Chaotic Quantum-inspired Evolutionary Algorithm: enhancing feature selection in BCI

Quantum-inspired Evolutionary Algorithms (QiEAs) have demonstrated to be very effective in several applications. In particular, employing this algorithm for feature selection as a wrapper technique in Brain-Computer Interfaces applications was recently proposed with great results. Moreover, the training time of the model was decreased while maintaining a high classification accuracy, both essential conditions for a successful BCI. The drawback of this model was the sensitiveness to changes in the direction and magnitude of the rotation angle, which can produce adverse effects in both performance and convergence time. Chaotic systems and Evolutionary algorithms, when combined, can enhance the convergence rate and speed of the evolutionary process, incrementing the capacity of reaching the global optima. In this paper we explore the effects of adding ergodicity to a QiEA by the employment of chaotic maps in two operators: chaotic uniform crossover and chaotic quantum update gate. To validate the proposed approach, six commonly used chaotic maps are tested with data of Motor Imagery (MI) Electroencephalography (EEG) of right and left hand movement. The results of these experiments are compared with the ones of a QiEA and a classical Genetic Algorithm (GA). In the proposed model, Wavelet Packet Decomposition is employed as the time-frequency analysis to characterize the signal, whereas a Multilayer Perceptron Neural Network is used as a classifier. The results demonstrated that Chaotic QiEAs can significantly improve the convergence time of the model with only a small loss in the final accuracy.

[1]  W. Spears,et al.  On the Virtues of Parameterized Uniform Crossover , 1995 .

[2]  Wei-Yen Hsu.  WAVELET-COHERENCE FEATURES FOR MOTOR IMAGERY EEG ANALYSIS POSTERIOR TO EOG NOISE ELIMINATION , 2012 .

[3]  Sang-Hong Lee,et al.  Minimum Feature Selection for Epileptic Seizure Classification using Wavelet-based Feature Extraction and a Fuzzy Neural Network , 2014 .

[4]  Marley M. B. R. Vellasco,et al.  Quantum-Inspired Evolutionary Algorithm for Numerical Optimization , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[5]  Michal Pluhacek,et al.  On the Population Diversity for the Chaotic Differential Evolution , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[6]  D. Sheskin.  Handbook of Parametric and Nonparametric Statistical Procedures: Third Edition , 2000 .

[7]  Jong-Hwan Kim,et al.  Quantum-Inspired Evolutionary Algorithms With a New Termination Criterion , H Gate , and Two-Phase Scheme , 2009 .

[8]  Huan Liu,et al.  Feature Selection: An Ever Evolving Frontier in Data Mining , 2010, FSDM.

[9]  Marley M. B. R. Vellasco,et al.  Quantum-inspired Evolutionary Algorithm for Feature Selection in Motor Imagery EEG Classification , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[10]  Brendan Z. Allison,et al.  Brain-Computer Interfaces: A Gentle Introduction , 2009 .

[11]  Jong-Hwan Kim,et al.  Quantum-inspired evolutionary algorithms with a new termination criterion, H/sub /spl epsi// gate, and two-phase scheme , 2004, IEEE Transactions on Evolutionary Computation.

[12]  Miguel Alfaro,et al.  Chaotic Genetic Algorithm and The Effects of Entropy in Performance Optimization , 2019, Chaos.

[13]  Alimed Celecia Ramos,et al.  Feature Selection methods applied to Motor Imagery task classification , 2016, 2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI).

[14]  David J. Sheskin,et al.  Handbook of Parametric and Nonparametric Statistical Procedures , 1997 .

[15]  Li-Yeh Chuang,et al.  Chaotic particle swarm optimization for data clustering , 2011, Expert Syst. Appl..

[16]  Marley M. B. R. Vellasco,et al.  Ensemble of classifiers applied to motor imagery task classification for BCI applications , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[17]  Siddhartha Bhattacharyya,et al.  An Efficient Quantum Inspired Genetic Algorithm with Chaotic Map Model Based Interference and Fuzzy Objective Function for Gray Level Image Thresholding , 2011, 2011 International Conference on Computational Intelligence and Communication Networks.

[18]  Huaixiao Wang,et al.  The Improvement of Quantum Genetic Algorithm and Its Application on Function Optimization , 2013 .

[19]  Abdulhamit Subasi,et al.  EEG signal classification using PCA, ICA, LDA and support vector machines , 2010, Expert Syst. Appl..

[20]  Marley M. B. R. Vellasco,et al.  Resource optimization for elective surgical procedures using quantum-inspired genetic algorithms , 2019, GECCO.

[21]  Dataset IIIb: Non-stationary 2-class BCI data , 2004 .

[22]  Emad A. Awada,et al.  Wavelet-Based Feature Extraction for the Analysis of EEG Signals Associated with Imagined Fists and Feet Movements , 2014, Comput. Inf. Sci..

[23]  Daniel Civitarese,et al.  Quantum-Inspired Neural Architecture Search , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[24]  L. Vega-Escobar,et al.  Feature extraction schemes for BCI systems , 2015, 2015 20th Symposium on Signal Processing, Images and Computer Vision (STSIVA).

[25]  Nasser L. Azad,et al.  Comparisons of several variants of continuous quantum-inspired evolutionary algorithms , 2017, J. Exp. Theor. Artif. Intell..

[26]  Zhang Chao,et al.  Chaos updating rotated gates quantum-inspired genetic algorithm , 2004, 2004 International Conference on Communications, Circuits and Systems (IEEE Cat. No.04EX914).

[27]  Snehanshu Saha,et al.  Evidence of Chaos in EEG Signals: An Application to BCI , 2016, Advances in Chaos Theory and Intelligent Control.

[28]  Madhav J. Nigam,et al.  Applications of quantum inspired computational intelligence: a survey , 2014, Artificial Intelligence Review.

[29]  Gexiang Zhang,et al.  Quantum-inspired evolutionary algorithms: a survey and empirical study , 2011, J. Heuristics.

[30]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update , 2018, Journal of neural engineering.

[31]  Subhojit Ghosh,et al.  Statistical Wavelet Features, PCA, and SVM Based Approach for EEG Signals Classification , 2015 .

[32]  Dong Ming,et al.  EEG oscillatory patterns and classification of sequential compound limb motor imagery , 2016, Journal of NeuroEngineering and Rehabilitation.

[33]  Jong-Hwan Kim,et al.  Quantum-inspired evolutionary algorithm for a class of combinatorial optimization , 2002, IEEE Trans. Evol. Comput..

[34]  Aboul Ella Hassanien,et al.  Feature selection via a novel chaotic crow search algorithm , 2017, Neural Computing and Applications.

[35]  Meikang Qiu,et al.  The Effects of Using Chaotic Map on Improving the Performance of Multiobjective Evolutionary Algorithms , 2014 .

[36]  Guanghua Xu,et al.  Real-coded chaotic quantum-inspired genetic algorithm for training of fuzzy neural networks , 2009, Comput. Math. Appl..

[37]  Cuntai Guan,et al.  A Large Clinical Study on the Ability of Stroke Patients to Use an EEG-Based Motor Imagery Brain-Computer Interface , 2011, Clinical EEG and neuroscience.

[38]  Yan Guozheng,et al.  EEG feature extraction based on wavelet packet decomposition for brain computer interface , 2008 .