Determination of Basic Probability Assignment Based on Recognition Sequence

Abstract:

In some practical application of target recognition with sensors, the sensors will give the recognition sequence of targets, which is more detailed than the single recognition result. How to properly construct the basic probability assignment by the recognition sequence becomes the key to successful application of evidence theory. For the recognition sequence of the target recognition results of general sensor is incomplete, and the importance of the types in the recognition sequence is in descending order, this paper proposes a method to construct weights of recognition sequence, the basic probability assignments constructed by the weights are closer to the real recognition results. Simulation results show that this method is more reasonable and effective than the method of contrast.

• Periodical: Advanced Materials Research (Volumes 1049-1050)
• Pages: 1171-1175
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1049-1050.1171
• Online since: October 2014
• Authors: Yan Fei Chen*, Xue Zhi Xia, Kui Tu
• Keywords: Basic Probability Assignment, Evidence Theory, Recognition Sequence, Target Recognition

References

[1] DEMPSTER A P: Upper and lower probabilities induced by a multivalued mapping．Annals of Mathematical Statistics. Vol. 38, No2 (1967), pp.325-329.

DOI: 10.1214/aoms/1177698950

[2] SHAFER G A: Mathematical Theory of Evidence. Princeton University Press, Princeton (1976), pp.19-63.

[3] Harmanec D: Uncertainty in Dempster-Shafer theory. Ph. D Dissertation, State University of New York (1996).

[4] Oberkampf W. L, et al: Challenge problems: uncertainty in system response given uncertain parameters. Reliability Engineering&System Safety, Vol85, No. 1-3 (2004), pp.11-19.

DOI: 10.1016/j.ress.2004.03.002

[5] Yanfei CHEN, Xuezhi XIA, et al: Conflict Evidence Combination Based on Evidence Classification Strategy. Chinese Automation Congress (2013), pp.167-170.

DOI: 10.1109/cac.2013.6775722

[6] Telmoudi, A., Chakhar, S: Data fusion application from evidential databases as a support for decision making. Information and Software Technology, Vol. 46, No. 8 (2004), pp.547-555.

DOI: 10.1016/j.infsof.2003.10.005

[7] Ho T. K, Hull J. J, Srihari S. N: Decision combination in multiple classifier systems. IEEE Trans. on PAMI, Vol16, No. 1 (1994), pp.66-75.

DOI: 10.1109/34.273716

[8] James L: Fusion-based methods for target identification in the absence of quantitative classifier confidence . 6th Conference on Signal processing, sensor fusion, and target recognition (1997), pp.491-502.

DOI: 10.1117/12.280831

[9] Jia Yuping: Target Recognition Fusion Based on Belief Function Theory. Ph. D Dissertation, National University of Defense Technology (2009), pp.52-60.

[10] Wen Jiang, Yong Deng: A New Method to Determine BPA in Evidence Theory. JOURNAL OF COMPUTERS, VOL. 6, NO. 6 (2011), pp.1162-1167.