Neural Computing and Applications

, Volume 31, Issue 12, pp 8519–8532 | Cite as

A motion classification model with improved robustness through deformation code integration

  • Lei Xia
  • Jiancheng LvEmail author
  • Dongbo Liu
Original Article


During data acquisition, samples in a time series may contain noise, such as inconsistent data ranges, inconsistent data, and incomplete data. Therefore, the classification model requires improved robustness to correctly classify the sequence of human motion. This paper presents a classification model with improved robustness performance based on the factored gated restricted Boltzmann machine to effectively overcome the various aforementioned data problems. The proposed model acquires the deformation code of each action first and integrates the deformation codes together to be an integrated deformation code of the entire sequence. Then, the model determines the classification from the integrated deformation code. This approach mainly focuses on the deformation relations among action samples in the extraction sequence, and it ignores the data expression in the sequence samples. Experiments show that the proposed model performs better than state-of-the-art approaches in terms of the robustness of time series classification with noise.


High-dimensional Deformation code Robustness Classification 



This work was supported by the National Science Foundation of China (Grant No. 61625204), partially supported by the State Key Program of National Science Foundation of China (Grant No. 61432012 and 61432014).

Compliance with ethical standards

Conflict of interest

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work and that there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled, “A Motion Classification Model with Improved Robustness through Deformation Code Integration.”


  1. 1.
    Ratanamahatana C, Keogh EJ (2005) Three myths about dynamic time warping data mining. In: SIAM international conference on data miningGoogle Scholar
  2. 2.
    Chen G, Srihari SH (2014) Restricted Boltzmann machine for classification with hierarchical correlated prior. Eprint ArxivGoogle Scholar
  3. 3.
    Elaiwat S (2016) A semantic RBM-based model for image set classification. Elsevier Science Publishers B. V., AmsterdamCrossRefGoogle Scholar
  4. 4.
    Fischer A, Igel C (2012) An introduction to restricted Boltzmann machines. In: Iberoamerican congress on pattern recognition, pp 14–36CrossRefGoogle Scholar
  5. 5.
    Frnay B, Verleysen M (2014) Classification in the presence of label noise: a survey. IEEE Trans Neural Netw Learn Syst 25(5):845CrossRefGoogle Scholar
  6. 6.
    Hinton G, Deng L (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82–97CrossRefGoogle Scholar
  7. 7.
    Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771–1800CrossRefGoogle Scholar
  8. 8.
    Hinton GE (2012) A practical guide to training restricted Boltzmann machines. Springer, BerlinCrossRefGoogle Scholar
  9. 9.
    Lee H, Yan P, Ng AY (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. In: International conference on neural information processing systems, pp 1096–1104Google Scholar
  10. 10.
    Li W (2010) Action recognition based on a bag of 3D points. In: Computer vision and pattern recognition workshops, pp 9–14Google Scholar
  11. 11.
    Lv F, Nevatia R (2006) Recognition and segmentation of 3-D human action using HMM and multi-class AdaBoost. Springer, BerlinCrossRefGoogle Scholar
  12. 12.
    Martens J, Sutskever I (2011) Learning recurrent neural networks with hessian-free optimization. In: International conference on international conference on machine learning, pp 1033–1040Google Scholar
  13. 13.
    Masnadi-Shirazi H (2011) The design of Bayes consistent loss functions for classification. University of California at San Diego, San DiegoGoogle Scholar
  14. 14.
    Masnadi-Shirazi H, Vasconcelos N (2008) On the design of loss functions for classification: theory, robustness to outliers, and savageboost. In: Conference on neural information processing systems, Vancouver, British Columbia, Canada, pp 1049–1056Google Scholar
  15. 15.
    Memisevic R, Hinton G (2007) Unsupervised learning of image transformations. In: IEEE conference on computer vision and pattern recognition. CVPR ’07, pp 1–8Google Scholar
  16. 16.
    Memisevic R, Hinton GE (2010) Learning to represent spatial transformations with factored higher-order Boltzmann machines. Neural Comput 22(6):1473–1492CrossRefGoogle Scholar
  17. 17.
    Muller M (2006) Motion templates for automatic classification and retrieval of motion capture data. In: ACM Siggraph/eurographics symposium on computer animation, SCA 2006, Vienna, Austria, pp 137–146Google Scholar
  18. 18.
    Salakhutdinov R (2007) Restricted Boltzmann machines for collaborative filtering. In: International conference on machine learning, pp 791–798Google Scholar
  19. 19.
    Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, Kipman A, Blake A (2011) Real-time human pose recognition in parts from single depth images. In: Computer vision and pattern recognition, pp 1297–1304Google Scholar
  20. 20.
    Srinivasan B, Prasad UR, Rao NJ (1994) Back propagation through adjoints for the identification of nonlinear dynamic systems using recurrent neural models. IEEE Trans Neural Netw 5(2):213–228CrossRefGoogle Scholar
  21. 21.
    Taylor GW (2006) Modeling human motion using binary latent variables. In: International conference on neural information processing systems, pp 1345–1352Google Scholar
  22. 22.
    Tomczak JM, Zieba M (2015) Classification restricted Boltzmann machine for comprehensible credit scoring model. Expert Syst Appl 42(4):1789–1796CrossRefGoogle Scholar
  23. 23.
    Welch G, Bishop G (2010) An introduction to the Kalman filter. Univ N C Chapel Hill 8(7):127–132Google Scholar
  24. 24.
    Wu Y (2012) Mining actionlet ensemble for action recognition with depth cameras. In: IEEE conference on computer vision and pattern recognition, pp 1290–1297Google Scholar
  25. 25.
    Wu Y, Liu Y (2007) Robust truncated hinge loss support vector machines. J Am Stat Assoc 102(479):974–983MathSciNetCrossRefGoogle Scholar
  26. 26.
    Zhang H, Cao X, Ho JK, Chow TW (2017) Object-level video advertising: an optimization framework. IEEE Trans Ind Inform 13(2):520–531CrossRefGoogle Scholar
  27. 27.
    Zhang H, Li J, Ji Y, Yue H (2017) Understanding subtitles by character-level sequence-to-sequence learning. IEEE Trans Ind Inform 13(2):616–624CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  1. 1.The Machine Intelligence Laboratory, Computer Science CollegeSichuan University, ChinaChengduChina

Personalised recommendations