Advertisement

A Data Fusion Algorithm Based on Clustering Evidence Theory

  • Yuchen WangEmail author
  • Wenqing Wang
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)

Abstract

Based on the idea of clustering and evidence theory, a new measurement data fusion algorithm is proposed. Firstly, all the measured values are clustered into groups according to the hierarchical clustering method, the best clustering group is selected, and each group is given different weights. Secondly, the set consisting of each group of measured values is regarded as identification framework, then the measured values in the group are converted into the corresponding evidence, which is fused after the evidence is modified, and the fused evidence is regarded as the weight of each measured value. Finally, after the data is weighted and summed within the group, weighted summation between groups to obtain the fusion result. The validity of the method is verified by the data simulation.

Keywords

Data fusion Hierarchical clustering Evidence theory 

Notes

Acknowledgements

This work is supported by Shaanxi Provincial Education Department industrialization project (16JF024) and is the key project in the field of industry (2018ZDXM-GY-039).

References

  1. 1.
    Xiong, Y., Ping, Z.: Data fusion algorithm inspired by evidence theory. J. Huazhong Univ. Sci. Technol. (Nat. Sci. Edn.), 39(10), 50–54 (2011).  https://doi.org/10.13245/j.hust.2011.10.007
  2. 2.
    Wang, W., Yang, Y., Yang, C.: A data fusion algorithm based on evidence theory. Control Decis. 1427–1430 (2013).  https://doi.org/10.13195/j.kzyjc.2013.09.027
  3. 3.
    Sun, Z.: Bayesian estimation method for multi-source data fusion. J. Qilu Univ. Technol. (Nat. Sci. Edn.) 73–76 (2018).  https://doi.org/10.16442/j.cnki.qlgydxxb.2018.01.016
  4. 4.
    Si, Y., Yang, X., Chen, Y., et al.: Multisensor weighted data fusion algorithm based on global state estimation. Infrared Technol. 36(5), 360–364 (2014)Google Scholar
  5. 5.
    He, L., Zhang, C., Jiang, P.: A new method of conflict evidence fusion based on confidence distance. Appl. Res. Comput. 31(10), 3041–3043 (2014)Google Scholar
  6. 6.
    Liang, X., Liu, X.: Improved consistency data fusion algorithm based on multicast tree. J. Huazhong Univ. Sci. Technol. (Nat. Sci. Edn.), 45(3), 374–379 (2011).  https://doi.org/10.19603/j.cnki.1000-1190.2011.03.007
  7. 7.
    Wang, H., Deng, J., Wang, L., et al.: Improved consistency data fusion algorithm and its application. J. China Univ. Min. Technol. 38(4), 590–594 (2009)Google Scholar
  8. 8.
    Dou, G., Wan, R., Zhang, X.: Data fusion algorithm based on fuzzy theory for wireless sensor networks. Microelectron. Comput. 29(9), 133–136 (2012).  https://doi.org/10.19304/j.cnki.issn1000-7180.2012.09.033
  9. 9.
    Wang, S., Dai, F., Liang, B., et al.: A path based partition clustering algorithm. Inf. Control 40(1), 141–144 (2011)Google Scholar
  10. 10.
    Feng, L.: Improved BP neural network algorithm and its application. Comput. Simul. 27(12), 172–175 (2010)Google Scholar
  11. 11.
    Chen, X., Lou, P.H.: Application of improved hierarchical clustering algorithm in document analysis. J. Numer. Methods Comput. Appl. 30(4), 277–287 (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of AutomationXi’an University of Posts and TelecommunicationsXi’anChina

Personalised recommendations