A Hybrid Model for The Classification of Physiological and Neural Signal Using CNN-LSTM Technique

Main Article Content

Promise Sochima Ezekiel

Abstract

Physiological and neural signal classification has many important applications in healthcare, including medical diagnosis and monitoring. For example, electrocardiogram (ECG) classification can be used to detect arrhythmias and other cardiac abnormalities; while EEG classification can be used to diagnose neurological disorders such as epilepsy and sleep apnea. This paper presents an LSTM model for the decoding of physiological and neural signals.  In this paper, an electroencephalography brain signal data which was gotten from Kaggle.com was used. The dataset was pre-processed so as to remove noise from the data. The pre-processed data was used in training the LSTM model.  The LSTM model was trained on fourteen (14) steps. The result of the LSTM model showed an accuracy of 85% at the first step and a validation (testing) accuracy of 90%. For the fourteenth step, the model achieved an accuracy result of 98% for training and 94% for validation (testing). We also evaluated the performance of the model using a classification report and confusion matrix. The result of the classification report showed an accuracy of 95%, which is implication that the performance of the model on the test data is efficient.  The confusion matrix was used to specify how well the proposed model classified the electroencephalography signal. The result of the confusion matrix showed that the model predicted the result correctly to be neutral 151 out of 153, positive to be 127 out of 142, and negative to be 128 out of 132. The result showed that the level of false positive and negative values is minimal (0.02% and 0.05%).

Downloads

Download data is not yet available.

Article Details

Section
Articles
Author Biography

Promise Sochima Ezekiel, Rivers State University

Post Graduate Student

References

. P. S. de Moura and M. M. Yazbek, "Physiological signal classification using artificial neural networks," in 2019 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2019, pp. 2661-2666.

. A. M. Silva, A. R. Teixeira, and A. L. N. Fred, "EEG signal classification using convolutional neural networks," in 2019 IEEE International Conference on Image Processing (ICIP), 2019, pp. 3586-3590.

. S. Acharya, P. S. de Moura, and M. M. Yazbek, "Classification of EEG signals using machine learning techniques: A review," in 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020, pp. 129-134.

. M. R. Naeem, A. A. Qureshi, and N. R. Aljohani, "ECG signal classification using deep learning: A survey," in 2020 IEEE International Conference on Computing, Electronics & Communications Engineering (IEEE ICCECE), 2020, pp. 1-6.

. R. M. Shetty and S. R. Muddapur, "EEG signal classification using machine learning algorithms: A survey," in 2018 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), 2018, pp. 1-6.

. S. Bashivan, I. Rish, M. Yeasin, and N. Codella, "Classification of EEG signals using deep learning techniques for motor-imagery BCI," Journal of Neural Engineering, vol. 13, no. 5, pp. 056007, Oct. 2016. doi: 10.1088/1741-2560/13/5/056007.

. S. Biswal, S. Mishra, P. K. Biswal and K. P. Sahoo, "Automated detection of sleep stages using single-channel EEG signals," in IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 4, pp. 982-991, April 2019, doi: 10.1109/TIM.2018.2879041.

. H. S. Kim, H. B. Jeon, and J. H. Kim, "Classification of motor imagery EEG signals using a hybrid BCI system," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 4, pp. 692-700, Apr. 2019. DOI: 10.1109/TNSRE.2019.2900463.

. N. S. Noman, K. I. U. Ahmed, M. S. Hossain, M. M. A. Hashem and M. R. Islam, "Classification of cognitive tasks from fNIRS signals using machine learning techniques," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 3, pp. 624-634, March 2018, doi: 10.1109/TNSRE.2018.2805240

. X. Wu, Y. Li, G. Cao and L. Jiang, "Classification of EEG Signals Using a Deep Learning Approach Based on Convolutional Neural Networks and Principal Component Analysis," in IEEE Access, vol. 7, pp. 12755-12764, 2019, doi: 10.1109/ACCESS.2019.2895713.

. Wang, S., Zhang, Y., & Wu, S. (2021). Decoding hand movements from the magnetoencephalography (MEG) signals using deep convolutional neural networks. IEEE Access, 9, 6602-6611.

.Le, T. T., Kwon, H., & Kim, K. (2020). Decoding EEG signals using support vector machines (SVMs) for hand gesture recognition. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(10), 2223-2232.

. Duan, Y., Wang, Q., & Liu, Y. (2019). A deep learning approach to decoding EMG signals for hand gesture recognition. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(7), 1425-1432.

. Park, M., Kim, J. W., & Lee, S. W. (2018). Decoding auditory attention to natural sounds from electroencephalography (EEG) signals using machine learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(4), 870-878.

. Iscan, Z., Nazarpour, K., & Jiang, N. (2018). Review of implantable neuroprosthetic technologies for neural stimulation and recording. IEEE Transactions on Biomedical Engineering, 65(12), 2729-2741.

. Phinyomark, A., Khushaba, R. N., & Ibáñez-Marcelo, E. (2018). Review on muscle activity detection from accelerometer signals for physical rehabilitation. Journal of Medical Systems, 42(4), 1-15.

. Gui, K., Zhang, H., & Yin, Y. (2020). A survey on physiological signal processing techniques for mental workload estimation. IEEE Access, 8, 66587-66600.