Skip to main content

Advertisement

SpringerLink
Log in

On the discovery of events in EEG data utilizing information fusion

  • Original Paper
  • Published:
Computational Statistics Aims and scope Submit manuscript

Abstract

One way to tackle brain computer interfaces is to consider event related potentials in electroencephalography, like the well established P300 phenomenon. In this paper a multiple classifier approach to discover these events in the bioelectrical signal and with them whether or not a subject has recognized a particular pattern, is employed. Dealing with noisy data as well as heavily imbalanced target class distributions are among the difficulties encountered. Our approach utilizes partitions of electrodes to create robust and meaningful individual classifiers, which are then subsequently combined using decision fusion. Furthermore, a classifier selection approach using genetic algorithms is evaluated and used for optimization. The proposed approach utilizing information fusion shows promising results (over 0.8 area under the ROC curve).

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

Similar content being viewed by others

References

  • Bäck T (1996) Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms. Oxford University Press, Oxford

    MATH  Google Scholar 

  • Birbaumer N, Schmidt RF (2006) Biologische psychologie. German edition. Springer, Berlin

    Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45: 5–32

    Article  MATH  Google Scholar 

  • Chen C, Liaw A, Breiman L (2004) Using random forest to learn imbalanced data. Technical report, Department of Statistics, University of Berkeley

  • Chumerin N, Manyakov NV, Combaz A, Suykens JAK, Yazicioglu RF, Torfs T, Merken P, Neves HP, Van Hoof C, Van Hulle MM (2009) P300 detection based on feature extraction in on-line brain-computer interface. In: KI’09: Proceedings of the 32nd annual German conference on Advances in artificial intelligence, Springer, pp 339–346

  • Dujardin K, Derambure P, Bourriez JL, Jacquesson JM, Guieu JD (1993) P300 component of the event-related potentials (ERP) during an attention task: effects of age, stimulus modality and event probability. Int J Psychophysiol 14(3): 255–267

    Article  Google Scholar 

  • Genolini C, Falissard B (2010) Kml: k-means for longitudinal data. Comput Stat 25: 317–328

    Article  MathSciNet  MATH  Google Scholar 

  • Giacinto G, Roli F (1999) Methods for dynamic classifier selection. In: ICIAP ’99 proceedings of the 10th international conference on image analysis and processing, IEEE Computer Society, pp 659–664

  • Gray HM, Ambady N, Lowenthal WT, Deldin P (2004) P300 as an index of attention to self-relevant stimuli. J Exp Soc Psychol 40(2): 216–224

    Article  Google Scholar 

  • Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3: 1157–1182

    MATH  Google Scholar 

  • Hild KE, Kurimo M, Calhoun VD (2010) The 6th annual mlsp competition. In: IEEE international workshop on machine learning for signal processing (MLSP), pp 107–111

  • Iscan Z (2010) Mlsp competition, 2010: description of second place method. In: IEEE international workshop on machine learning for signal processing (MLSP), pp 114–115

  • Japkowicz N (2000) Learning from imbalanced data sets: a comparison of various strategies. In: Proceeding of AAAI workshop learning from imbalanced data sets, pp 10–15

  • Jordan MI, Jacobs RA (1994) Hierarchical mixtures of experts and the em algorithm. Neural Comput 6: 181–214

    Article  Google Scholar 

  • Kittler J, Hatef M, Duin RPW, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20(3): 226–239

    Article  Google Scholar 

  • Kraus J, Müssel C, Palm G, Kestler HA (2011) Multi-objective selection for collecting cluster alternatives. Comput Stat 26: 341–353

    Article  Google Scholar 

  • Kuncheva L (2002) Switching between selection and fusion in combining classifiers: an experiment. IEEE Trans Syst Man Cybern Part B Cybern 32(2): 146–156

    Article  Google Scholar 

  • Kuncheva L, Bezdek JC, Duin RPW (2001) Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recogn 34(2): 299–314

    Article  MATH  Google Scholar 

  • Kuncheva L, Jain L (2000) Designing classifier fusion systems by genetic algorithms. IEEE Trans Evol Comput 4(4): 327–336

    Article  Google Scholar 

  • Kuncheva LI, Whitaker CJ (2003) Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Mach Learn 51(2): 181–207

    Article  MATH  Google Scholar 

  • Labbe B, Tian X, Rakotomamonjy A (2010) Mlsp competition, 2010: description of third place method. In: IEEE international workshop on machine learning for signal processing (MLSP), pp 116–117

  • Leiva J, Martens S (2010) Mlsp competition, 2010: description of first place method. In: IEEE international workshop on machine learning for signal processing (MLSP), pp 112–113

  • Margineantu DD, Dietterich TG (1997) Pruning adaptive boosting. In: ICML ’97 proceedings of the 14th international conference on machine learning. Morgan Kaufmann Publishers Inc., pp 211–218

  • Osuna E, Freund R, Girosi F (1997) Support vector machines: training and applications. Technical report, Massachusetts Institute of Technology, Cambridge

  • Picton T, Bentin S, Berg P, Donchin E, Hillyard S, Johnson R, Miller G, Ritter W, Ruchkin D, Rugg M, Taylor M (2000) Guidelines for using human event-related potentials to study cognition: Recording standards and publication criteria. Psychophysiology 37(02): 127–152

    Article  Google Scholar 

  • Platt J (1999a) Fast training of support vector machines using sequential minimal optimization. In: Advances in kernel methods, MIT press, pp 185–208

  • Platt J (1999b) Probabilistic outputs for support vector machines and comparison to regularize likelihood methods. In: Advances in large margin classifiers. MIT press, pp 61–74

  • Rakotomamonjy A, Guigue V (2005) Bci competition iii: dataset ii—ensemble of svms for bci p300 speller. IEEE Trans Biomed Eng 55(3): 1147–1154

    Article  Google Scholar 

  • Ruta D, Gabrys B (2005) Classifier selection for majority voting. Inf Fusion 6(1): 63–81

    Article  Google Scholar 

  • Schölkopf B, Smola AJ (2001) Learning with kernels: support vector machines, regularization, optimization, and beyond (adaptive computation and machine learning). The MIT Press, Cambridge

  • Segalowitz SJ, Bernstein DM, Lawson S (2001) P300 event-related potential decrements in well-functioning university students with mild head injury. Brain Cogn 45(3): 342–356

    Article  Google Scholar 

  • Sörnmo L, Laguna P (2005) Bioelectrical signal processing in cardiac and neurological applications. 1. Elsevier, Amsterdam

    Google Scholar 

  • Thiel C, Scherer S, Schwenker F (2007) Fuzzy-input fuzzy-output one-against-all support vector machines. In: Knowledge-based intelligent information and engineering systems 2007, Springer, pp 156–165

  • Walter S, Scherer S, Schels M, Glodek M, Hrabal D, Schmidt M, Böck R, Limbrecht K, Traue HC, Schwenker F (2011) Multimodal emotion classification in naturalistic user behavior. In: Proceedings of 14th international conference on human–computer interaction (HCII’11), Springer

  • Xu Y, Yin K, Zhang J, Yao L (2008) A spatiotemporal approach to n170 detection with application to brain-computer interfaces. In: IEEE international conference on systems, man and cybernetics, pp 886–891

  • Zhang JC, Xu YQ, Yao L (2007) P300 detection using boosting neural networks with application to bci. In: IEEE/ICME international conference on complex medical engineering, pp 1526–1530

  • Zhou ZH, Liu XY (2006) Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng 18(1): 63–77

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Neural Information Processing, University of Ulm, Ulm, Germany

    Martin Schels, Stefan Scherer, Michael Glodek, Hans A. Kestler, Günther Palm & Friedhelm Schwenker

  2. Speech Communication Laboratory, Trinity College Dublin, Dublin, Ireland

    Stefan Scherer

  3. Internal Medicine I, University Hospital, Ulm, Germany

    Hans A. Kestler

Authors
  1. Martin Schels
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stefan Scherer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Michael Glodek
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hans A. Kestler
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Günther Palm
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Friedhelm Schwenker
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Friedhelm Schwenker.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Schels, M., Scherer, S., Glodek, M. et al. On the discovery of events in EEG data utilizing information fusion. Comput Stat 28, 5–18 (2013). https://doi.org/10.1007/s00180-011-0292-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00180-011-0292-y

Keywords

Search

Navigation