Real-time seizure prediction using RLS filtering and interpolated histogram feature based on hybrid optimization algorithm of Bayesian classifier and Hunting search

BACKGROUND AND OBJECTIVES Epileptic seizure prediction using EEG signal analysis is an important application for drug therapy and pediatric patient monitoring. Time series estimation to obtain the future samples of EEG signal has vital role for detecting seizure attack. In this paper, a novel density-based real-time seizure prediction algorithm based on a trained offline seizure detection algorithm is proposed. METHODS In the offline seizure detection procedure, after signal preprocessing, histogram-based statistical features are extracted from signal probability distribution. By defining a deterministic polynomial model on the normalized histogram, a novel syntactic feature that is named Interpolated Histogram Feature (IHF) is proposed. Moreover, with this feature, Seizure Distribution Model (SDM) as a descriptor of the seizure and non-seizure signals is presented. By using a novel hybrid optimization algorithm based on Bayesian classifier and Hunting Search (HuS) algorithm, the optimal features are selected. To detect the seizure attacks in the online mode, a Multi-Layer Perceptron (MLP) classifier is trained with the optimal features in the offline procedure. For online prediction, the enhanced Recursive Least Square (RLS) filter is applied to estimate sample-by-sample of the EEG signal. Also, a density-based signal tracking scenario is introduced to update and tune the parameters of RLS filtering algorithm. RESULTS Our prediction algorithm is evaluated on 104 hours of EEG signals recorded from 23 pediatric patients. Our online signal prediction algorithm provides the accuracy rate of 86.56% and precision rate of 86.53% simultaneously using the trained MLP classifier from the offline mode. The recall rate of seizure prediction is 97.27% and the false prediction rate of 0.00215 per hour is achieved as well. Ultimately, the future samples of EEG signal are estimated, and the time of seizure signal prediction is also converged to 6.64 seconds. CONCLUSION In our proposed real-time algorithm, by implementing a density-based signal tracking scenario, the future samples of signal with suitable time is predicted and the seizure is detected based on the optimal features from the IHF and histogram-based statistical features with acceptable performance.

[1]  Hossein Pourghassem,et al.  A novel effective feature selection algorithm based on S-PCA and wavelet transform features in EEG signal classification , 2011, 2011 IEEE 3rd International Conference on Communication Software and Networks.

[2]  S. Nasehi,et al.  Seizure Detection Algorithms Based on Analysis of EEG and ECG Signals: a Survey , 2012, Neurophysiology.

[3]  Ziyi Chen,et al.  Construction of rules for seizure prediction based on approximate entropy , 2014, Clinical Neurophysiology.

[4]  Mikael Persson,et al.  Application of particle swarm optimization in epileptic spike EEG source localization , 2013, Appl. Soft Comput..

[5]  Ali H. Shoeb,et al.  Detecting Seizure Onset in the Ambulatory Setting: Demonstrating Feasibility , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[6]  J. Gotman,et al.  Discriminating preictal and interictal states in patients with temporal lobe epilepsy using wavelet analysis of intracerebral EEG , 2012, Clinical Neurophysiology.

[7]  R. Rajavel,et al.  Low-complexity Power Spectral Density Estimation , 2015 .

[8]  Hossein Pourghassem,et al.  Singular Lorenz Measures Method for seizure detection using KNN-Scatter Search optimization algorithm , 2015, 2015 Signal Processing and Intelligent Systems Conference (SPIS).

[9]  Ahmed Mehaoua,et al.  Epileptic seizure detection from EEG signal using Discrete Wavelet Transform and Ant Colony classifier , 2014, 2014 IEEE International Conference on Communications (ICC).

[10]  M. J. Mahjoob,et al.  A novel meta-heuristic optimization algorithm inspired by group hunting of animals: Hunting search , 2010, Comput. Math. Appl..

[11]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[12]  B. Chaudhuri,et al.  Pattern defined heuristic rules and directional histogram based online ECG parameter extraction , 2009 .

[13]  G. Larry Bretthorst,et al.  Automating the analysis of EEG recordings from prematurely-born infants: A Bayesian approach , 2013, Clinical Neurophysiology.

[14]  Yongming Li,et al.  Sequential multi-criteria feature selection algorithm based on agent genetic algorithm , 2008, Applied Intelligence.

[15]  Sung-Nien Yu,et al.  Detection of seizures in EEG using subband nonlinear parameters and genetic algorithm , 2010, Comput. Biol. Medicine.

[16]  Mehdi Dehghan,et al.  Determination of a matrix function using the divided difference method of Newton and the interpolation technique of Hermite , 2009, J. Comput. Appl. Math..

[17]  Babak Nadjar Araabi,et al.  Variational Bayesian learning for Gaussian mixture HMM in seizure prediction based on long term EEG of epileptic rats , 2014, 2014 21th Iranian Conference on Biomedical Engineering (ICBME).

[18]  Banghua Yang,et al.  Fast removal of ocular artifacts from electroencephalogram signals using spatial constraint independent component analysis based recursive least squares in brain-computer interface , 2015, Frontiers of Information Technology & Electronic Engineering.

[19]  Abdulhamit Subasi,et al.  Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders , 2013, Comput. Biol. Medicine.

[20]  Mohammad Hossein Sedaaghi,et al.  An efficient seizure prediction method using KNN-based undersampling and linear frequency measures , 2014, Journal of Neuroscience Methods.

[21]  V. Sugumaran,et al.  Studies on Bayes classifier for condition monitoring of single point carbide tipped tool based on statistical and histogram features , 2010, Expert Syst. Appl..

[22]  Sotiris B. Kotsiantis,et al.  Combining bagging, boosting, rotation forest and random subspace methods , 2011, Artificial Intelligence Review.

[23]  R. E. Madsen,et al.  Channel selection for automatic seizure detection , 2012, Clinical Neurophysiology.

[24]  Hossein Pourghassem,et al.  Epileptic Seizure Onset Detection Algorithm Using Dynamic Cascade Feed-Forward Neural Networks , 2011, 2011 International Conference on Intelligent Computation and Bio-Medical Instrumentation.

[25]  Tobias Loddenkemper,et al.  Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy , 2014, Epilepsy & Behavior.

[26]  Hossein Pourghassem,et al.  Real-Time Seizure Detection Based on EEG and ECG Fused Features Using Gabor Functions , 2011, 2011 International Conference on Intelligent Computation and Bio-Medical Instrumentation.

[27]  Saeid Sanei,et al.  EEG signal processing , 2000, Clinical Neurophysiology.

[28]  Weidong Zhou,et al.  A low computation cost method for seizure prediction , 2014, Epilepsy Research.

[29]  S. Ravikumar,et al.  Condition monitoring of Self aligning carrying idler (SAI) in belt-conveyor system using statistical features and decision tree algorithm , 2014 .

[30]  Yusuf Uzzaman Khan,et al.  Seizure prediction using statistical dispersion measures of intracranial EEG , 2014, Biomed. Signal Process. Control..

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

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

[33]  Xiaoyuan He,et al.  Noise robustness and parallel computation of the inverse compositional Gauss-Newton algorithm in digital image correlation , 2015 .

[34]  Erchin Serpedin,et al.  Band-sensitive seizure onset detection via CSP-enhanced EEG features , 2015, Epilepsy & Behavior.

[35]  Christa Neuper,et al.  Hidden Markov models for online classification of single trial EEG data , 2001, Pattern Recognit. Lett..

[36]  Scott B. Wilson.  Algorithm architectures for patient dependent seizure detection , 2006, Clinical Neurophysiology.

[37]  Emmanuel Ifeachor,et al.  Digital Signal Processing: A Practical Approach , 1993 .

[38]  Bin He,et al.  A rule-based seizure prediction method for focal neocortical epilepsy , 2012, Clinical Neurophysiology.

[39]  Yanqing Zhang,et al.  SVMs Modeling for Highly Imbalanced Classification , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[40]  Sabri Koçer,et al.  Classifying Epilepsy Diseases Using Artificial Neural Networks and Genetic Algorithm , 2011, Journal of Medical Systems.

[41]  José Carlos M. Bermudez,et al.  A noise resilient variable step-size LMS algorithm , 2008, Signal Process..

[42]  Francisco Sepulveda,et al.  Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface , 2008, Inf. Sci..

[43]  Qiang Ye,et al.  Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects: Experiments with statistical features and different classification models , 2015, Biomed. Signal Process. Control..

[44]  R. Engelhardt,et al.  Single-channel amplitude integrated EEG recording for the identification of epileptic seizures by nonexpert physicians in the adult acute care setting , 2011, Journal of Clinical Monitoring and Computing.

[45]  David P. Doane.  Using Simulation to Teach Distributions , 2004 .

[46]  Mojtaba Bandarabadi,et al.  Epileptic seizure prediction using relative spectral power features , 2015, Clinical Neurophysiology.

[47]  Hossein Pourghassem,et al.  Online Mental Task Classification based on DWT-PCA Features and Probabilistic Neural Network , 2012 .

[48]  Ioannis Kalatzis,et al.  Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals , 2004, Comput. Methods Programs Biomed..

[49]  Robert M. Worth,et al.  Real-time seizure prediction from local field potentials using an adaptive Wiener algorithm , 2010, Comput. Biol. Medicine.

[50]  Hossein Pourghassem,et al.  A Novel Fast Epileptic Seizure Onset Detection Algorithm Using General Tensor Discriminant Analysis , 2013, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[51]  A. Kraskov,et al.  On the predictability of epileptic seizures , 2005, Clinical Neurophysiology.

[52]  Hossein Pourghassem,et al.  Periodogram pattern feature-based seizure detection algorithm using optimized hybrid model of MLP and Ant Colony , 2015, 2015 23rd Iranian Conference on Electrical Engineering.

[53]  António Dourado,et al.  Epileptic Seizure Classification Using Neural Networks with 14 Features , 2008, KES.

[54]  Ahmet Alkan,et al.  Comparison of AR and Welch Methods in Epileptic Seizure Detection , 2006, Journal of Medical Systems.

[55]  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.

[56]  H. Pourghassem,et al.  Mental Task Classification Based on HMM and BPNN , 2013, 2013 International Conference on Communication Systems and Network Technologies.

[57]  J. Gotman,et al.  A system for automatic artifact removal in ictal scalp EEG based on independent component analysis and Bayesian classification , 2006, Clinical Neurophysiology.