Classification of Emotional States in a Woz Scenario Exploiting Labeled and Unlabeled Bio-physiological Data

  • Martin Schels
  • Markus Kächele
  • David Hrabal
  • Steffen Walter
  • Harald C. Traue
  • Friedhelm Schwenker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7081)


In this paper, a partially supervised machine learning approach is proposed for the recognition of emotional user states in HCI from bio-physiological data. To do so, an unsupervised learning preprocessing step is integrated into the training of a classifier. This makes it feasible to utilize unlabeled data or – as it is conducted in this study – data that is labeled in others than the considered categories. Thus, the data is transformed into a new representation and a standard classifier approach is subsequently applied. Experimental evidences that such an approach is beneficial in this particular setting is provided using classification experiments. Finally, the results are discussed and arguments when such an partially supervised approach is promising to yield robust and increased classification performances are given.


Heart Rate Variability Cluster Center Gaussian Mixture Model Unsupervised Learning Unlabeled Data 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bennett, K.P., Campbell, C.: Support vector machines: hype or hallelujah? SIGKDD Explor. Newsl. 2, 1–13 (2000)CrossRefGoogle Scholar
  2. 2.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, pp. 92–100 (1998)Google Scholar
  3. 3.
    Boiten, F.A., Frijda, N.H., Wientjes, C.J.: Emotions and respiratory patterns: review and critical analysis. International Journal of Psychophysiology 17(2), 103–128 (1994)CrossRefGoogle Scholar
  4. 4.
    Cohn, D.A., Ghahramani, Z., Jordan, M.I.: Active learning with statistical models. J. Artif. Int. Res. 4, 129–145 (1996)zbMATHGoogle Scholar
  5. 5.
    Darrow, C.W.: The equation of the galvanic skin reflex curve: I. the dynamics of reaction in relation to excitation-background. The Journal of General Psychology 16(2), 285–309 (1937)CrossRefGoogle Scholar
  6. 6.
    Hady, M.F.A., Schwenker, F., Palm, G.: Semi-supervised learning for tree-structured ensembles of RBF networks with co-training. Neural Networks 23(4), 497–509 (2010)CrossRefGoogle Scholar
  7. 7.
    Kelley, J.F.: An empirical methodology for writing user-friendly natural language computer applications. In: Proceedings of the SIGCHI conference on Human Factors in Computing Systems, pp. 193–196 (1983)Google Scholar
  8. 8.
    Kestler, H.A., Schwenker, F., Hoher, M., Palm, G.: Adaptive class-specific partitioning as a means of initializing RBF-networks. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 1, pp. 46–49 (1995)Google Scholar
  9. 9.
    Ling, C.X., Du, J., Zhou, Z.H.: When does co-training work in real data? In: Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, pp. 596–603 (2009)Google Scholar
  10. 10.
    Marciano, F., Migaux, M., Acanfora, D., Furgi, G., Rengo, F.: Quantification of Poincaré maps for the evaluation of heart rate variability. Computers in Cardiology, 577–580 (1994)Google Scholar
  11. 11.
    Martinetz, T., Schulten, K.: A ”Neural-Gas” Network Learns Topologies. Artificial Neural Networks I, 397–402 (1991)Google Scholar
  12. 12.
    Mietus, J.E., Peng, C.K., Goldsmith, R.L., Goldberger, A.L.: The pNNx files: re-examining a widely used heart rate variability measure. Heart 8, 378–380 (2007)Google Scholar
  13. 13.
    Pincus, S.M.: Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences of the United States of America 88(6), 2297–2301 (1991)CrossRefzbMATHMathSciNetGoogle Scholar
  14. 14.
    Ros, F., Pintore, M., Deman, A., Chrtien, J.R.: Automatical initialization of RBF neural networks. Chemometrics and Intelligent Laboratory Systems 87(1), 26–32 (2007)CrossRefGoogle Scholar
  15. 15.
    Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-supervised self-training of object detection models. In: Proceedings of the Seventh IEEE Workshops on Application of Computer Vision, pp. 29–36 (2005)Google Scholar
  16. 16.
    Rudnicki, M., Strumiłło, P.: A Real-Time Adaptive Wavelet Transform-Based QRS Complex Detector. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds.) ICANNGA 2007. LNCS, vol. 4432, pp. 281–289. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  17. 17.
    Russell, J.: A circumplex model of affect. Journal of Personality and Social Psychology 39, 1161–1178 (1980)CrossRefGoogle Scholar
  18. 18.
    Sayers, B.: Analysis of heart rate variability. Ergonomics 16(1), 17–32 (1973)CrossRefGoogle Scholar
  19. 19.
    Schels, M., Schillinger, P., Schwenker, F.: Training of multiple classifier systems utilizing partially labeled sequences. In: Proceedings of the 19th European Symposium on Artificial Neural Networks, pp. 71–76 (2011)Google Scholar
  20. 20.
    Schölkopf, B., Smola, A.J., Williamson, R.C., Bartlett, P.L.: New support vector algorithms. Neural Comput. 12, 1207–1245 (2000)CrossRefGoogle Scholar
  21. 21.
    Schwenker, F., Kestler, H., Palm, G., Hoher, M.: Similarities of LVQ and RBF learning-a survey of learning rules and the application to the classification of signals from high-resolution electrocardiography. In: IEEE International Conference on Systems, Man, and Cybernetics, vol. 1, pp. 646–651 (1994)Google Scholar
  22. 22.
    Schwenker, F., Kestler, H.A., Palm, G.: Three learning phases for radial-basis-function networks. Neural Netw. 14, 439–458 (2001)CrossRefzbMATHGoogle Scholar
  23. 23.
    Simson, M.: Use of signals in the terminal QRS complex to identify patients with ventricular tachycardia after myocardial infarction. Circulation 64(2), 235–242 (1981)CrossRefGoogle Scholar
  24. 24.
    Walter, S., Scherer, S., Schels, M., Glodek, M., Hrabal, D., Schmidt, M., Böck, R., Limbrecht, K., Traue, H.C., Schwenker, F.: Multimodal Emotion Classification in Naturalistic user Behavior. In: Jacko, J.A. (ed.) HCI International 2011, Part III. LNCS, vol. 6763, pp. 603–611. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  25. 25.
    Webb, A.R.: Statistical Pattern Recognition. John Wiley and Sons Ltd. (2002)Google Scholar
  26. 26.
    Welch, P.: The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. IEEE Transactions on Audio and Electroacoustics 15(2), 70–73 (1967)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Martin Schels
    • 1
  • Markus Kächele
    • 1
  • David Hrabal
    • 2
  • Steffen Walter
    • 2
  • Harald C. Traue
    • 2
  • Friedhelm Schwenker
    • 1
  1. 1.Institute of Neural Information ProcessingUniversity of UlmGermany
  2. 2.Medical PsychologyUniversity of UlmGermany

Personalised recommendations