基于多尺度排列熵的脑电信号分类
|
摘要
头皮脑电(electroencephalogram,EEG)中包含了大量的生理和病理信息,在癫痫等脑科疾病的诊断中起着非常重要的作用。当前临床上对EEG信号的分析主要以临床医师目测分析为主,这使临床医师任务繁重,且分析结果没有定量化的标准。因此,癫痫脑电信号的自动化分类在当前临床应用上有着巨大的潜力。提出一种自动检测癫痫发作信号的方法,基于多尺度排列熵结合极限学习机分类器来识别癫痫脑电信号和正常脑电信号。实验结果表明这种自动识别癫痫脑电信号的方法不仅分类精度高,且计算速度快,对于癫痫发作的实时检测应用提供更多的可行性。
Electroencephalogram(EEG) contains a lot of physiological and pathological information and plays a very important role in the diagnosis of brain diseases such as epilepsy. The current clinical analysis of EEG signal is mainly based on the visual analysis of clinicians, so that the tasks of clinicians are onerous, and there is no quantitative standard for the analysis results. Therefore, automatic classification of EEG signal of epilepsy has great potential in current clinical applications. In this paper, a method for automatic detection of epileptic seizure signal is proposed. EEG signal of epilepsy and normal EEG signal can be recognized based on multiscale permutation entropy combined with the extreme learning machine classifier. The experimental results show that this method for automatic EEG recognition of epilepsy is not only accurate in classification, but also fast in computation. It provides more feasibility for the real-time detection and application of epileptic seizure.
Electroencephalogram(EEG) contains a lot of physiological and pathological information and plays a very important role in the diagnosis of brain diseases such as epilepsy. The current clinical analysis of EEG signal is mainly based on the visual analysis of clinicians, so that the tasks of clinicians are onerous, and there is no quantitative standard for the analysis results. Therefore, automatic classification of EEG signal of epilepsy has great potential in current clinical applications. In this paper, a method for automatic detection of epileptic seizure signal is proposed. EEG signal of epilepsy and normal EEG signal can be recognized based on multiscale permutation entropy combined with the extreme learning machine classifier. The experimental results show that this method for automatic EEG recognition of epilepsy is not only accurate in classification, but also fast in computation. It provides more feasibility for the real-time detection and application of epileptic seizure.
引文
[1]Gel J,Pedley TA.Epilepsy:a comprehensive textbook[J].Epilepsy A Comprehensive Textbook,2008(19):1564-1565.
[2]Stam CJ,Pijn JP,Suffczynski P,et al.Dynamics of the human alpha rhythm:evidence for non-linearity?[J].Clinical Neurophysiology,1999,110(10):1801-1813.
[3]Srinivasan V,Eswaran C,Sriraam N.Approximate entropy-based epileptic EEGdetection using artificial neural networks[J].IEEE Transactions on Information Technology in Biomedicine A Publication of the IEEE Engineering in Medicine&Biology Society,2007,11(3):288-295.
[4]Nurujjaman M,Narayanan R,Iyengar AS.Comparative study of nonlinear properties of EEG signals of normal persons and epileptic patients[J].Nonlinear Biomedical Physics,2009,3(1):1-5.(下转第26页)
[5]Osowski S,Swiderski B,Cichocki A,et al.Lyapunov exponent of EEG signal for epileptic seizure characterization[C]//European Conference on Circuit Theory and Design,2005.
[6]Kalauzi A,Vuckovic A,Boji?T.Topographic distribution of EEG alpha attractor correlation dimension values in wake and drowsy states in humans[J].International Journal of Psychophysiology Official Journal of the International Organization of Psychophysiology,2015,95(3):278.
[7]Levan P,Urrestarazu E,Gotman J.A system for automatic artifact removal in ictal scalp EEGbased on independent component analysis and Bayesian classification[J].Clinical Neurophysiol ogy,2006,117(4610):912-927.
[8]Tang Z,Li C,Sun S.Single-trial EEGclassification of motor imagery using deep convolutional neural networks[J].OptikInternational Journal for Light and Electron Optics,2016(130):11-18.
[9]Mursalin M,Zhang Y,Chen Y,et al.Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier[J].Neurocomputing,2017.
[10]Li S,Zhou W,Yuan Q,et al.Feature extraction and recognition of ictal EEG using EMD and SVM[J].Computers in Biology&Medicine,2013,43(7):807-816.
[11]Richman JS,Moorman JR.Physiological time-series analysis using approximate entropy and sample entropy[J].American Journal of Physiology-Heart and Circulatory Physiology,2000,278(6):H2039-H2049.
[12]Guo L,Hao JH,Liu M.An incremental extreme learning machine for online sequential learning problems[J].Neurocomputing,2014,128(27):50-58.
[13]Pincus DSM,Gladstone IM,Ehrenkranz RA.A regularity statistic for medical data analysis[J].Journal of Clinical Monitoring and Computing,1991,7(4):335.
[14]Huang GB,Zhu QY,Siew CK.Extreme learning machine:a new learning scheme of feedforward neural networks[J].Proc.int.joint Conf.neural Netw,2004(2):985-990.
[15]Song Y,Zhang J.Discriminating preictal and interictal brain states in intracranial EEG by sample entropy and extreme learning machine[J].Journal of Neuroscience Methods,2016(257):45-54.
[2]Stam CJ,Pijn JP,Suffczynski P,et al.Dynamics of the human alpha rhythm:evidence for non-linearity?[J].Clinical Neurophysiology,1999,110(10):1801-1813.
[3]Srinivasan V,Eswaran C,Sriraam N.Approximate entropy-based epileptic EEGdetection using artificial neural networks[J].IEEE Transactions on Information Technology in Biomedicine A Publication of the IEEE Engineering in Medicine&Biology Society,2007,11(3):288-295.
[4]Nurujjaman M,Narayanan R,Iyengar AS.Comparative study of nonlinear properties of EEG signals of normal persons and epileptic patients[J].Nonlinear Biomedical Physics,2009,3(1):1-5.(下转第26页)
[5]Osowski S,Swiderski B,Cichocki A,et al.Lyapunov exponent of EEG signal for epileptic seizure characterization[C]//European Conference on Circuit Theory and Design,2005.
[6]Kalauzi A,Vuckovic A,Boji?T.Topographic distribution of EEG alpha attractor correlation dimension values in wake and drowsy states in humans[J].International Journal of Psychophysiology Official Journal of the International Organization of Psychophysiology,2015,95(3):278.
[7]Levan P,Urrestarazu E,Gotman J.A system for automatic artifact removal in ictal scalp EEGbased on independent component analysis and Bayesian classification[J].Clinical Neurophysiol ogy,2006,117(4610):912-927.
[8]Tang Z,Li C,Sun S.Single-trial EEGclassification of motor imagery using deep convolutional neural networks[J].OptikInternational Journal for Light and Electron Optics,2016(130):11-18.
[9]Mursalin M,Zhang Y,Chen Y,et al.Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier[J].Neurocomputing,2017.
[10]Li S,Zhou W,Yuan Q,et al.Feature extraction and recognition of ictal EEG using EMD and SVM[J].Computers in Biology&Medicine,2013,43(7):807-816.
[11]Richman JS,Moorman JR.Physiological time-series analysis using approximate entropy and sample entropy[J].American Journal of Physiology-Heart and Circulatory Physiology,2000,278(6):H2039-H2049.
[12]Guo L,Hao JH,Liu M.An incremental extreme learning machine for online sequential learning problems[J].Neurocomputing,2014,128(27):50-58.
[13]Pincus DSM,Gladstone IM,Ehrenkranz RA.A regularity statistic for medical data analysis[J].Journal of Clinical Monitoring and Computing,1991,7(4):335.
[14]Huang GB,Zhu QY,Siew CK.Extreme learning machine:a new learning scheme of feedforward neural networks[J].Proc.int.joint Conf.neural Netw,2004(2):985-990.
[15]Song Y,Zhang J.Discriminating preictal and interictal brain states in intracranial EEG by sample entropy and extreme learning machine[J].Journal of Neuroscience Methods,2016(257):45-54.