Soft Computing

, Volume 19, Issue 10, pp 2799–2812 | Cite as

Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods

  • Akshansh GuptaEmail author
  • R. K. Agrawal
  • Baljeet Kaur
Methodologies and Application


In the recent years, the research community has shown interest in the development of brain–computer interface applications which assist physically challenged people to communicate with their brain electroencephalogram (EEG) signal. Representation of these EEG signals for mental task classification in terms of relevant features is important to achieve higher performance in terms of accuracy and computation time. For feature extraction from the EEG, empirical mode decomposition and wavelet transform are more appropriate as they are suitable for the analysis of non-linear and non-stationary time series signals. However, the size of the feature vector obtained from them is huge and may hinder the performance of mental task classification. To obtain a minimal set of relevant and non-redundant features for classification, six popular multivariate filter methods have been investigated which are based on different criteria: distance measure, causal effect and mutual information. Experimental results demonstrate that the classification accuracy improves while the computation time reduces considerably with the use of each of the six multivariate feature selection methods. Among all the combinations of feature extraction and selection methods that are investigated, the combination of wavelet transform and linear regression performs the best. Ranking analysis and statistical tests are also performed to validate the empirical results.


Empirical mode decomposition Wavelet transform Bhattacharyya distance Kullback–Leibler distance Ratio of scatter matrices Linear regression Minimum redundancy and maximum relevance 



The first author expresses his gratitude to the Council of Scientific and Industrial Research (CSIR), India, for the obtained financial support in performing this research work. We also thank the reviewers for the constructive and valuable review of our paper that has helped us to further strengthen the overall quality of the paper.


  1. Adhikari R, Agrawal RK (2012) Performance evaluation of weights selection schemes for linear combination of multiple forecasts. Artif Intell Rev. doi: 10.1007/s10462-012-9361-z
  2. Anderson CW, Stolz EA, Shamsunder S (1998) Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks. IEEE Trans Biomed Eng 45(3):277–286CrossRefGoogle Scholar
  3. Babiloni F, Cincotti F, Lazzarini L, Millan J, Mourino J, Varsta M, Heikkonen J, Bianchi L, Marciani MG (2000) Linear classification of low-resolution EEG patterns produced by imagined hand movements. IEEE Trans Rehab Eng 8(2):184–186CrossRefGoogle Scholar
  4. Bashashati A, Faourechi M, Ward RK, Brich GE (2007) A survey of signal processing algorithms in brain computer interface based on electrical brain signals. J Neural Eng 4:R32–R57CrossRefGoogle Scholar
  5. Basseville M, Benveniste A (1983) Sequential segmentation of non-stationary digital signals using spectral analysis. Inf Sci 29(1):57–73CrossRefzbMATHGoogle Scholar
  6. Bellman RE (1961) Adaptive control processes: a guided tour. Princeton University Press, PrincetonGoogle Scholar
  7. Bhattacharyya A (1943) On a measure of divergence between two statistical populations defined by their probability distributions. Bull Calcutta Math Soc 35:99–110zbMATHMathSciNetGoogle Scholar
  8. Bhattacharyya S, Sengupta A, Chakraborti T, Konar A, Tibarewala D (2014) Automatic feature selection of motor imagery EEG signals using differential evolution and learning automata. Med Biol Eng Comput 52(2):131–139CrossRefGoogle Scholar
  9. Bostanov V (2004) BCI competition 2003-data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram. IEEE Trans Biomed Eng 51(6):1057–1061Google Scholar
  10. Cabrera A, Farina D, Dremstrup K (2010) Comparison of feature selection and classification methods for a brain-computer interface driven by non-motor imagery. Med Biol Eng Comput 0140–0118(48):123–132CrossRefGoogle Scholar
  11. Corralejo R, Hornero R, Alvarez D (2011) Feature selection using a genetic algorithm in a motor imagery-based brain computer interface. In: Annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp 7703–7706Google Scholar
  12. Cvetkovic D, Übeyli ED, Cosic I (2008) Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study. Digit Signal Process 18(5):861–874Google Scholar
  13. Daubcheies I (1990) The wavelet transform. Time–frequency localizition and signal analysis. IEEE Trans Inf Theory 3(5):961–1005CrossRefGoogle Scholar
  14. Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30zbMATHMathSciNetGoogle Scholar
  15. Derrac J, Garcia S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology or comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1:3–18Google Scholar
  16. Devijver PA, Kittler J (1982) Pattern recognition: a statistical approach. PHIGoogle Scholar
  17. Dias N, Kamrunnahar M, Mendes P, Schiff S, Correia J (2010) Feature selection on movement imagery discrimination and attention detection. Med Biol Eng Comput 48:331–341CrossRefGoogle Scholar
  18. Diez PF, Mut V, Lacier E (2009) Application of the empirical mode decomposition to the extraction of features from EEG signals for mental task classification. In: 31st Annual International Conference of the IEEE EMBS Minneapolis, pp 2579–2582Google Scholar
  19. Freeman WJ (1999) Comparison of brain models for active vs. passive perception. Inf Sci 116:97–107CrossRefGoogle Scholar
  20. Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 32(1937):674–701Google Scholar
  21. Garrett D, Peterson D, Anderson C, Thaut M (2003) Comparison of linear, nonlinear, and feature selection methods for EEG signal classification. IEEE Trans Neural Syst Rehab Eng 11(2):141–144Google Scholar
  22. Graimann B, Huggins JE, Schlogl A, Levine SP, Pfurtscheller G (2003) Detection of movement-related desynchronization patterns in on-going single-channel electrocardiogram. IEEE Trans Neural Syst Rehab Eng 11(3):276–281CrossRefGoogle Scholar
  23. Groissboeck W, Lughofer E, Klement EP (2004) A comparison of variable selection methods with the main focus on orthogonalization. Adv Soft Comput 479–486Google Scholar
  24. Gupta A, Agrawal RK (2012) Relevant feature selection from EEG signal for mental task classification. In: Pacific-Asia conference on knowledge discovery and data mining (PAKDD), in part II. Lecture Notes in Computer Science, vol 7302, pp 431–442Google Scholar
  25. Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182zbMATHGoogle Scholar
  26. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction, 2nd edn. Springer, New YorkCrossRefGoogle Scholar
  27. Haury AC, Gestraud P, Vert JP (2011) The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures. PLoS One 6(12). doi: 10.1371/journal.pone.0028210
  28. Hazarika N, Chen JZ, Tsoi AC, Sergejew A (1997) Classification of EEG signals using the wavelet transform. Signal Process 59(1):61–72CrossRefzbMATHGoogle Scholar
  29. Hsu WY, Sun YN (2009) EEG-based motor imagery analysis using weighted wavelet transform features. J Neurosci Methods 176(2):310–318CrossRefGoogle Scholar
  30. Huang NE, Shen Z, Long SR, Wu ML, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationarytime series analysis. Proc R Soc Lond A 454:903–995CrossRefzbMATHMathSciNetGoogle Scholar
  31. Iman R, Davenport J (1980) Approximations of the critical region of the Friedman statistic. Commun Stat 9(1980):571–595CrossRefGoogle Scholar
  32. Kaleem MF, Sugavaneswaran L, Guergachi A, Krishnan S (2010) Application of empirical mode decomposition and teager energy operator to EEG signals for mental task classification. In: Annual international conference of the engineering in medicine and biology society (EMBC). IEEE Press, New York, pp 4590–4593Google Scholar
  33. Kauhanen L, Nykopp T, Lehtonen J, Jylanki P, Heikkonen J, Rantanen P, Alaranta H, Sams M (2006) EEG and MEG brain-computer interface for tetraplegic patients. IEEE Trans Neural Syst Rehab Eng 14(2):190–193CrossRefGoogle Scholar
  34. Keirn ZA, Aunon JI (1990) A new mode of communication between man and his surroundings. IEEE Trans Biomed Eng 37(12):1209–1214CrossRefGoogle Scholar
  35. Kohavi R, John G (1997) Wrapper for feature subset selection. Artif Intell 97(1–2):273–324CrossRefzbMATHGoogle Scholar
  36. Koprinska I (2009) Feature selection for brain-computer interfaces. In: International workshop on new frontiers in applied data mining (PAKDD), LNCS, vol 5669, pp 106–117Google Scholar
  37. Kronegg J, Chanel G, Voloshynovskiy S, Pun T (2007) EEG-based synchronized brain-computer interfaces: a model for optimizing the number of mental tasks. IEEE Trans Neural Syst Rehab Eng 15(1):50–58CrossRefGoogle Scholar
  38. Kullback S, Liebler RA (1951) On information and sufficiency. Ann Math Stat 22:79–86CrossRefzbMATHGoogle Scholar
  39. Lakany H, Conway BA (2007) Understanding intention of movement from electroencephalograms. Expert Syst 24:295–304CrossRefGoogle Scholar
  40. Lempel A, Ziv J (1976) On the complexity of finite sequences. IEEE Trans Inf Theory 22:75–81Google Scholar
  41. Li Y (2004) On incremental and robust subspace learning. Pattern Recognit 37(7):1509–1518Google Scholar
  42. Lughofer E (2011) On-line incremental feature weighting in evolving fuzzy classifiers. Fuzzy Sets Syst 163(1):1–23CrossRefzbMATHMathSciNetGoogle Scholar
  43. Mallat GS (1989) A theory for multi-resolution signal decomposition the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693Google Scholar
  44. Mosquera C, Verleysen M, Navia Vazquez A (2010) EEG feature selection using mutual information and support vector machine: a comparative analysis. In: 32nd annual international IEEE EMBC conference, pp 4946–4949Google Scholar
  45. Murugappan M, Ramachandran N, Sazali Y (2010) Classification of human emotion from EEG using discrete wavelet transform. J Biomed Sci Eng 3(4):390–396Google Scholar
  46. Ocak H (2009) Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Syst Appl 36(2):2027–2036CrossRefGoogle Scholar
  47. Park HS, Yoo SHY, Cho SB (2007) Forward selection method with regression analysis for optimal gene selection in cancer classification. Int J Comput Math 84(5):653–668Google Scholar
  48. Peng H, Loung F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency. Max-relevance and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238CrossRefGoogle Scholar
  49. Penny WD, Roberts SJ, Curran EA, Stokes MJ (2000) Eeg-based communication: a pattern recognition approach. IEEE Trans Rehab Eng 8(2):214–215CrossRefGoogle Scholar
  50. Pfurtscheller G, Neuper C, Schlogl A, Lugger K (1998) Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans Rehab Eng 6(3):316–325Google Scholar
  51. Rejer I, Lorenz K (2013) Genetic algorithm and forward method for feature selection in EEG feature space. J Theor Appl Comput Sci 7(2):72–82Google Scholar
  52. Rodríguez-Bermúdez G, García-Laencina PJ, Roca-Dorda J (2013) Efficient automatic selection and combination of EEG features in least squares classifiers for motor imagery brain-computer interfaces. Int J Neural Syst 23(4). doi: 10.1142/S0129065713500159
  53. Sakar OC, Kursun O, Gurgen F (2012) A feature selection method based on kernel canonical correlation analysis and the minimum redundancy-maximum relevance filter method. Expert Syst Appl 39:3432–3437CrossRefGoogle Scholar
  54. Shannon CE (1948) A mathematical theory of communication. AT T Tech J 27(379–423):623–656MathSciNetGoogle Scholar
  55. Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1:80–83CrossRefGoogle Scholar
  56. Wolpaw RJ, Birbaumer N, McFarland JD, Pfurtscheller G, Vaughaun MT (2002) Brain-computer interfaces for communication and control. Clin Neurophysiol 767–791Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.School of Computer and Systems SciencesJawaharlal Nehru UniversityNew DelhiIndia
  2. 2.Department of Computer Science, Hansraj CollegeUniversity of DelhiDelhiIndia

Personalised recommendations