基于最大相关和最小冗余准则及极限学习机的癫痫发作检测方法

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3614-3617.

基于最大相关和最小冗余准则及极限学习机的癫痫发作检测方法

张新静¹,²,³,徐欣⁴,凌至培⁴,黄永志²,王守岩²,王心醉²

1. 中国科学院长春光学精密机械与物理研究所,长春130000；
2. 中国科学院苏州生物医学工程技术研究所,江苏苏州 215163
3. 中国科学院大学,北京100049
4. 中国人民解放军总医院,北京100853

收稿日期:2014-06-23 修回日期:2014-08-09 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 张新静
作者简介:张新静(1989-）,女,河北衡水人,硕士,主要研究方向:癫痫脑电信号的状态识别；徐欣(1971-）,女,湖北十堰人,医师,硕士,主要研究方向:癫痫和运动障碍性疾病的神经电生理；凌至培(1962-),男,安徽合肥人,主任医师,硕士,主要研究方向:难治性癫痫的评估、外科治疗；黄永志(1991-）,男,安徽六安人,博士,主要研究方向:神经解码、脑网络、模式识别；王心醉(1979-）,男,吉林长春人,副研究员,博士,主要研究方向:生物医学信号处理；王守岩(1972-）,男,黑龙江克山人,研究员,博士,主要研究方向:生物医学信号处理、神经工程。
基金资助:
中国科学院“百人计划”项目

Seizure detection based on max-relevance and min-redundancy criteria and extreme learning machine

ZHANG Xinjing¹,²,³,XU Xin⁴,LING Zhipei⁴,HUANG Yongzhi²,WANG Shouyan²,WANG Xinzui²

1. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun Jilin 130000,China;
2. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou Jiangsu 215163, China;
3. University of Chinese Academy of Sciences, Beijing 100049, China;
4. The General Hospital of Chinese Peoples Liberation Army, Beijing 100853, China

Received:2014-06-23 Revised:2014-08-09 Online:2014-12-01 Published:2014-12-31
Contact: ZHANG Xinjing

摘要/Abstract

摘要：

癫痫发作检测可以实现脑电分类和病灶定位,对癫痫的临床治疗具有重要意义。针对大数据量、高特征值空间长程脑电的快速和准确分类问题,提出一种基于最大相关和最小冗余准则及极限学习机的癫痫发作检测方法。对脑电信号进行短时傅里叶变换,并选取能量时频分布为特征,利用基于最大相关和最小冗余准则的方法进行特征选择,并使用极限学习机、支持向量机和反向传播算法对癫痫不同状态进行分类和判别。实验结果表明,极限学习机的分类准确率和训练速度两方面性能优于支持向量机和反向传播算法,发作间期和发作期的分类准确率达到98%以上,训练时间仅为0.8s,所提方法能够实时准确地检测癫痫发作。

Abstract:

The seizure detection is important for the localization and classification of epileptic seizures. In order to solve the problem brought by large amount of data and high feature space in EEG (Electroencephalograph) for quickly and accurately detecting the seizures, a method based on max-Relevance and Min-Redundancy (mRMR) criteria and Extreme Learning Machine (ELM) was proposed. The time-frequency measures by Short-Time Fourier Transform (STFT) were extracted as features, and the large set of features were selected based on max-relevance and min-redundancy criteria. The states were classified using the extreme learning machine, Support Vector Machine (SVM) and Back Propagation (BP) algorithm. The result shows that the performance of ELM is better than SVM and BP algorithms in terms of computation time and classification accuracy. The classification accuracy rate of interictal durations and seizures can reach more than 98%, and the computation efficiency is only 0.8s. This approach can detect epileptic seizures accurately in real-time.

中图分类号:

TP183

张新静徐欣凌至培黄永志王守岩王心醉. 基于最大相关和最小冗余准则及极限学习机的癫痫发作检测方法[J]. 计算机应用, 2014, 34(12): 3614-3617.

ZHANG Xinjing XU Xin LING Zhipei HUANG Yongzhi WANG Shouyan WANG Xinzui. Seizure detection based on max-relevance and min-redundancy criteria and extreme learning machine[J]. Journal of Computer Applications, 2014, 34(12): 3614-3617.

参考文献

［1］LITT B, ESTELLER R, ECHAUS J, et al. Epileptic seizures may begin hours in advance of clinical onset: a report of five patients ［J］. Neuron, 2001, 30(1): 51-64.
［2］MORMANN F, ANDRZEJAK R G, ELGER C E, et al. Seizure prediction: the long and winding road ［J］. Brain, 2007, 130(2): 314-333.
［3］PENG H C, LONG F H, DING C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238.
［4］CORTES C, VAPNIK V. Support-vector networks ［J］. Machine Learning, 1995, 20(3): 273-297.
［5］YUAN Q, ZHOU W, LI S, et al. Approach of EEG detection based on ELM and approximate entropy ［J］. Chinese Journal of Scientific Instrument, 2012, 33(3): 514-519.(袁琦, 周卫东, 李淑芳, 等.基于ELM和近似熵的脑电信号检测方法［J］. 仪器仪表学报, 2012, 33(3): 514-519.)
［6］HUANG G B, CHEN L, SIEW C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes ［J］. IEEE Transactions on Neural Networks, 2006, 17(4): 879-892.
［7］HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications［J］. Neurocomputing, 2006, 70(1/2/3): 489-501.
［8］QU H, GOTMAN J. A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning device ［J］. IEEE Transactions on Biomedical Engineering, 1997, 44(2): 115-122.
［9］TZALLAS A T, TSIPOURAS M G, FOTIADIS D I. Epileptic seizure detection in EEGs using time-frequency analysis ［J］. IEEE Transactions on Information Technology in Biomedicine, 2009, 13(5): 703-710.
［10］MORMANN F, KREUZ T, RIEKE C, et al. On the predictability of epileptic seizures ［J］. Clinical Neurophysiology, 2005, 116(3): 569-587.
［11］CHANG C C, LIN C J. LIBSVM: a library for support vector machines ［J］. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):1-39.
［12］LI G, WANG W, ZHANG S. Application of SVM in EEG signal classification［J］. Journal of Computer Applications, 2006, 26(6): 1431-1433,1436.(李钢, 王蔚, 张胜. 支持向量机在脑电信号分类中的应用［J］. 计算机应用, 2006, 26(6): 1431-1433,1436.)
［13］JIA L, ZHANG X. Analysis and improvements of BP algorithm［J］. Computer Technology and Development, 2006, 16(10): 101-103,107. (贾丽会, 张修如. BP算法分析与改进［J］. 计算机技术与发展, 2006, 16(10):101-103,107.)
［14］WANG L, GUO H, YU X, et al. Responsive electrical stimulation suppresses epileptic seizures in rats［J］. PLoS One, 2012, 7(5):1-7.
［15］ESTELLER R, ECHAUS J, DALESSANDRO M, et al. Continuous energy variation during the seizure cycle: towards an on-line accumulated energy ［J］. Clinical Neurophysiology, 2005, 116(3): 517-526.
［16］LEHNERTZ K, LITT B. The first international collaborative workshop on seizure prediction: summary and data description［J］. Clinical Neurophysiology, 2005, 116(3): 493-505.

[1]	杜航原郝思聪王文剑. 结合图自编码器与聚类的半监督表示学习方法[J]. 计算机应用, 0, (): 0-0.
[2]	张建严珂马祥. 基于神经网络的复杂垃圾信息过滤算法分析[J]. 计算机应用, 0, (): 0-0.
[3]	潘仁志钱付兰赵姝张燕平. 基于卷积神经网络交互的用户属性偏好建模的推荐模型[J]. 计算机应用, 0, (): 0-0.
[4]	杨书新, 张楠. 融合情感词典与上下文语言模型的文本情感分析[J]. 计算机应用, 2021, 41(10): 2829-2834.
[5]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[6]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[7]	刘志华陈文洁陈爱斌. 基于自注意力机制时频谱同源特征融合的鸟鸣声分类[J]. 计算机应用, 0, (): 0-0.
[8]	王颖洁朱久祺汪祖民白凤波弓箭. 自然语言处理在情感分析领域应用综述[J]. 计算机应用, 0, (): 0-0.
[9]	余晓鹏何儒汉黄晋张俊杰胡新荣. 基于改进Inception结构的知识图谱嵌入模型[J]. 计算机应用, 0, (): 0-0.
[10]	陈伟杨燕. 基于指针网络的抽取生成式摘要生成模型[J]. 计算机应用, 0, (): 0-0.
[11]	张继杰杨艳刘勇. 利用初始残差和解耦操作的自适应深层图卷积[J]. 计算机应用, 0, (): 0-0.
[12]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[13]	张国辉, 陆熙熙, 胡一凡, 孙靖贺. 基于改进帝国竞争算法的柔性作业车间机器故障重调度[J]. 计算机应用, 2021, 41(8): 2242-2248.
[14]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[15]	刘欢, 李晓戈, 胡立坤, 胡飞雄, 王鹏华. 基于知识图谱驱动的图神经网络推荐模型[J]. 计算机应用, 2021, 41(7): 1865-1870.