Epilepsy EEG classification method based on supervised locality preserving canonical correlation analysis

Hongming Liu; Yunyuan Gao; Jianhai Zhang; Juanjuan Zhang; Hongming Liu; Yunyuan Gao; Jianhai Zhang; Juanjuan Zhang

doi:10.3934/mbe.2022028

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 1: 624-642. doi: 10.3934/mbe.2022028

Previous Article Next Article

Research article

Epilepsy EEG classification method based on supervised locality preserving canonical correlation analysis

1.
Zhuoyue Honors College, Hangzhou Dianzi University, Hangzhou, China
2.
College of Automation, Hangzhou Dianzi University, Hangzhou, China
3.
College of Computer & Software, Hangzhou Dianzi University, Hangzhou, China
4.
Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, China
5.
Wenzhou branch, China Mobile Group Zhejiang Co, Ltd

Academic Editor: Weining Wu

Received: 09 July 2021 Accepted: 15 November 2021 Published: 18 November 2021

Existing epileptic seizure automatic detection systems are often troubled by high-dimensional electroencephalogram (EEG) features. High-dimensional features will not only bring redundant information and noise, but also reduce the response speed of the system. In order to solve this problem, supervised locality preserving canonical correlation analysis (SLPCCA), which can effectively use both sample category information and nonlinear relationships between features, is introduced. And an epileptic signal classification method based on SLPCCA is proposed. Firstly, the power spectral density and the fluctuation index of the frequency slice wavelet transform are extracted as features from the EEG fragments. Next, SLPCCA obtains the optimal projection direction by maximizing the weight correlation between the paired samples in the class and their neighbors. And the projection combination of original features in the optimal direction is the fusion feature. The fusion features are then input into LS-SVM for training and testing. This method is verified on the Bonn dataset and the CHB-MIT dataset and gets good results. On various classification tasks of Bonn data set, the proposed method achieves an average classification accuracy of 99.16%. On the binary classification task of the inter-seizure and seizure epileptic EEG of the CHB-MIT dataset, the proposed method achieves an average accuracy of 97.18%. The experimental results show that the algorithm achieves excellent results compared with several state-of-the-art methods. In addition, the parameter sensitivity of SLPCCA and the relationship between the dimension of the fusion features and the classification results are discussed. Therefore, the stability and effectiveness of the method are further verified.
- epileptic seizure,
- electroencephalogram (EEG),
- feature extraction,
- feature fusion,
- supervised locality preserving canonical correlation analysis (SLPCCA)
Citation: Hongming Liu, Yunyuan Gao, Jianhai Zhang, Juanjuan Zhang. Epilepsy EEG classification method based on supervised locality preserving canonical correlation analysis[J]. Mathematical Biosciences and Engineering, 2022, 19(1): 624-642. doi: 10.3934/mbe.2022028

Related Papers:

Abstract

Existing epileptic seizure automatic detection systems are often troubled by high-dimensional electroencephalogram (EEG) features. High-dimensional features will not only bring redundant information and noise, but also reduce the response speed of the system. In order to solve this problem, supervised locality preserving canonical correlation analysis (SLPCCA), which can effectively use both sample category information and nonlinear relationships between features, is introduced. And an epileptic signal classification method based on SLPCCA is proposed. Firstly, the power spectral density and the fluctuation index of the frequency slice wavelet transform are extracted as features from the EEG fragments. Next, SLPCCA obtains the optimal projection direction by maximizing the weight correlation between the paired samples in the class and their neighbors. And the projection combination of original features in the optimal direction is the fusion feature. The fusion features are then input into LS-SVM for training and testing. This method is verified on the Bonn dataset and the CHB-MIT dataset and gets good results. On various classification tasks of Bonn data set, the proposed method achieves an average classification accuracy of 99.16%. On the binary classification task of the inter-seizure and seizure epileptic EEG of the CHB-MIT dataset, the proposed method achieves an average accuracy of 97.18%. The experimental results show that the algorithm achieves excellent results compared with several state-of-the-art methods. In addition, the parameter sensitivity of SLPCCA and the relationship between the dimension of the fusion features and the classification results are discussed. Therefore, the stability and effectiveness of the method are further verified.

References

[1]	A. J. Durnford, W. Rodgers, F. J. Kirkham, M. A. Mullee, A. Whitney, M. Prevett, et al., Very good inter-rater reliability of engel and ilae epilepsy surgery outcome classifications in a series of 76 patients, Seizure, 20 (2011), 809–812. doi: 10.1016/j.seizure.2011.08.004. doi: 10.1016/j.seizure.2011.08.004
[2]	E. Howell, Epilepsy stigma: Moving from a global problem to a global solution, Seizure-Eur. J. Epilepsy, 19 (2010), 628–629. doi: 10.1016/j.seizure.2010.10.016. doi: 10.1016/j.seizure.2010.10.016
[3]	M. Yildiz, E. Bergİl, The investigation of channel selection effects on epileptic analysis of eeg signals, Balk. J. Electr. Comput. Eng., 3 (2015), 236–241.
[4]	A. Matin, R. A. Bhuiyan, S. R. Shafi, A. K. Kundu, M. U. Islam, A hybrid scheme using pca and ica based statistical feature for epileptic seizure recognition from eeg signal, in 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), IEEE, (2019), 301–306. doi: 10.1109/ICIEV.2019.8858573.
[5]	Y. Liu, B. Jiang, J. Feng, J. Hu, H. Zhang, Classification of EEG signals for epileptic seizures using feature dimension reduction algorithm based on LPP, Multimedia Tools Appl., 80 (2020), 30261-–30282. doi: 10.1007/s11042-020-09135-7. doi: 10.1007/s11042-020-09135-7
[6]	J. Birjandtalab, M. B. Pouyan, M. Nourani, Nonlinear dimension reduction for eeg-based epileptic seizure detection, in 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), IEEE, (2016), 595–598. doi: 10.1109/BHI.2016.7455968.
[7]	Q. Hou, Y. Liu, J. Liu, S. Sun, Epilepsy detection using random forest classification based on locally linear embedding algorithm, in 2020 5th International Conference on Control, Robotics and Cybernetics (CRC), IEEE, (2020), 202–206. doi: 10.1109/CRC51253.2020.9253455.
[8]	K. C. Chua, V. Chandran, R. Acharya, C. Lim, Automatic identification of epilepsy by hos and power spectrum parameters using eeg signals: A comparative study, in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, (2008), 3824–3827. doi: 10.1109/IEMBS.2008.4650043.
[9]	Z. Yan, A. Miyamoto, Z. Jiang, Frequency slice wavelet transform for transient vibration response analysis, Mech. Syst. Signal Process., 23 (2009), 1474–1489. doi: 10.1016/j.ymssp.2009.01.008. doi: 10.1016/j.ymssp.2009.01.008
[10]	Z. Yan, T. Tao, Z. Jiang, H. Wang, Discrete frequency slice wavelet transform, Mech. Syst. Signal Process., 96 (2017), 385–392. doi: 10.1016/j.ymssp.2017.04.019. doi: 10.1016/j.ymssp.2017.04.019
[11]	H. Hotelling, Relations between two sets of variates, in Breakthroughs in statistics, Springer, (1992), 162–190. doi: 10.1007/978-1-4612-4380-9_14.
[12]	Q. S. Sun, S. G. Zeng, Y. Liu, P. A. Heng, D. S. Xia, A new method of feature fusion and its application in image recognition, Pattern Recognition, 38 (2005), 2437–2448. doi: 10.1016/j.patcog.2004.12.013. doi: 10.1016/j.patcog.2004.12.013
[13]	T. Sun, S. Chen, J. Yang, P. Shi, A supervised combined feature extraction method for recognition, in Procedings of the IEEE International Conference on Data Mining, Pisa, Italy, Citeseer, (2008), 1043–1048.
[14]	T. Melzer, M. Reiter, H. Bischof, Appearance models based on kernel canonical correlation analysis, Pattern Recognit., 36 (2003), 1961–1971. doi: 10.1016/S0031-3203(03)00058-X. doi: 10.1016/S0031-3203(03)00058-X
[15]	T. Sun, S. Chen, Locality preserving cca with applications to data visualization and pose estimation, Image Vision Comput., 25 (2007), 531–543. doi: 10.1016/j.imavis.2006.04.014. doi: 10.1016/j.imavis.2006.04.014
[16]	S. D. Hou, Q. S. Sun, D. S. Xia, Supervised locality preserving canonical correlation analysis algorithm, Pattern Recognit. Artif. Intell., 2012, 143–149.
[17]	R. Andrzejak, K. Lehnertz, F. Mormann, C. Rieke, P. David, C. Elger, Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state, Phys. Rev. E, 2001, 061907. doi: 10.1103/PhysRevE.64.061907. doi: 10.1103/PhysRevE.64.061907
[18]	A. Shoeb, J. Guttat, Application of machine learning To epileptic seizure detection, in International Conference on Machine Learning, 2010.
[19]	R. W. Homan, J. Herman, P. Purdy, Cerebral location of international 10–20 system electrode placement, Electroencephalogr. Clin. Neurophysiol., 66 (1987), 376–382. doi: 10.1016/0013-4694(87)90206-9. doi: 10.1016/0013-4694(87)90206-9
[20]	R. J. Martis, U. R. Acharya, J. H. Tan, A. Petznick, L. Tong, C. K. Chua, et al., Application of intrinsic time-scale decomposition (itd) to eeg signals for automated seizure prediction, Int. J. Neural Syst., 23 (2013), 1350023. doi: 10.1142/S0129065713500238. doi: 10.1142/S0129065713500238
[21]	N. Ahammad, T. Fathima, P. Joseph, Detection of epileptic seizure event and onset using EEG, BioMed. Res. Int., 2014. doi: 10.1155/2014/450573. doi: 10.1155/2014/450573
[22]	R. J. Martis, J. H. Tan, C. K. Chua, T. C. Loon, S. W. J. YEO, L. Tong, Epileptic eeg classification using nonlinear parameters on different frequency bands, J. Mech. Med. Biol., 15 (2015), 1550040. doi: 10.1142/S0219519415500402. doi: 10.1142/S0219519415500402
[23]	N. S. Tawfik, S. M. Youssef, M. Kholief, A hybrid automated detection of epileptic seizures in eeg records, Comput. Electr. Eng., 53 (2016), 177–190. doi:10.1016/j.compeleceng.2015.09.001. doi: 10.1016/j.compeleceng.2015.09.001
[24]	E. Kabir, Y. Zhang, Epileptic seizure detection from eeg signals using logistic model trees, Brain Inf., 3 (2016), 93–100. doi: 10.1007/s40708-015-0030-2. doi: 10.1007/s40708-015-0030-2
[25]	R. R. Sharma, R. B. Pachori, Time-frequency representation using ievdhm-ht with application to classification of epileptic eeg signals, IET Sci., Meas. Technol., 12 (2018), 72–82.
[26]	V. Gupta, R. B. Pachori, Epileptic seizure identification using entropy of fbse based eeg rhythms, Biomed. Signal Process. Control, 53 (2019), 101569. doi: 10.1016/j.bspc.2019.101569. doi: 10.1016/j.bspc.2019.101569
[27]	H. Al-Hadeethi, S. Abdulla, M. Diykh, R. C. Deo, J. H. Green, Adaptive boost ls-svm classification approach for time-series signal classification in epileptic seizure diagnosis applications, Expert Syst. Appl., 161 (2020), 113676. doi: 10.1016/j.eswa.2020.113676. doi: 10.1016/j.eswa.2020.113676
[28]	N. Rafiuddin, Y. U. Khan, O. Farooq, Feature extraction and classification of eeg for automatic seizure detection, in 2011 International Conference on Multimedia, Signal Processing and Communication Technologies, IEEE, (2011), 184–187. doi: 10.1109/MSPCT.2011.6150470.
[29]	Y. U. Khan, N. Rafiuddin, O. Farooq, Automated seizure detection in scalp eeg using multiple wavelet scales, in 2012 IEEE international conference on signal processing, computing and control, IEEE, (2012), 1–5. doi: 10.1109/ISPCC.2012.6224361.
[30]	M. Zabihi, S. Kiranyaz, A. B. Rad, A. K. Katsaggelos, M. Gabbouj, T. Ince, Analysis of high-dimensional phase space via poincaré section for patient-specific seizure detection, IEEE Trans. Neural Syst. Rehabil. Eng., 24 (2015), 386–398. doi: 10.1109/TNSRE.2015.2505238. doi: 10.1109/TNSRE.2015.2505238
[31]	P. Thodoroff, J. Pineau, A. Lim, Learning robust features using deep learning for automatic seizure detection, in Machine learning for healthcare conference, PMLR, (2016), 178–190.
[32]	M. Z. Ahmad, A. M. Kamboh, S. Saleem, A. A. Khan, Mallat's scattering transform based anomaly sensing for detection of seizures in scalp EEG, IEEE Access, 5 (2017), 16919–16929. doi: 10.1109/ACCESS.2017.2736014. doi: 10.1109/ACCESS.2017.2736014
[33]	D. Chen, S. Wan, J. Xiang, F. S. Bao, A high-performance seizure detection algorithm based on discrete wavelet transform (dwt) and EEG, PloS one, 12 (2017), e0173138. doi: 10.1371/journal.pone.0173138. doi: 10.1371/journal.pone.0173138
[34]	J. Bonello, L. Garg, G. Garg, E. E. Audu, Effective data acquisition for machine learning algorithm in eeg signal processing, in Soft Computing: Theories and Applications, Springer, (2018), 233–244. doi: 10.1007/978-981-10-5699-4_23.
[35]	K. M. Tsiouris, S. Markoula, S. Konitsiotis, D. D. Koutsouris, D. I. Fotiadis, A robust unsupervised epileptic seizure detection methodology to accelerate large EEG database evaluation, Biomed. Signal Process. Control, 40 (2018), 275–285. doi: 10.1016/j.bspc.2017.09.029. doi: 10.1016/j.bspc.2017.09.029
[36]	M. Zhou, C. Tian, R. Cao, B. Wang, Y. Niu, T. Hu, et al., Epileptic seizure detection based on EEG signals and CNN, Front. Neuroinf., 12 (2018), 95. doi: 10.3389/fninf.2018.00095. doi: 10.3389/fninf.2018.00095
[37]	M. B. Ahmadi, A. Craik, H. F. Azgomi, J. T. Francis, J. L. Contreras-Vidal, R. T. Faghih, Real-time seizure state tracking using two channels: A mixed-filter approach, in 2019 53rd Asilomar Conference on Signals, Systems, and Computers, IEEE, (2019), 2033–2039. doi: 10.1109/IEEECONF44664.2019.9048990.
[38]	J. Wu, T. Zhou, T. Li, Detecting epileptic seizures in eeg signals with complementary ensemble empirical mode decomposition and extreme gradient boosting, Entropy, 22 (2020), 140. doi: 10.3390/e22020140. doi: 10.3390/e22020140
[39]	S. Chakrabarti, A. Swetapadma, A. Ranjan, P. K. Pattnaik, Time domain implementation of pediatric epileptic seizure detection system for enhancing the performance of detection and easy monitoring of pediatric patients, Biomed. Signal Process. Control, 59 (2020), 101930. doi: 10.1016/j.bspc.2020.101930. doi: 10.1016/j.bspc.2020.101930
[40]	L. A. Moctezuma, M. Molinas, EEG channel-selection method for epileptic-seizure classification based on multi-objective optimization, Front. Neurosci., 14 (2020), 593. doi: 10.3389/fnins.2020.00593. doi: 10.3389/fnins.2020.00593
[41]	L. A. Moctezuma, M. Molinas, Classification of low-density eeg for epileptic seizures by energy and fractal features based on emd, J. Biomed. Res., 34 (2020), 180–190. doi: 10.7555/JBR.33.20190009. doi: 10.7555/JBR.33.20190009

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)