Научная электронная библиотека ULRICH'S Periodicals Directory

Сибирский государственный университет
науки и технологий имени академика М.Ф. Решетнева

Сибирский аэрокосмический журнал
ISSN 2712-8970 (Print) ISSN 2782-5760 (on-line)

Сведения об образовательной организации

UDK УДК 004.5
MULTI-OBJECTIVE APPROACH FOR DESIGNING ENSEMBLE OF NEURAL NETWORK CLASSIFIERS WITH FEATURE SELECTION FOR EMOTION RECOGNITION PROBLEM
I. A. Ivanov*, E. A. Sopov, I. A. Panfilov
Reshetnev Siberian State Aerospace University 31, Krasnoyarsky Rabochy Av., Krasnoyarsk, 660037, Russian Federation *E-mail: ilyaiv92@gmail.com
Reducing the dimensionality of datasets and configuring learning algorithms for solving particular practical tasks are the main problems in machine learning. In this work we propose the multi-objective optimization approach to fea-ture selection and base learners hyper-parameter optimization. The effectiveness of the proposed multi-objective ap-proach is compared to the single-objective approach. We chose emotion recognition problem by audio-visual data as a benchmark for comparing the two mentioned approaches. Also we chose neural network as a base learning algorithm for testing the proposed approach to parameter optimization. As a result of multi-objective optimization applied to pa-rameter configuration we get the Pareto set of neural networks with optimal parameter values. In order to get the single output, the Pareto optimal neural networks were combined into an ensemble. We tried several ensemble model fusion techniques including voting, average class probabilities and meta-classification. According to the results, multi-objective optimization approach to feature selection provided an average 2.8 % better emotion classification rate on the given datasets than single-objective approach. Multi-objective approach is 5.4 % more effective compared to principal components analysis, and 13.9 % more effective compared to not using any dimensionality reduction at all. Multi-objective approach applied to neural networks parameter optimization provided on average 7.1 % higher classification rate than single-objective approach. The results suggest that the multi-objective optimization approach proposed in this article is more effective at solving considered emotion recognition problem.
Keywords: multi-objective optimization, emotion recognition, data fusion, model fusion, human-machine interaction (HMI), neural network.
References

References

 

  1. Zitzler E., Thiele L. Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE transactions on evolutionary computation, 1999, P. 257–271.
  2. Deb K., Pratap A., Agarwal S., Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. on Evolutionary Computation, Vol. 6, No. 2, April 2002, P. 182–197.
  3. Schaffer J. D. Multiple objective optimization with vector evaluated genetic algorithms. Proc. of the 1st International Conference on Genetic Algorithms, 1985, P. 93–100.
  4. Bergstra J., Bengio Y. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, 2012, P. 281–305.
  5. Larochelle H., Bengio Y., Louradour J, Lamblin P. Exploring strategies for training deep neural networks. Journal of Machine Learning Research 1, 2009, P. 1–40.
  6. Opitz D. W., Shavlik J. W. Generating accurate and diverse members of a neural-network ensemble. Advances in neural information processing systems, 1996, P. 535–541.
  7. Smith C., Jin Y. Evolutionary multi-objective generation of recurrent neural network ensembles for time series prediction. Neurocomputing, 2014, Vol. 143, P. 302–311.
  8. Phuong T. M., Lin Z., Altman R. B. Choosing SNPs using feature selection. Proceedings IEEE Computational Systems Bioinformatics Conference, 2005, P. 301–309.
  9. Duval B., Hao J.-K., Hernandez Hernandez J. C. A memetic algorithm for gene selection and molecular classification of an cancer. In Proceedings of the 11th Annual conference on Genetic and evolutionary computation, GECCO ’09, New York, NY, USA, 2009, P. 201–208.
  10. Rashid M., Abu-Bakar S. A. R., Mokji M. Human emotion recognition from videos using spatio-temporal and audio features. Vis Comput, 2013, Vol. 29, P. 1269–1275.
  11. Kahou S. E., Pal C., Bouthillier X., Froumenty P., Gulcehre C., Memisevic R., Vincent P., Courville A., Bengio Y. Combining modality specific deep neural
    networks for emotion recognition in video. Proceedings of the 15th ACM on International Conference on Multimodal Interaction, 2013, Sydney, Australia, P. 543–550.
  12. Cruz A., Bhanu B., Thakoor N. Facial emotion recognition in continuous video. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR 2012), November 11–15, 2012, Tsukuba, Japan, P. 1880–1883.
  13. Soleymani M., Pantic M., Pun T. Multimodal emotion recognition in response to videos. IEEE Transactions on affective computing, Vol. 3, No. 2, April-June, 2012, P. 211–223.
  14. Busso C., Deng Z., Yildirim S., Bulut M., Lee C. M., Kazemzadeh A., Lee S., Neumann U., Narayanan S. Analysis of emotion recognition using facial expressions. Proceedings of the 6th international conference on Multimodal interfaces, 2004, P. 205–211.
  15. Ivanov I. A., Sopov E. A. [Self-configuring genetic algorithm for solving multi-objective choice support problems]. Vestnik SibGAU, 2013, No. 1 (47), P. 30–35 (In Russ.).
  16. Haq, S., Jackson, P. J. B. Speaker-dependent audio-visual emotion recognition. Proc. Int. Conf. on Auditory-Visual Speech Processing (AVSP'09), Norwich, UK, 2009, P.53-58.
  17. Eyben F., Wullmer M, Schuller B. OpenSMILE – the Munich versatile and fast open-source audio feature extractor. In Proceedings ACM Multimedia (MM), ACM, Florence, Italy, ISBN 978-1-60558-933-6, 25.-29.10. 2010, P. 1459–1462.
  18. Sariyanidi E., Gunes H., Gokmen M., Cavallaro A. Local Zernike moment representation for facial affect recognition. Proc. of British Machine Vision Conference, 2013, P. 1–13.
  19. Ojala T., Pietikäinen M., Harwood D. A comparative study of texture measures with classification based on feature distributions. Pattern Recognition 29, 1996, P. 51–59.

20.    Zhao G., Pietikäinen M. Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Analysis and Machine Intelligence 29(6), 2007, P. 915–928.


Ivanov Ilia Andreievich – postgraduate student, Reshetnev Siberian State Aerospace University. E-mail: ilyaiv92@gmail.com, phone num.

Sopov Evgenii Aleksandrovich – Cand. Sc., Docent of Systems Analysis and Operations Research department, Reshetnev Siberian State Aerospace University. E-mail: evgenysopov@gmail.com.

Panfilov Ilia Aleksandrovich – Cand. Sc., Docent of Systems Analysis and Operations Research department, Reshetnev Siberian State Aerospace University. Е-mail: crook_80@mail.ru, phone num.