Improved Empirical Wavelet Transform Based Signal Preprocessing And Attention-Based Residual Optimized Bilstm (AROBILSTM) Classifier For Epileptic Seizure Detection
Keywords:
Epileptic seizure detection (ESD), scalp EEG, AROBILSTM network, Improved Empirical Wavelet Transform (IEWT), and ResNet-50 modelAbstract
The primary diagnostic procedure for epilepsy is the electroencephalogram (EEG). A human expert often detects epileptic activity. Finding particular patterns in the multi-channel (MC) EEG is the foundation of this detection. When using EEG signals to detect epileptic seizures (ESD), pre-processing is essential. Pre-processing eliminates noise and artifacts to guarantee proper analysis and classification. Their ability for feature extraction (FE) from noisy inputs was thus limited. Numerous attempts are made for automating this time-consuming and challenging task using both traditional and Deep Learning (DL) methods. For signal pre-processing, an Improved Empirical (WT) Wavelet Transform (IEWT) is applied to EEG recordings, and it was suggested in this study. The boundaries are separated from the spectrum in order to execute IEWT. To reconstruct the spectrum's (TC) trend component, IEWT selects several points in the spectrum's Fourier transform (FT). Then, the Improved ResNet-50 model computes the features of EEG signals in a number of specific frequency bands (FB). By incorporating the residual structure and layer normalisation (LN) into a BILSTM, the Attention-based Residual Optimised (BI-LSTM) Bidirectional Long Short-Term Memory (AROBILSTM) network classifier is presented. The accuracy (ACC) and stability of epilepsy detection are eventually improved by this integration. In order to optimise the final feature information, this integration also provides an attention mechanism (AM) and enhances the network's FE capabilities. The outputs of the epilepsy network are further processed utilising seizure merging, threshold (T) comparison, and moving average filtering (MAF) to ascertain whether or not the tested EEG that are related to a seizure. On the scalp EEG database from Children's Hospital Boston-Mass Institute of Technology (CHB-MIT), the suggested approach performed better than alternative methods in terms of precision (P), recall/sensitivity (R/S), F-measure, and accuracy (ACC).
Downloads
Metrics
References
Vidyaratne, L.S. and Iftekharuddin, K.M., 2017. Real-time epileptic seizure detection using EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(11), pp.2146-2156.
Bhattacharyya, A., Pachori, R.B., Upadhyay, A. and Acharya, U.R., 2017. Tunable-Q wavelet transform based multiscale entropy measure for automated classification of epileptic EEG signals. Applied Sciences, 7(4), pp.1-18.
Kulaseharan, S.; Aminpour, A.; Ebrahimi, M.; Widjaja, E. Identifying lesions in paediatric epilepsy using morphometric and textural analysis of magnetic resonance images. Clin. NeuroImage 2019, 21, pp.1-8.
Zazzaro, G., Cuomo, S., Martone, A., Montaquila, R.V., Toraldo, G. and Pavone, L., 2021. EEG signal analysis for epileptic seizures detection by applying data mining techniques. Internet of Things, 14, pp.1-17.
Chakrabarti, S.; Swetapadma, A.; Pattnaik, P.K. A review on epileptic seizure detection and prediction using soft computing techniques. In Smart Techniques for a Smarter Planet; Springer: Cham, Switzerland, 2019; pp. 37–51.
Liu, X.Y., Wang, W.L., Liu, M., Chen, M.Y., Pereira, T., Doda, D.Y., Ke, Y.F., Wang, S.Y., Wen, D., Tong, X.G. and Li, W.G., 2025. Recent applications of EEG-based brain-computer-interface in the medical field. Military Medical Research, 12(1), pp.1-42.
Kedadouche, M., Thomas, M. and Tahan, A.J.M.S., 2016. A comparative study between Empirical Wavelet Transforms and Empirical Mode Decomposition Methods: Application to bearing defect diagnosis. Mechanical Systems and Signal Processing, 81, pp.88-107.
Zheng, J.D.; Pan, H.Y.; Yang, S.B. Adaptive parameterless empirical wavelet transform based time-frequency analysis method and its application to rotor rubbing fault diagnosis. Signal Process. 2017, 130, 305–314.
Liu, W. and Chen, W., 2019. Recent advancements in empirical wavelet transform and its applications. IEEE Access, 7, pp.103770-103780.
Elouaham, S., Dliou, A., Jenkal, W., Louzazni, M., Zougagh, H. and Dlimi, S., 2024. Empirical wavelet transforms based ECG signal filtering method. Journal of Electrical and Computer Engineering, 2024(1), pp.1-13.
Wei Z., J. Zou, J. Zhang, and J. Xu, “Automatic epileptic EEG detection using convolutional neural network with improvements in time-domain,” Biomed. Signal Process. Control, vol. 53, Aug. 2019, Art. no. 101551, pp.1-11.
Geng M., W. Zhou, G. Liu, C. Li, and Y. Zhang, “Epileptic seizure detection based on stockwell transform and bidirectional long shortterm memory,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 3, pp. 573–580, Mar. 2020.
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, pp.1-12.
Prabin Jose J., M. Sundaram, and G. Jaffino, “Adaptive rag-bull rider: A modified self-adaptive optimization algorithm for epileptic seizure detection with deep stacked autoencoder using electroencephalogram,” Biomed. Signal Process. Control, vol. 64, Feb. 2021, Art. no. 102322, pp.1-11.
Zhou, M., Tian, C., Cao, R., Wang, B., Niu, Y., Hu, T., Guo, H. and Xiang, J., 2018. Epileptic seizure detection based on EEG signals and CNN. Frontiers in neuroinformatics, 12, pp.1-14.
Shoeibi, A.; Ghassemi, N.; Alizadehsani, R.; Rouhani, M.; Hosseini-Nejad, H.; Khosravi, A.; Panahiazar, M.; Nahavandi, S. A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals. Expert Syst. Appl. 2021, vol.163, no.113788, pp.1-16.
Yuan Y., G. Xun, K. Jia, and A. Zhang, “A multi-view deep learning framework for EEG seizure detection,” IEEE J. Biomed. Health Inform., vol. 23, no. 1, pp. 83–94, Jan. 2019.
Li Y., W.-G. Cui, H. Huang, Y.-Z. Guo, K. Li, and T. Tan, “Epileptic seizure detection in EEG signals using sparse multiscale radial basis function networks and the Fisher vector approach,” Knowl.-Based Syst., vol. 164, pp. 96–106, Jan. 2019.
Sahani, M., Rout, S.K. and Dash, P.K., 2021. Epileptic seizure recognition using reduced deep convolutional stack autoencoder and improved kernel RVFLN from EEG signals. IEEE transactions on biomedical circuits and systems, 15(3), pp.595-605.
Li, Y., Liu, Y., Cui, W.G., Guo, Y.Z., Huang, H. and Hu, Z.Y., 2020. Epileptic seizure detection in EEG signals using a unified temporal-spectral squeeze-and-excitation network. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(4), pp.782-794.
Hu, X., Yuan, S., Xu, F., Leng, Y., Yuan, K. and Yuan, Q., 2020. Scalp EEG classification using deep Bi-LSTM network for seizure detection. Computers in Biology and Medicine, 124, pp.1-8.
Liu, G., Tian, L. and Zhou, W., 2022. Patient-independent seizure detection based on channel-perturbation convolutional neural network and bidirectional long short-term memory. International journal of neural systems, 32(06), pp.1-17.
He J., J. Cui, G. Zhang, M. Xue, D. Chu, and Y. Zhao, “Spatial–temporal seizure detection with graph attention network and bi-directional LSTM architecture,” Biomedical Signal Processing and Control, vol. 78, no.103908, pp.1-9, 2022.
Tawhid M. N. A., S. Siuly, and T. Li, “A convolutional long short-term memory-based neural network for epilepsy detection from EEG,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–11, 2022.
Quadri, Z.F., Akhoon, M.S. and Loan, S.A., 2024. Epileptic Seizure Prediction using Stacked CNN-BiLSTM: A Novel Approach. IEEE Transactions on Artificial Intelligence, vol.5, no.11, pp. 5553 – 5560.
Zhang, Y., Yao, S., Yang, R., Liu, X., Qiu, W., Han, L., Zhou, W. and Shang, W., 2022. Epileptic seizure detection based on bidirectional gated recurrent unit network. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, pp.135-145.
Liu, W. and Chen, W., 2019. Recent advancements in empirical wavelet transform and its applications. IEEE Access, 7, pp.103770-103780.
Bhattacharyya, A., Sharma, M., Pachori, R.B., Sircar, P. and Acharya, U.R., 2018. A novel approach for automated detection of focal EEG signals using empirical wavelet transform. Neural Computing and Applications, 29, pp.47-57.
Xu, Y., Zhang, K., Ma, C., Li, X. and Zhang, J., 2018. An improved empirical wavelet transform and its applications in rolling bearing fault diagnosis. Applied sciences, 8(12), pp.1-24.
Wen, L., Li, X. and Gao, L., 2020. A transfer convolutional neural network for fault diagnosis based on ResNet-50. Neural Computing and Applications, 32(10), pp.6111-6124.
Yadav, R.K., Mishra, A.K., Saini, J.B., Pant, H., Biradar, R.G. and Waghodekar, P., 2024. A Model for Brain Tumor Detection Using a Modified Convolution Layer ResNet-50. Indian Journal of Information Sources and Services, 14(1), pp.29-38.
Siami-Namini, S., Tavakoli, N. and Namin, A.S., 2019, The performance of LSTM and BiLSTM in forecasting time series. In 2019 IEEE International conference on big data (Big Data), pp. 3285-3292.
Cheng, J., Zou, Q. and Zhao, Y., 2021. ECG signal classification based on deep CNN and BiLSTM. BMC medical informatics and decision making, 21, pp.1-12.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
