Neural Computing and Applications

, Volume 31, Supplement 2, pp 693–705 | Cite as

An adaptive PNN-DS approach to classification using multi-sensor information fusion

  • Ning ChenEmail author
  • Fuchun Sun
  • Linge Ding
  • Hongqiao Wang
ISNN 2008


In this paper, an adaptive neural network approach to classification which combines modified probabilistic neural network and D-S evidence theory (PNN-DS) is proposed. It attempts to deal with the drawbacks of information uncertainty and imprecision using single classification algorithm. This PNN-DS approach firstly adopts a modified probabilistic neural network (PNN) to obtain posteriori probabilities and make a primary classification decision in feature-level fusion. Then posteriori probabilities are transformed to masses noting the evidence of the D-S evidential theory. Finally advanced D-S evidential theory is utilized to gain more accurate classification results in the last decision-level fusion. In order to implement PNN-DS, covariance matrices are firstly employed in the modified PNN module to replace the singular smoothing factor in the PNN’s kernel function, and linear function is utilized in the pattern of summation layer. Secondly, the whole scheme of the proposed approach is explained in depth. Thirdly, three classification experiments are carried out on the proposed approach and a large amount of comparable analyses are done to demonstrate the effectiveness and robustness of the proposed approach. Experiments reveal that the PNN-DS outperforms BPNN-DS, which provides encouraging results in terms of classification accuracy and the speed of learning convergence.


Multi-sensor information fusion Target classification Probabilistic neural network (PNN) D-S evidence theory (DSET) 



This work was jointly supported by the National Science Fund for Distinguished Young Scholars (Grant No: 60625304), the National Natural Science Foundation of China (Grants No: 60621062, 60504003, 60474025, 90405017), the National Key Project for Basic Research of China (Grant No: G2007CB311003, G2002cb312205) and the Specialized Research Fund for the Doctoral Program of Higher Education (Grant No: 20050003049).


  1. 1.
    Basir Otman, Karray Fakhri, Zhu Hongwei (2005) Connectionist-based Dempster–Shafer evidential reasoning for data fusion. IEEE Trans Neural Netw 16:1513–1516CrossRefGoogle Scholar
  2. 2.
    Hégarat-Mascle SL, Bloch I, Vidal-Madjar D (1997) Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing. IEEE Trans Geosci Remote Sens 35:1018–1031CrossRefGoogle Scholar
  3. 3.
    Hégarat-Mascle SL, Bloch I, Vidal-Madjar D (1998) Introduction of neighborhood information in evidence theory and application to data fusion of radar and optical images with partial cloud cover. Pattern Recognit 31:1811–1823Google Scholar
  4. 4.
    Bloch I (1996) Some aspects of Dempster-Shafer evidence theory for classification of multi-modality medical images taking partial volume effect into account. Pattern Recognit Lett 17:905–919CrossRefGoogle Scholar
  5. 5.
    Rombaut M, Zhu YM (2002) Study of Dempster–Shafer for image segmentation applications. Image Vis Comput 20:15–23CrossRefGoogle Scholar
  6. 6.
    Huang J, Cheng Y, Pi Y, Pan Q (2005) Airplane image recognition based on BP neural network and DS evidence reasoning. Comput Simul China 22:184–186Google Scholar
  7. 7.
    Chiping Z (2006) Methods of multi-sensor data fusion and their application in the spatial targets recogntion, Doctoral dissertation, V249.122, pp 1–11Google Scholar
  8. 8.
    Shijie T, Shesheng G, Hualing X (2007) Research of information fusion model combining DS evidence theory and neural Network. Chin J Sens Actuators 1815–1818Google Scholar
  9. 9.
    Poirazi P, Neocleous C, Pattichis CS, Schizas CN (2004) Classification capacity of a modular neural network implementing neurally inspired architecture and training rules. IEEE Trans Neural Netw 15:597–612CrossRefGoogle Scholar
  10. 10.
    Specht DF (1990) Probabilistic neural networks. Neural Netw 3:109–118CrossRefGoogle Scholar
  11. 11.
    Song T, Jamshidi MM, Lee RR, Huang M (2007) A modified probabilistic neural network for partial volume segmentation in brain MR image. IEEE Trans Neural Netw 18:1424–1432Google Scholar
  12. 12.
    Zhang C, Cui P, Zhang Y (2006) An algorithm of data fusion combined neural networks with DS evidential theory. In: First international aerospace and astronautics ISSCAA 2006, Harbin, EI, pp 1141–1144Google Scholar
  13. 13.
    Zhang C, Cui P, Zhang Y (2006) An algorithm of characteristic data fusion based on neural network group. In: Proceedings of the fifth international conference on machine learning and cybernetics, Aug 2006, pp 2917–2919Google Scholar
  14. 14.
    Zhu H, Basir O (2006) A novel fuzzy evidental reasoning paradigm for data fusion with applications in image processing. Soft Comput 10:1169–1180CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2008

Authors and Affiliations

  • Ning Chen
    • 1
    Email author
  • Fuchun Sun
    • 1
  • Linge Ding
    • 1
  • Hongqiao Wang
    • 1
  1. 1.Department of Computer Science and TechnologyTsinghua UniversityBeijingChina

Personalised recommendations