Individual and Mutual Feature Processed ELM Model for EEG Signal Based Brain Activity Classification

BCI deals to map the brain signal or activity to evaluate the human behaviour, activities or disease. The aim of this research is to utilize the different features of EEG signal to recognize the brain activity. The composite feature model with ELM classification method is presented in this research to recognize the human activity. In this paper, multiple aspects including time domain, frequency domain and least square evaluation based features are processed under ELM classifier to recognize the human-activities. Multiple quantified features are generated under each time, frequency and the least square categories. These features are processed individually and mutually with probabilistic evaluation to expand the processing-featureset. This expanded-composite featureset is trained under ELM (Extreme Learning Machine) classifier to perform intra-class and inter-class classification. The experimentation is applied on five distinctive experiments of Dataset IIIa of BCI completion III. Each experiment is conducted with variant training and testing instances. The evaluation results identified that the proposed hybrid model has achieved the average accuracy over 80%. Comparative results are generated against ANN, SVM, KNN and Multiscale Wavelet Kernel ELM by utilizing each kind of individual and mutual feature. The results taken from various experimentations have validated that the proposed model has improved the accuracy against each of the existing feature processed classification methods.

[1]  Seungjin Choi,et al.  Bayesian common spatial patterns for multi-subject EEG classification , 2014, Neural Networks.

[2]  Jing Wang,et al.  L1-norm based discriminative spatial pattern for single-trial EEG classification , 2014, Biomed. Signal Process. Control..

[3]  Hamid Mirvaziri,et al.  Improvement of EEG-based motor imagery classification using ring topology-based particle swarm optimization , 2017, Biomed. Signal Process. Control..

[4]  Ram Bilas Pachori,et al.  Time-frequency localized three-band biorthogonal wavelet filter bank using semidefinite relaxation and nonlinear least squares with epileptic seizure EEG signal classification , 2017, Digit. Signal Process..

[5]  N. Arunkumar,et al.  Classification of focal and non focal EEG using entropies , 2017, Pattern Recognit. Lett..

[6]  Pratyusha Rakshit,et al.  Evolutionary perspective for optimal selection of EEG electrodes and features , 2017, Biomed. Signal Process. Control..

[7]  Zhong Yin,et al.  Cross-session classification of mental workload levels using EEG and an adaptive deep learning model , 2017, Biomed. Signal Process. Control..

[8]  John Q. Gan,et al.  A supervised filter method for multi-objective feature selection in EEG classification based on multi-resolution analysis for BCI , 2017, Neurocomputing.

[9]  Roberto Antonio Vázquez,et al.  Evaluating spiking neural models in the classification of motor imagery EEG signals using short calibration sessions , 2018, Appl. Soft Comput..

[10]  Reza Langari,et al.  Classification of EEG signals for epileptic seizures using hybrid artificial neural networks based wavelet transforms and fuzzy relations , 2017, Expert Syst. Appl..

[11]  Ram Bilas Pachori,et al.  Classification of seizure and seizure-free EEG signals using local binary patterns , 2015, Biomed. Signal Process. Control..

[12]  Vahid Abolghasemi,et al.  Projective dictionary pair learning for EEG signal classification in brain computer interface applications , 2016, Neurocomputing.

[13]  Yu Zhang,et al.  Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces , 2018, Expert Syst. Appl..

[14]  Adham Atyabi,et al.  Mixture of autoregressive modeling orders and its implication on single trial EEG classification , 2016, Expert Syst. Appl..

[15]  MengChu Zhou,et al.  Common Bayesian Network for Classification of EEG-Based Multiclass Motor Imagery BCI , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[16]  Yanchun Zhang,et al.  Multi-category EEG signal classification developing time-frequency texture features based Fisher Vector encoding method , 2016, Neurocomputing.

[17]  Xingyu Wang,et al.  Sparse Bayesian Classification of EEG for Brain–Computer Interface , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Satchidananda Dehuri,et al.  EEG signal classification using PSO trained RBF neural network for epilepsy identification , 2017 .

[19]  Haider Banka,et al.  Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals , 2017, Biomed. Signal Process. Control..

[20]  Saeid Nahavandi,et al.  A fresh look at functional link neural network for motor imagery-based brain–computer interface , 2018, Journal of Neuroscience Methods.

[21]  T. Satya Savithri,et al.  Classification of EEG Motor Imagery Multi Class Signals Based on Cross Correlation , 2016 .

[22]  Tapio Saramäki,et al.  Long-term epileptic EEG classification via 2D mapping and textural features , 2015, Expert Syst. Appl..

[23]  Shouqian Sun,et al.  Single-trial EEG classification of motor imagery using deep convolutional neural networks , 2017 .

[24]  Jun Guo,et al.  Feature selection for neutral vector in EEG signal classification , 2016, Neurocomputing.

[25]  Klaus-Robert Müller,et al.  Interpretable deep neural networks for single-trial EEG classification , 2016, Journal of Neuroscience Methods.

[26]  Satchidananda Dehuri,et al.  ABC optimized RBF network for classification of EEG signal for epileptic seizure identification , 2017 .

[27]  David Cuesta-Frau,et al.  Noisy EEG signals classification based on entropy metrics. Performance assessment using first and second generation statistics , 2017, Comput. Biol. Medicine.

[28]  Yong Peng,et al.  Discriminative manifold extreme learning machine and applications to image and EEG signal classification , 2016, Neurocomputing.

[29]  Yan Li,et al.  A novel statistical algorithm for multiclass EEG signal classification , 2014, Eng. Appl. Artif. Intell..

[30]  Jayadeva,et al.  High performance EEG signal classification using classifiability and the Twin SVM , 2015, Appl. Soft Comput..

[31]  Wei Wu,et al.  RSTFC: A Novel Algorithm for Spatio-Temporal Filtering and Classification of Single-Trial EEG , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[32]  Toshihisa Tanaka,et al.  Robust Averaging of Covariances for EEG Recordings Classification in Motor Imagery Brain-Computer Interfaces , 2017, Neural Computation.

[33]  Shiliang Sun,et al.  A subject transfer framework for EEG classification , 2012, Neurocomputing.

[34]  Dario Farina,et al.  Classification of EEG signals to identify variations in attention during motor task execution , 2017, Journal of Neuroscience Methods.