Skip to main content
SpringerLink
Log in

Echo State Networks for Feature Selection in Affective Computing

  • Conference paper
  • First Online:
Advances in Practical Applications of Agents, Multi-Agent Systems, and Sustainability: The PAAMS Collection (PAAMS 2015)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 9086))

Abstract

The Echo State Networks (ESNs) are dynamical structures designed initially to facilitate learning in Recurrent Neural Networks which are normally applied for time series modeling. In this paper we show that the ESN reservoirs can serve as an effective feature selection procedure that improved the discrimination of human emotion valence from EEG signals, a task that belongs to the research field of affective computing. A number of supervised and unsupervised machine learning techniques provided with the new feature vector extracted from ESN reservoir states were comparatively studied with respect to their discrimination accuracy. This novel application serves as a proof of concept for the possibility of extending the usability of the ESNs in classification or clustering frameworks.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ackley, D.H., Hinton, G.E., Sejnowski, T.J.: A learning algorithm for Boltzmann machines. Cognitive Science 9, 147–169 (1985)

    Article  Google Scholar 

  2. Brody, C.D., Romo, R., Kepecs, A.: Basic mechanisms for graded persistent activity: Discrete attractors, continuous attractors, and dynamical representations. Current Opinion in Neurobiology 13, 204–211 (2003)

    Article  Google Scholar 

  3. Haddad, W.M., Chellaboina, V.S., Nersesov, S.G.: Thermodynamics: A Dynamical System Approach. Princeton University Press (2005)

    Google Scholar 

  4. Hinton, G.E., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  5. Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach, GMD Report 159, German National Research Center for Information Technology (2002)

    Google Scholar 

  6. Koprinkova-Hristova, P., Palm, G.: ESN Intrinsic Plasticity versus Reservoir Stability. In: Honkela, T. (ed.) ICANN 2011, Part I. LNCS, vol. 6791, pp. 69–76. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

  7. Koprinkova-Hristova, P., Tontchev, N.: Echo State Networks for Multi-dimensional Data Clustering. In: Villa, A.E., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol. 7552, pp. 571–578. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  8. Koprinkova-Hristova, P., Alexiev, K., Borisova, D., Jelev, G., Atanassov, V.: Recurrent neural networks for automatic clustering of multispectral satellite images. In: Bruzzone, L. (ed.) Proceedings of SPIE, Image and Signal Processing for Remote Sensing XIX, 88920X, vol. 8892 (October 17, 2013) doi:10.1117/12

  9. Koprinkova-Hristova, P., Angelova, D., Borisova, D., Jelev, G.: Clustering of spectral images using Echo state networks. In: 2013 IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA 2013, June 19-21, Albena, Bulgaria (2013). doi:10.1109/INISTA.2013.6577633

  10. Koprinkova-Hristova, P., Doukovska, L., Kostov, P.: Working regimes classification for predictive maintenance of mill fan systems. In: 2013 IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA 2013, June 19-21, Albena, Bulgaria (2013) doi:10.1109/INISTA.2013.6577632

  11. Koprinkova-Hristova, P., Alexiev, K.: Echo State Networks in Dynamic Data Clustering. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 343–350. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  12. Koprinkova-Hristova, P., Alexiev, K.: Sound fields clusterization via neural networks. In: 2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications, INISTA 2014, June 23–25, Alberobello, Italy, pp. 368–374 (2014)

    Google Scholar 

  13. Koprinkova-Hristova, P., Alexiev, K.: Dynamic Sound Fields Clusterization Using Neuro-Fuzzy Approach. In: Agre, G., Hitzler, P., Krisnadhi, A.A., Kuznetsov, S.O. (eds.) AIMSA 2014. LNCS, vol. 8722, pp. 194–205. Springer, Heidelberg (2014)

    Chapter  Google Scholar 

  14. Lazar, A., Pipa, G., Triesch, J.: Predictive Coding in Cortical Microcircuits. In: Kurková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part II. LNCS, vol. 5164, pp. 386–395. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  15. Lukosevicius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Computer Science Review 3, 127–149 (2009)

    Article  MATH  Google Scholar 

  16. Ozturk, M., Xu, D., Principe, J.: Analysis and design of Echo state networks. Neural Computation 19, 111–138 (2007)

    Google Scholar 

  17. Peng, X., Guo, J., Lei, M., Peng, Yu.: Analog Circuit Fault Diagnosis with Echo State Networks Based on Corresponding Clusters. In: Liu, D., Zhang, H., Polycarpou, M., Alippi, C., He, H. (eds.) ISNN 2011, Part I. LNCS, vol. 6675, pp. 437–444. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

  18. Schrauwen, B., Wandermann, M., Verstraeten, D., Steil, J.J., Stroobandt, D.: Improving reservoirs using intrinsic plasticity. Neurocomputing 71, 1159–1171 (2008)

    Article  Google Scholar 

  19. Steil, J.J.: Online reservoir adaptation by intrinsic plasticity for back-propagation-decoleration and echo state learning. Neural Networks 20, 353–364 (2007)

    Article  MATH  Google Scholar 

  20. Woodward, A., Ikegami, T.: A reservoir computing approach to image classification using coupled echo state and back-propagation neural networks. In: Proc. of 26th Int. Conf. on Image and Vision Computing, Auckland, New Zealand, November. 29–December 1, 2011, pp. 543–458 (2011)

    Google Scholar 

  21. Calvo, R.A., D’Mello, S.K.: Affect Detection: An Interdisciplinary Review of Models, Methods, and their Applications. IEEE Transactions on Affective Computing 1(1), 18–37 (2010)

    Article  Google Scholar 

  22. Georgieva, O., Milanov, S., Georgieva, P., Santos, I.M., Pereira, A.T., da Silva, C.F.: Learning to decode human emotions from ERPs. Neural Computing and Applications, Springer, On-line Access (2014). doi:10.1007/s00521-014-1653-6

    MATH  Google Scholar 

  23. Bozhkov, L., Georgieva, P., Trifonov, R.: Brain Neural Data Analysis Using Machine Learning Feature Selection and Classification Methods. In: Mladenov, V., Jayne, C., Iliadis, L. (eds.) EANN 2014. CCIS, vol. 459, pp. 123–132. Springer, Heidelberg (2014)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, Sofia, Bulgaria

    P. Koprinkova-Hristova

  2. Technical University of Sofia, Sofia, Bulgaria

    L. Bozhkov

  3. DETI/IEETA, University of Aveiro, Aveiro, Portugal

    P. Georgieva

Authors
  1. P. Koprinkova-Hristova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. L. Bozhkov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. P. Georgieva
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to P. Georgieva .

Editor information

Editors and Affiliations

  1. Centre National de la Recherche Scientifique, Grenoble, France

    Yves Demazeau

  2. University of Delaware, Newark, Delaware, USA

    Keith S. Decker

  3. Universidad Politécnica, Madrid, Spain

    Javier Bajo Pérez

  4. Department of Computing Science, Universidad de Salamanca, Salamanca, Spain

    Fernando de la Prieta

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Koprinkova-Hristova, P., Bozhkov, L., Georgieva, P. (2015). Echo State Networks for Feature Selection in Affective Computing. In: Demazeau, Y., Decker, K., Bajo Pérez, J., de la Prieta, F. (eds) Advances in Practical Applications of Agents, Multi-Agent Systems, and Sustainability: The PAAMS Collection. PAAMS 2015. Lecture Notes in Computer Science(), vol 9086. Springer, Cham. https://doi.org/10.1007/978-3-319-18944-4_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-18944-4_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-18943-7

  • Online ISBN: 978-3-319-18944-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation