Post-Stroke identification of EEG signals using recurrent neural networks and long short-term memory

(1) Wanodya Sansiagi Mail (Universitas Jenderal Achmad Yani, Indonesia)
(2) * Esmeralda Contessa Djamal Mail (Universitas Jenderal Achmad Yani, Indonesia)
(3) Daswara Djajasasmita Mail (Universitas Jenderal Achmad Yani, Indonesia)
(4) Arlisa Wulandari Mail (Universitas Jenderal Achmad Yani, Indonesia)
*corresponding author


Stroke often causes disability, so patients need rehabilitation for recovery. Therefore, it is necessary to measure its effectiveness. An Electroencephalogram (EEG) can capture the improvement of activity in the brain in stroke rehabilitation. Therefore, the focus is on the identification of several post-rehabilitation conditions. This paper proposed identifying post-stroke EEG signals using Recurrent Neural Networks (RNN) to process sequential data. Memory control in the use of RNN adopted Long Short-Term Memory. Identification was provided out on two classes based on patient condition, particularly "No Stroke" and "Stroke". EEG signals are filtered using Wavelet to get the waves that characterize a stroke. The four waves and the average amplitude are features of the identification model. The experiment also varied the weight correction, i.e., Adaptive Moment Optimization (Adam) and Stochastic Gradient Descent (SGD). This research showed the highest accuracy using Wavelet without amplitude features of 94.80% for new data with Adam optimization model. Meanwhile, the feature configuration tested effect shows that the use of the amplitude feature slightly reduces the accuracy to 91.38%. The results also show that the effect of the optimization model, namely Adam has a higher accuracy of 94.8% compared to SGD, only 74.14%. The number of hidden layers showed that three hidden layers could slightly increase the accuracy from 93.10% to 94.8%. Therefore, wavelets as extraction are more significant than other configurations, which slightly differ in performance. Adam's model achieved convergence in earlier times, but the speed of each iteration is slower than the SGD model. Experiments also showed that the optimization model, number of epochs, configuration, and duration of the EEG signal provide the best accuracy settings.


Post-stroke; EEG signal; Wavelet; Recurrent Neural Networks; Long Short-Term Memory



Article metrics

Abstract views : 178 | PDF views : 33




Full Text



[1] World Stroke Organization, "Facts and Figures about Stroke," Kenes Media, 2015. Available at:

[2] S. E. Kasner, "Clinical Interpretation and Use of Stroke Scales," The Lancet Neurology, vol. 5, no. 7, pp. 603–612, 2006. doi: 10.1016/S1474-4422(06)70495-1

[3] W. R. R. Omar, R. Jailani, M. N. Taib, N. A. A. Razak, N. H. A. Wahab, and W. N. Nafisah, "An analysis of male stroke patients' brain signal according to NIHSS score," IEEE Conference on Systems, Process and Control (ICSPC 2014), pp. 183–187, 2014. doi: 10.1109/SPC.2014.7086254

[4] E. C. Djamal and P. Lodaya, "EEG Based Emotion Monitoring Using Wavelet and Learning Vector Quantization," 2017 4Th International Conference on Electrical Engineering, Computer Science and Informatics (Eecsi), pp. 94–99, 2017. doi: 10.1109/EECSI.2017.8239090

[5] O. Faust, U. R. Acharya, H. Adeli, and A. Adeli, "Wavelet-based EEG Processing for Computer-aided Seizure Detection and Epilepsy Diagnosis," Seizure: European Journal of Epilepsy, vol. 26, 2015, [Online]. doi: 10.1016/j.seizure.2015.01.012.

[6] F. Cincotti et al., "EEG-Based Brain-Computer Interface to Support Post-Stroke Motor Rehabilitation of The Upper Limb," 34th Annual International Conference of the IEEE EMBS, pp. 4112–4115, 2012. doi: 10.1109/EMBC.2012.6346871

[7] E. C. Djamal, D. P. Gustiawan, and D. Djajasasmita, “Significant Variables Extraction of Post-Stroke EEG Signal using Wavelet and SOM Kohonen,” TELKOMNIKA, vol. 17, no. 3, pp. 1149–1158, 2019, doi: 10.12928/TELKOMNIKA.v17i3.11776.

[8] W. R. W. Omar et al., "Acute Ischemic Stroke Brainwave Classification Using Relative Power Ratio Cluster Analysis," The 9th International Conference on Cognitive Science, pp. 546–552, 2013. doi: 10.1016/j.sbspro.2013.10.271

[9] S. Z. Bong, K. Wan, M. Murugappan, N. M. Ibrahim, Y. Rajamanickam, and K. Mohamad, "Implementation of Wavelet Packet Transform and Non Linear Analysis for Emotion Classification in Stroke Patient using Brain Signals," Biomedical Signal Processing and Control, vol. 36, pp. 102–112, 2017. doi: 10.1016/j.bspc.2017.03.016.

[10] M. Kaleem, A. Guergachi, and S. Krishnan, "Biomedical Signal Processing and Control Patient-Specific Seizure Detection in Long-Term EEG using Wavelet Decomposition," Biomedical Signal Processing and Control, vol. 46, pp. 157–165, 2018. doi: 10.1016/j.bspc.2018.07.006

[11] M. Sharma, P. V. Achuth, D. Deb, S. D. Puthankattil, and U. Rajendra Acharya, "An Automated Diagnosis of Depression Using Three-Channel Bandwidth-Duration Localized Wavelet Filter Bank with EEG Signals," Cognitive Systems Research, 2018. doi: 10.1016/j.cogsys.2018.07.010.

[12] Y. L. Huang et al., "An Improved Forecasting Model Based on The Weighted Fuzzy Relationship Matrix Combined With a PSO Adaptation for Enrollments," International Journal of Innovative Computing, Information and Control, vol. 7, no. 7 A, pp. 4027–4046, 2011. Available at: Google Scholar.

[13] S. Alhagry, A. A. Fahmy, and R. A. El-Khoribi, "Emotion Recognition based on EEG using LSTM Recurrent Neural Network," International Journal of Advanced Computer Science and Applications (IJACSA), vol. 8, no. 10, pp. 355–358, 2017. doi: 10.14569/IJACSA.2017.081046

[14] M. Li, M. Zhang, X. Luo, and J. Yang, "Combined Long Short-Term Memory Based Network Employing Wavelet Coefficients for MI-EEG Recognition," 2016 IEEE International Conference on Mechatronics and Automation, IEEE ICMA 2016, pp. 1971–1976, 2016. doi: 10.1109/ICMA.2016.7558868

[15] S. Roy, I. Kiral-kornek, and S. Harrer, "ChronoNet : A Deep Recurrent Neural Network for Abnormal EEG Identification," International Joint Conferences on Artificial Intelligence (IJCAI), pp. 1–10, 2018. doi: 10.1007/978-3-030-21642-9_8

[16] D. Cheng, Y. Liu, and L. Zhang, "Exploring Motor Imagery Eeg Patterns for Stroke Patients with Deep Neural Networks," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2561–2565, 2018. doi: 10.1109/ICASSP.2018.8461525

[17] M. M. Shaker, "EEG Waves Classifier using Wavelet Transform and Fourier Transform," International Journal of Medical, Health, Biomedical, Bioengineering and Pharmaceutical Engineering, vol. 1, no. 3, pp. 169–174, 2007. Available at: Google Scholar.

[18] F. M. Bayer, A. J. Kozakevicius, and R. J. Cintra, "An Iterative Wavelet Threshold for Signal Denoising," Signal Processing, vol. 162, pp. 10–20, 2019, doi: 10.1016/j.sigpro.2019.04.005.

[19] Z. A. A. Alyasseri, A. T. Khader, M. A. Al-Betar, and M. A. Awadallah, "Hybridizing β-hill Climbing with Wavelet Transform for Denoising ECG Signals," Information Sciences, vol. 429, pp. 229–246, 2018, doi: 10.1016/j.ins.2017.11.026.

[20] N. Gurudath and H. Bryan Riley, "Drowsy driving detection by EEG analysis using Wavelet Transform and K-means clustering," Procedia Computer Science, vol. 34, pp. 400–409, 2014, doi: 10.1016/j.procs.2014.07.045.

[21] C. Li, Y. Huang, X. Yang, and H. Chen, "Marginal Distribution Covariance Model in The Multiple Wavelet Domain for Texture Representation," Pattern Recognition, vol. 92, pp. 246–257, 2019, doi: 10.1016/j.patcog.2019.04.003.

[22] P. V. Kasambe and S. S. Rathod, "VLSI Wavelet Based Denoising of PPG Signal," Procedia Computer Science, vol. 49, no. 1, pp. 282–288, 2015, doi: 10.1016/j.procs.2015.04.254.

[23] H. Fadhilah, E. C. Djamal, and R. Ilyas, "Non-Halal Ingredients Detection of Food Packaging Image Using Convolutional Neural Networks," 2018. doi: 10.1109/SAIN.2018.8673376

[24] E. P. Giri, M. I. Fanany, A. M. Aryrnurthy, and S. K. Wijaya, "Ischemic Stroke Identification Based on EEG and EOG using 1D Convolutional Neural Network and Batch Normalization," in 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2016, pp. 484–491. doi: 10.1109/ICACSIS.2016.7872780

[25] L. Torop, J. Morton, and J. B. West, "Unsupervised Feature Learning for Audio Classification using Convolutional Deep Belief Networks," Proceedings of the 22th Annual Conference on Advances in Neural Information Processing Systems (NIPS), pp. 1096–1104, 2008. Available at: Google Scholar.

[26] N. F. Gu¨ler, E. D. U¨ beyli, and I. Gu¨ler, "Recurrent Neural Networks Employing Lyapunov Exponents for EEG Signals Classification," Expert Systems with Applications, vol. 29, no. 3, pp. 506–514, 2005, doi: 10.1016/j.eswa.2005.04.011.

[27] F. J. Ordóñez and D. Roggen, "Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition," Sensors (Switzerland), vol. 16, no. 1, 2016. doi: 10.3390/s16010115

[28] H. Sak, A. Senior, and F. Beaufays, "Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling," INTERSPEECH, 2014. Available at: Google Scholar.

[29] F. A. Gers and F. Cummins, "Learning to Forget : Continual Prediction with LSTM," 9th International Conference on Artificial Neural Networks, vol. 12, no. 10, pp. 2451–2471, 2000. doi: 10.1162/089976600300015015

[30] S. Ruder, "An Overview of Gradient Descent Optimization Algorithms," arXiv:1609.04747, pp. 1–14, 2016. Available at: Google Scholar.

[31] D. P. Kingma and J. L. Ba, "Adam : A Method for Stochastic Optimization," 3rd International Conference for Learning Representations, pp. 1–15, 2015. Available at: Google Scholar.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by Informatics Department - Universitas Ahmad Dahlan, and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
E: (paper handling issues), (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0