Biological Cybernetics

, Volume 106, Issue 6–7, pp 389–405 | Cite as

Regularized logistic regression and multiobjective variable selection for classifying MEG data

  • Roberto Santana
  • Concha Bielza
  • Pedro Larrañaga
Original Paper


This paper addresses the question of maximizing classifier accuracy for classifying task-related mental activity from Magnetoencelophalography (MEG) data. We propose the use of different sources of information and introduce an automatic channel selection procedure. To determine an informative set of channels, our approach combines a variety of machine learning algorithms: feature subset selection methods, classifiers based on regularized logistic regression, information fusion, and multiobjective optimization based on probabilistic modeling of the search space. The experimental results show that our proposal is able to improve classification accuracy compared to approaches whose classifiers use only one type of MEG information or for which the set of channels is fixed a priori.


Brain computer interface MEG Multiobjective optimization Classification Feature subset selection Probabilistic modeling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Armañanzas R, Saeys Y, Inza I, García-Torres M, Bielza C, van de Peer Y, Larrañaga P (2011) Peakbin selection in mass spectrometry data using a consensus approach with estimation of distribution algorithms. IEEE/ACM Trans Comput Biol Bioinf 8(3): 760–774CrossRefGoogle Scholar
  2. Asano F, Kimura M, Sekiguchi T, Kamitani Y (2009) Classification of movement-related single-trial MEG data using adaptive spatial filter. In: Acoustics, speech and signal processing, 2009. ICASSP 2009. IEEE international conference on, pp 357–360. IEEE, RotterdamGoogle Scholar
  3. Besserve M, Jerbi K, Laurent F, Baillet S, Martinerie J, Garnero L (2007) Classification methods for ongoing EEG and MEG signals. Biol Res 40(4): 415–437PubMedCrossRefGoogle Scholar
  4. Bianchi L, Sami S, Hillebrand A, Fawcett I, Quitadamo L, Seri S (2010) Which physiological components are more suitable for visual ERP based brain–computer interface? A preliminary MEG/EEG study. Brain Topogr 23(2): 180–185PubMedCrossRefGoogle Scholar
  5. Bucolo M, Di Grazia F, Frasca M (2008) From synchronization to network theory: a strategy for MEG data analysis. In: Proceedings of 16th mediterranean conference on control and automation, pp 854–859, Ajaccio, France. IEEE Press, Piscataway, NJGoogle Scholar
  6. Carmena J, Lebedev M, Crist R, Doherty J, Santucci D, Dimitrov D, Patil P, Henriquez C, Nicolelis M (2003) Learning to control a brain-machine interface for reaching and grasping by primates. PLoS Biol 1(2): 193–208CrossRefGoogle Scholar
  7. Coello C, Lamont G, Van Veldhuizen D (2007) Evolutionary algorithms for solving multi-objective problems. Springer, New YorkGoogle Scholar
  8. Darvas F, Leahy RM (2007) Handbook of brain connectivity, chapter functional imaging of brain activity and connectivity with MEG, pp 201–220. Kluwer Academic Publishers, BostonGoogle Scholar
  9. de Lange FP, Jensen O, Bauer M, Toni I (2008) Interactions between posterior gamma and frontal alpha/beta oscillations during imagined actions. Front Hum Neurosci 2(7): 1–12Google Scholar
  10. Di Grazia F, Sapuppo F, Shannahoff-Khalsa D, Bucolo M (2009) Network parameters for studying functional connectivity in brain MEG data. Int J Bioelectromagn 11(4): 161–169Google Scholar
  11. Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1): 1–22PubMedGoogle Scholar
  12. Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading, MAGoogle Scholar
  13. Guimera R, Amaral LAN (2005) Functional cartography of complex metabolic networks. Nature 433: 895–900PubMedCrossRefGoogle Scholar
  14. Haufe S, Tomioka R, Nolte G, Muller K, Kawanabe M (2010) Modeling sparse connectivity between underlying brain sources for eeg/meg. IEEE Trans Biomed Eng 57(8): 1954–1963PubMedCrossRefGoogle Scholar
  15. Hoffmann U, Vesin J, Ebrahimi T, Diserens K (2008) An efficient p300-based brain-computer interface for disabled subjects. J Neurosci Methods 167(1): 115–125PubMedCrossRefGoogle Scholar
  16. Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. University of Michigan Press, Ann Arbor, MIGoogle Scholar
  17. Inza I, Larrañaga P, Etxeberria R, Sierra B (2000) Feature subset selection by Bayesian network-based optimization. Artif Intell 123(1–2): 157–184CrossRefGoogle Scholar
  18. Iturrate I, Antelis J, Minguez J, Kübler A (2009) A non-invasive brain-actuated wheelchair based on a p300 neurophysiological protocol and automated navigation. IEEE Trans Robot 25(3): 614–627CrossRefGoogle Scholar
  19. Kelly S, Lalor E, Finucane C, McDarby G, Reilly R (2005) Visual spatial attention control in an independent brain-computer interface. IEEE Trans Biomed Eng 52(9): 1588–1596PubMedCrossRefGoogle Scholar
  20. Larrañaga, P, Lozano, JA (eds) (2002) Estimation of distribution algorithms. A new tool for evolutionary computation. Kluwer Academic Publishers, BostonGoogle Scholar
  21. Lebedev M, Nicolelis M (2006) Brain-machine interfaces: past, present and future. Trends Neurosci 29(9): 536–546PubMedCrossRefGoogle Scholar
  22. Leicht EA, Newman MEJ (2008) Community structure in directed networks. Phys Rev Lett 100: 118703PubMedCrossRefGoogle Scholar
  23. 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: R1–R13PubMedCrossRefGoogle Scholar
  24. McLachlan G (1992) Discriminant analysis and statistical pattern recognition. Wiley, New YorkCrossRefGoogle Scholar
  25. Mendiburu A, Miguel-Alonso J, Lozano JA, Ostra M, Ubide C (2006) Parallel EDAs to create multivariate calibration models for quantitative chemical applications. J Parallel Distrib Comput 66(8): 1002–1013CrossRefGoogle Scholar
  26. Milo R, Shen-Orr S, Itzkovitz S, Kashtan N, Chklovskii D, Alon U (2002) Network motifs: simple building blocks of complex networks. Science 298: 824–827PubMedCrossRefGoogle Scholar
  27. Mühlenbein H, Paaß G (1996) From recombination of genes to the estimation of distributions I. Binary parameters. In: Voigt H-M, Ebeling W, Rechenberg I, Schwefel H-P (eds) Proceedings of the 4th international conference on parallel problem solving from nature-PPSN IV, vol 1141 of lectures notes in computer science, pp 178–187. Springer, BerlinGoogle Scholar
  28. Nicolelis M (2003) Brain–machine interfaces to restore motor function and probe neural circuits. Nat Rev Neurosci 4(5): 417–422PubMedCrossRefGoogle Scholar
  29. Obermaier B, Munteanu C, Rosa A, Pfurtscheller G (2001) Asymmetric hemisphere modeling in an offline brain–computer interface. IEEE Trans Syst, Man, Cybern C 31(4): 537–540CrossRefGoogle Scholar
  30. Pelikan M, Goldberg DE, Lobo F (2002) A survey of optimization by building and using probabilistic models. Comput Opt Appl 21(1): 5–20CrossRefGoogle Scholar
  31. Rieger J, Reichert C, Gegenfurtner K, Noesselt T, Braun C, Heinze H, Kruse R, Hinrichs H (2008) Predicting the recognition of natural scenes from single trial MEG recordings of brain activity. Neuroimage 42(3): 1056–1068PubMedCrossRefGoogle Scholar
  32. Rossini L, Izzo D, Summerer L (2009) Brain-machine interfaces for space applications. In: Proceedings of the annual international conference of the IEEE engineering in medicine and biology society, vol 1, pp 520–523, MinnesotaGoogle Scholar
  33. Saeys Y, Inza I, Larrañaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23(19): 2507–2517PubMedCrossRefGoogle Scholar
  34. Santana R, Bielza C, Larrañaga P (2010a) Synergies between network-based representations and probabilistic graphical modeling in the solution of problems from neuroscience. In: García-Pedrajas N et al. (eds) Proceedings of the twenty third international conference on industrial, engineering and other applications of applied intelligent systems, vol 6098 of lecture notes in artificial intelligence, pp 149–158, Springer, CórdobaGoogle Scholar
  35. Santana R, Bielza C, Larrañaga P (2010b) Using probabilistic dependencies improves the search of conductance-based compartmental neuron models. In C. Pizzuti, M. D. Ritchie, and M. Giacobini, editors, Proceedings of the 8th European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, volume 6023 of Lecture Notes in Artificial Intelligence, pages 170–181. SpringerGoogle Scholar
  36. Santana R, Bielza C, Larrañaga P, Lozano JA, Echegoyen C, Mendiburu A, Armañanzas R, Shakya S (2010c) Mateda-2.0: A MATLAB package for the implementation and analysis of estimation of distribution algorithms. J Stat Softw 35(7): 1–30Google Scholar
  37. Santana R, Ochoa A, Soto MR (2001) The mixture of trees factorized distribution algorithm. In: Proceedings of the genetic and evolutionary computation conference GECCO-2001, pp 543–550. Morgan Kaufmann Publishers, San Francisco, CAGoogle Scholar
  38. Sporns O (2002) Neuroscience databases. A practical guide, chapter graph theory methods for the analysis of neural connectivity patterns, pp 171–186. Kluwer, Boston, MAGoogle Scholar
  39. Tan L, Jansari A, Keng S, Goh S (2009) Human-computer interaction. Novel interaction methods and techniques, chapter effect of mental training on BCI performance, pp 632–635. Springer, BerlinGoogle Scholar
  40. The MathWorks Inc. (2007) MATLAB—the language of technical computing, version 7.5. The MathWorks Inc., Natick, MAGoogle Scholar
  41. Valdés-Sosa PA, Sánchez-Bornot JM, Lage-Castellanos A, Vega-Hernández M, Bosch-Bayard J, Melie-García L, Canales-Rodríguez E (2005) Estimating brain functional connectivity with sparse multivariate autoregression. Philos Trans 360(1457): 969–981CrossRefGoogle Scholar
  42. van-Gerven M, Bahramisharif A, Heskes T, Jensen O (2009) Selecting features for BCI control based on a covert spatial attention paradigm. Neural Networks 22: 1271–1277PubMedCrossRefGoogle Scholar
  43. van-Gerven M, Jensen O (2009) Attention modulations of posterior alpha as a control signal for two-dimensional brain-computer interfaces. J Neurosci Methods 179: 78–84PubMedCrossRefGoogle Scholar
  44. Vapnik V (2000) The nature of statistical learning theory. Springer, New YorkGoogle Scholar
  45. Waldert S, Braun C, Preissl H, Birbaumer N, Aertsen A, Mehring C (2007) Decoding performance for hand movements: EEG vs. MEG. In: Engineering in medicine and biology society, 2007. EMBS 2007. 29th Annual international conference of the IEEE, pp 5346–5348. IEEE, Washington, DCGoogle Scholar
  46. Wang W, Sudre G, Xu Y, Kass R, Collinger J, Degenhart A, Bagic A, Weber D (2010) Decoding and cortical source localization for intended movement direction with MEG. J Neurophysiol 104(5): 2451–2461PubMedCrossRefGoogle Scholar
  47. Wolpaw J, Birbaumer N, McFarland D, Pfurtscheller G, Vaughan T (2002) Brain-computer interfaces for communication and control. Clin Neurophysiol 113(6): 767–791PubMedCrossRefGoogle Scholar
  48. Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc: Ser B 67(2): 301–320CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • Roberto Santana
    • 1
  • Concha Bielza
    • 2
  • Pedro Larrañaga
    • 2
  1. 1.Intelligent Systems GroupUniversity of the Basque Country (UPV/EHU)San SebastianSpain
  2. 2.Computational Intelligence GroupDepartamento de Inteligencia Artificial Universidad Politécnica de MadridBoadilla del Monte, MadridSpain

Personalised recommendations