Advertisement

Evolutionary Algorithms for the Design of Neural Network Classifiers for the Classification of Pain Intensity

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11377)

Abstract

In this paper we present a study on multi-modal pain intensity recognition based on video and bio-physiological sensor data. The newly recorded SenseEmotion dataset consisting of 40 individuals, each subjected to three gradually increasing levels of painful heat stimuli, has been used for the evaluation of the proposed algorithms. We propose and evaluated evolutionary algorithms for the design and adaptation of the structure of deep artificial neural network architectures. Feedforward Neural Network and Recurrent Neural Network have been considered for the optimisation by using a Self-Configuring Genetic Algorithm (SelfCGA) and Self-Configuring Genetic Programming (SelfCGP).

Keywords

Multimodal pain intensity recognition Evolutionary algorithm Neural network 

Notes

Acknowledgements

The reported study was funded by Krasnoyarsk Regional Fund of Science according to the participation in the internship Recurrent neural Networks, Deep Learning for Video retrieval. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research. The work of FS was support by the SenseEmotion project funded by the Federal Ministry of Education and Research (BMBF).

References

  1. 1.
    Amirian, M., Kächele, M., Schwenker, F.: Using radial basis function neural networks for continuous and discrete pain estimation from bio-physiological signals. In: Schwenker, F., Abbas, H.M., El Gayar, N., Trentin, E. (eds.) ANNPR 2016. LNCS (LNAI), vol. 9896, pp. 269–284. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46182-3_23CrossRefGoogle Scholar
  2. 2.
    Aung, M.S.H., et al.: The automatic detection of chronic pain-related expression: requirements, challenges and multimodal dataset. IEEE Trans. Affect. Comput. 7, 435–451 (2016)CrossRefGoogle Scholar
  3. 3.
    Bellmann, P., Thiam, P., Schwenker, F.: Multi-classifier-systems: architectures, algorithms and applications. In: Pedrycz, W., Chen, S.-M. (eds.) Computational Intelligence for Pattern Recognition. SCI, vol. 777, pp. 83–113. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-89629-8_4CrossRefGoogle Scholar
  4. 4.
    Chollet, F., et al.: Keras (2015). https://keras.io
  5. 5.
    Chu, Y., Zhao, X., Yao, J., Zhao, Y., Wu, Z.: Physiological signals based quantitative evaluation method of the pain. In: Proceedings of the 19th IFAC World Congress, pp. 2981–2986 (2014)Google Scholar
  6. 6.
    Coello, C.A.C., Lamont, G.B., Van Veldhuizen, D.A., et al.: Evolutionary Algorithms for Solving Multi-objective Problems, vol. 5. Springer, New York (2007).  https://doi.org/10.1007/978-0-387-36797-2CrossRefzbMATHGoogle Scholar
  7. 7.
    Florea, C., Florea, L., Vertan, C.: Learning pain from emotion: transferred hot data representation for pain intensity estimation. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8927, pp. 778–790. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-16199-0_54CrossRefGoogle Scholar
  8. 8.
    Glodek, M., Scherer, S., Schwenker, F.: Conditioned hidden Markov model fusion for multimodal classification. In: Twelfth Annual Conference of the International Speech Communication Association (2011)Google Scholar
  9. 9.
    Glodek, M., et al.: Multiple classifier systems for the classification of audio-visual emotional states. In: D’Mello, S., Graesser, A., Schuller, B., Martin, J.-C. (eds.) ACII 2011. LNCS, vol. 6975, pp. 359–368. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-24571-8_47CrossRefGoogle Scholar
  10. 10.
    Gruss, S., et al.: Pain intensity recognition rates via biopotential feature patterns with support vector machines. PLoS ONE 10, e0140330 (2015)CrossRefGoogle Scholar
  11. 11.
    Hagenbuchner, M., Tsoi, A.C., Scarselli, F., Zhang, S.J.: A fully recursive perceptron network architecture. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–8. IEEE (2017)Google Scholar
  12. 12.
    Kächele, M., Thiam, P., Amirian, M., Schwenker, F., Palm, G.: Methods for person-centered continuous pain intensity assessment from bio-physiological channels. IEEE J. Sel. Top. Signal Process. 10, 854–864 (2016)CrossRefGoogle Scholar
  13. 13.
    Kächele, M., et al.: Multimodal data fusion for person-independent, continuous estimation of pain intensity. In: Iliadis, L., Jayne, C. (eds.) EANN 2015. CCIS, vol. 517, pp. 275–285. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-23983-5_26CrossRefGoogle Scholar
  14. 14.
    Kächele, M., Werner, P., Al-Hamadi, A., Palm, G., Walter, S., Schwenker, F.: Bio-visual fusion for person-independent recognition of pain intensity. In: Schwenker, F., Roli, F., Kittler, J. (eds.) MCS 2015. LNCS, vol. 9132, pp. 220–230. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-20248-8_19CrossRefGoogle Scholar
  15. 15.
    Kaltwang, S., Rudovic, O., Pantic, M.: Continuous pain intensity estimation from facial expressions. In: Bebis, G., et al. (eds.) ISVC 2012. LNCS, vol. 7432, pp. 368–377. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33191-6_36CrossRefGoogle Scholar
  16. 16.
    Kessler, V., Thiam, P., Amirian, M., Schwenker, F.: Pain recognition with camera photoplethysmography. In: 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1–5. IEEE (2017)Google Scholar
  17. 17.
    Kestler, H., et al.: De-noising of high-resolution ECG signals by combining the discrete wavelet transform with the wiener filter. In: Computers in Cardiology, pp. 233–236. IEEE (1998)Google Scholar
  18. 18.
    Meshheryakov, R., Khodashinskij, I., Gusakova, E.: Evaluation of feature space for intrusion detection system. News of Southern Federal University. Tech. Sci. 12(149) (2013)Google Scholar
  19. 19.
    Olugbade, T.A., Bianchi-Berthouze, N., Marquardt, N., Williams, A.C.: Pain level recognition using kinematics and muscle activity for physical rehabilitation in chronic pain. In: IEEE Proceedings of International Conference on Affective Computing and Intelligent Interaction, pp. 243–249 (2015)Google Scholar
  20. 20.
    Qin, Q., Cheng, S., Zhang, Q., Li, L., Shi, Y.: Biomimicry of parasitic behavior in a coevolutionary particle swarm optimization algorithm for global optimization. Appl. Soft Comput. 32, 224–240 (2015)CrossRefGoogle Scholar
  21. 21.
    Schels, M., Schwenker, F.: A multiple classifier system approach for facial expressions in image sequences utilizing GMM supervectors. In: 2010 20th International Conference on Pattern Recognition (ICPR), pp. 4251–4254. IEEE (2010)Google Scholar
  22. 22.
    Schmidt, M., Schels, M., Schwenker, F.: A hidden Markov model based approach for facial expression recognition in image sequences. In: Schwenker, F., El Gayar, N. (eds.) ANNPR 2010. LNCS (LNAI), vol. 5998, pp. 149–160. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-12159-3_14CrossRefGoogle Scholar
  23. 23.
    Schwenker, F., Kestler, H.A., Palm, G.: Three learning phases for radial-basis-function networks. Neural Netw. 14(4–5), 439–458 (2001)CrossRefGoogle Scholar
  24. 24.
    Schwenker, F., Trentin, E.: Pattern classification and clustering: a review of partially supervised learning approaches. Pattern Recognit. Lett. 37, 4–14 (2014)CrossRefGoogle Scholar
  25. 25.
    Semenkin, E., Semenkina, M.: Self-configuring genetic algorithm with modified uniform crossover operator. In: Tan, Y., Shi, Y., Ji, Z. (eds.) ICSI 2012. LNCS, vol. 7331, pp. 414–421. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-30976-2_50CrossRefGoogle Scholar
  26. 26.
    Semenkin, E., Semenkina, M.: Self-configuring genetic programming algorithm with modified uniform crossover. In: 2012 IEEE Congress on Evolutionary Computation (CEC), pp. 1–6. IEEE (2012)Google Scholar
  27. 27.
    Semenkin, E., Semenkina, M., Panfilov, I.: Neural network ensembles design with self-configuring genetic programming algorithm for solving computer security problems. In: Herrero, Á., et al. (eds.) International Joint Conference CISIS 2012-ICEUTE 2012-SOCO 2012 Special Sessions. AISC, vol. 189, pp. 25–32. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-33018-6_3CrossRefGoogle Scholar
  28. 28.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  29. 29.
    Thiam, P., et al.: Multi-modal pain intensity recognition based on the sense emotion database. IEEE (2019)Google Scholar
  30. 30.
    Thiam, P., Kessler, V., Schwenker, F.: Hierarchical combination of video features for personalised pain level recognition. In: 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 465–470 (2017)Google Scholar
  31. 31.
    Thiam, P., Schwenker, F.: Multi-modal data fusion for pain intensity assessment and classification. In: 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1–6. IEEE (2017)Google Scholar
  32. 32.
    Werner, P., Al-Hamadi, A., Niese, R., Walter, S., Gruss, S., Traue, H.C.: Towards pain monitoring: facial expression, head pose, a new database, an automatic system and remaining challenges. In: Proceedings of the British Machine Vision Conference, pp. 1–13 (2013)Google Scholar
  33. 33.
    Werner, P., Al-Hamadi, A., Niese, R., Walter, S., Gruss, S., Traue, H.C.: Automatic pain recognition from video and biomedical signals. In: Proceedings of the International Conference on Pattern Recognition (ICPR), pp. 4582–4587 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Reshetnev Siberian State University of Science and TechnologyKrasnoyarskRussia
  2. 2.Institute of Neural Information ProcessingUlm UniversityUlmGermany

Personalised recommendations