Neural Computing and Applications

, Volume 28, Issue 11, pp 3239–3258 | Cite as

PSO-based feature selection and neighborhood rough set-based classification for BCI multiclass motor imagery task

  • S. Udhaya KumarEmail author
  • H. Hannah Inbarani
Original Article


In recent years, most of the researchers are developing brain–computer interface (BCI) applications for the physically disabled to be able to interconnect with peripheral devices based on brain activities. Electroencephalogram (EEG) is a very powerful tool for investigating patient’s health and different physiological activities of the brain. A significant challenge in this BCI application is the accurate and reliable recognition of motor imagery (MI) task. A brain–computer interface based on MI interprets the patient’s brain activities into a control signal through classifying EEG patterns of various motor imagination tasks. The appropriate features are essential to achieving higher classification accuracy of EEG motor imagery task. For EEG signal feature extraction, wavelet transform is suitable for analysis of nonlinear time series signals. Nevertheless, the dimension of the extracted feature is huge and it may reduce the performance of classification method. Dimensionality reduction and classification play an important role in BCI motor imagery research. In this study, hybridization of particle swarm optimization (PSO)-based rough set feature selection technique is proposed for achieving a minimal set of relevant features from extracted features. The selected features are applied to the proposed novel neighborhood rough set classifier (NRSC) method for classification of multiclass motor imagery. The experimental results are delivered for nine subjects of the BCI Competition 2008 Dataset IIa to show the greater performance of the proposed algorithm. The outcome of proposed algorithms produces a higher mean kappa of 0.743 compared to 0.70 from sequential updating semi-supervised spectral regression kernel discriminant analysis. Experimental results show that the strength of the proposed PSO-rough set and NRSC algorithms outperforms the champion of the BCI Competition IV Dataset IIa and other existing research using this dataset.


Rough set Neighborhood rough set Electroencephalogram Motor imagery Brain–computer interface 



The first author immensely acknowledges the partial financial assistance under the University Research Fellowship, Periyar University, Salem. The second author would like to thank UGC, New Delhi, for the financial support received under UGC Major Research Project No. F-41-650/2012 (SR).


  1. 1.
    Ahangi A, Karamnejad M, Mohammadi N, Ebrahimpour R, Bagheri N (2013) Multiple classifier system for EEG signal classification with application to brain–computer interfaces. Neural Comput Appl 23(1):1319–1327CrossRefGoogle Scholar
  2. 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. 3.
    Ang KK, Chin ZY, Zhang H, Guan C (2008) Filter bank common spatial pattern (FBCSP) in brain–computer interface. In: IEEE international joint conference on neural networks, pp 2391–2398Google Scholar
  4. 4.
    Ang KK, Chin ZY, Wang C, Guan C, Zhang H (2012) Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci 6:1–9CrossRefGoogle Scholar
  5. 5.
    Asensio-Cubero J, Gan JQ, Palaniappan R (2013) Multiresolution analysis over simple graphs for brain computer interfaces. J Neural Eng. doi: 10.1088/1741-2560/10/4/046014 Google Scholar
  6. 6.
    Asensio-Cubero J, Gan JQ, Palaniappan R (2013) Extracting optimal tempo-spatial features using local discriminant bases and common spatial patterns for brain computer interfacing. Biomed Signal Process 8:772–778CrossRefGoogle Scholar
  7. 7.
    Azar AT (2014) Neuro-fuzzy feature selection approach based on linguistic hedges for medical diagnosis. Int J Modell Identif Control (IJMIC) 22(3):195–206. doi: 10.1504/IJMIC.2014.065338 CrossRefGoogle Scholar
  8. 8.
    Azar AT, Banu PKN, Inbarani HH (2013). PSORR—an unsupervised feature selection technique for fetal heart rate. In: 5th international conference on modelling, identification and control (ICMIC 2013), 31 Aug, 1–2 Sept 2013, EgyptGoogle Scholar
  9. 9.
    Azar AT, Balas VE, Olariu T (2014) Classification of EEG-based brain–computer interfaces. Adv Intell Comput Technol Decis Support Syst Stud Comput Intell 486:97–106. doi: 10.1007/978-3-319-00467-9_9 Google Scholar
  10. 10.
    Azar AT, El-Said SA (2014) Performance analysis of support vector machines classifiers in breast cancer mammography recognition. Neural Comput Appl 24(5):1163–1177CrossRefGoogle Scholar
  11. 11.
    Azar AT, Hassanien AE (2015) Dimensionality reduction of medical big data using neural-fuzzy classifier. Soft Comput 19(4):1115–1127CrossRefGoogle Scholar
  12. 12.
    Azar AT, Vaidyanathan S (2015) Computational intelligence applications in modeling and control. Studies in computational intelligence, vol 575. Springer, Germany. ISBN 978-3-319-11016-5Google Scholar
  13. 13.
    Azar AT, Vashist R, Vashishtha A (2015) A rough set based total quality management approach in higher education. In: Zhu Q, Azar AT (eds) Complex system modelling and control through intelligent soft computations studies in fuzziness and soft computing, vol 319. Springer, Germany, pp 389–406. doi: 10.1007/978-3-319-12883-2_14 Google Scholar
  14. 14.
    Banu PKN, Inbarani HH, Azar AT, Hala S. Own HS, Hassanien AE (2014) Rough set based feature selection for Egyptian neonatal jaundice. In: Hassanien AE, Tolba M, Azar AT (eds) Advanced machine learning technologies and applications. In: Second international conference, AMLTA 2014, Cairo, Egypt, 28–30 Nov 2014. Proceedings, communications in computer and information science, vol 488. Springer, Berlin. ISBN: 978-3-319-13460-4Google Scholar
  15. 15.
    Barachant A, Bonnet S, Congedo M, Jutten C (2012) Multiclass brain–computer interface classification by Riemannian geometry. IEEE Trans Biomed Eng 59(1):920–928CrossRefGoogle Scholar
  16. 16.
    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(2):32–57CrossRefGoogle Scholar
  17. 17.
    Charfi F, Kraiem A (2012) Comparative study of ECG classification performance using decision tree algorithms. Int J E Health Med Commun 3(4):102–120CrossRefGoogle Scholar
  18. 18.
    Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20(1):37–46CrossRefGoogle Scholar
  19. 19.
    Cohen WW (1995) Fast effective rule induction. In: Prieditis A, Russell SJ (eds) Proc ICML, Morgan Kaufmann, CA, pp 115–123Google Scholar
  20. 20.
    Desgraupes B (2013) Clustering indices. University of Paris Ouest—Lab Modal’X, Nanterre, pp 1–34Google Scholar
  21. 21.
    Dingyin H, Wei L, Xi C (2011) Feature extraction of motor imagery EEG signals based on wavelet packet decomposition. In: Proceedings of the 2011 IEEE international conference on complex medical engineering, pp 694–697Google Scholar
  22. 22.
    Dong T, Shang W, Zhu H (2011) Naïve Bayesian classifier based on the improved feature weighting algorithm. In: International conference on advanced research on computer science and information engineering, vol 152, pp 142–147Google Scholar
  23. 23.
    Daubechies I (1990) The wavelet transform, time–frequency localization and signal analysis. IEEE Trans Inf Theory 36(5):961–1005MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Eberhart RC, Shi Y (2001) Particle swarm optimization: developments, applications and resources. In: Proceedings of IEEE international conference on evolutionary computation, vol 1, pp 81–86Google Scholar
  25. 25.
    Elshazly HI, Azar AT, Elkorany AM, Hassanien AE (2013) Hybrid system based on rough sets and genetic algorithms for medical data classifications. Int J Fuzzy Syst Appl (IJFSA) 3(4):31–46CrossRefGoogle Scholar
  26. 26.
    Elshazly HI, Elkorany AM, Hassanien AE, Azar AT (2013) Ensemble classifiers for biomedical data: performance evaluation. In: IEEE 8th international conference on computer engineering and systems (ICCES), 26–28 Nov 2013, Ain Shams University, pp 184–189. doi: 10.1109/ICCES.2013.6707198. Print ISBN: 978-1-4799-0078-7
  27. 27.
    Garrett D, Peterson DA, Anderson CW, Thaut MH (2003) Comparison of linear, nonlinear, and feature selection methods for EEG signal classification. IEEE Trans Neural Syst Rehabil Eng 11(2):141–144CrossRefGoogle Scholar
  28. 28.
    Gouy-Pailler C, Congedo M, Brunner C, Jutten C, Pfurtscheller G (2010) Nonstationary brain source separation for multiclass motor imagery. IEEE Trans Biomed Eng 57(2):469–478CrossRefGoogle Scholar
  29. 29.
    Greco S, Matarazzo B, Slowinski R (1999) Rough approximation of a preference relation by dominance relations. Eur J Oper Res 117(1):63–83CrossRefzbMATHGoogle Scholar
  30. 30.
    Guo L, Wu Y, Zhao L, Cao T, Yan W, Shen X (2011) Classification of mental task from EEG signals using immune feature weighted support vector machines. IEEE Trans Magn 47(5):866–869CrossRefGoogle Scholar
  31. 31.
    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
  32. 32.
    Gupta A, Agrawal RK, Kaur B (2015) Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods. Soft Comput 19(10):1–14CrossRefGoogle Scholar
  33. 33.
    Hari MR, Anuragm T, Shailja S (2013) ECG signal processing for abnormalities detection using multi-resolution wavelet transform and artificial neural network classifier. Measurement 46(9):3238–3246CrossRefGoogle Scholar
  34. 34.
    Hassanien AE, Azar AT (2015) Brain computer interfaces: current trends and applications, intelligent systems reference library, vol 74. Springer, Berlin. ISBN: 978-3-319-10977-0Google Scholar
  35. 35.
    Hassanien AE, Azar AT, Snasel V, Kacprzyk J, Abawajy JH (2015) Big data in complex systems: challenges and opportunities, studies in big data, vol 9. Springer, Berlin. ISBN 978-3-319-11055-4Google Scholar
  36. 36.
    Hassanien AE, Tolba M, Azar AT (2014) Advanced machine learning technologies and applications: second international conference. In: AMLTA 2014, Cairo, Egypt, 28–30 Nov 2014. Proceedings, communications in computer and information science, vol 488. Springer, Berlin. ISBN: 978-3-319-13460-4Google Scholar
  37. 37.
    Hu Q, Yu D, Liu J, Wu C (2008) Neighborhood rough set based heterogeneous feature subset selection. Infor Science 178(18):3577–3594MathSciNetCrossRefzbMATHGoogle Scholar
  38. 38.
    Hu Q, Yu D, Xie Z (2008) Neighborhood classifiers. Expert Syst Appl 34(2):866–876CrossRefGoogle Scholar
  39. 39.
    Hu Q, Yu D, Xie Z, Liu J (2006) Fuzzy probabilistic approximation spaces and their information measures. IEEE Trans Fuzzy Syst 14(2):191–201CrossRefGoogle Scholar
  40. 40.
    Inbarani HH, Azar AT, Jothi G (2014) Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis. Comput Methods Programs Biomed 113(1):175–185CrossRefGoogle Scholar
  41. 41.
    Inbarani HH, Bagyamathi M, Azar AT (2015) A novel hybrid feature selection method based on rough set and improved harmony search. Neural Comput Appl 26(8):1859–1880CrossRefGoogle Scholar
  42. 42.
    Inbarani HH, Banu PKN, Azar AT (2014) Feature selection using swarm-based relative reduct technique for fetal heart rate. Neural Comput Appl 25(3–4):793–806CrossRefGoogle Scholar
  43. 43.
    Inbarani HH, Kumar SS, Azar AT, Hassanien AE (2015) Hybrid TRS-PSO clustering approach for Web2.0 social tagging system. Int J Rough Sets Data Anal (IJRSDA) 2(1):22–37CrossRefGoogle Scholar
  44. 44.
    Jothi G, Inbarani HH, Azar AT (2013) Hybrid tolerance-PSO based supervised feature selection for digital mammogram images. Int J Fuzzy Syst Appl (IJFSA) 3(4):15–30CrossRefGoogle Scholar
  45. 45.
    Kam TK, Suk HI, Lee SW (2013) Non-homogeneous spatial filter optimization for ElectroEncephaloGram (EEG) based motor imagery classification. Neurocomputing 108:58–68CrossRefGoogle Scholar
  46. 46.
    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
  47. 47.
    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
  48. 48.
    Kumar SS, Inbarani HH, Azar AT, Own HS, Balas VE (2014) Optimistic multi-granulation rough set based classification for neonatal jaundice diagnosis. In: 6th International workshop on soft computing applications, 24–26 July 2014, Timisoara, RomaniaGoogle Scholar
  49. 49.
    Kumar SU, Inbarani HH (2015) A novel neighborhood rough set based classification approach for medical diagnosis. Procedia Comput Sci 47:351–359CrossRefGoogle Scholar
  50. 50.
    Kumar SU, Inbarani HH, Azar AT, Hassanien AE (2014) Identification of heart valve disease using Bijective soft sets theory. Int J Rough Sets Data Anal 1(2):1–14CrossRefGoogle Scholar
  51. 51.
    Kumar SU, Inbarani HH, Azar AT (2015) Hybrid Bijective soft set—neural network for ECG arrhythmia classification. Int J Hybrid Intell Syst 12(2):103–118CrossRefGoogle Scholar
  52. 52.
    Li X, Chen X, Yan Y, Wei W, Wang ZJ (2014) Classification of EEG signals using a multiple kernel learning support vector machine. Sens (Basel) 14(7):12784–12802CrossRefGoogle Scholar
  53. 53.
    Liu H, Feng B, Wei J (2008) An effective data classification algorithm based on the decision table grid. In: Seventh IEEE/ACIS international conference on computer and information science, pp 306–311Google Scholar
  54. 54.
    Lotte F, Congedo M, Lecuyer A, Lamarche F, Arnaldi B (2007) A review of classification algorithms for eeg-based brain–computer interfaces. J Neural Eng 4(2):1–13CrossRefGoogle Scholar
  55. 55.
    Nicolas-Alonso LF, Corralejo R, Gomez-Pilar J, Álvarez D, Hornero R (2015) Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain computer interfaces. Neurocomputing 159:186–196CrossRefGoogle Scholar
  56. 56.
    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
  57. 57.
    Palaniappan R (2005) Brain computer interface design using band powers extracted during mental tasks. In: Proceedings of the 2nd international IEEE EMBS conference on neural engineering, Arlington, pp 321–324Google Scholar
  58. 58.
    Palaniappan R, Raveendran P, Nishida S, Saiwaki N (2002) A new brain-computer interface design using fuzzy ARTMAP. IEEE Trans Neural Syst Rehabil Eng 10(3):140–148CrossRefGoogle Scholar
  59. 59.
    Pawlak Z (1982) Rough sets. Int J Comput Inf Sci 11(5):341–356CrossRefzbMATHGoogle Scholar
  60. 60.
    Pawlak Z, Skowron A (2007) Rough sets: some extensions. Inf Sci 77:28–40MathSciNetCrossRefzbMATHGoogle Scholar
  61. 61.
    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 Rehabil Eng 6(3):316–325CrossRefGoogle Scholar
  62. 62.
    Shi SP, Qiu J, Sun XY, Suo SB, Huang SY, Liang RP (2012) PMeS: prediction of methylation sites based on enhanced feature encoding scheme. PLoS One 7(6):1–11Google Scholar
  63. 63.
    Skowron A, Stepaniuk J (1996) Tolerance approximation spaces. Fundamenta Informaticae 27(2–3):245–253MathSciNetzbMATHGoogle Scholar
  64. 64.
    Slezak D, Ziarko W (2005) The investigation of the Bayesian rough set model. Int J Approx Reason 40(1–2):81–91MathSciNetCrossRefzbMATHGoogle Scholar
  65. 65.
    Slowinski R, Vanderpooten D (2000) A generalized definition of rough approximations based on similarity. IEEE Trans Knowl Data Eng 12(2):331–336CrossRefGoogle Scholar
  66. 66.
    Subasi A (2007) EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 32(4):1084–1093CrossRefGoogle Scholar
  67. 67.
    Tangermann M, Müller KR, Aertsen A, Birbaumer N, Braun C, Brunner C, Leeb R, Mehring C, Miller KJ, Mueller-Putz G, Nolte G, Pfurtscheller G, Preissl H, Schalk G, Schlögl A, Vidaurre C, Waldert S, Blankertz B (2012) Review of the BCI competition IV. Front Neurosci 6 article 55:1–31Google Scholar
  68. 68.
    Wang H (2011) Multiclass filters by a weighted pairwise criterion for EEG single-trial classification. IEEE Trans Biomed Eng 58:1412–1420CrossRefGoogle Scholar
  69. 69.
    Wang D, Miao D, Blohm G (2012) Multi-class motor imagery EEG decoding for brain-computer interfaces. Front Neurosci 6 article 151:1–13Google Scholar
  70. 70.
    Wang Y, Gao S, Gao X (2005) Common spatial pattern method for channel selection in motor imagery based brain computer interface. Conf Proc IEEE Eng Med Biol Soc 1:5392–5395Google Scholar
  71. 71.
    Wolpaw RJ, Birbaumer N, McFarland JD, Pfurtscheller G, Vaughaun MT (2002) Brain-computer interfaces for communication and control. Clin Neurophysiol 113(6):767–791CrossRefGoogle Scholar
  72. 72.
    Yao Y (2005) Probabilistic rough set approximations. Int J Approx Reason 49(2):255–271CrossRefzbMATHGoogle Scholar
  73. 73.
    Yao Y, Yao B (2012) Covering based rough set approximations. Inf Sci 200(1):91–107MathSciNetCrossRefzbMATHGoogle Scholar
  74. 74.
    Yao Y, Zhao Y (2008) Attribute reduction in decision-theoretic rough set models. Inf Sci 178(17):3356–3373MathSciNetCrossRefzbMATHGoogle Scholar
  75. 75.
    Yong L, Wenliang H, Yunliang J, Zhiyong Z (2014) Quick attribute reduct algorithm for neighborhood rough set model. Inf Sci 271(1):65–81MathSciNetCrossRefzbMATHGoogle Scholar
  76. 76.
    Zhu Q, Azar AT (2015) Complex system modelling and control through intelligent soft computations. Studies in fuzziness and soft computing, vol 319. Springer, Germany. ISBN: 978-3-319-12882-5Google Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  1. 1.Department of Computer SciencePeriyar UniversitySalemIndia

Personalised recommendations