Comparison of Deep Learning Model with other Automatic Learning Models for Recognizing Spikes Expressed from Epilepsy Patients
Main Article Content
Abstract
In the clinical diagnosis of epilepsy using EEG data, the ability to automatically detect and correctly classify epilepsy spikes is helpful and significant for medicines. The article introduces a new approach for automatic detection of spike. Currently, epilepsy classification has been progressed based on many combined methods of machine learning models. This study investigates a new combined model that specifically takes deep learning as a subset of machine learning to perform the classification of epilepsy based on existing standard data sources. The study also implements experimental models in other deep learning models to evaluate the applicability of the model in detecting epilepsy spikes. Experimental results show that the proposed model has high accuracy (98.8%) compared to other studies.
Keywords
Convolutional Neural Network (CNN), deep learning, machine learning, spike epilepsy, pick, EEG Electroencephalogram (EEG)
Article Details
References
[1] C. D. A. Vanitha, D. Devaraj, and M. Venkatesulu, Gene expression data classification using support vector machine and mutual information-based gene selection, Procedia Comput. Sci., vol. 47, pp. 13–21, 2015.
[2] Chung JE, Magland JF, Barnett AH, Tolosa VM, Tooker AC, Lee KY, Shah KG, Felix SH, Frank LM, Greengard LF, A Fully Automated Approach to Spike Sorting, Neuron (2017).
[3] Rossant C, Kadir SN, Goodman DFM, Schulman J, Hunter MLD, Saleem AB, Grosmark A, Belluscio M, Denfield GH, Ecker AS, Tolias AS, Solomon S, Buzsáki G, Carandini M, Harris KD. Spike sorting for large, dense electrode arrays, Nature Neuroscience (2016): 634-641.
[4] Fakoor R, Ladhak F, Nazi A et al. Using deep learning to enhance cancer diagnosis and classification, Proceedings of the International Conference on Machine Learning, 2013.
[5] Y. Kim, Convolutional neural networks for sentence classification, 2014.
[6] E. I. Zacharaki, Prediction of protein function using a deep CNN ensemble, PeerJ Prepr, 2017.
[7] S. Min, B. Lee, and S. Yoon, Deep learning in bioinformatics, Brief. Bioinform, 2016.
[8] Stallkamp, Johannes, et al. The German Traffic Sign Recognition Benchmark: A multi-class classification competition. Neural Networks (IJCNN), The 2011 International Joint Conference on Neural Networks. San Jose, CA, USA: IEEE, 2011.
[9] Gotman, J. and Gloor, P. (1976), Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG, Electroenceph. Clin. Neurophysiol 41, 513-529.
[10] Le Trung Thanh, Nguyen Thi Anh-Dao, Viet-Dung Nguyen, Nguyen LinhTrung, and Karim Abed-Meraim, Multi-channel EEG epileptic spike detection by a new method of tensor decomposition, Journal of Neural Engineering (major revise).
[11] Martin Abadi et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. 2015.
[12] Q. Li, W. Cai, et al. Medical image classification with convolutional neural network in Control Automation Robotics & Vision (ICARCV) 2014.
[13] Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature, vol. 521, no. 7553, pp. 436–444, 2015.
[14] Stallkamp, Johannes, et al. The German Traffic Sign Recognition Benchmark: A multi-class classification competition, Neural Networks (IJCNN), The 2011 International Joint Conference on Neural Networks. San Jose, CA, USA: IEEE, 2011.
[15] Kelley DR, Snoek J, Rinn J. Basset: Learning the regulatory code of the accessible genome with deep convolutional neural networks. bioRxiv 2015:028399.
[16] Le Thanh Xuyên et al. VNU Journal of Science: Comp. Science & Com. Eng., Vol. 33, No. 2 (2017) 1-13.
[17] Ali Shoeb, Herman Edwards, Jack Connolly, Blaise Bourgeois, S. T. Ted Treves, John Guttag. Patient-Specific Seizure Onset Detection. Epilepsy and Behavior. August 2004, 5(4): 483-498.
[18] Y. Kim, Convolutional neural networks for sentence classification, 2014.
[2] Chung JE, Magland JF, Barnett AH, Tolosa VM, Tooker AC, Lee KY, Shah KG, Felix SH, Frank LM, Greengard LF, A Fully Automated Approach to Spike Sorting, Neuron (2017).
[3] Rossant C, Kadir SN, Goodman DFM, Schulman J, Hunter MLD, Saleem AB, Grosmark A, Belluscio M, Denfield GH, Ecker AS, Tolias AS, Solomon S, Buzsáki G, Carandini M, Harris KD. Spike sorting for large, dense electrode arrays, Nature Neuroscience (2016): 634-641.
[4] Fakoor R, Ladhak F, Nazi A et al. Using deep learning to enhance cancer diagnosis and classification, Proceedings of the International Conference on Machine Learning, 2013.
[5] Y. Kim, Convolutional neural networks for sentence classification, 2014.
[6] E. I. Zacharaki, Prediction of protein function using a deep CNN ensemble, PeerJ Prepr, 2017.
[7] S. Min, B. Lee, and S. Yoon, Deep learning in bioinformatics, Brief. Bioinform, 2016.
[8] Stallkamp, Johannes, et al. The German Traffic Sign Recognition Benchmark: A multi-class classification competition. Neural Networks (IJCNN), The 2011 International Joint Conference on Neural Networks. San Jose, CA, USA: IEEE, 2011.
[9] Gotman, J. and Gloor, P. (1976), Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG, Electroenceph. Clin. Neurophysiol 41, 513-529.
[10] Le Trung Thanh, Nguyen Thi Anh-Dao, Viet-Dung Nguyen, Nguyen LinhTrung, and Karim Abed-Meraim, Multi-channel EEG epileptic spike detection by a new method of tensor decomposition, Journal of Neural Engineering (major revise).
[11] Martin Abadi et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. 2015.
[12] Q. Li, W. Cai, et al. Medical image classification with convolutional neural network in Control Automation Robotics & Vision (ICARCV) 2014.
[13] Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature, vol. 521, no. 7553, pp. 436–444, 2015.
[14] Stallkamp, Johannes, et al. The German Traffic Sign Recognition Benchmark: A multi-class classification competition, Neural Networks (IJCNN), The 2011 International Joint Conference on Neural Networks. San Jose, CA, USA: IEEE, 2011.
[15] Kelley DR, Snoek J, Rinn J. Basset: Learning the regulatory code of the accessible genome with deep convolutional neural networks. bioRxiv 2015:028399.
[16] Le Thanh Xuyên et al. VNU Journal of Science: Comp. Science & Com. Eng., Vol. 33, No. 2 (2017) 1-13.
[17] Ali Shoeb, Herman Edwards, Jack Connolly, Blaise Bourgeois, S. T. Ted Treves, John Guttag. Patient-Specific Seizure Onset Detection. Epilepsy and Behavior. August 2004, 5(4): 483-498.
[18] Y. Kim, Convolutional neural networks for sentence classification, 2014.