Skip to main content

Advertisement

SpringerLink
Log in

A comparison of feature extraction strategies using wavelet dictionaries and feature selection methods for single trial P300-based BCI

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

The P300 component of event-related potentials (ERPs) is widely used in the implementation of brain computer interfaces (BCI). In this context, one of the main issues to solve is the binary classification problem that entails differentiating between electroencephalographic (EEG) signals with and without P300. Given the particularly unfavorable signal-to-noise ratio (SNR) in the single-trial detection scenario, this is a challenging problem in the pattern recognition field. To the best of our knowledge, there are no previous experimental studies comparing feature extraction and selection methods for single trial P300-based BCIs using unified criteria and data. In order to improve the performance and robustness of single-trial classifiers, we analyzed and compared different alternatives for the feature generation and feature selection blocks. We evaluated different orthogonal decompositions based on the wavelet transform for feature extraction, as well as different filter, wrapper, and embedded alternatives for feature selection. Accuracies over 75% were obtained for most of the analyzed strategies with a relatively low computational cost, making them attractive for a practical BCI implementation using inexpensive hardware.

Experiments performed for P300 detection

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. Available in http://akimpech.izt.uam.mx/p300db/doku.php

  2. The DDWT decompositions were obtained using the MATLAB Wavelet Toolbox (Mathworks, Inc., Natica, MA, USA)

  3. The WPT decompositions were obtained using the MLDB7 MATLAB Toolbox provided by Dr. Naoki Saito.

  4. Statistics were carried out using SigmaPlot 12 from Systat Software, Inc., San Jose California USA, www.systatsoftware.com.

References

  1. Amini Z, Abootalebi V, Sadeghi M (2013) Comparison of performance of different feature extraction methods in detection of P300. Biocybern Biomed Eng 33(1):3–20

    Article  Google Scholar 

  2. Bashashati A, Fatourechi M, Ward R, Birch G (2007) A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals. J Neural Eng 4(2):32–57

    Article  Google Scholar 

  3. Blankertz B, Lemm S, Treder M, Haufe S, Müller K-R (2011) Single-trial analysis and classification of ERP components — a tutorial. Neuroimage 56(2):814–825

    Article  PubMed  Google Scholar 

  4. 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):1057–1061

    Article  PubMed  Google Scholar 

  5. Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electric Eng 40(1):16–28

    Article  Google Scholar 

  6. Coifman R, Wickerhauser M (1992) Entropy-based algorithms for best basis selection. IEEE Trans Inf Theory 38(2):713– 718

    Article  Google Scholar 

  7. Dal Seno B, Matteucci M, Mainardi L (2008) A genetic algorithm for automatic feature extraction in P300 detection. In: 2008 IEEE International joint conference on neural networks (IEEE World congress on computational intelligence), pp 3145–3152

  8. Dal Seno B, Matteucci M, Mainardi L (2010) Online detection of P300 and error potentials in a BCI speller. Comput Intell Neurosci 2010:11

    Article  Google Scholar 

  9. Duin R, Juszczak P, Paclik P, Pekalska E, de Ridder D, Tax D (2004) PRTools4 - a matlab toolbox for pattern recognition

  10. Farwell L, Donchin E (1988) Talking off the top of your head: toward a metal prosthesis utilizing event-related brain potentials. Electroencephalograph Clinical Neurophysiol 70:510–523

    Article  CAS  Google Scholar 

  11. Goldberg D (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley Publishing

  12. Guyon I, Gunn S, Nikravesh M, Zadeh L (2006) Feature extraction, foundations and applications. Series studies in fuzziness and soft computing. Springer

  13. Herrmann S, Rach S, Vosskuhl J, Struber D (2014) Time–frequency analysis of event-related potentials: a brief tutorial. Brain Topograph 27:438–450

    Article  Google Scholar 

  14. Jansen B, Allam A, Kota P, Lachance K, Osho A, Sundaresan K (2004) An exploratory study of factors affecting single trial p300 detection. IEEE Trans Biomed Eng 51(6):975–978, 6

    Article  PubMed  Google Scholar 

  15. Kaper M, Meinicke P, Grossekathoefer U, Lingner T, Ritter H (2004) Bci competition 2003-data set iib: support vector machines for the p300 speller paradigm. IEEE Trans Biomed Eng 51(6):1073–1076

    Article  PubMed  Google Scholar 

  16. Kee C-Y, Ponnambalam S, Loo C-K (2015) Multi-objective genetic algorithm as channel selection method for P300 and motor imagery data set. Neurocomputing 161:120–131

    Article  Google Scholar 

  17. Kindermans P-J, Verschore H, Verstraeten D, Schrauwen B (2012) A P300 BCI for the masses: prior information enables instant unsupervised spelling. In: Advances in neural information processing systems, pp 710–718

  18. Kubler A, Mushahwar V, Hochberg L, Donoghue J (2006) BCI meeting 2005-workshop on clinical issues and applications. IEEE Trans Neural Syst Rehabil Eng 14(2):131–134

    Article  PubMed  CAS  Google Scholar 

  19. Li K, Narayan Raju V, Sankar R, Arbel Y, Donchin E (2011) Advances and challenges in signal analysis for single trial P300-BCI. Springer, Berlin, pp 87–94

    Google Scholar 

  20. Lindig León C, Yáñez Suárez O (2013) Optimized detection of the infrequent response in P300-based brain-computer interfaces. Revista Mexicana de Ingeniería Biomédica 34(1):53–70

    Google Scholar 

  21. Lotte F, Congedo M, Lécuyer A, Lamarche F, Arnaldi B (2007) A review of classification algorithms for EEG-based brain-computer interfaces. J Neural Eng 4(2)

  22. Mak JN, Arbel Y, Minett JW, McCane LM, Yuksel B, Ryan D, Thompson D, Bianchi L, Erdogmus D (2011) Optimizing the P300-based brain-computer interface: current status, limitations and future directions. J Neural Eng 8(2):025003

    Article  PubMed  CAS  Google Scholar 

  23. Milone D, Rufiner L, Acevedo R, Di Persia L, Torres H (2006) Introducción a las Señales y a los Sistemas Discretos. EDUNER

  24. Mitchell M (1999) An introduction to genetic algorithms 5ed. MIT Press, Cambridge

    Google Scholar 

  25. Mowla MR, Huggins JE, Thompson DE (2017) Enhancing P300-BCI performance using latency estimation. Brain-Comput Interfaces 4(3):137–145

    Article  Google Scholar 

  26. NYSD of Health (2006) BCI laboratory of the wadsworth center, Junio

  27. Pacheco M, Atum Y, Acevedo R, Rufiner L (2016) Evaluation of different parents selection methods in a genetic algorithm wrapper for P300 BCI. In: XXV Congresso Brasileiro de Engenharia Biomédica (SBEB 2016)

  28. Perseh B, Sharafat A (2012) An efficient P300-based BCI using wavelet features and IBPSO-based channel selection. J Med Signals Sensors 2(3):128

    Google Scholar 

  29. Peterson V, Acevedo R, Rufiner HL, Spies R (2015) Local discriminant wavelet packet basis for signal classification in brain computer interface. In: VI Latin American congress on biomedical engineering CLAIB 2014, Paraná, Argentina. Springer International Publishing, Cham, pp 584–587

  30. Peterson V, Atum Y, Jauregui F, Gareis I, Acevedo R, Rufiner L (2013) Detección de potenciales evocados relacionados a eventos en interfaces cerebro-computadora mediante transformada wavelet. Revista Ingeniería Biomédica 7(14):51–59

    Google Scholar 

  31. Picton TW (1992) The P300 wave of the human event-related potential. J Clin Neurophysiol 9(4):456–479

    Article  PubMed  CAS  Google Scholar 

  32. Qi H, Xu M, Li W, Yuan D, Zhu W, An X, Ming D, Wan B, Wang W (2010) Feature selection study of P300 speller using support vector machine. In: 2010 IEEE International conference on robotics and biomimetics (ROBIO). IEEE, pp 1331–1334

  33. Rakotomamonjy A, Guigue V (2008) Competition III: dataset II- ensemble of SVMs for BCI P300 Speller. IEEE Trans Biomed Eng 55(3):1147–1154

    Article  PubMed  Google Scholar 

  34. Rufiner L (2006) Análisis y modelado digital de la voz. Técnicas recientes y aplicaciones. Ediciones UNL, Colecci’on Ciencia y Técnica, 1a. ed edition

  35. Saavedra C, Bougrain L (2013) Wavelet-based semblance for P300 single-trial detection. In: International conference on bio-inspired systems and signal processing BIOSIGNAL 2013

  36. Saito N (2000) Local feature extraction and its applications using a library of bases. In: Topics in analysis and its applications: selected theses. World Scientific, pp 269–451

  37. Saito N, Coifman R (1995) Local discriminant bases and their applications. J Math Imaging Vis 5:337–358

    Article  Google Scholar 

  38. Samar V (1999) Wavelet analysis of neuroelectric waveforms: a conceptual tutorial. Brain Lang 66:7–60

    Article  PubMed  CAS  Google Scholar 

  39. Schalk G, McFarland D, Hinterberger T, Birbaumer N, Wolpaw J (2004) BCI2000: a general-purpose brain-computer interface (BCI) system. IEEE Trans Biomed Eng 51(6):1034–1043

    Article  PubMed  Google Scholar 

  40. Sellers EW, Donchin E (2006) A P300-based brain–computer interface: initial tests by ALS patients. Clinical Neurophysiol 117(3):538–548

    Article  Google Scholar 

  41. Serby H, Yom-Tov E, Inbar GF (2005) An improved p300-based brain-computer interface. IEEE Trans Neural Syst Rehab Eng 13(1):89–98

    Article  Google Scholar 

  42. Smith E, Delargy M (2005) Locked-in syndrome. Bmj 330(7488):406–409

    Article  PubMed  PubMed Central  Google Scholar 

  43. Turnip A, Haryadi, Kusumandari D, Soetraprawata D (2014) A comparison of extraction techniques for the rapid electroencephalogram-P300 signals. Adv Sci Lett 20(1):80–85

    Article  Google Scholar 

  44. Wang P, Shen J (2011) Research of P300 feature extraction algorithm based on wavelet transform and fisher distance. Int J Educ Manag Eng 1(6):36–43

    Article  CAS  Google Scholar 

  45. Webb A, Copsey A (2011) Statistical pattern recognition, 3rd edn. Wiley, Chichester

    Book  Google Scholar 

  46. Wolpaw J, Birbaumer N, Heetderks W, McFarland D, Peckham P, Schalk G, Donchin E, Quatrano L, Robinson C, Vaughan T (2000) Brain-computer interface technology: a review of the first international meeting. IEEE Trans Rehab Eng 8(2):164–173

    Article  CAS  Google Scholar 

  47. Xie J, Qiu Z (2007) The effect of imbalanced data sets on LDA: a theoretical and empirical analysis. Pattern Recogn 40:557–562

    Article  Google Scholar 

  48. Zhuo L, Zheng J, Wang F, Li X, Ai B, Qian J (2008) A genetic algorithm based wrapper feature selection method for classification of hyperspectral images using support vector machine. Int Arch Photogram Remote Sensing Spatial Inf Sci 37:397–402

    Google Scholar 

Download references

Funding

This study received financial support from Universidad Nacional de Entre Ríos (UNER), Universidad Nacional del Litoral (UNL), and Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET).

Author information

Authors and Affiliations

  1. LIRINS - Facultad de Ingeniería, Universidad Nacional de Entre Rios, Oro Verde, Argentina

    R. Acevedo, Y. Atum & J. Biurrun Manresa

  2. Facultad de Ingenieria, Universidad Nacional de Entre Rios, Oro Verde, Argentina

    I. Gareis & L. Rufiner

  3. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional (SINC), CONICET-UNL, Santa Fe, Argentina

    I. Gareis & L. Rufiner

  4. Instituto de Investigación y Desarrollo en Bioingeniería y Bioinformática (IBB), CONICET-UNER, Oro Verde, Argentina

    J. Biurrun Manresa

  5. Universidad Autonoma Metropolina, Unidad Iztapalapa, Ciudad de México, Mexico

    V. Medina Bañuelos

Authors
  1. R. Acevedo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Y. Atum
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. I. Gareis
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. Biurrun Manresa
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. V. Medina Bañuelos
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. L. Rufiner
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to R. Acevedo.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Acevedo, R., Atum, Y., Gareis, I. et al. A comparison of feature extraction strategies using wavelet dictionaries and feature selection methods for single trial P300-based BCI. Med Biol Eng Comput 57, 589–600 (2019). https://doi.org/10.1007/s11517-018-1898-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-018-1898-9

Keywords

Search

Navigation