基于判别性流形正则和域分布适配的跨被试癫痫发作检测方法

doi:10.3969/j.issn.0258-8021.2024.06.006

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1483 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Automatic detection of seizure is of great significance for epilepsy diagnosis, monitoring, and intervention treatment. Aiming to address the problems that ictal electroencephalogram (EEG) is limited and data distributions among different patients are significantly different, a cross-subject seizure detection method was proposed based on discriminative manifold regularization and domain distribution adaptation in this work. First, the EEG of patients to be tested andthelabeled EEG of other patients were used as target and source domain data, respectively, and the EEG features such as the mean, variance and sample entropy of the wavelet packet decomposition coefficients were extracted. Then, a manifold regularization containing category information of source samples and an intra-class distance minimization constraint were introduced into domain distribution adaptation. Meanwhile, the relative deviation between conditional distribution distance and marginal distribution distance was adopted to dynamically adjust the distribution weight. Finally, pattern classification and seizure detection of target data were realized using the random forest classifier trained by source domain samples after space projection. The detection performance of the proposed method was validated using scalp EEG data from 24 patients in the CHB-MIT database and compared with existing domain adaptation algorithms. The average detection sensitivity and accuracy achieved by the proposed method were 94.94% and 95.66%, respectively, which were 15.07% and 9.98% higher than the CORAL algorithm using second-order statistic alignment, and 3.90% and 2.52% higher than the BDA algorithm that only performs balanced distribution adaptation. In conclusion, the combination of discriminative manifold regularization and domain distribution adaptation reduced the distribution differences between EEG signals from different patients and effectively utilized the discriminative information in the manifold structure and labels of the source domain data, providing a new idea for the research of cross-subject epileptic seizure detection.

Key words： electroencephalogram (EEG) epileptic seizure detection cross-subject domain distribution adaptation manifold regularization

Received: 30 July 2023

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhang Yanli
	Qiu Wenlong
	Zhou Weidong

Cite this article:

Zhang Yanli,Qiu Wenlong,Zhou Weidong. Cross-Subject Epileptic Seizure Detection Method Based on Discriminative Manifold Regularizationand Domain Distribution Adaptation[J]. Chinese Journal of Biomedical Engineering, 2024, 43(6): 693-701.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2024.06.006 OR http://cjbme.csbme.org/EN/Y2024/V43/I6/693

[1] Wang Gang, Wang Dong, Du Changwang, et al. Seizure prediction using directed transfer function and convolution neural network on intracranial EEG [J]. IEEE Trans Neural Syst Rehabil Eng, 2020, 28(12): 2711-2720.
[2] Acharya UR, Sree SV, Swapna G, et al. Automated EEG analysis of epilepsy: a review [J]. Knowledge-Based Syst, 2013, 45: 147-165.
[3] 徐嘉阳,杨婷婷,李雯,等. 基于自适应多尺度脑功能连接的局灶性癫痫发作检测方法研究 [J]. 中国生物医学工程学报, 2022, 41(4): 393-401.
[4] Liu Guoyang, Tian Lan, Zhou Weidong. Patient-independent seizure detection based on channel-perturbation convolutional neural network and bidirectional long short-term memory [J]. Int J Neural Syst, 2022, 32(6): 2150051.
[5] Cheriane R, Kanaga G. Theoretical and methodological analysis of EEG based seizure detection and prediction: an exhaustive review [J]. J Neurosci Methods, 2022, 369: 109483.
[6] Hassan KM, Islam MR, Nguyen TT, et al. Epileptic seizure detection in EEG using mutual information-based best individual feature selection [J]. Expert Syst Appl, 2022, 193: 116414.
[7] Zeng Jiale, Tan Xiaodan, Zhan Chang'an. Automatic detection of epileptic seizure events using the time-frequency features and machine learning [J]. Biomed Signal Process Control, 2021, 69: 102916.
[8] Zhou Jiazheng, Liu Li, Leng Yan, et al. Both cross-patient and patient-specific seizure detection based on self-organizing fuzzy logic [J]. Int J Neural Syst, 2022, 32(6): 2250017.
[9] Shoeibi A, Khodatars M, Ghassemi N, et al. Epileptic seizures detection using deep learning techniques: a review [J]. Int J Environ Res Public Health, 2021, 18(11): 5780.
[10] Zhang Yanli, Yao Shuxin, Yang Rendi, et al. Epileptic seizure detection based on bidirectional gated recurrent unit network [J]. IEEE Trans Neural Syst Rehabil Eng, 2022, 30: 135-145.
[11] Chan Hsiao-Lung, Yuan Ouyang, Huang Po-Jung, et al. Deep neural networks for the detection of temporal-lobe epileptiform discharges from scalp electroencephalograms [J]. Biomed Signal Process Control, 2023, 84: 104698.
[12] Si Xiaopeng, Yang Zhuobin, Zhang Xingjian, et al. Patient-independent seizure detection based on long-term iEEG and a novel lightweight CNN [J]. J Neural Eng, 2023, 20(1): 016037.
[13] Gao Bin, Zhou Jiazheng, Yang Yuying, et al. Generative adversarial network and convolutional neural network-based EEG imbalanced classification model for seizure detection [J]. Biocybern Biomed Eng, 2022, 42(1): 1-15.
[14] Kouw WM, Loog M. A review of domain adaptation without target labels [J]. IEEE Trans Pattern Anal Mach Intell, 2021, 43(3): 766-785.
[15] 沈雷,耿馨佚,王守岩. 基于迁移学习和空洞卷积的癫痫状态识别方法 [J]. 中国生物医学工程学报, 2020, 39(6): 700-710.
[16] Peng Peizhen, Xie Liping, Zhang Kanjian, et al. Domain adaptation for epileptic EEG classification using adversarial learning and Riemannian manifold [J]. Biomed Signal Process Control, 2022, 75: 103555.
[17] Goldberger A, Amaral L, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals [J]. Circulation, 2000, 101(23): e215-e220.
[18] Wang Jindong, Chen Yiqiang, Hao Shuji, et al. Balanced distribution adaptation for transfer learning [C]//Proceedings of 2017 IEEE International Conference on Data Mining. Los Alamitos: IEEE Computer Society Press, 2017: 1129-1134.
[19] Pan SJ, Tsang IW, Kwok JT, et al. Domain adaptation via transfer component analysis [J]. IEEE Transactions on Neural Networks, 2011, 22(2): 199-210.
[20] Long Mingsheng, Wang Jianmin, Ding Guiguang, et al. Transfer feature learning with joint distribution adaptation [C]//Proceedings of 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 2200-2207.
[21] 史玉皓,田建艳,刘军军,等. 基于流形结构的多源自适应迁移学习算法及应用研究 [J]. 控制与决策, 2023, 38(3): 797-804.
[22] 郭方方,吕宏武,任威霖,等. 基于有监督判别投影的网络安全数据降维算法 [J]. 通信学报, 2021, 42(6): 84-93.
[23] 吴琳琳,彭国华,延伟东. 基于判别性样本选择的无监督领域自适应方法 [J]. 西北工业大学学报, 2020, 38(4): 828-837.
[24] Sun Baochen, Feng Jiashi, Saenko K. Return of frustratingly easy domain adaptation [C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2016: 2058-2065.
[25] 雷子豪,温广瑞,周桥,等. 基于MMDFE-DA的滚动轴承故障诊断方法 [J]. 振动、测试与诊断, 2022, 42(1): 182-189.
[26] Wei Zuochen, Zou Junzhong, Zhang Jian, et al. Automatic epileptic EEG detection using convolutional neural network with improvements in time-domain [J]. Biomed Signal Process Control, 2019, 53: 101551.
[27] Wang Xiaoshuang, Wang Xiulin, Liu Wenya, et al. One dimensional convolutional neural networks for seizure onset detection using long-term scalp and intracranial EEG [J]. Neurocomputing, 2021, 459: 212-222.
[28] Cura OK, Akan A. Classification of epileptic EEG signals using synchrosqueezing transform and machine learning [J]. Int J Neural Syst, 2021, 31(5): 1-17.
[29] Duan Lijuan, Wang Zeyu, Qiao Yuanhua, et al. An automatic method for epileptic seizure detection based on deep metric learning [J]. IEEE J Biomed Health Inform, 2022, 26(5): 2147-2157.
[30] Guo Yao, Jiang Xinyu, Tao Linkai, et al. Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble [J]. IEEE Trans Neural Syst Rehabil Eng, 2022, 30: 915-924.