing-based high-resolution time-frequency analysis tool for the analysis of non-stationary signals. Journal of Sound and Vibration, 492, 115813. https://doi.org/10.1016/J.JSV.2020.115813

Yu, G., Wang, Z., Zhao, P., & Li, Z. (2019). Local maximum synchrosqueezing transform: An energy-concentrated time-frequency analysis tool. Mechanical Systems and Signal Processing, 117, 537–552. https://doi.org/10.1016/J.YMSSP.2018.08.006

Zegallai, H. M., & Emsilkh, D. A. (2024). EEG Motor Imagery Classification using Graphical Neural Networks with Attention Mechanism. 2024 IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering, MI-STA 2024 - Proceeding, 723–728. https://doi.org/10.1109/MI-STA61267.2024.10599653

Zhang, Y., Zhou, G., Jin, J., Zhao, Q., Wang, X., & Cichocki, A. (2016). Sparse Bayesian Classification of EEG for Brain-Computer Interface. IEEE Transactions on Neural Networks and Learning Systems, 27(11), 2256–2267. https://doi.org/10.1109/TNNLS.2015.2476656