Multi-Band EEG Spectrogram Decomposition with Residual Attention Network for Enhanced Stress Classification
DOI:
https://doi.org/10.29207/resti.v10i2.7225Keywords:
attention, decomposition, EEG, RAN, ResNet, spectrogram, stressAbstract
Stress can affect both physical and mental health, and it is important to support faster intervention. EEG can record brain activity directly, but EEG signals are complex, noisy, and difficult to handle. This study explores how EEG spectrogram decomposition can improve stress classification accuracy using deep learning models. Decomposition was accomplished by splitting a single EEG spectrogram into five distinct segments based on frequency range. Deep neural networks resembling ResNet are well-suited for spectrogram data, as the iterative feature extraction across layers facilitates the identification of hidden patterns. Incorporating an attention module before the classification layer further strengthens the model's capabilities by highlighting the most pertinent features during the training process. The baseline architecture employed in this study was ResNet-152. By incorporating a Multi-Head Attention mechanism prior to the Fully Connected layer, the modified network is denoted as RAN-152. The combination of spectrogram decomposition, ResNet, and attention has been proven to improve classification accuracy in complex EEG data. Without these three together, the accuracy obtained was only 0.5479, while the combination of the three achieved the highest accuracy of 0.9026. Evaluation of other metrics such as precision, recall, and F1-score also confirms that the attention module is good enough to highlight important features while reducing noise, thereby making classification more balanced across classes. These findings show that the combination of EEG decomposition and attention can be a promising approach for stress detection.
Downloads
References
R. S. Lalawat, V. Bajaj, and P. K. padhy, “Optimal variational mode decomposition based automatic stress classification system using EEG signals,” Applied Acoustics, vol. 231, Mar. 2025, doi: 10.1016/j.apacoust.2024.110478.
H. Lee, J. Kim, B. Han, S. M. Park, and J. Chang, “Developing an explainable Deep Neural Network for stress detection using biosignals and human-engineered features,” Biomed. Signal Process. Control, vol. 109, Nov. 2025, doi: 10.1016/j.bspc.2025.107960.
Y. Zhang, Q. Wang, Z. Y. Chin, and K. K. Ang, “Investigating different stress-relief methods using Electroencephalogram (EEG),” 2020. doi: https://doi.org/10.1109/EMBC44109.2020.9175900.
World Health Organization, “Suicide.”
D. Konar, S. De, P. Mukherjee, and A. H. Roy, “A Novel Human Stress Level Detection Technique Using EEG,” in 2023 International Conference on Network, Multimedia and Information Technology, NMITCON 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/NMITCON58196.2023.10276159.
A. Alberdi, A. Aztiria, and A. Basarab, “Towards an automatic early stress recognition system for office environments based on multimodal measurements: A review,” Feb. 01, 2016, Academic Press Inc. doi: 10.1016/j.jbi.2015.11.007.
S. S. A. Larasati and F. A. Bachtiar, “Harnessing Residual Attention Networks for Stress Level Classification Using EEG Spectrograms,” in 2024 9th International Conference on Informatics and Computing, ICIC 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICIC64337.2024.10956441.
S. Muñoz, C. Iglesias, O. Mayora, and V. Osmani, “Prediction of stress levels in the workplace using surrounding stress,” Inf. Process. Manag., vol. 59, no. 6, Nov. 2022, doi: 10.1016/j.ipm.2022.103064.
S.-H. Cheng and S. E. Wong, “Stress, Emotional Eating and Food Choices Among University Students During the Covid-19,” Malaysian Journal of Social Sciences and Humanities (MJSSH), vol. 6, no. 9, pp. 335–346, Sep. 2021, doi: 10.47405/mjssh.v6i9.983.
S. S. A. Larasati, E. N. K. Dewi, B. H. Farhansyah, F. A. Bachtiar, and F. Pradana, “Penerapan Decision Tree dan Random Forest dalam Deteksi Tingkat Stres Manusia Berdasarkan Kondisi Tidur,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 5, pp. 1043–1050, Oct. 2024, doi: 10.25126/jtiik.2024117993.
R. B. Ramteke, G. O. Gajbhiye, and V. R. Thool, “Acute mental stress level detection: ECG-scalogram based attentive convolutional network,” Franklin Open, vol. 10, Mar. 2025, doi: 10.1016/j.fraope.2025.100233.
J. Shah, A. Chougule, V. Chamola, and A. Hussain, “Novel welch-transform based enhanced spectro-temporal analysis for cognitive microsleep detection using a single electrode EEG,” Neurocomputing, vol. 549, Sep. 2023, doi: 10.1016/j.neucom.2023.126387.
A. Rafiei, R. Zahedifar, C. Sitaula, and F. Marzbanrad, “Automated Detection of Major Depressive Disorder With EEG Signals: A Time Series Classification Using Deep Learning,” IEEE Access, vol. 10, pp. 73804–73817, 2022, doi: 10.1109/ACCESS.2022.3190502.
D. Gao et al., “EEG driving fatigue detection based on log-Mel spectrogram and convolutional recurrent neural networks,” Front Neurosci. 2023. doi: 10.3389/fnins.2023.1136609
V. Vatsa, A. Maingi, H. Agarwal, R. Patel, and M. S. Adhikari, “Deep Learning for Multi-Class Classification of Harmful Brain Activity Using EEG Spectrogram Analysis,” in 2025 International Conference on Data Science and Business Systems, ICDSBS 2025, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/ICDSBS63635.2025.11031822.
M. Mustafa, M. N. Taib, Z. H. Murat, N. Sulaiman, and S. A. M. Aris, “Classification of EEG spectrogram image with ANN approach for brainwave balancing application,” International Journal of Simulation: Systems, Science and Technology, vol. 12, no. 5, pp. 29–36, 2011, doi: 10.5013/ijssst.a.12.05.05.
R. K. Rai and D. K. Singh, “Stress detection through wearable EEG technology: A signal-based approach,” Computers and Electrical Engineering, vol. 126, Aug. 2025, doi: 10.1016/j.compeleceng.2025.110478.
S. Acharya, A. Khosravi, D. Creighton, R. Alizadehsani, and U. R. Acharya, “Neurostressology: A systematic review of EEG-based automated mental stress perspectives,” Information Fusion, vol. 124, Dec. 2025, doi: 10.1016/j.inffus.2025.103368.
A. Nirabi, F. A. Rahman, M. H. Habaebi, K. A. Sidek, and S. Yusoff, “Machine Learning-Based Stress Level Detection from EEG Signals,” in 2021 IEEE 7th International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2021, Institute of Electrical and Electronics Engineers Inc., Aug. 2021, pp. 53–58. doi: 10.1109/ICSIMA50015.2021.9526333.
G. C. Jana, R. Sharma, and A. Agrawal, “A 1D-CNN-Spectrogram Based Approach for Seizure Detection from EEG Signal,” in Procedia Computer Science, Elsevier B.V., 2020, pp. 403–412. doi: 10.1016/j.procs.2020.03.248.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” Dec. 2015, [Online]. Available: http://arxiv.org/abs/1512.03385
S. S. A. Larasati, S. R. Shalsadilla, and F. Utaminingrum, “Enhancing Stroke Detection in Brain CT Images with Residual Attention Networks,” in IET Conference Proceedings, Institution of Engineering and Technology, 2024, pp. 574–579. doi: 10.1049/icp.2025.0312.
T. Waili, Y. Sa’Ad Alshebly, K. Azami Sidek, and M. G. Md Johar, “Stress recognition using Electroencephalogram (EEG) signal,” in Journal of Physics: Conference Series, Institute of Physics Publishing, Jun. 2020. doi: 10.1088/1742-6596/1502/1/012052.
U. D. Rosiani, P. Y. Saputra, and M. A. Hendrawan, “The Impact of Segment Length on EEG Based Biometric System,” in Proceedings - 2021 IEEE 7th Information Technology International Seminar, ITIS 2021, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/ITIS53497.2021.9791686.
Sebastian. Raschka and Vahid. Mirjalili, Python machine learning : machine learning and deep learning with python, scikit-learn, and tensorflow 2. Packt Publishing, Limited, 2019.
L. S. Darfiansa, Fitriyani, and S. S. A. Larasati, “Optimizing IndoBERT for Revised Bloom’s Taxonomy Question Classification Using Neural Network Classifier,” Journal of Information Systems Engineering and Business Intelligence, vol. 11, no. 2, pp. 226–237, Jun. 2025, doi: 10.20473/jisebi.11.2.226-237.
S. S. A. Larasati, A. F. Rahmaniati, F. I. S. Ms, Y. C. Utomo, F. Ariadi, and F. Utaminingrum, “Advancement in deep learning for skin detection: A comprehensive review,” Biomed. Signal Process. Control, vol. 112, p. 108738, 2026, doi: https://doi.org/10.1016/j.bspc.2025.108738 .
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;





