Multi-view Epilepsy Detection Algorithm Combining Deep and Shallow Features

doi:10.3778/j.issn.1673-9418.1906013

Abstract

Abstract:

Epilepsy is a common neurological illness. By analyzing the electroencephalo-graph (EEG) signals of patients with epilepsy, their conditions can be monitored so that seizure can be detected and intervened in time. In epilepsy research, how to obtain effective features and construct an effective classifier is the key to epilepsy detection and recognition. In order to obtain better epilepsy detection effect, this paper proposes a multi-view seizure detection algorithm that combines deep and shallow features. The method first uses FFT (fast Fourier transform) and WPD (wavelet packet decomposition) to obtain the shallow features in the frequency domain and the time-frequency domain. Then, CNN (convolutional neural network) is used to obtain the deep features in the frequency domain and the time-frequency domain. Further the multi-view TSK fuzzy system is used to construct the classification model of shallow and deep features. Experimental studies show that in the detection of EEG signal epilepsy, the effects of shallow features and deep features proposed in this paper are more than 1% higher than those of commonly used feature extraction methods such as PCA (principal component analysis), LDA (linear discriminant analysis) and etc. The multi-view epileptic detection algorithm which combines deep features and shallow features has a classification effect higher than that of the single-view algorithm by more than 1%, and the average detection effect is more than 5% higher than that of the single-view algorithm.

Key words: EEG, epilepsy detection, multi-view, feature extraction, deep learning

摘要：

癫痫是一种常见的精神疾病。通过分析EEG信号可以监控癫痫病人的状态，在病人发病时及时地发现并且介入来保护病人的生命安全。在癫痫检测研究中，如何获得有效的特征和构建有效的分类器是癫痫检测和识别的关键。为了获得更好的癫痫检测效果，提出了一种融合深度和浅层特征的多视角癫痫检测算法。该算法首先使用FFT和WPD来获取EEG信号频域和时频域的浅层特征；然后使用CNN网络学习得到频域和时频域的深度特征；进一步使用多视角TSK模糊系统对浅层和深度特征进行分类模型的构建。实验研究表明，在EEG信号癫痫检测方面，提出的浅层特征和深度特征的效果与PCA、LDA等常用的特征提取方法相比均高出1%以上；使用融合深度特征和浅层特征的多视角癫痫检测算法的分类效果比单视角算法的检测效果均高出1%以上，比单视角算法的平均检测效果高出5%以上。

关键词: EEG, 癫痫检测, 多视角, 特征提取, 深度学习

TIAN Xiaobin, DENG Zhaohong, WANG Shitong. Multi-view Epilepsy Detection Algorithm Combining Deep and Shallow Features[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(10): 1712-1726.

田晓彬，邓赵红，王士同. 融合深度和浅层特征的多视角癫痫检测算法[J]. 计算机科学与探索, 2020, 14(10): 1712-1726.

References

[1] Deng Z H, Choi K S, Jiang Y Z, et al. Generalized hidden-mapping ridge regression, knowledge-leveraged inductive transfer learning for neural networks, fuzzy systems and kernel methods[J]. IEEE Transactions on Cybernetics, 2014, 44(12): 2585-2599.
[2] Zhang Y, Zhang Y T, Wang J Y, et al. Comparison of class-ification methods on EEG signals based on wavelet packet decomposition[J]. Neural Computing and Applications, 2015, 26(5): 1217-1225.
[3] Fu K, Qu J F, Chai Y, et al. Classification of seizure based on the time-frequency image of EEG signals using HHT and SVM[J]. Biomedical Signal Processing and Control, 2014, 13: 15-22.
[4] Bhattacharyya A, Pachori R B. A multivariate approach for patient specific EEG seizure detection using empirical wavelet transform[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(9): 2003-2015.
[5] Deng Z H, Xu P, Xie L X, et al. Transductive joint-knowledge- transfer TSK FS for recognition of epileptic EEG signals[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26(8): 1481-1494.
[6] Jiang Y Z, Deng Z H, Chung F L, et al. Recognition of epileptic EEG signals using a novel multiview TSK fuzzy system[J]. IEEE Transactions on Fuzzy Systems, 2017, 25(1): 3-20.
[7] Villar J R, Menéndez M, Cal E D L, et al. Identification of abnormal movements with 3D accelerometer sensors for seizure recognition[J]. Journal of Applied Logic, 2017, 24: 54-61.
[8] Sugianela Y, Sutino Q L, Herumurti D. EEG classification for epilepsy based on wavelet packet decomposition and random forest[J]. Jurnal Ilmu Komputer dan Informasi, 2018, 11: 27-33.
[9] Nasehi S, Pourghassem H, Etesami A. Online epilepsy diagnosis based on analysis of EEG signals by hybrid adaptive filtering and higher-order crossings[C]//Proceedings of the 2011 Inter-national Conference on Intelligent Computation & Bio-medical Instrumentation, Wuhan, Dec 14-17, 2011. Washington: IEEE Computer Society, 2011: 192-195.
[10] Antoniades A, Spyrou L, Took C C, et al. Deep learning for epileptic intracranial EEG data[C]//Proceedings of the 26th IEEE International Workshop on Machine Learning for Signal Processing, Salerno, Sep 13-16, 2016. Piscataway:IEEE, 2016: 1-6.
[11] Cecotti H, Gr?ser A. Convolutional neural network with embedded Fourier transform for EEG classification[C]// Proceedings of the 19th International Conference on Pattern Recognition, Tampa, Dec 8-11, 2008. Piscataway: IEEE, 2008: 1-4.
[12] Mirowski P, Madhavan D, Lecun Y, et al. Classification of patterns of EEG synchronization for seizure prediction[J]. Clinical Neurophysiology, 2009, 120(11): 1927-1940.
[13] Xu C, Tao D C, Xu C. A survey on multi-view learning[J]. arXiv:1304.5634, 2013.
[14] Sun S. A survey of multi-view machine learning[J]. Neural Computing & Applications, 2013, 23(7/8): 2031-2038.
[15] Spyrou L, Kouchaki S, Sanei S. Multiview classification and dimensionality reduction of scalp and intracranial EEG data through tensor factorisation[J]. Journal of Signal Proce-ssing Systems, 2016, 90: 273-284.
[16] Jiang Y Z, Wu D R, Deng Z H, et al. Seizure classification from EEG signals using transfer learning, semi-supervised learning and TSK fuzzy system[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017, 25(12): 2270-2284.
[17] Wang G J, Deng Z H, Choi K S. Detection of epileptic seizures in EEG signals with rule-based interpretation by random forest approach[C]//LNCS 9227: Proceedings of the 11th International Conference on Advanced Intelligent Computing Theories and Applications, Fuzhou, Aug 20-23, 2015. Berlin, Heidelberg: Springer, 2015: 738-744.
[18] Zhang Y, Liu B, Ji X M, et al. Classification of EEG signals based on autoregressive model and wavelet packet decom-position[J]. Neural Processing Letters, 2017, 45(2): 365-378.
[19] Yang C J, Deng Z H, Choi K S, et al. Takagi-Sugeno-Kang transfer learning fuzzy logic system for the adaptive reco-gnition of epileptic electroencephalogram signals[J]. IEEE Transactions on Fuzzy Systems, 2016, 24(5): 1079-1094.
[20] Heffernan R, Paliwal K, Lyons J, et al. Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning[J]. Scientific Reports, 2015, 5: 11476.
[21] Xu J, Xiang L, Liu Q S, et al. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images[J]. IEEE Transactions on Medical Imaging, 2016, 35(1): 119-130.
[22] Suwicha J, Setha P N, Pasin I. EEG-based emotion reco-gnition using deep learning network with principal component based covariate shift adaptation[J]. The Scientific World Journal, 2014: 627892.
[23] Spencer M, Eickholt J, Cheng J. A deep learning network approach to ab initio protein secondary structure prediction[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2015, 12(1): 103-112.
[24] Plis S M, Hjelm D R, Ruslan S, et al. Deep learning for neuroimaging: a validation study[J]. Frontiers in Neuroscience, 2014, 2014: 1-10.
[25] An X, Kuang D P, Guo X J, et al. A deep learning method for classification of EEG data based on motor imagery[C]//LNCS 8590: Proceedings of the 10th International Conference on Intelligent Computing in Bioinformatics, Taiyuan, Aug 3-6, 2014. Berlin, Heidelberg: Springer, 2014: 203-210.
[26] Alipanahi B, Delong A, Weirauch M T, et al. Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning[J]. Nature Biotechnology, 2015, 33(8): 831-838.
[27] Ning F, Delhomme D, LeCun Y, et al. Toward automatic phenotyping of developing embryos from videos[J]. IEEE Transactions on Image Processing, 2005, 14(9): 1360-1371.
[28] Cecotti H, Gr?ser A. Convolutional neural networks for P300 detection with application to brain-computer interfaces[J]. IEEE Transactions on Pattern Analysis and Machine Inte-lligence, 2011, 33(3): 433-445.
[29] S?nderby S K, S?nderby C K, Nielsen H, et al. Con-volutional LSTM networks for subcellular localization of proteins[C]//LNCS 9199: Proceedings of the 2nd International Conference on Algorithms for Computational Biology, Mexico City, Aug 4-5, 2015. Berlin, Heidelberg: Springer, 2015: 68-80.
[30] Graves A, Schmidhuber J. Offline handwriting recognition with multidimensional recurrent neural networks[C]//Pro-ceedings of the 23rd Annual Conference on Neural Information Processing Systems, Vancouver, Dec 8-11, 2008. Red Hook: Curran Associates, 2009: 545-552.
[31] Davidson P R, Jones R D, Peiris M T R. EEG-based lapse detection with high temporal resolution[J]. IEEE Transactions on Biomedical Engineering, 2007, 54(5): 832-839.
[32] Lee S, Choi M, Choi H S, et al. FingerNet: deep learning-based robust finger joint detection from radiographs[C]//Proceedings of the 2015 IEEE Biomedical Circuits and Systems Conference, Atlanta, Oct 22-24, 2015. Piscataway:IEEE, 2015: 1-4.
[33] Yin Q Y, Wu S, Wang L. Incomplete multi-view clustering via subspace learning[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management, Melbourne, Oct 19-23, 2015. New York: ACM, 2015: 383-392.
[34] Hotelling H. Relations between two sets of variates[M]//Breakthroughs in Statistics. New York: Springer, 1992: 162-190.
[35] Blum A, Mitchell T M. Combining labeled and unlabeled data with co-training[C]//Proceedings of the 11th Annual Conference on Computational Learning Theory, Madison, Jul 24-26, 1998. New York: ACM, 1998: 92-100.
[36] Hardoon D R, Shawetaylor J. Sparse canonical correlation analysis[J]. Machine Learning, 2011, 83(3): 331-353.
[37] Sun S L, Shawe-Taylor J. Sparse semi-supervised learning using conjugate functions[J]. Journal of Machine Learning Research, 2010, 11: 2423-2455.
[38] Bashivan P, Bidelman G M, Yeasin M. Spectrotemporal dynamics of the EEG during working memory encoding and maintenance predicts individual behavioral capacity[J]. European Journal of Neuroscience, 2014, 40(12): 3774-3784.
[39] Jensen O. Frontal theta activity in humans increases with memory load in a working memory task[J]. European Journal of Neuroscience, 2002, 15(8): 1395-1399.
[40] Hu D Y, Li W, Chen X. Feature extraction of motor imagery EEG signals based on wavelet packet decomposition[C]// Proceedings of the 2011 IEEE/ICME International Con-ference on Complex Medical Engineering, Harbin, May 22-25, 2011. Piscataway: IEEE, 2011: 694-697.
[41] Liang F M, Liu C H, Carroll R J. Stochastic approximation in Monte Carlo computation[J]. Journal of the American Statistical Association, 2007, 102(477): 305-320.
[42] Deng Z H, Chung F L, Wang S T. Robust relief-feature weighting, margin maximization, and fuzzy optimization[J]. IEEE Transactions on Fuzzy Systems, 2010, 18(4): 726-744.
[43] Zhou W, Liu Y, Yuan Q, et al. Epileptic seizure detection using lacunarity and Bayesian linear discriminant analysis in intracranial EEG[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(12): 3375-3381.
[44] Shoeb A H. Application of machine learning to epileptic seizure onset detection and treatment[D]. Cambridge: Mas-sachusetts Institute of Technology, 2009: 184-187.
[45] Rafiuddin N, Khan Y U, Farooq O. Feature extraction and classification of EEG for automatic seizure detection[C]// Proceedings of the 2011 International Conference on Multi-media, Signal Processing and Communication Technologies, Aligarh, Dec 17-19, 2011. Piscataway: IEEE, 2011: 184-187.
[46] Khan Y U, Rafiuddin N, Farooq O. Automated seizure detection in scalp EEG using multiple wavelet scales[C]//Proceedings of the 2012 IEEE International Conference on Signal Processing, Beijing, Oct 21-25, 2012. Piscataway:IEEE, 2012: 1-5.
[47] Kiranyaz S, Ince T, Zabihi M, et al. Automated patient-specific classification of long-term electroencephalography[J]. Journal of Biomedical Informatics, 2014, 49: 16-31.
[48] Zabihi M, Kiranyaz S, Bahrami Rad A, et al. Analysis of high-dimensional phase space via Poincaré section for patient-specific seizure detection[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2016, 24(3): 386-398.
[49] Samiee K, Kiranyaz S, Gabbouj M, et al. Long-term epileptic EEG classification via 2D mapping and textural features[J]. Expert Systems with Applications, 2015, 42(20): 7175-7185.
[50] Yao X H, Li X J, Ye Q, et al. A robust deep learning app-roach for automatic seizure detection[J]. arXiv:1812.06562,2018.
[51] Yao X H, Cheng Q, Zhang G Q. A novel independent RNN approach to classification of seizures against non-seizures[J]. arXiv:1903.09326, 2019.
[52] Ke H J, Chen D, Li X L, et al. Towards brain big data classification: epileptic EEG identification with a lightweight VGGNet on global MIC[J]. IEEE Access, 2018, 6: 14722-14733.