Pengembangan Model Klasifikasi Kejang Epilepsi Multiclass pada Sinyal EEG Menggunakan CNN+BI-LSTM

Authors

  • Bima Dinda Nurwibowo Institut Teknologi Sepuluh Nopember
  • Ahmad Saikhu Institut Teknologi Sepuluh Nopember

DOI:

https://doi.org/10.30736/jt.v17i1.1354

Keywords:

Klasifikasi, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi- LSTM), Deteksi Kejang Epilepsi, Sinyal EEG

Abstract

Epilepsi merupakan gangguan neurologis yang membutuhkan identifikasi jenis kejang yang akurat untuk pengobatan yang efektif. Klasifikasi sinyal EEG pada periode normal, interictal, dan ictal sangat penting dalam membantu diagnosis epilepsi. Namun, analisis EEG secara otomatis sangat menantang karena kompleksitas sinyal yang tinggi dan pola-pola kompleks yang sering kali tidak terlihat oleh profesional non-ahli. Untuk mengatasi kesulitan ini, penelitian ini mengembangkan model klasifikasi kejang epilepsi multiclass menggunakan pendekatan deep learning berbasis Convolutional Neural Network (CNN) dan Bidirectional Long Short-Term Memory (Bi-LSTM). CNN berperan dalam mengekstraksi fitur secara otomats dari segmen EEG yang lebih pendek, sementara Bi-LSTM membantu dalam memahami pola temporal yang kompleks. Proses prapemrosesan melibatkan segmentasi sinyal, pemisahan komponen independen dan normalisasi, serta augmentasi data dengan Cubic Spline Interpolation (CSI). Model CNN+Bi-LSTM diuji pada dua skenario klasifikasi, yakni data asli dan data augmentasi, serta dua kombinasi subset (A/D/E dan B/D/E). Hasil pengujian menunjukkan model mencapai akurasi tertinggi sebesar 99.87% pada data augmentasi, yang melebihi metode klasifikasi sebelumnya.

Downloads

References

Abbasi, M. U., Rashad, A., Basalamah, A., & Tariq, M. (2019). Detection of Epilepsy Seizures in Neo-Natal EEG Using LSTM Architecture. IEEE Access, 7, 179074–179085. https://doi.org/10.1109/ACCESS.2019.2959234

Ahmed M., A., Hisham G., D., & Magdy, B. (2023). Deep Convolutional Bidirectional LSTM Recurrent Neural Network for Epileptic Seizure Detection. International Conference on Telecommunications and Signal Processing (TSP).

Eviyanti, A., Saikhu, A., & Fatichah, C. (2022). Epileptic Seizure Detection Using Machine Learning and Deep Learning Method. Proceedings - 2022 IEEE International Conference on Cybernetics and Computational Intelligence, CyberneticsCom 2022, 463–468. https://doi.org/10.1109/CyberneticsCom55287.2022.9865313

Mamun Or Rashid, M., & Ahmad, M. (2017). Epileptic Seizure Classification using Statistical Features of EEG Signal. International Conference on Electrical, Computer and Communication Engineering (ECCE).

Manasvi Bhat, K., Pratiksha P, A., Yashashree, S., Sanjeetha, R., & Anita, K. (2019). Detection and Prediction of the Preictal State of an Epileptic Seizure using Machine Learning Techniques on EEG Data. Bombay Section Signature Conference.

Nanthini, K., Tamilarasi, A., Pyingkodi, M., Dishanthi, M., Kaviya, S. M., & Mohideen, P. A. (2022). Epileptic Seizure Detection and Prediction Using Deep Learning Technique. 2022 International Conference on Computer Communication and Informatics, ICCCI 2022. https://doi.org/10.1109/ICCCI54379.2022.9740802

Oliva, J. T., & Rosa, J. L. G. (2021). Binary and multiclass classifiers based on multitaper spectral features for epilepsy detection. Biomedical Signal Processing and Control, 66. https://doi.org/10.1016/j.bspc.2021.102469

Pedram, R., Farzanehkari, P., & Chaibakhsh, A. (2023). Enhancing Epileptic Seizure Detection Using Convolutional Neural Networks and Data Augmentation Techniques. 2023 30th National and 8th International Iranian Conference on Biomedical Engineering, ICBME 2023, 132–137. https://doi.org/10.1109/ICBME61513.2023.10488640

Reddy, S. K. C., & Suchetha, M. (2022). A 1-D CNN-FSVM Model with a multi-scale sub-band feature learning for automated seizure detection. Proceedings - IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2022. https://doi.org/10.1109/ACCAI53970.2022.9752500

Rohan, T. I., Yusuf, Md. S. U., Islam, M., & Roy, S. (2020). Efficient Approach to Detect Epileptic Seizure using Machine Learning Models for Modern Healthcare System. Region 10 Symposium (TENSYMP).

Roy, A. D., & Islam, M. M. (2020, December 19). Detection of Epileptic Seizures from Wavelet Scalogram of EEG Signal Using Transfer Learning with AlexNet Convolutional Neural Network. ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings. https://doi.org/10.1109/ICCIT51783.2020.9392720

Shakeel, S., Afzal, N., Khan, G. H., Khan, N. A., Abid, M. U. R., & Altaf, M. A. Bin. (2021). EDM: A multiclassification support system to identify seizure type using K Nearest Neighbor. 2021 28th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2021 - Proceedings. https://doi.org/10.1109/ICECS53924.2021.9665565

Shanmugam, S., & Dharmar, S. (2023). A CNN-LSTM hybrid network for automatic seizure detection in EEG signals. Neural Computing and Applications, 35(28), 20605–20617. https://doi.org/10.1007/s00521-023-08832-2

Tales Oliva, J., Luís Garcia Rosa, J., Carlos, S., Paulo, S., & Senior Member, B. (2019). Epilepsy detection using multiclass classifier based on spectral features. International Joint Conference on Neural Networks. http://epileptologie-bonn.de/cms/front

Yildirim, Ö. (2018). A novel wavelet sequences based on deep bidirectional LSTM network model for ECG signal classification. Computers in Biology and Medicine, 96, 189–202. https://doi.org/10.1016/j.compbiomed.2018.03.016

Downloads

PlumX Metrics

Published

2025-03-18

How to Cite

Bima Dinda Nurwibowo, & Ahmad Saikhu. (2025). Pengembangan Model Klasifikasi Kejang Epilepsi Multiclass pada Sinyal EEG Menggunakan CNN+BI-LSTM. Jurnal Teknika, 17(1), 21–28. https://doi.org/10.30736/jt.v17i1.1354

Issue

Section

Jurnal teknika