Deep Learning Epileptic Seizure Detection based on the Matching Pursuit Algorithm and its Time–Frequency Graphical Representation

Mateusz M. Kunik; Artur Gramacki

doi:10.61822/amcs-2025-0044

Abstract

Electroencephalography (EEG) is the primary diagnostic and an important prognostic clinical tool for epilepsy. The detection of epileptic activity is usually performed by a human expert and is based on finding specific patterns in the multi-channel electroencephalogram. However, the manual inspection of EEG signals is a time-consuming procedure for neurologists. Therefore, various attempts are made to automate it using both conventional and deep learning techniques. In this article, (i) we investigate the possibility of using time-frequency maps of energy derived from the matching pursuit algorithm for accurate detection of epileptic seizures (to the best of our knowledge, such an approach has not been analyzed so far, making this a pilot study); (ii) we show how to build an effective deep convolutional neural network with the so-called (2+1)D convolution technique; (iii) using carefully selected 79 neonatal EEG recordings, we develop a complete framework for seizure detection employing a deep learning approach, (iv) we share a ready to use R and Python codes which allow reproducing all the results presented in the paper.

References

Abbas, A.K., Azemi, G., Ravanshadi, S. and Omidvarnia, A. (2021). An EEG-based methodology for the estimation of functional brain connectivity networks: Application to the analysis of newborn EEG seizure, Biomedical Signal Processing and Control 63: 102229, DOI: 10.1016/j.bspc.2020.102229.
Search in Google Scholar Back to article
Akbar, W., Soomro, A., Hussain, A., Hussain, T., Ali, F., Haq, M.I.U., Attar, R.W., Alhomoud, A., Alzubi, A.A. and Alsagri, R. (2024). Pneumonia detection: A comprehensive study of diverse neural network architectures using chest x-rays, International Journal of Applied Mathematics and Computer Science 34(4): 679–699, DOI: 10.61822/amcs-2024-0045.
Search in Google Scholar Back to article
Bai, L., Litscher, G. and Li, X. (2025). Epileptic seizure detection using machine learning: A systematic review and meta-analysis, Brain Sciences 15(6), DOI: 10.3390/brainsci15060634.
Search in Google Scholar Back to article
Bajaj, V. and Pachori, R.B. (2013). Automatic classification of sleep stages based on the time-frequency image of EEG signals, Computer Methods and Programs in Biomedicine 112(3): 320–328, DOI: 10.1016/j.cmpb.2013.07.006.
Search in Google Scholar Back to article
Caliskan, A. and Rencuzogullari, S. (2021). Transfer learning to detect neonatal seizure from electroencephalography signals, Neural Computing and Applications 33: 12087–12101, DOI: 10.1007/s00521-021-05878-y.
Search in Google Scholar Back to article
Carmo, A.S., Abreu, M., Baptista, M.F., de Oliveira Carvalho, M., Peralta, A.R., Fred, A., Bentes, C. and da Silva, H.P. (2024). Automated algorithms for seizure forecast: A systematic review and meta-analysis, Journal of Neurology 271: 6573–6587, DOI: 10.1007/s00415-024-12655-z.
Search in Google Scholar Back to article
Diykh, M., Miften, F.S., Abdulla, S., Deo, R.C., Siuly, S., Green, J.H. and Oudahb, A.Y. (2022). Texture analysis based graph approach for automatic detection of neonatal seizure from multi-channel EEG signals, Measurement 190: 110731, DOI: 10.1016/j.measurement.2022.110731.
Search in Google Scholar Back to article
Dong, X., He, L., Li, H., Liu, Z., Shang, W. and Zhou, W. (2024). Deep learning based automatic seizure prediction with EEG time-frequency representation, Biomedical Signal Processing and Control 95: 106447, DOI: 10.1016/j.bspc.2024.106447.
Search in Google Scholar Back to article
Durka, P.J. (2007). Matching Pursuit and Unification in EEG Analysis, Artech House Engineering in Medicine and Biology, Boston/London.
Search in Google Scholar Back to article
Gramacki, A. and Gramacki, J. (2022). A deep learning framework for epileptic seizure detection based on neonatal EEG signals, Scientific Reports 12: 1–21, Article no. 13010, DOI: 10.1038/s41598-022-15830-2.
Search in Google Scholar Back to article
He, K., Zhang, X., Ren, S. and Sun, J. (2016). Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770–778, DOI: 10.48550/arXiv.1512.03385.
Search in Google Scholar Back to article
Kaczmarek, M., Kowal, M. and Korbicz, J. (2025). Exploring data preparation strategies: A comparative analysis of vision transformer and ConvNeXT architectures in breast cancer histopathology classification, International Journal of Applied Mathematics and Computer Science 35(2): 329–339, DOI: 10.61822/amcs-2025-0023.
Search in Google Scholar Back to article
Kingma, D.P. and Ba, J. (2014). Adam: A method for stochastic optimization, arXiv 1412.6980, DOI: 10.48550/arXiv.1412.6980.
Search in Google Scholar Back to article
Klem, G.H., Lüders, H.O., Jasper, H.H. and Elger, C. (1999). The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology, Electroencephalography and Clinical Neurophysiology 52: 3–6, DOI: 10.1016/0022-510x(84)90023-6, PubMed ID: 10590970.
Search in Google Scholar Back to article
Kuś, R., Rózański, P.T. and Durka, P.J. (2013). Multivariate matching pursuit in optimal Gabor dictionaries: Theory and software with interface for EEG/MEG via Svarog, BioMedical Engineering OnLine 12: 1–28, Article no. 94, DOI: 10.1186/1475-925X-12-94.
Search in Google Scholar Back to article
Mallat, S. and Shang, Z. (1993). Matching pursuits with time-frequency dictionaries, IEEE Transactions on Signal Processing 41: 3397–3415, DOI: 10.1109/78.258082.
Search in Google Scholar Back to article
Miltiadous, A., Tzimourta, K., Giannakeas, N., Tsipouras, M., Glavas, E., Kalafatakis, K. and Tzallas, A. (2022). Machine learning algorithms for epilepsy detection based on published EEG databases: A systematic review, IEEE Access 11: 564–594, DOI: 10.1109/ACCESS.2022.3232563.
Search in Google Scholar Back to article
Nelson, M., Rajendran, S., Osamah Ibrahim, K. and Hamam, H. (2024). Deep-learning-based intelligent neonatal seizure identification using spatial and spectral GNN optimized with the Aquila algorithm, AIMS Mathematics 9(7): 19645–19669, DOI: 10.3934/math.2024958.
Search in Google Scholar Back to article
Niedermeyer, E. and da Silva, F.L. (2005). Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, Lippincott Williams & Wilkins, Philadelphia.
Search in Google Scholar Back to article
O’Shea, A., Lightbody, G., Boylan, G. and Temko, A. (2020). Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture, Neural Networks 123: 12–25, DOI: 10.1016/j.neunet.2019.11.023.
Search in Google Scholar Back to article
Pan, Y., Zhou, Xiaoyu nad Dong, F., Wu, J., Xu, Y. and Zheng, S. (2022). Epileptic seizure detection with hybrid time-frequency EEG input: A deep learning approach, Computational and Mathematical Methods in Medicine 2022, Article ID: 8724536, DOI: 10.1155/2022/8724536.
Search in Google Scholar Back to article
Raab, D., Theissler, A. and Spiliopoulou, M. (2023). XAI4EEG: Spectral and spatio-temporal explanation of deep learningbased seizure detection in EEG time series, Neural Computing and Applications 35: 10051–10068, DOI: 10.1007/s00521-022-07809-x.
Search in Google Scholar Back to article
Raeisi, K., Khazaei, M., Croce, P., Tamburro, G., Comani, S. and Zappasodi, F. (2022). A graph convolutional neural network for the automated detection of seizures in the neonatal EEG, Computer Methods and Programs in Biomedicine 222: 106950, DOI: 10.1016/j.cmpb.2022.106950.
Search in Google Scholar Back to article
Rashed-Al-Mahfuz, M., Moni, M.A., Uddin, S., Alyami, S.A., Summers, M.A. and Eapen, V. (2021). A deep convolutional neural network method to detect seizures and characteristic frequencies using epileptic electroencephalogram (EEG) data, IEEE Journal of Translational Engineering in Health and Medicine 9: 1–12, DOI: 10.1109/JTEHM.2021.3050925.
Search in Google Scholar Back to article
Rózański, P.T. (2024). EMPI: GPU-accelerated matching pursuit with continuous dictionaries, ACM Transactions on Mathematical Software 50: 1–17, DOI: 10.1145/3674832.
Search in Google Scholar Back to article
Rózański, P.T. (2025). Enhanced Matching Pursuit Implementation (empi), https://github.com/develancer/empi.
Search in Google Scholar Back to article
Şengür, A., Guo, Y. and Akbulut, Y. (2016). Time-frequency texture descriptors of EEG signals for efficient detection of epileptic seizure, Brain Informatics 3: 101–108, DOI: 10.1007/s40708-015-0029-8.
Search in Google Scholar Back to article
Shen, M., Yang, F., Wen, P. and Li, Y. (2024). A real-time epilepsy seizure detection approach based on EEG using short-time Fourier transform and Google-Net convolutional neural network, Heliyon 10(11), DOI: 10.1016/j.heliyon.2024.e31827.
Search in Google Scholar Back to article
Shoeibi, A., Moridian, P., Khodatars, M., Ghassemi, N., Jafari, M., Alizadehsani, R., Kong, Y., Gorriz, J.M., Ramírez, J., Khosravi, A., Nahavandi, S. and Acharya, U.R. (2022). An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works, Computers in Biology and Medicine 149: 106053, DOI: 10.1016/compbiomed.2022.106053.
Search in Google Scholar Back to article
Siddartha, K.M., Yuvaraj, R., Thomas, J. and Jac Fredo, A.R. (2024). Comparative study of time-frequency spectrogram techniques for the classification of seizure types using EEG signals and deep learning models, Expert Systems with Applications, DOI: 10.2139/ssrn.4883195 (preprint).
Search in Google Scholar Back to article
Stevenson, N.J., Clancy, R.R., Vanhatalo, S., Rosén, I., Rennie, J.M. and Boylan, G.B. (2015). Interobserver agreement for neonatal seizure detection using multichannel EEG, Annals of Clinical and Translational Neurology 2(11): 1002–1011, DOI: 10.1002/acn3.249.
Search in Google Scholar Back to article
Stevenson, N.J., Tapani, K., Lauronen, L. and Vanhatalo, S. (2019). A dataset of neonatal EEG recordings with seizure annotations, Scientific Data 6, DOI: 10.1038/sdata.2019.39.
Search in Google Scholar Back to article
Tanveer, M.A., Khan, M.J., Sajid, H. and Naseer, N. (2021). Convolutional neural networks ensemble model for neonatal seizure detection, Journal of Neuroscience Methods 358: 109197, DOI: 10.1016/j.jneumeth.2021.109197.
Search in Google Scholar Back to article
Tapani, K.T., Vanhatalo, S. and Stevenson, N.J. (2019). Time-varying EEG correlations improve automated neonatal seizure detection, International Journal of Neural Systems 29(4), DOI: 10.1142/S0129065718500302.
Search in Google Scholar Back to article
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y. and Paluri, M. (2018). A closer look at spatiotemporal convolutions for action recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 6450–6459, DOI: 10.48550/arXiv.1711.11248.
Search in Google Scholar Back to article
Truong, N.D., Nguyen, A.D., Kuhlmann, L., Bonyadi, M.R., Yang, J., Ippolito, S. and Kavehei, O. (2018). Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram, Neural Networks 105: 104–111, DOI: 10.1016/j.neunet.2018.04.018.
Search in Google Scholar Back to article
Türk, O. and Özerdem, M.S. (2019). Epilepsy detection by using scalogram based convolutional neural network from EEG signals, Brain Sciences 9(5), DOI: 10.3390/brainsci9050115.
Search in Google Scholar Back to article
Tzallas, A.T., Tsipouras, M.G. and Fotiadis, D.I. (2009). Epileptic seizure detection in EEGs using time-frequency analysis, IEEE Transactions on Information Technology in Biomedicine 13(5): 703–710, DOI: 10.1109/TITB.2009.2017939.
Search in Google Scholar Back to article
Wei, S., Sun, Z., Wang, Z., Liao, F., Li, Z. and Mi, H. (2023). An efficient data augmentation method for automatic modulation recognition from low-data imbalanced-class regime, Applied Sciences 13(5): 3177, DOI: 10.3390/app13053177.
Search in Google Scholar Back to article
Widmann, A., Schröger, E. and Maess, B. (2015). Digital filter design for electrophysiological data—A practical approach, Journal of Neuroscience Methods 250: 34–46, DOI: 10.1016/j.jneumeth.2014.08.002.
Search in Google Scholar Back to article
Xi, H., Ren, K., Lu, P., Li, Y. and Hu, C. (2024). SSGait: Enhancing gait recognition via semi-supervised self-supervised learning, Applied Intelligence 54(7): 5639–5657, DOI: 10.1007/s10489-024-05385-2.
Search in Google Scholar Back to article
Xu, J., Yan, K., Deng, Z., Yang, Y., Liu, J.-X., Wang, J. and Yuan, S. (2024). EEG-based epileptic seizure detection using deep learning techniques: A survey, Neurocomputing 610: 128644, DOI: 10.1016/j.neucom.2024.128644.
Search in Google Scholar Back to article
Yao, H., Huang, L.-K., Zhang, L., Wei, Y., Tian, L., Zou, J., Huang, J. and Li, Z. (2021). Improving generalization in meta-learning via task augmentation, International Conference on Machine Learning (ICML 2021), pp. 11887–11897, DOI: 10.48550/arXiv.2007.13040, (virtual event).
Search in Google Scholar Back to article
Zhang, X., Zhou, X., Lin, M. and Sun, J. (2018). ShuffleNet: An extremely efficient convolutional neural network for mobile devices, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 6848–6856, DOI: 10.48550/arXiv.1707.01083.
Search in Google Scholar Back to article
Zhou, W., Zheng, W., Feng, Y. and Li, X. (2024). LMA-EEGNet: A Lightweight multi-attention network for neonatal seizure detection using EEG signals, Electronics 13(12), DOI: 10.3390/electronics13122354.
Search in Google Scholar Back to article
Zou, Z., Chen, B., Xiao, D., Tang, F. and Li, X. (2024). Accuracy of machine learning in detecting pediatric epileptic seizures: Systematic review and meta-analysis, Journal of Medical Internet Research 26: e55986, DOI: 10.2196/55986.
Search in Google Scholar Back to article

Deep Learning Epileptic Seizure Detection based on the Matching Pursuit Algorithm and its Time–Frequency Graphical Representation

Abstract

Paradigm

My account