Advertisement

Online Semi-supervised Ensemble Updates for fMRI Data

  • Catrin O. Plumpton
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7081)

Abstract

Advances in Eelectroencephalography (EEG) and functional magnetic resonance imaging (fMRI) have opened up the possibility for real time data classification. A small amount of labelled training data is usually available, followed by a large stream of unlabelled data. Noise and possible concept drift pose a further challenge. A fixed pre-trained classifier may not always work. One solution is to update the classifier in real-time. Since true labels are not available, the classifier is updated using the predicted label, a method called naive labelling. We propose to use classifier ensembles in order to counteract the adverse effect of ‘run-away’ classifiers, associated with naive labelling. A new ensemble method for naive labelling is proposed. The label taken to update each member-classifier is the ensemble prediction. We use an fMRI dataset to demonstrate the advantage of the proposed method over the fixed classifier and the single classifier updated through naive labelling.

Keywords

Semi-supervised learning random subspace ensemble fMRI 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cozman, F.G., Cohen, I.: Unlabeled Data can Degrade Classification Performance of Generative Classifiers. In: Proceedings of the 15th International FLAIR Conference, pp. 327–331 (2002)Google Scholar
  2. 2.
    De Martino, F., Valente, G., Staeren, N., Ashburner, J., Goebel, R., Formisano, E.: Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns. NeuroImage 43(1), 44–58 (2008)CrossRefGoogle Scholar
  3. 3.
    de Charms, R.C.: Applications of real-time fMRI. Nature Reviews Neuroscience 9(9), 720–729 (2008)CrossRefGoogle Scholar
  4. 4.
    de Charms, R.C., Maeda, F., Glover, G.H., Ludlow, D., Pauly, J.M., Soneji, D., Gabrieli, J.D.E., Mackey, S.C.: Control over brain activation and pain learned by using real-time functional MRI. Proc. Natl. Acad. Sci. USA 102(51), 18626–18631 (2005)CrossRefGoogle Scholar
  5. 5.
    Eklund, A., Andersson, M., Ohlsson, H., Ynnerman, A., Knutsson, H.: A Brain Computer Interface for Communication Using Real-Time fMRI. In: International Conference on Pattern Recognition (2010)Google Scholar
  6. 6.
    Eklund, A., Ohlsson, H., Andersson, M., Rydell, J., Ynnerman, A., Knutsson, H.: Using Real-Time fMRI to Control a Dynamical System by Brain Activity Classification. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5761, pp. 1000–1008. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  7. 7.
    Fleiss, J.L.: Statistical Methods for Rates and Proportions. John Wiley & Sons (1981)Google Scholar
  8. 8.
    van Gerven, M., Farquhar, J., Schaefer, R., Vlek, R., Geuze, J., Nijholt, A., Ramsay, N., Haselager, P., Vuurpijl, L., Gielen, S., Desain, P.: The Brain-Computer Interface Cycle. Journal of Neural Engineering 6 (2009)Google Scholar
  9. 9.
    Golub, T.R., Slonim, D.K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J.P., Coller, H., Loh, M.L., Downing, J.R., Caligiuri, M.A., Bloomfield, C.D., Lander, E.S.: Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring. Science 286(5439), 531–537 (1999)CrossRefGoogle Scholar
  10. 10.
    Guyon, I., Hur, A.B., Gunn, S., Dror, G.: Result analysis of the NIPS 2003 feature selection challenge. In: Advances in Neural Information Processing Systems, vol. 17, pp. 545–552 (2004)Google Scholar
  11. 11.
    Handwerker, D.A., Ollinger, J.M., D’Esposito, M.: Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses. Neuroimage 21(4), 1639–1651 (2004)CrossRefGoogle Scholar
  12. 12.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, Heidelberg (2001)CrossRefzbMATHGoogle Scholar
  13. 13.
    Haxby, J.V., Gobbini, M.I., Furey, M.L., Ishai, A., Schouten, J.L., Pietrini, P.: Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science 293(5539), 2425–2430 (2001)CrossRefGoogle Scholar
  14. 14.
    Ho, T.K.: The random space method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(8), 832–844 (1998)CrossRefGoogle Scholar
  15. 15.
    Holmes, A.J., MacDonald, A., Carter, C.S., Barch, D.M., Stenger, V.A., Cohen, J.D.: Prefrontal functioning during context processing in schizophrenia and major depression: An event-related fMRI study. Schizophrenia Research 76, 199–206 (2005)CrossRefGoogle Scholar
  16. 16.
    Hugdah, K., Rund, B.R., Lund, A., Asbjornsen, A., Egeland, J., Ersland, L., Landr, N.I., Roness, A., Stordal, K.I., Sundet, K., Thomsen, T.: Brain Activation Measured With fMRI During a Mental Arithmetic Task in Schizophrenia and Major Depression. American Journal of Psychiatry 161, 286–293 (2004)CrossRefGoogle Scholar
  17. 17.
    Johnston, S.J., Boehm, S.G., Healy, D., Goebel, R., Linden, D.E.J.: Neurofeedback: A promising tool for the self-regulation of emotion networks. Neuroimage 29 (2009)Google Scholar
  18. 18.
    Kuncheva, L., Whitaker, C., Narasimhamurthy, A.: A case study on naïve labelling for the nearest mean and the linear discriminant classifiers. Pattern Recognition 41, 3010–3020 (2008)CrossRefzbMATHGoogle Scholar
  19. 19.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley Interscience (2004)Google Scholar
  20. 20.
    Kuncheva, L.I., Plumpton, C.O.: Choosing parameters for random subspace ensembles for fMRI classification. In: Proc. Multiple Classifier Systems (2010)Google Scholar
  21. 21.
    Kuncheva, L.I., Plumpton, C.O.: Adaptive learning rate for online linear discriminant classifiers. In: Proc. S+SSPR, Orlando, Florida, USA, pp. 510–519 (2008)Google Scholar
  22. 22.
    Kuncheva, L.I., Rodríguez, J.J.: Classifier ensembles for fMRI data analysis: An experiment. Magnetic Resonance Imaging 28, 583–593 (2010)CrossRefGoogle Scholar
  23. 23.
    Kuncheva, L.I., Rodríguez, J.J., Plumpton, C.O., Linden, D.E.J., Johnston, S.J.: Random subspace ensembles for fMRI classification. IEEE Transaction on Medical ImagingGoogle Scholar
  24. 24.
    LaConte, S.M.: Decoding fMRI brain states in real-time. NeuroImage (2010)Google Scholar
  25. 25.
    Lang, P., Bradley, M., Cuthbert, B.: International Affective Picture System (IAPS): Technical Manual and Affective RatingsGoogle Scholar
  26. 26.
    Li, M., Zhou, Z.-H.: Improve computer-aided diagnosis with machine learning techniques using undiagnosed samples. IEEE Transactions on Systems, Man and Cybernetics A 37(6), 1088–1098 (2007)CrossRefGoogle Scholar
  27. 27.
    Misaki, M., Kim, Y., Bandettini, P.A., Kriegeskorte, N.: Comparison of multivariate classifiers and response normalizations for pattern-information fMRI. NeuroImage (2010), doi:10.1016/j.neuroimage.2010.05.051Google Scholar
  28. 28.
    Moench, T., Hollmann, M., Grzeschik, R., Muller, C., Luetzkendorf, R., Baecke, S., Luchtmann, M., Wagegg, D., Bernarding, J.: Real-time classification of activated brain areas for fMRI-based human-brain-interfaces. In: Medical Imaging 2008: Physiology, Function, and Structure from Medical Images, vol. 6916, pp. 69161R – 69161R-10 (2008)Google Scholar
  29. 29.
    Nigam, K.P.: Using Unlabeled Data to Improve Text Classification. PhD thesis, School of Computer Science, Carnegie Mellon University, Pittsburgh, US (2001)Google Scholar
  30. 30.
    Pereira, F., Mitchell, T., Botvinick, M.: Machine learning classifiers and fMRI: a tutorial overview. NeuroImage 45, S199–S209 (2009)CrossRefGoogle Scholar
  31. 31.
    Plumpton, C.O., Kuncheva, L.I., Linden, D.E.J., Johnston, S.J.: On-line fMRI Data Classification Using Linear and Ensemble Classifiers. In: Proc. 20th International Conference on Pattern Recognition (2010)Google Scholar
  32. 32.
    Plumpton, C.O., Kuncheva, L.I., Oosterhof, N.N., Johnston, S.J.: Naive random subspace ensemble with linear classifiers for real-time classification of fMRI data. Pattern Recognition special edition on Brain Decoding (in Press, Corrected Proof, 2011)Google Scholar
  33. 33.
    Posse, S., Fitzgerald, D., Gao, K., Habel, U., Rosenberg, D., Moore, G.J., Schneider, F.: Real-time fMRI of temporolimbic regions detects amygdala activation during single-trial self-induced sadness. NeuroImage 18, 760–768 (2003)CrossRefGoogle Scholar
  34. 34.
    Seeger, M.: Learning with labeled and unlabeled data. Technical report, University of Edinburgh (2001)Google Scholar
  35. 35.
    Sheline, Y.I., Barch, D.M., Donnelly, J.M., Ollinger, J.M., Snyder, A.Z., Mintun, M.A.: Increased Amygdala Response to Masked Emotional Faces in Depressed Subjects Resolves with Antidepressant Treatment: An fMRI Study. Biological Psychiatry 50(9), 651–658 (2001)CrossRefGoogle Scholar
  36. 36.
    Weiskopf, N., Sitaram, R., Josephs, O., Veit, R., Scharnowski, F., Goebel, R., Birbaumer, N., Deichmann, R., Mathiak, K.: Real-time functional magnetic resonance imaging: methods and applications. Magnetic Resonance Imaging 25, 989–1003 (2007)CrossRefGoogle Scholar
  37. 37.
    Yoo, S.S., Fairneny, T., Chen, N.K., Choo, S.E., Panych, L.P., Park, H.W., Lee, S.Y., Jolesz, F.A.: Brain–computer interface using fMRI: spatial navigation by thoughts. NeuroReport 15(10), 1591–1595 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Catrin O. Plumpton
    • 1
  1. 1.School of Computer ScienceBangor UniversityUnited Kingdom

Personalised recommendations