Global Epileptic Seizure Identification With Affinity Propagation Clustering Partition Mutual Information Using Cross-Layer Fully Connected Neural Network

A longstanding challenge in epilepsy research and practice is the need to classify synchronization patterns hidden in multivariate electroencephalography (EEG) data that is routinely superimposed with intensive noise. It is essential to select a suitable feature extraction method to achieve high recognition performance. A typical approach is to extract the mutual information (MI) between pairs of channels. This calculation, which considers the differences between the sequence pairs to build a reasonable partition, can improve the classification performance. On this basis, however, it is even more difficult to adaptively classify the synchronization patterns hidden in multivariate EEG data under circumstances of insufficient a priori knowledge of domain dependency, such as denoising, feature extraction on a special patient, etc. To address these problems by (1) effectively calculating the MI matrix (synchronization pattern) and (2) accurately classifying the seizure or non-seizure state, this study first accurately measures the synchronization between channel pairs in terms of affinity propagation clustering partition MI (APCPMI). The global synchronization measurement is then obtained by organizing APCPMIs of all channel pairs into a correlation matrix. Finally, a cross-layer fully connected net is designed to characterize the synchronization dynamics correlation matrices adaptively and identify seizure or non-seizure states automatically. Experiments are performed using the CHB-MIT scalp EEG dataset to evaluate the proposed approach. Seizure states are identified with an accuracy, sensitivity, and specificity of 0.9793 ± 0.002, 0.9942 ± 0.0005, and 0.9676 ± 0.003, respectively; the resulting performance is superior to those achieved by most existing methods over the same dataset. Furthermore, the approach alleviates the necessity for strictly preprocessing (denoising, removing interferences and artifacts) the EEG data using prior knowledge, which is usually required by existing approaches.

[1]  Hossein Pourghassem,et al.  Real-time seizure prediction using RLS filtering and interpolated histogram feature based on hybrid optimization algorithm of Bayesian classifier and Hunting search , 2016, Comput. Methods Programs Biomed..

[2]  Kaspar Anton Schindler,et al.  EEG synchronization measures are early outcome predictors in comatose patients after cardiac arrest , 2017, Clinical Neurophysiology.

[3]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[4]  Tardi Tjahjadi,et al.  A Mutual Information Based Adaptive Windowing of Informative EEG for Emotion Recognition , 2020, IEEE Transactions on Affective Computing.

[5]  Yann LeCun,et al.  Classification of patterns of EEG synchronization for seizure prediction , 2009, Clinical Neurophysiology.

[6]  Jing Liu,et al.  A new EEG synchronization strength analysis method: S-estimator based normalized weighted-permutation mutual information , 2016, Neural Networks.

[7]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  P. Rapp,et al.  Time domain measures of inter-channel EEG correlations: a comparison of linear, nonparametric and nonlinear measures , 2013, Cognitive Neurodynamics.

[9]  Gahangir Hossain,et al.  Seizure Prediction and Detection via Phase and Amplitude Lock Values , 2016, Front. Hum. Neurosci..

[10]  E. Kandel,et al.  Neuroscience thinks big (and collaboratively) , 2013, Nature Reviews Neuroscience.

[11]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[12]  Seetha Hari,et al.  Learning From Imbalanced Data , 2019, Advances in Computer and Electrical Engineering.

[13]  Philippe Renevey,et al.  SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in Brain-Computer Interfaces , 2005, Signal Process..

[14]  Xiaoli Li,et al.  Estimation of genuine and random synchronization in multivariate neural series , 2010, Neural Networks.

[15]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[16]  Shuilong He,et al.  A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection , 2017, Knowl. Based Syst..

[17]  Koushik Maharatna,et al.  Classification of autism spectrum disorder using supervised learning of brain connectivity measures extracted from synchrostates , 2014, Journal of neural engineering.

[18]  C. Stam,et al.  Seizure detection in adult ICU patients based on changes in EEG synchronization likelihood , 2006, Neurocritical care.

[19]  Aamir Saeed Malik,et al.  A wavelet-based technique to predict treatment outcome for Major Depressive Disorder , 2017, PloS one.

[20]  Lizhe Wang,et al.  Global Synchronization Measurement of Multivariate Neural Signals with Massively Parallel Nonlinear Interdependence Analysis , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[21]  H. Pourghassem,et al.  Patient-Specific Epileptic Seizure Onset Detection Algorithm Based on Spectral Features and IPSONN Classifier , 2013, 2013 International Conference on Communication Systems and Network Technologies.

[22]  Neil A. Macmillan,et al.  Detection Theory: A User's Guide , 1991 .

[23]  Hoon Kim,et al.  Monte Carlo Statistical Methods , 2000, Technometrics.

[24]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[25]  Dhiya Al-Jumeily,et al.  A machine learning system for automated whole-brain seizure detection , 2016 .

[26]  Shimon Ullman,et al.  Recognition invariance obtained by extended and invariant features , 2004, Neural Networks.

[27]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[28]  J. Martinerie,et al.  Preictal state identification by synchronization changes in long-term intracranial EEG recordings , 2005, Clinical Neurophysiology.

[29]  Pablo F. Diez,et al.  Patient non-specific algorithm for seizures detection in scalp EEG , 2016, Comput. Biol. Medicine.

[30]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[31]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[32]  Maria G. Knyazeva,et al.  Assessment of EEG synchronization based on state-space analysis , 2005, NeuroImage.

[33]  Alok Sharma,et al.  An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information , 2017, BMC Bioinformatics.

[34]  M. Hasan Shaheed,et al.  Cancer classification using a novel gene selection approach by means of shuffling based on data clustering with optimization , 2015, Appl. Soft Comput..

[35]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[36]  Gary E. Birch,et al.  Comparison of Evaluation Metrics in Classification Applications with Imbalanced Datasets , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[37]  Elly Gysels.  Phase synchronization for classification of spontaneous EEG signals in brain-computer interfaces , 2005 .

[38]  Heung-Il Suk,et al.  A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.