The Improvement of DS Evidence Theory and Its Application in IR/MMW Target Recognition

Abstract

ATR system has a broad application prospect in the military field, especially in the field of modern defense technology. When paradoxes are in existence in ATR system due to adverse battlefield environment, integration cannot be effectively and reliably carried out only by traditional DS evidence theory. In this paper, a modified DS evidence theory is presented and applied in IR/MMW target recognition system. The improvement of DS evidence theory is realized by three parts: the introduction of sensor priority and evidence credibility to realize the discount processing of evidences, the modification of DS combination rule to enhance the accuracy of synthesis results, and the compound decision-making rule. The application of the modified algorithm in IR/MMW system is designed to deal with paradoxes, improve the target recognition rate, and ensure the reliability of target recognition system. Experiments are given to illustrate that the introduction of the modified DS evidence theory in IR/MMW system is better able to realize satisfactory target recognition performance through multisensor information fusion than any single-mode system.

An Efficient Method to Measure Evidence Conflict

“…4 d , evidence 1 supports a , evidence 2 and Evidence 3 Supports c . Therefore, the conflict between evidence 1 and evidence 2 should be greater than the conflict between evidence 2 and evidence 3, which is consistent with the actual analysis results.…”

“…As a method of uncertainty reasoning, Dempster-Shafer (D-S) evidence theory [1,2] can model and reason in uncertain problems and realize the fusion of no a priori information, and has been widely used in target recognition tracking , fault diagnosis, network security assessment and other areas [3][4][5][6][7][8][9]. However, when the evidence is highly conflicting, the results of the fusion of evidence often appear contrary to the facts.…”

Health Monitoring and Diagnosis of Equipment Based on Multi-sensor Fusion

“…Its greatest feature is the use of "interval estimation" for the description of uncertainty information. Compared to Bayesian networks, DS theory can produce a better fusion results by simple reasoning without knowing prior probability [23]. The basic mathematical concepts of DS theory are defined as follows.…”

Evaluation method based on fuzzy relations between Dempster-Shafer belief structure

“…When the data given by BPA distribution degenerate into the form of probability distribution, PT can also handle problems in DST. Several methods based on DST were applied to many real applications such as decision making under uncertain environments, pattern recognition, failure analysis, uncertainty modeling, and data fusion . Evidence theory, however, also has some open issues, such as conflicting management and dependence evidence combination …”

“…Several methods based on DST were applied to many real applications such as decision making under uncertain environments, [20][21][22][23] pattern recognition, 24,25 failure analysis, [26][27][28] uncertainty modeling, [29][30][31][32][33] and data fusion. [34][35][36] Evidence theory, however, also has some open issues, such as conflicting management 37,38 and dependence evidence combination. 39,40 FST and DST are both widely used in uncertainty analysis, but their theoretical principles are completely different.…”