北京生物医学工程

基于AR模型和Lempel-Ziv复杂度的癫痫发作预报

Epileptic seizure prediction based on AR model and LZC

作者：韩敏曹占吉孙磊磊洪晓军

单位：大连理工大学电子信息与电气工程学部(辽宁大连 116023)

分类号：

出版年·卷·期（页码）：2012·31·3（273-277）

摘要：

目的癫痫是由多种病因引起的慢性脑功能障碍综合征，及时的发作预报，对于建立新的治疗方法和改善患者的生活质量有着至关重要的作用。目前大部分脑电分析算法存在计算速度慢、适应性差等问题，无法满足癫痫脑电发作预报的要求。方法本文应用自回归模型对脑电信号进行特征提取，支持向量机（support vector machine, SVM）作脑电各个时期分类器，并与Lempel-Ziv复杂度分析计算相结合，准确识别发作前期，以实现癫痫的发作预报。结果应用弗莱堡大学数据对上述方法的有效性进行验证。仿真结果表明，该方法得到的发作漏检率、误报率较低，预报提前时间较长。结论将AR模型和Lempel-Ziv复杂度相结合，对癫痫发作预报的实现，有一定参考价值和意义。

Objective Epilepsy is a chronic brain dysfunction syndrome caused by many diseases. The predictions of epilepsy seizure are significant for both the establishment of new treatment methods and the improvement of the patients’ life qualities. The current EEG analysis algorithm cannot meet the requirement of epileptic seizure prediction for the slow computation and the poor adaptability. Methods This paper applies autoregressive(AR) model for feature extraction, a support vector machine as a classifier, and combines Lempel-Ziv complexity(LZC) to identify preictal accurately. Results Using the data from Freiburg University, the simulation results show that the methods used in this paper achieve a lower false alarm rate, a lower failed reporting rate and a longer lead time. Conclusions This paper provides references for the realization of the epileptic seizure prediction by combining AR model and LZC.

参考文献：

［1］李颖洁, 邱意弘, 朱贻盛. 脑电信号分析方法及其应用［M］. 北京：科学出版社, 2009.
Li Yingjie,Qiu Yihong,Zhu Yisheng.Naodian Xinhao Fenxi Fangfa Jiqi Yingyong［M］. beijing:Science Press, 2009.
［2］刘旋, 高小榕，张国君，等. 量化脑电分析方法及其在癫痫易发作期检测中的应用［J］. 北京生物医学工程， 2007, 26(3): 274-279.
Liu Xuan, Gao Xiaorong, Zhang Guojun,et al. Quantitative electroencephalogram analysis methods and its application in epileptic seizure vulnerable period detection［J］. Beijing Biomedical Engineering, 2007, 26(3): 274-279.
［3］汪春梅, 邹俊忠，张见,等. 基于多分辨分析的脑电癫痫波自动检测［J］. 计算机应用研究,2009, 26(8): 2958-2961.
Wang Chunmei, Zou Junzhong, Zhang Jian, et al. Automatic detection of epileptiform wave in EEG by multi-resolution analysis［J］. Application Research of Computers, 2009, 26(8): 2958-2961.
［4］Brunner C, Scherer R, Graimann B. Online control of a brain-computer interface using phase synchronization［J］. IEEE Transactions on Biomedical Engineering, 2006, 53(12): 2501-2506.
［5］Mirzaei A, Ayatollahi A, Gifani,P, et al. EEG Analysis based on wavelet-spectral entropy for epileptic seizures detection［C］. 2010 3rd International Conference on Biomedical Engineering and Informatics, 2010: 878-882.
［6］Li T, Hong J. EEG classification based on small-world neural network for brain-computer interface［C］. Natural Comutation(ICNC), 2010, 5(1): 252-256.
［7］蔡冬梅, 周卫东, 刘凯,等. 基于Hurst指数和SVM的癫痫脑电检测方法［J］. 中国生物医学工程学报,2010, 29(6): 836-840.
Cai Dongmei, Zhou Weidong, Liu Kai, et al. Approach of epileptic EEG detection based on Hurst exponent and SVM［J］. Chinese Journal of Biomedical Engineering,2010, 29(6), 836-840.］
［8］马颖颖, 张泾周, 吴疆. 脑电信号处理方法［J］. 北京生物医学工程, 2007, 26(1): 99-102.
Ma Yingying, Zhang Jingzhou, Wu Jiang. The modern processing method of EEG signal［J］. Beijing Biomedical Engineering, 2007, 26(1): 99-102.］
［9］Padmasai Y;SubbaRso K;Malini V. Linear Prediction Modelling for the Analysis of the Epileptic EEG［C］. Advances in Computer Engineering (ACE),2010 International Conference. 2010:6-9.
［10］Schneider, Mustaro M, Lima PN, et al. Automatic recognition of eplilepic seizure in EEG via support vector machine and dimension fractal［C］. International Joint Conference on Neural Network, 2009: 2841-2845.
［11］EEG Database at Epilepsy Center of the University Hospital of Freiburg, Germany［EB/OL］.(2003). https://epilepsy.uni-freiburg.de/freiburg-seizure-prediction-project/eeg.
［12］Chisci L, Mavino A, Perferi G. Real-time epileptic seizure prediction using AR models and support vector machines［J］. IEEE Transactions on Biomedical Engineering, 2010, 57(5): 1124-1132.
［13］朱天桥, 黄力宇. 单导癫痫脑电模糊特征提取的支持向量机发作预测［J］. 仪器仪表学报, 2010, 31(11): 2434-2439.
Zhu Tianqiao, Huang Liyu. Epileptic seizure prediction from single-channel scalp EEG using support vector machine based on fuzzy feature extracted with empirical mode decomposition［J］. Chinese Journal of Scientific Instrument, 2010, 31(11): 2434-2439.］
［14］朱俊玲，林宏，宿长军,等. 小波能量评价EEG的不同成分对癫痫发作预报的价值［J］. 生物物理学报,2003, 19(1): 73-78 .
Zhu Junling, Lin Hong, Su Changjun, et al. The roles of different components of eggs for seizure prediction-wavelet energy evaluation［J］. Acta Biophysica Sinica, 2003, 19(1): 73-78.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录