A performance based feature selection technique for subject independent MI based BCI

  • Md. A. Mannan JoadderEmail author
  • Joshua J. Myszewski
  • Mohammad H. Rahman
  • Inga Wang
Part of the following topical collections:
  1. Special Issue on Artificial Intelligence in Health Informatics



Significant research has been conducted in the field of brain computer interface (BCI) algorithm development, however, many of the resulting algorithms are both complex, and specific to a particular user as the most successful methodology can vary between individuals and sessions. The objective of this study was to develop a simple yet effective method of feature selection to improve the accuracy of a subject independent BCI algorithm and streamline the process of BCI algorithm development. Over the past several years, several high precision features have been suggested by researchers to classify different motor imagery tasks. This research applies fourteen of these features as a feature pool that can be used as a reference for future researchers. Additionally, we look for the most efficient feature or feature set with four different classifiers that best differentiates several motor imagery tasks. In this work we have successfully employed a feature fusion method to obtain the best sub-set of features. We have proposed a novel computer aided feature selection method to determine the best set of features for distinguishing between motor imagery tasks in lieu of the manual feature selection that has been performed in past studies. The features selected by this method were then fed into a Linear Discriminant Analysis, K-nearest neighbor, decision tree, or support vector machine classifier for classification to determine the overall performance.


The methods used were a novel performance based additive feature fusion algorithm working in conjunction with machine learning in order to classify the motor imagery signals into particular states. The data used for this study was collected from BCI competition III dataset IVa.


The result of this algorithm was a classification accuracy of 99% for a subject independent algorithm with less computation cost compared to traditional methods, in addition to multiple feature/classifier combinations that outperform current subject independent methods.


The conclusion of this study and its significance is that it developed a viable methodology for simple, efficient feature selection and BCI algorithm development, which leads to an overall increase in algorithm classification accuracy.


Machine learning Brain computer interfaces Motor imagery Subject independent BCI Biomedical signal processing Electroencephalography 



The continued support of the University of Wisconsin-Milwaukee and the University of Wisconsin-Milwaukee College of Engineering and Applied Science, as well as the continued support of our mentors and loved ones throughout our work.


  1. 1.
    Siuly S, Li Y. Improving the separability of motor imagery EEG signals using a cross correlation-based least square support vector machine for brain–computer interface. IEEE Trans Neural Syst Rehabilit Eng. 2012;20(4):526–38.CrossRefGoogle Scholar
  2. 2.
    Zhou J, et al. Classification of motor imagery EEG using wavelet envelope analysis and LSTM networks. In: 2018 Chinese Control and Decision Conference (CCDC). IEEE, 2018.Google Scholar
  3. 3.
    Kamousi B, Liu Z, He B. Classification of motor imagery tasks for brain-computer interface applications by means of two equivalent dipoles analysis. IEEE Trans Neural Syst Rehabilit Eng. 2005;13(2):166–71.CrossRefGoogle Scholar
  4. 4.
    Cantillo-Negrete J, et al. An approach to improve the performance of subject-independent BCIs-based on motor imagery allocating subjects by gender. Biomed Eng. 2014;13(1):158.Google Scholar
  5. 5.
    Vansteensel MJ, Kristo G, Aarnoutse EJ, Ramsey NF. The brain-computer interface researcher’s questionnaire: from research to application. Brain-Comput Interfaces. 2017;4(4):236–47. Scholar
  6. 6.
    Saha S, Mamun KA, Ahmed K, Mostafa R, et al. Progress in brain computer interfaces: challenges and trends. arXiv:1901.03442v1 [cs.HC}, 2019.Google Scholar
  7. 7.
    Ahn M, Jun SC. Performance variation in motor imagery brain–computer interface: a brief review. J Neurosci Methods. 2015;243:103–10.CrossRefGoogle Scholar
  8. 8.
    Vega R, Sajed T, Mathewson KW, Khare K, et al. Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals. Artif Intell Res. 2017;6(1):37–51. Scholar
  9. 9.
    Lotte F, Bougrain L, Cichocki A, Clerc M, et al. A review of classification algorithms for EEG-based brain-computer interfaces: a 10 year update. J Neural Eng. 2018. Scholar
  10. 10.
    Shenoy P, Krauledat M, Blankertz B, Rao RPN, Müller KR. Towards adaptive classification for BCI. J Neural Eng. 2006;3:1. Scholar
  11. 11.
    Jayaram V, et al. Transfer learning in brain-computer interfaces. IEEE Comput Intell Mag. 2016;11:1. Scholar
  12. 12.
    Tomioka R, Müller KR. A regularized discriminative framework for EEG analysis with application to brain-computer interface. NeuroImage. 2010;49(1):415–32. Scholar
  13. 13.
    Rahman MKM, Mannan Joadder MA. A review on the components of EEG-based motor imagery classification with quantitative comparison. Appl Theory Comput Technol. 2017;2(2):1–15.CrossRefGoogle Scholar
  14. 14.
    Ghaemi A, et al. Automatic channel selection in EEG signals for classification of left or right hand movement in Brain Computer Interfaces using improved binary gravitation search algorithm. Biomed Signal Process Control. 2017;33:109–18.CrossRefGoogle Scholar
  15. 15.
    Atkinson J, Campos D. Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers. Expert Syst Appl. 2016;47:35–41.CrossRefGoogle Scholar
  16. 16.
    Bajaj V, Taran S, Sengur A. Emotion classification using flexible analytic wavelet transform for electroencephalogram signals. Health Inf Sci Syst. 2018;6(1):12.CrossRefGoogle Scholar
  17. 17.
    Taran S, Bajaj V, Siuly S. An optimum allocation sampling based feature extraction scheme for distinguishing seizure and seizure-free EEG signals. Health Inf Sci Syst. 2017;5(1):7.CrossRefGoogle Scholar
  18. 18.
    Wu W, et al. Probabilistic common spatial patterns for multichannel EEG analysis. IEE Trans Pattern Anal Mach Intell. 2015;37(3):639–53. Scholar
  19. 19.
    Sannelli C, Vidaurre C, Müller KR, Blankertz B. Ensembles of adaptive spatial filters increase BCI performance: an online evaluation. J Neural Eng. 2016;13:4. Scholar
  20. 20.
    Kevric J, Subasi A. Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system. Biomed Signal Process Control. 2017;31:398–406. Scholar
  21. 21.
    Blankertz B, et al. The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans Biomed Eng. 2004;51(6):1044–51.CrossRefGoogle Scholar
  22. 22.
    Siuly S, Li Y, Zhang Y. EEG Signal Analysis and Classification. IEEE Trans Neural Syst Rehabilit Eng. 2016;11:141–4.Google Scholar
  23. 23.
    Dornhege G, Blankertz B, Curio G, Müller KR. Boosting bit rates in non-invasive EEG single-trial classifications by feature combination and multi-class paradigms. IEEE Trans Biomed Eng. 2004;51(6):993–1002.CrossRefGoogle Scholar
  24. 24.
    Kamousi B, Liu Z, He B. Classification of motor imagery tasks for brain-computer interface applications by means of two equivalent dipoles analysis. IEEE Trans Neural Syst Rehabilit Eng. 2005;13(2):166–71.CrossRefGoogle Scholar
  25. 25.
    Lotte F, Guan C. Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Trans Biomed Eng. 2011;58(2):355–62.CrossRefGoogle Scholar
  26. 26.
    Shan H, et al. EEG-based motor imagery classification accuracy improves with gradually increased channel number. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) IEEE, 2012.Google Scholar
  27. 27.
    Su Y, Li Y, Wang S. Filter ensemble regularized common spatial pattern for EEG classification. In: Seventh International Conference on Digital Image Processing (ICDIP 2015). Vol 9631. International Society for Optics and Photonics, 2015.Google Scholar
  28. 28.
    Ramoser H, Muller-Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans Rehabilit Eng. 2000;8(4):441–6.CrossRefGoogle Scholar
  29. 29.
    Baziyad AG, Djemal R. A study and performance analysis of three paradigms of wavelet coefficients combinations in three-class motor imagery based BCI. In: 2014 5th International Conference on Intelligent Systems, Modelling and Simulation (ISMS), IEEE, 2014.Google Scholar
  30. 30.
    Dutta S, Chatterjee A, Munshi S. Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification. Med Eng Phys. 2010;32(10):1161–9.CrossRefGoogle Scholar
  31. 31.
    Chandaka S, Chatterjee A, Munshi S. Cross-correlation aided support vector machine classifier for classification of EEG signals. Expert Syst Appl. 2009;36(2):1329–36.CrossRefGoogle Scholar
  32. 32.
    Chandaka S, Amitava C, Sugata M. Support vector machines employing cross-correlation for emotional speech recognition. Measurement. 2009;42(4):611–8.CrossRefGoogle Scholar
  33. 33.
    Krishna DH, Pasha IA, Savithri TS. Classification of EEG motor imagery multi class signals based on cross correlation. Procedia Comput Sci. 2016;85:490–5.CrossRefGoogle Scholar
  34. 34.
    Siuly S, Yan L, Yanchun Z. Cross-correlation aided logistic regression model for the identification of motor imagery EEG signals in BCI applications. EEG signal analysis and classification. Cham: Springer; 2016. p. 153–72.Google Scholar
  35. 35.
    Zarei R, et al. A PCA aided cross-covariance scheme for discriminative feature extraction from EEG signals. Comput Methods Prog Biomed. 2017;146:47–57.CrossRefGoogle Scholar
  36. 36.
    Yin X, Hadjiloucas S, Zhang Y. Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers. Comput Methods Prog Biomed. 2016;127:64–82.CrossRefGoogle Scholar
  37. 37.
    Meng J, et al. Automated selecting subset of channels based on CSP in motor imagery brain-computer interface system. In: 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO) IEEE, 2009.Google Scholar
  38. 38.
    Reeves RD, et al. Application of correlation analysis for signal-to-noise enhancement in flame spectrometry. Use of correlation in determination of rhodium by atomic fluorescence. Anal Chem. 1973;45(2):253–8.CrossRefGoogle Scholar
  39. 39.
    Taran S, et al. Features based on analytic IMF for classifying motor imagery EEG signals in BCI applications. Measurement. 2018;116:68–76.CrossRefGoogle Scholar
  40. 40.
    Resalat SN, Valiallah S. A study of various feature extraction methods on a motor imagery based brain computer interface system. Basic Clin Neurosci. 2016;7(1):13.Google Scholar
  41. 41.
    Cantillo-Negrete J, et al. An approach to improve the performance of subject-independent BCIs-based on motor imagery allocating subjects by gender. Biomed Eng. 2014;13(1):158.Google Scholar
  42. 42.
    Katz MJ. Fractals and the analysis of waveforms. Comput Biol Med. 1988;18(3):145–56.CrossRefGoogle Scholar
  43. 43.
    Higuchi T. Approach to an irregular time series on the basis of the fractal theory. Physica D. 1988;31(2):277–83.MathSciNetCrossRefGoogle Scholar
  44. 44.
    Tolić M, Jović F. Classification of wavelet transformed EEG signals with neural network for imagined mental and motor tasks. Int J Fundam Appl Kinesiol. 2013;45(1):130–8.Google Scholar
  45. 45.
    Hu J, Xiao D, Mu Z. Application of energy entropy in motor imagery EEG classification. JDCTA. 2009;3(2):83–90.Google Scholar
  46. 46.
    Abdul-Latif AA, et al. Power changes of EEG signals associated with muscle fatigue: the root mean square analysis of EEG bands. In: Proceedings of the 2004, Intelligent Sensors, Sensor Networks and Information Processing Conference, 2004. IEEE, 2004.Google Scholar
  47. 47.
    Al-Fahoum AS, Ausilah AA. Methods of EEG signal features extraction using linear analysis in frequency and time-frequency domains. ISRN Neuroscience. 2014;2014:7.CrossRefGoogle Scholar
  48. 48.
    Gurudath N, Riley HB. Drowsy driving detection by EEG analysis using wavelet transform and K-means clustering. Procedia Comput Sci. 2014;34:400–9.CrossRefGoogle Scholar
  49. 49.
    Ho TK. The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell. 1998;20(8):832–44.CrossRefGoogle Scholar
  50. 50.
    Mathworks®, MATLAB™ R2017b, Natick, Massachusetts 2017.Google Scholar
  51. 51.
    Myszewski J, Reina T, Bergendahl E, Rahman M, Development of a classification algorithm for bicep flexion from multi-subject EEG data. In: Proceedings of the Biomedical Engineering Society 2018 Meeting, Oct 2018, Atlanta, Georgia [Online]. Available: 3 Feb 2019.
  52. 52.
    Wang H, Zhang Y. Detection of motor imagery EEG signals employing Naïve Bayes based learning process. Measurement. 2016;86:148–58.CrossRefGoogle Scholar
  53. 53.
    Fu R, et al. Improvement motor imagery EEG classification based on regularized linear discriminant analysis. J Med Syst. 2019;43(6):169.CrossRefGoogle Scholar
  54. 54.
    Ye J, et al. Feature reduction via generalized uncorrelated linear discriminant analysis. IEEE Trans Knowl Data Eng. 2006;10:1312–22.Google Scholar
  55. 55.
    Szuflitowska B, Orłowski P. Comparison of the EEG signal classifiers LDA, NBC and GNBC based on time-frequency features. Pomiary Automatyka Robotyka. 2017;21:39–45.CrossRefGoogle Scholar
  56. 56.
    Bostanov V. 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. 2004;51(6):1057–106.CrossRefGoogle Scholar
  57. 57.
    Garrett D, et al. Comparison of linear, nonlinear, and feature selection methods for EEG signal classification. IEEE Trans Neural Syst Rehabilit Eng. 2003;11(2):141–4.CrossRefGoogle Scholar
  58. 58.
    Spiewak C, Islam M, Zaman MA, Rahman MH. A comprehensive study on EMG feature extraction and classifiers. Op Acc J Bio Eng App. 2018. Scholar
  59. 59.
    Altman NS. An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat. 1992;46(3):175–85. Scholar
  60. 60.
    Prashant G. Decision trees in machine learning. 2017. Available online: Accessed 05 May 2019).
  61. 61.
    Hatamikia S, Nasrabadi AM. Subject independent BCI based on LTCCSP method and GA wrapper optimization. In: IEEE 22nd Iranian Conference on Biomedical Engineering (ICBME), 2015.Google Scholar
  62. 62.
    Dai M, et al. Transfer kernel common spatial patterns for motor imagery brain-computer interface classification. In: Computational and Mathematical Methods in Medicine 2018 (2018).CrossRefGoogle Scholar
  63. 63.
    Lotte F, Cuntai G, Ang KK. Comparison of designs towards a subject-independent brain-computer interface based on motor imagery. In: 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2009.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Md. A. Mannan Joadder
    • 1
    Email author
  • Joshua J. Myszewski
    • 2
  • Mohammad H. Rahman
    • 2
  • Inga Wang
    • 3
  1. 1.Department of Electrical, & Electronic EngineeringUnited International UniversityDhakaBangladesh
  2. 2.Department of Biomedical EngineeringUniversity of Wisconsin-MilwaukeeMilwaukeeUSA
  3. 3.Department of Occupational Science & TechnologyUniversity of Wisconsin-MilwaukeeMilwaukeeUSA

Personalised recommendations