Graph attention network and radial basis function neural network-based hybrid framework for epileptic seizure detection from EEG signal
Abstract
Epileptic seizure is a neurological disorder characterized by recurrent, abrupt behavioral changes attributed to transient shifts in excessive electrical discharges within specific brain cell groups. Electroencephalogram (EEG) signals are the primary modality for capturing seizure activity, offering real-time, computer-assisted detection through long-term monitoring. Over the last decade, extensive experiments through deep learning techniques on EEG signal analysis, and automatic seizure detection. Nevertheless, realizing the full potential of deep neural networks in seizure detection remains a challenge, primarily due to limitations in model architecture design and their capacity to handle time series brain data. The fundamental drawback of current deep learning methods is their struggle to effectively represent physiological EEG recordings; as it is irregular and unstructured in nature, which is difficult to fit into matrix format in traditional methods. Because of this constraint, a significant research gap remains in this research field. In this context, we propose a novel approach to bridge this gap, leveraging the inherent relationships within EEG data. Graph neural networks (GNNs) offer a potential solution, capitalizing on their ability to naturally encapsulate relational data between variables. By representing interacting nodes as entities connected by edges with weights determined by either temporal associations or anatomical connections, GNNs have garnered substantial attention for their potential in configuring brain anatomical systems. In this paper, we introduce a hybrid framework for epileptic seizure detection, combining the Graph Attention Network (GAT) with the Radial Basis Function Neural Network (RBFN) to address the limitations of existing approaches. Unlike traditional graph-based networks, GAT automatically assigns weights to neighbouring nodes, capturing the significance of connections between nodes within the graph. The RBFN supports this by employing linear optimization techniques to provide a globally optimal solution for adjustable weights, optimizing the model in terms of the minimum mean square error (MSE). Power spectral density is used in the proposed method to analyze and extract features from electroencephalogram (EEG) signals because it is naturally simple to analyze, synthesize, and fit into the graph attention network (GAT), which aids in RBFN optimization. The proposed hybrid framework outperforms the state-of-the-art in seizure detection tasks, obtaining an accuracy of 98.74%, F1-score of 96.2%, and Area Under Curve (AUC) of 97.3% in a comprehensive experiment on the publicly available CHB-MIT EEG dataset.
Keywords
Full Text:
PDFReferences
1. Wang Y, Pan Y, Li H. What is brain health and why is it important? The BMJ 2020; 371. doi: 10.1136/bmj.m3683
2. Jibon FA, Islam MS, Islam R. Log-polar Transformation based Feature Extraction Method for Tumor Detection and Classification of brain MRI. Available online: http://103.133.35.64:8080/xmlui/handle/123456789/427 (accessed on 1 June 2019).
3. Jibon FA, Khandaker MU, Miraz MH, et al. Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation. Healthcare 2022; 10(9): 1801. doi: 10.3390/healthcare10091801.
4. Shoeibi A, Ghassemi N, Alizadehsani R, et al. A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals. Expert Systems with Applications 2021; 163: 113788. doi: 10.1016/j.eswa.2020.113788
5. Huang X, Sun X, Zhang L, et al. A novel epilepsy detection method based on feature extraction by deep autoencoder on EEG signal. International Journal of Environmental Research and Public Health 2022; 19(22): 15110. doi: 10.3390/ijerph192215110
6. Wen T, Zhang Z. Special section on trends, perspectives and prospects of machine learning applied to biomedical systems in internet of medical things deep convolution neural network and autoencoders-based unsupervised feature learning of EEG signals. IEEE Access 2018; 6: 25399–25410. doi: 10.1109/access.2018.2833746
7. Saminu S, Xu G, Shuai Z, et al. A recent investigation on detection and classification of epileptic seizure techniques using EEG signal. Brain Sciences 2021; 11(5): 668. doi: 10.3390/brainsci11050668
8. Ramos-Aguilar R, Olvera-López JA, Olmos-Pineda I, Sánchez-Urrieta S. Feature extraction from EEG spectrograms for epileptic seizure detection. Pattern Recognition Letters 2020; 133: 202–209. doi: 10.1016/j.patrec.2020.03.006
9. Zhang H, Krooswyk S, Ou J. PCB Design for Signal Integrity. High Speed Digital Design 2015; 27–115.
10. Kumari RSS, Abirami R. Automatic detection and classification of epileptic seizure using radial basis function and power spectral density. In: Proceedings of the 2019 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET 2019); 21–23 March 2019; Chennai, India. pp. 6–9.
11. Savadkoohi M, Oladunni T, Thompson L. A machine learning approach to epileptic seizure prediction using Electroencephalogram (EEG) Signal. Biocybernetics and Biomedical Engineering 2020; 40(3): 1328–1341. doi: 10.1016/j.bbe.2020.07.004
12. Chauhan NK, Singh K. A Review on Conventional Machine Learning vs Deep Learning. In: Proceedings of the 2018 International Conference on Computing, Power and Communication Technologies (GUCON); 28–29 September 2018; Greater Noida, India. pp. 347–352. doi: 10.1109/GUCON.2018.8675097.
13. Shoeibi A, Khodatars M, Ghassemi N, et al. Epileptic seizures detection using deep learning techniques: A review. International Journal of Environmental Research and Public Health 2021; 18(11): 5780. doi: 10.3390/ijerph18115780
14. Zhang XM, Liang L, Liu L, et al. Graph neural networks and their current applications in bioinformatics. Frontiers in Genetics 2021; 12: 690049. doi: 10.3389/fgene.2021.690049
15. Li Y. A survey of EEG analysis based on graph neural network. In: Proceedings of the 2nd International Conference on Electronics, Communications and Information Technology (CECIT 2021); 27–29 December 2021; Sanya, China. pp. 151–155.
16. Ahmedt-Aristizabal D, Armin MA, Denman S, et al. Graph-based deep learning for medical diagnosis and analysis: Past, present and future. Sensors 2021; 21(14): 4758. doi: 10.3390/s21144758
17. He J, Cui J, Zhang G, et al. Spatial-temporal seizure detection with graph attention network and bi-directional LSTM architecture. Biomedical Signal Processing and Control 2022; 78: 103908. doi: 10.1016/j.bspc.2022.103908
18. Devi MG, Akila IS. Deep Learning based Compressive Sensing–Radial Basis Functional Neural Network for Image Fusion. In: Proceedings of the 2023 4th International Conference on Signal Processing and Communication (ICSPC); 2023; Coimbatore, Indian. pp. 432–435. doi: 10.1109/ICSPC57692.2023.10125721.
19. Aslan K, Bozdemir H, Şahin C, et al. A radial basis function neural network model for classification of epilepsy using EEG signals. Journal of Medical Systems 2008; 32(5): 403–408. doi: 10.1007/s10916-008-9145-9
20. Tran LV, Tran HM, Le TM, et al. Application of machine learning in epileptic seizure detection. Diagnostics 2022; 12(11): 2879. doi: 10.3390/diagnostics12112879
21. Tzallas AT, Tsipouras MG, Fotiadis DI. Epileptic seizure detection in EEGs using time-frequency analysis. IEEE Transactions on Information Technology in Biomedicine 2009; 13(5): 703–710. doi: 10.1109/titb.2009.2017939
22. Birjandtalab J, Heydarzadeh M, Nourani M. Automated EEG-based epileptic seizure detection using deep neural networks. In: Proceedings of the 2017 IEEE International Conference on Healthcare Informatics (ICHI 2017); 23–26 August 2017; Park City, UT, USA. pp. 552–555.
23. Zhou M, Tian C, Cao R, et al. Epileptic seizure detection based on EEG signals and CNN. Frontiers in Neuroinformatics 2018; 12. doi: 10.3389/fninf.2018.00095
24. Tsiouris ΚΜ, Pezoulas VC, Zervakis M, et al. A long short-term memory deep learning network for the prediction of epileptic seizures using EEG signals. Computers in Biology and Medicine 2018; 99: 24–37. doi: 10.1016/j.compbiomed.2018.05.019
25. Xu G, Ren T, Chen Y, et al. A one-dimensional CNN-LSTM model for epileptic seizure recognition using EEG signal analysis. Frontiers in Neuroscience 2020; 14: 578126. doi: 10.3389/fnins.2020.578126
26. Schuster M, Paliwal KK. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing 1997; 45(11): 2673–2681. doi: 10.1109/78.650093
27. Hu X, Yuan S, Xu F, et al. Scalp EEG classification using deep Bi-LSTM network for seizure detection. Computers in Biology and Medicine 2020; 124: 103919. doi: 10.1016/j.compbiomed.2020.103919
28. Geng M, Zhou W, Liu G, et al. Epileptic seizure detection based on stockwell transform and bidirectional long short-term memory. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2020; 28(3): 573–580. doi: 10.1109/tnsre.2020.2966290
29. Osman AH, Alzahrani AA. New approach for automated epileptic disease diagnosis using an integrated self-organization map and radial basis function neural network algorithm. IEEE Access 2019; 7: 4741–4747. doi: 10.1109/ACCESS.2018.2886608
30. Ghosh-Dastidar S, Adeli H, Dadmehr N. Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection. IEEE Transactions on Biomedical Engineering 2008; 55(2): 512–518. doi: 10.1109/tbme.2007.905490
31. Henaff M, Bruna J, LeCun Y. Deep convolutional networks on graph-structured data. Available online: http://arxiv.org/abs/1506.05163 (accessed on 23 November 2023).
32. Grattarola D, Livi L, Alippi C, et al. Seizure localisation with attention-based graph neural networks. Expert Systems with Applications 2022; 203: 117330. doi: 10.1016/j.eswa.2022.117330
33. Li Z, Hwang K, Li K, et al. Graph-generative neural network for EEG-based epileptic seizure detection via discovery of dynamic brain functional connectivity. Scientific Reports 2022; 12(1): 18998. doi: 10.1038/s41598-022-23656-1
34. Zeng D, Huang K, Xu C, et al. Hierarchy graph convolution network and tree classification for epileptic detection on electroencephalography signals. IEEE Transactions on Cognitive and Developmental Systems 2021; 13(4): 955–968. doi: 10.1109/tcds.2020.3012278
35. Chen X, Zheng Y, Niu Y, et al. Epilepsy classification for mining deeper relationships between EEG channels based on GCN. In: Proceedings of the 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL 2020); 10–12 July 2020; Chongqing, China. pp. 701–706.
36. He J, Cui J, Zhao Y, et al. Spatial-temporal seizure detection with graph attention network and bi-directional LSTM architecture. Available online: https://ssrn.com/abstract=3987849 (accessed on 23 November 2023).
37. Raeisi K, Khazaei M, Croce P, et al. A graph convolutional neural network for the automated detection of seizures in the neonatal EEG. Computer Methods and Programs in Biomedicine 2022; 222: 106950. doi: 10.1016/j.cmpb.2022.106950
38. Jibon FA, Miraz MH, Khandaker MU, et al. Epileptic seizure detection from electroencephalogram (EEG) signals using linear graph convolutional network and DenseNet based hybrid framework. Journal of Radiation Research and Applied Sciences 2023; 16(3): 100607. doi: 10.1016/j.jrras.2023.100607
39. Boonyakitanont P, Lek-uthai A, Chomtho K, et al. A review of feature extraction and performance evaluation in epileptic seizure detection using EEG. Available online: http://arxiv.org/abs/1908.00492 (accessed on 23 November 2023).
40. Brillinger DR. John W. Tukey’s work on time series and spectrum analysis. The Annals of Statistics 2002; 30(6): 1595–1618. doi: 10.1214/aos/1043351248
41. Sri Sivasubramaniya Nadar College of Engineering. Electronics and communication engineering department and institute of electrical and electronics engineers. In: Proceedings of the 2019 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET 2019); 21–23 March 2019; Chennai, India.
42. Ge L, Parhi KK. Seizure Detection Using Power Spectral Density via Hyperdimensional Computing. In: Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 6–11 June 2021; Toronto, ON, Canada. doi: 10.1109/ICASSP39728.2021.9414083.
43. Veličković P, Cucurull G, Casanova A, et al. Graph attention networks. Available online: http://arxiv.org/abs/1710.10903 (accessed on 23 November 2023).
44. Khan ZN, Ahmad J. Attention induced multi-head convolutional neural network for human activity recognition. Applied Soft Computing 2021; 110: 107671. doi: 10.1016/j.asoc.2021.107671
45. Li J, Zeng H, Peng L, et al. Learning to rank method combining multi-head self-attention with conditional generative adversarial nets. Array 2022; 15(3): 100205. doi: 10.1016/j.array.2022.100205
46. Zhang L, Song H, Aletras N, Lu H. Graph node-feature convolution for representation learning. Available online: http://arxiv.org/abs/1812.00086 (accessed on 23 November 2023).
47. Boomhead DSB, Id Lowe D. Multivariable Functional Interpolation and Adaptive Networks. Complex Systems 1988; 2(3): 321–355.
48. Borş AG, Pitas I. Median radial basis function neural network. IEEE Transactions on Neural Networks 1996; 7(6): 1351–1364. doi: 10.1109/72.548164.
49. Li Y, Liu Q, Tan SR, Chan RHM. High-resolution time-frequency analysis of EEG signals using multiscale radial basis functions. Neurocomputing 2016; 195: 96–103. doi: 10.1016/j.neucom.2015.04.128
50. Janjarasjitt S. Epileptic seizure classifications of single-channel scalp EEG data using wavelet-based features and SVM. Medical & Biological Engineering & Computing 2017; 55(10): 1743–1761. doi: 10.1007/s11517-017-1613-2
51. Hussain W, Sadiq MT, Siuly S, et al. Epileptic seizure detection using 1 D-convolutional long short-term memory neural networks. Applied Acoustics 2021; 177: 107941. doi: 10.1016/j.apacoust.2021.107941
DOI: https://doi.org/10.32629/jai.v7i3.1149
Refbacks
- There are currently no refbacks.
Copyright (c) 2023 Authors
License URL: https://creativecommons.org/licenses/by-nc/4.0/