Time Series Data Analysis with Particle Filter-Based Relevance Vectors Machine Learning

  • Xiuli NingEmail author
  • Yingcheng Xu
  • Ying Li
  • Ya Li
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 82)


Analyzing and processing big data of product quality inspection is the key to guarantee product quality and safety. Time series data is one of the most important forms of product quality inspection data. Therefore, it is significant to research time series data. In this paper, we focus on the time series prediction data to contain complex noise and uncertainties. We use the correlation vector machine to carry out regression modeling, find the regularity in this series of complex data, and return the RVM regression model with the largest information to establish the state Spatial model. And then use the particle filter method, the model is constantly updated, in order to achieve better prediction. The experimental results show that this method can effectively solve the problem of noise and uncertainty in time series data analysis, and obtain better performance of time series data analysis.


Time series prediction Relevance vector machine Particle filter 



This research is supported and funded by the National Key Research and Development Plan under Grant No. 2016YFF0202600 and No. 2016YFF020260, the National Natural Science Foundation of China under Grant No. 71301152 and No. 91646122.


  1. 1.
    Zhang, S., Liu, P.: Prediction of chaotic time series based on the relevance vector machine. In: IEEE Fifth International Conference on Advanced Computational Intelligence, pp. 314–318. IEEE (2012)Google Scholar
  2. 2.
    Nikolaev, N., Tino, P.: Sequential relevance vector machine learning from time series. In: IEEE International Joint Conference on Neural Networks. In: Proceedings of IEEE Xplore, IJCNN 2005, vol. 2, pp. 1308–1313 (2005)Google Scholar
  3. 3.
    Liu, F., Song, H., Qi, Q., et al.: Time series regression based on relevance vector learning mechanism. In: International Conference on Wireless Communications, Networking and Mobile Computing. IEEE, pp. 1–4 (2008)Google Scholar
  4. 4.
    Quinonero-Candela, J., Hansen, L.K.: Time series prediction based on the Relevance Vector Machine with adaptive kernels. In: IEEE International Conference on Acoustics, Speech, and Signal Processing. IEEE Xplore, pp. I-985–I-988 (2002)Google Scholar
  5. 5.
    Zhou, Z.Q., Zhu, Q.X., Xu, Y.: Time series extended finite-state machine-based relevance vector machine multi-fault prediction. Chem. Eng. Technol. 2017, 40 (2017)Google Scholar
  6. 6.
    Fan, G., Deng-Wu, M.A., Ming-Hui, W.U., et al.: Condition time series prediction of electronic system based on optimized relevance vector machine. XI Tong Gong Cheng Yu Dian Zi Ji Shu/Syst. Eng. Electron. 35(9), 2011–2015 (2013)Google Scholar
  7. 7.
    Islam, M.Z., Oh, C.M., Lee, C.W.: Real time moving object tracking by particle filter. In: International Symposium on Computer Science and ITS Applications, pp. 347–352. IEEE Computer Society (2008)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Quality Management BranchChina National Institute of StandardizationBeijingChina

Personalised recommendations