Advertisement

A Comparison of Computational Intelligence Techniques for Real-Time Discrete Multivariate Time Series Classification of Conducting Gestures

  • Justin van Heek
  • Gideon Woo
  • Jack Park
  • Herbert H. TsangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11754)

Abstract

Gesture classification is a computational process that can identify and classify human gestures. More specifically, gesture classification is often a discrete multivariate time series classification problem and various computational intelligence solutions have been developed for these problems. It is difficult to determine which existing techniques and approaches to algorithms will produce the most effective solutions for discrete multivariate time series classification problems. In this study, we compare twelve different classification algorithms to report which techniques and approaches are most effective for recognizing conducting beat pattern gestures. After performing 10-fold cross-validation tests on twelve commonly used algorithms, the results show that of the algorithms tested, the most accurate were RNN, LSTM, and DTW; all of which had an accuracy of 100%. We found that in general, algorithms which can take in a dynamic sequence input and classification algorithms that are discriminative performed consistently well, while their counterparts varied in performance. From these results we determine that when selecting a computational intelligence technique to solve these classification problems, it would be advantageous to consider the top performing algorithms along with furthering research into new dynamic input and discriminative algorithms.

Keywords

Gesture recognition Classification Conducting Computational intelligence Neural networks Machine learning 

References

  1. 1.
    Chin-Shyurng, F., Lee, S.E., Wu, M.L.: Real-time musical conducting gesture recognition based on a dynamic time warping classifier using a single-depth camera. Appl. Sci. 9(3), 528 (2019).  https://doi.org/10.3390/app9030528CrossRefGoogle Scholar
  2. 2.
    Chung, J., Gülçehre, Ç., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR abs/1412.3555 (2014)Google Scholar
  3. 3.
    van Heek, J., Park, J., Yu, X., Tsang, H.H.: An evaluation study of recognizing conducting gesture using computational intelligence techniques. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1005–1012, November 2018.  https://doi.org/10.1109/SSCI.2018.8628906
  4. 4.
    Kolesnik, P., Wanderley, M,M.: Recognition, analysis and performance with expressive conducting gestures. In: In Proceedings of the International Computer Music Conference (2004)Google Scholar
  5. 5.
    Lee-Cosio, B.M., Delgado-Mata, C., Ibanez, J.: ANN for gesture recognition using accelerometer data. In: the 2012 IberoAmerican Conference on Electronics Engineering and Computer Science, Procedia Technology, vol. 3, pp. 109–120 (2012)CrossRefGoogle Scholar
  6. 6.
    Li, C., Xie, C., Zhang, B., Chen, C., Han, J.: Deep fisher discriminant learning for mobile hand gesture recognition. Pattern Recogn. 77, 276–288 (2018).  https://doi.org/10.1016/j.patcog.2017.12.023CrossRefGoogle Scholar
  7. 7.
    Lu, Z., Chen, X., Li, Q., Zhang, X., Zhou, P.: A hand gesture recognition framework and wearable gesture-based interaction prototype for mobile devices. IEEE Trans. Hum.-Mach. Syst. 44(2), 293–299 (2014).  https://doi.org/10.1109/THMS.2014.2302794CrossRefGoogle Scholar
  8. 8.
    Ma’asum, F.F.M., Sulaiman, S., Saparon, A.: An overview of hand gestures recognition system techniques. In: 2012 IOP Conference Series: Materials Science and Engineering, vol. 99, no. 01, November 2015.  https://doi.org/10.1088/1757-899x/99/1/012012CrossRefGoogle Scholar
  9. 9.
    Paalanen, P.: Bayesian classification using gaussian mixture model and EM estimation: implementations and comparisons. Information Technology Project (2004)Google Scholar
  10. 10.
    Ratanamahatana, C., Keogh, E.: Everything you know about dynamic time warping is wrong. In: 3rd Workshop on Mining Temporal and Sequential Data SIGKDD, January 2004Google Scholar
  11. 11.
    Rish, I.: An empirical study of the naive bayes classifier. In: IJCAI 2001 Work Empircal Methods Artifical Intelligence, vol. 3, January 2001Google Scholar
  12. 12.
    Yadav, M., Alam, A.: Dynamic time warping (DTW) algorithm in speech: a review. Int. J. Res. Electron. Comput. Eng. 6 (2018)Google Scholar
  13. 13.
    Yuan, T., Wang, B.: Accelerometer-based Chinese traffic police gesture recognition system. Chin. J. Electron. 19, 270–274 (2010) Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Justin van Heek
    • 1
  • Gideon Woo
    • 1
  • Jack Park
    • 1
  • Herbert H. Tsang
    • 1
    Email author
  1. 1.Applied Research LabTrinity Western UniversityLangleyCanada

Personalised recommendations