Personal and Ubiquitous Computing

, Volume 13, Issue 7, pp 499–508 | Cite as

An efficient scheme of target classification and information fusion in wireless sensor networks

  • Youngsoo KimEmail author
  • Sangbae Jeong
  • Daeyoung Kim
  • Tomás Sánchez López
Original Article


In this paper, an efficient target classification and fusion scheme for wireless sensor networks (WSNs) is proposed and evaluated. When a classification algorithm for WSN nodes is designed, parametric approaches such as Gaussian mixture model (GMM) should be more preferred to non-parametric ones due to the hard limitation in resources. The GMM algorithm not only shows good performances for target classification in WSNs but it also requires very small resources. Based on the classifier, a decision tree generated by the classification and regression tree algorithm is used to fuse the information from heterogeneous sensors. This node-level classification scheme provides a satisfactory classification rate, 94.10%, with little resources. Finally, a confidence-based fusion algorithm improves the overall accuracy by fusing the information among sensor nodes. Our experimental results show that the proposed group-level fusion algorithm improves the accuracy by an average of 4.17% accuracy with randomly selected nodes.


Sensor network Target classification Sensor fusion Gaussian mixture model (GMM) Classification and regression tree (CART) 



This research was supported by the MKE (Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2008-C1090-0801-0047) and the Korea Science and Engineering Foundation (KOSEF) grant funded by the Korea government(MOST) (No. R0A-2007-000-10038-0)


  1. 1.
    Duarte M, Hu Y-H (2004) Vehicle classification in distributed sensor networks. J Parallel Distribut Comput 64(7):826–838CrossRefGoogle Scholar
  2. 2.
    Meesookho C, Narayanan S, Raghavendra CS (2002) Collaborative classification applications in sensor networks. In: Second IEEE sensor array and multichannel signal processing workshop, pp 370–374Google Scholar
  3. 3.
    Li D, Wong KD, Hu YH, Sayeed AM (2002) Detection, classification and tracking of targets in distributed sensor networks. IEEE Signal Processing Magazine, pp 17–29Google Scholar
  4. 4.
    Brooks RR, Griffin C, Friedlander D (2003) Distributed target classification and tracking in sensor networks. Proc IEEE, pp 1163–1171Google Scholar
  5. 5.
    Arora A et al (2004) A line in the sand: a wireless sensor network for target detection, classification, and tracking. Comput Networks J 46(5):605–634CrossRefGoogle Scholar
  6. 6.
    Dasarathy BV (1990) Nearest neighbor: pattern classification techniques. IEEE Comput Soc. ISBN 0-8186-8930-7Google Scholar
  7. 7.
    Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Mining Knowledge Discovery 2:121–167CrossRefGoogle Scholar
  8. 8.
    Duarte M, Hu Y (2004) Distance based decision fusion in a distributed wireless sensor network. Telecomm Syst 26:339–350CrossRefGoogle Scholar
  9. 9.
    Klein LA (2004) Sensor and data fusion. SPIE. ISBN 0-8194-5435-4Google Scholar
  10. 10.
    Reynolds DA, (1992) Gaussian mixture modeling approach to text-independent speaker identification. Ph.D. thesis, Georgia Institute of TechnologyGoogle Scholar
  11. 11.
    Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, CAzbMATHGoogle Scholar
  12. 12.
    Kay SM (1993) Fundamentals of statistical signal processing: estimation theory. Prentice Hall, NJ. ISBN 0-13-345711-7Google Scholar
  13. 13.
    Zheng F, Zhang G, Song Z (2001) Comparison of different implementations of MFCC. J Comput Sci Technol 16(6):582–589zbMATHCrossRefGoogle Scholar
  14. 14.
    Falk TH, Chan WY (2005) A sequential feature selection algorithm for GMM-based Speech Quality Estimation, European Signal Processing ConferenceGoogle Scholar
  15. 15.
    Xuan G, Zhang W, Chai P (2001) EM algorithms of Gaussian mixture model and hidden markov model. In: Proceedings of the international conference on image processing, pp 145–148Google Scholar
  16. 16.
    Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. John-Wiley, pp 282–347Google Scholar
  17. 17.
    Loh W-Y, Nunta Vanichsetakul N (1988) Tree-structured classification via generalized discriminant analysis. J Am Stat Associat 83(403):715–728zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  • Youngsoo Kim
    • 1
    Email author
  • Sangbae Jeong
    • 2
  • Daeyoung Kim
    • 1
  • Tomás Sánchez López
    • 1
  1. 1.Real-time and Embedded System LaboratoryInformation and Communications UniversityDaejonKorea
  2. 2.Electronics Engineering DepartmentGyeongsang National UniversityJinjuKorea

Personalised recommendations