Classifying epileptic EEG signals with delay permutation entropy and Multi-Scale K-means.

Most epileptic EEG classification algorithms are supervised and require large training datasets, that hinder their use in real time applications. This chapter proposes an unsupervised Multi-Scale K-means (MSK-means) MSK-means algorithm to distinguish epileptic EEG signals and identify epileptic zones. The random initialization of the K-means algorithm can lead to wrong clusters. Based on the characteristics of EEGs, the MSK-means MSK-means algorithm initializes the coarse-scale centroid of a cluster with a suitable scale factor. In this chapter, the MSK-means algorithm is proved theoretically superior to the K-means algorithm on efficiency. In addition, three classifiers: the K-means, MSK-means MSK-means and support vector machine (SVM), are used to identify seizure and localize epileptogenic zone using delay permutation entropy features. The experimental results demonstrate that identifying seizure with the MSK-means algorithm and delay permutation entropy achieves 4. 7 % higher accuracy than that of K-means, and 0. 7 % higher accuracy than that of the SVM.

[1]  R. V. Van Heertum,et al.  Positron emission tomography and single photon emission computed tomography in epilepsy care. , 2003, Seminars in nuclear medicine.

[2]  Madalena Costa,et al.  Multiscale entropy analysis of complex physiologic time series. , 2002, Physical review letters.

[3]  Yves Pomeau,et al.  The long and winding road , 2016, Nature Physics.

[4]  Howard Carter,et al.  A PRELIMINARY INVESTIGATION , 2010 .

[5]  Kemal Polat,et al.  Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform , 2007, Appl. Math. Comput..

[6]  Julius Georgiou,et al.  Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines , 2012, Expert Syst. Appl..

[7]  Yan Li,et al.  Epileptogenic focus detection in intracranial EEG based on delay permutation entropy , 2013 .

[8]  Andrea Vattani,et al.  k-means Requires Exponentially Many Iterations Even in the Plane , 2008, SCG '09.

[9]  Al Bartolucci,et al.  Functional imaging: II. Prediction of epilepsy surgery outcome , 2008, Annals of neurology.

[10]  Daniel Rivero,et al.  Automatic feature extraction using genetic programming: An application to epileptic EEG classification , 2011, Expert Syst. Appl..

[11]  Ning Zhong,et al.  Unsupervised Classification of Epileptic EEG Signals with Multi Scale K-Means Algorithm , 2013, Brain and Health Informatics.

[12]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[13]  Sergei Vassilvitskii,et al.  Scalable K-Means++ , 2012, Proc. VLDB Endow..

[14]  R Sankar,et al.  Magnetic source imaging localizes epileptogenic zone in children with tuberous sclerosis complex , 2006, Neurology.

[15]  H. Lüders,et al.  Presurgical evaluation of epilepsy. , 2001, Brain : a journal of neurology.

[16]  Mahmut Ozer,et al.  EEG signals classification using the K-means clustering and a multilayer perceptron neural network model , 2011, Expert Syst. Appl..

[17]  Yan Li,et al.  Clustering technique-based least square support vector machine for EEG signal classification , 2011, Comput. Methods Programs Biomed..

[18]  Pavel Krsek,et al.  Localizing value of ictal SPECT is comparable to MRI and EEG in children with focal cortical dysplasia , 2013, Epilepsia.

[19]  Hans Hallez,et al.  Ictal‐onset localization through connectivity analysis of intracranial EEG signals in patients with refractory epilepsy , 2013, Epilepsia.

[20]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[21]  Oren Sagher,et al.  Mapping and assessment of epileptogenic foci using frequency-entropy templates. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[23]  Pietro Liò,et al.  A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine , 2010 .

[24]  K Lehnertz,et al.  Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[25]  Ralph G Andrzejak,et al.  Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[26]  Abdulhamit Subasi.  Automatic detection of epileptic seizure using dynamic fuzzy neural networks , 2006, Expert Syst. Appl..

[27]  F. Mormann,et al.  Seizure prediction: the long and winding road. , 2007, Brain : a journal of neurology.

[28]  Chang-Hwan Im,et al.  Localization of epileptogenic zones in Lennox–Gastaut syndrome using frequency domain source imaging of intracranial electroencephalography: a preliminary investigation , 2013, Physiological measurement.

[29]  Yan Li,et al.  Analysing epileptic EEGs with a visibility graph algorithm , 2012, 2012 5th International Conference on BioMedical Engineering and Informatics.

[30]  I G Zubal,et al.  Sensitivity and specificity of quantitative difference SPECT analysis in seizure localization. , 1999, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[31]  W. van Paesschen,et al.  Neuronuclear assessment of patients with epilepsy. , 2008, Seminars in nuclear medicine.

[32]  Anton Popov,et al.  Saturation of electroencephalogram permutation entropy for large time lags , 2013, 2013 IEEE XXXIII International Scientific Conference Electronics and Nanotechnology (ELNANO).

[33]  B. Pompe,et al.  Permutation entropy: a natural complexity measure for time series. , 2002, Physical review letters.

[34]  Mariano Matilla-García,et al.  Detection of non-linear structure in time series , 2009 .