A new multi-objective wrapper method for feature selection - Accuracy and stability analysis for BCI

Abstract Feature selection is an important step in building classifiers for high-dimensional data problems, such as EEG classification for BCI applications. This paper proposes a new wrapper method for feature selection, based on a multi-objective evolutionary algorithm, where the representation of the individuals or potential solutions, along with the breeding operators and objective functions, have been carefully designed to select a small subset of features that has good generalization capability, trying to avoid the over-fitting problems that wrapper methods usually suffer. A novel feature ranking procedure is also proposed in order to analyze the stability of the proposed wrapper method. Four different classification schemes have been applied within the proposed wrapper method in order to evaluate its accuracy and stability for feature selection on a real motor imagery dataset. Experimental results show that the wrapper method presented in this paper is able to obtain very small subsets of features, which are quite stable and also achieve high classification accuracy, regardless of the classifiers used.

[1]  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.

[2]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[3]  Hua Yu,et al.  A direct LDA algorithm for high-dimensional data - with application to face recognition , 2001, Pattern Recognit..

[4]  Dinggang Shen,et al.  A novel relational regularization feature selection method for joint regression and classification in AD diagnosis , 2017, Medical Image Anal..

[5]  Xiaofeng Zhu,et al.  Local and Global Structure Preservation for Robust Unsupervised Spectral Feature Selection , 2018, IEEE Transactions on Knowledge and Data Engineering.

[6]  Blaise Hanczar,et al.  Analysis of feature selection stability on high dimension and small sample data , 2014, Comput. Stat. Data Anal..

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  Vinod Achutavarrier Prasad,et al.  Optimized Bi-Objective EEG Channel Selection and Cross-Subject Generalization With Brain–Computer Interfaces , 2016, IEEE Transactions on Human-Machine Systems.

[9]  A. Al-Jumaily,et al.  Intelligent Artificial Ants based feature extraction from wavelet packet coefficients for biomedical signal classification , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.

[10]  Lie Wang,et al.  Orthogonal Matching Pursuit for Sparse Signal Recovery With Noise , 2011, IEEE Transactions on Information Theory.

[11]  C. Richards,et al.  Potential role of mental practice using motor imagery in neurologic rehabilitation. , 2001, Archives of physical medicine and rehabilitation.

[12]  Thomas Stützle,et al.  Ant Colony Optimization , 2009, EMO.

[13]  Klaus-Robert Müller,et al.  Classifying Single Trial EEG: Towards Brain Computer Interfacing , 2001, NIPS.

[14]  Geoffrey J McLachlan,et al.  Selection bias in gene extraction on the basis of microarray gene-expression data , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[15]  J. Steurer,et al.  Journal of Neuroengineering and Rehabilitation Efficacy of Motor Imagery in Post-stroke Rehabilitation: a Systematic Review , 2022 .

[16]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[17]  Huan Liu,et al.  Toward integrating feature selection algorithms for classification and clustering , 2005, IEEE Transactions on Knowledge and Data Engineering.

[18]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 2000, Springer Berlin Heidelberg.

[19]  Sanghamitra Bandyopadhyay,et al.  Many-objective feature selection for motor imagery EEG signals using differential evolution and support vector machine , 2016, 2016 International Conference on Microelectronics, Computing and Communications (MicroCom).

[20]  George Atia,et al.  Motor imagery classification using multiresolution analysis and sparse representation of EEG signals , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[21]  Xin Yao,et al.  A Survey on Evolutionary Computation Approaches to Feature Selection , 2016, IEEE Transactions on Evolutionary Computation.

[22]  A. Balbinot,et al.  A study of the Naive Bayes classifier for analyzing imaginary movement EEG signals using the Periodogram as spectral estimator , 2013, 2013 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC).

[23]  Xuelong Li,et al.  Joint Embedding Learning and Sparse Regression: A Framework for Unsupervised Feature Selection , 2014, IEEE Transactions on Cybernetics.

[24]  Zengyou He,et al.  Stable Feature Selection for Biomarker Discovery , 2010, Comput. Biol. Chem..

[25]  Yubo Wang,et al.  Evolutionary Algorithm Based Feature Optimization for Multi-Channel EEG Classification , 2017, Front. Neurosci..

[26]  Héctor Pomares,et al.  Parallel multiobjective memetic RBFNNs design and feature selection for function approximation problems , 2009, Neurocomputing.

[27]  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).

[28]  Thiago Bassani,et al.  Brain-computer interface using wavelet transformation and naïve bayes classifier. , 2010, Advances in experimental medicine and biology.

[29]  Richard Bellman,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[30]  Gary E. Birch,et al.  Brain-computer interface design for asynchronous control applications: improvements to the LF-ASD asynchronous brain switch , 2004, IEEE Transactions on Biomedical Engineering.

[31]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[32]  Andrés Ortiz,et al.  Classification of motor imagery tasks for BCI with multiresolution analysis and multiobjective feature selection , 2016, Biomedical engineering online.

[33]  Huan Liu,et al.  Toward Time-Evolving Feature Selection on Dynamic Networks , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[34]  Feiping Nie,et al.  Efficient and Robust Feature Selection via Joint ℓ2, 1-Norms Minimization , 2010, NIPS.

[35]  Mengjie Zhang,et al.  Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach , 2013, IEEE Transactions on Cybernetics.

[36]  T. Pedley.  Current Practice of Clinical Electroenceph‐alography , 1980, Neurology.

[37]  John Q. Gan,et al.  Deep Belief Networks and Multiobjective Feature Selection for BCI with Multiresolution Analysis , 2017, IWANN.

[38]  Xiaofeng Zhu,et al.  Graph self-representation method for unsupervised feature selection , 2017, Neurocomputing.

[39]  Ujjwal Maulik,et al.  A Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part I , 2014, IEEE Transactions on Evolutionary Computation.

[40]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[41]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[42]  Chong Liu,et al.  EEG classification for multiclass motor imagery BCI , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[43]  Marco Laumanns,et al.  SPEA2: Improving the Strength Pareto Evolutionary Algorithm For Multiobjective Optimization , 2002 .

[44]  Sebastián Basterrech,et al.  Nature-Inspired Algorithms for Selecting EEG Sources for Motor Imagery Based BCI , 2015, ICAISC.

[45]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[46]  Günter Rudolph,et al.  Multi-objective evolutionary feature selection for instrument recognition in polyphonic audio mixtures , 2012, Soft Comput..

[47]  Pavel Pudil,et al.  Identifying the most Informative Variables for Decision-Making Problems - a Survey of Recent Approaches and Accompanying Problems , 2008 .

[48]  David Corne,et al.  The Pareto archived evolution strategy: a new baseline algorithm for Pareto multiobjective optimisation , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[49]  Xuelong Li,et al.  Unsupervised Feature Selection with Structured Graph Optimization , 2016, AAAI.

[50]  Feiping Nie,et al.  Efficient semi-supervised feature selection with noise insensitive trace ratio criterion , 2013, Neurocomputing.

[51]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[52]  Albert Y. Zomaya,et al.  Stability of feature selection algorithms and ensemble feature selection methods in bioinformatics , 2013 .

[53]  Hua Wang,et al.  Detection of motor imagery EEG signals employing Naïve Bayes based learning process , 2016 .

[54]  Rebeca Corralejo,et al.  Feature selection using a genetic algorithm in a motor imagery-based Brain Computer Interface , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[55]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[56]  Jacob Scharcanski,et al.  Feature selection for face recognition based on multi-objective evolutionary wrappers , 2013, Expert Syst. Appl..

[57]  Ali Khadem,et al.  Enhancing LDA-based discrimination of left and right hand motor imagery: Outperforming the winner of BCI Competition II , 2015, 2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI).

[58]  Isao Nambu,et al.  EEG Channel Selection Using Particle Swarm Optimization for the Classification of Auditory Event-Related Potentials , 2014, TheScientificWorldJournal.

[59]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[60]  Xiaohui Cheng,et al.  Feature self-representation based hypergraph unsupervised feature selection via low-rank representation , 2017, Neurocomputing.

[61]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[62]  Francisco Herrera,et al.  A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behaviour: a case study on the CEC’2005 Special Session on Real Parameter Optimization , 2009, J. Heuristics.

[63]  Kenneth Sörensen,et al.  Metaheuristics - the metaphor exposed , 2015, Int. Trans. Oper. Res..

[64]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[65]  Melanie Hilario,et al.  Knowledge and Information Systems , 2007 .

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

[67]  Feiping Nie,et al.  Trace Ratio Criterion for Feature Selection , 2008, AAAI.

[68]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[69]  Jun Zhang,et al.  Dynamic frequency feature selection based approach for classification of motor imageries , 2016, Comput. Biol. Medicine.

[70]  Izabela Rejer,et al.  Genetic algorithm with aggressive mutation for feature selection in BCI feature space , 2014, Pattern Analysis and Applications.

[71]  T. Hinterberger,et al.  Automated EEG feature selection for brain computer interfaces , 2003, First International IEEE EMBS Conference on Neural Engineering, 2003. Conference Proceedings..

[72]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[73]  J. Q. Gan,et al.  Multiresolution analysis over simple graphs for brain computer interfaces , 2013, Journal of neural engineering.

[74]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[75]  Bernhard Graimann,et al.  A comparison approach toward finding the best feature and classifier in cue-based BCI , 2007, Medical & Biological Engineering & Computing.

[76]  Izabela Rejer,et al.  Feature selection with NSGA and GAAM in EEG signals domain , 2015, 2015 8th International Conference on Human System Interaction (HSI).