Title :
A new method of determining the basic belief assignment in D-S evidence theory
Author :
Yong ; Gao, Jun ; Liang-Mei Hu ; Dong, Hou-ming
Author_Institution :
Lab. on Image Inf. Process., Hefei Univ. of Tech., China
Abstract :
In this paper, the application of D-S evidence theory in multi-feature, multi-neural network classifier pattern recognition has been researched. The key problem in determining the basic belief assignment (BBA) has been discussed in detail. A new method of determining the BBA based on neural network is presented in this paper. The result of traffic sign shape recognition experiment shows that this new method can not only improve the total correct recognition percentage, but also reduce the fuzziness of decision-making and simplify the calculation.
Keywords :
belief networks; decision making; neural nets; pattern classification; uncertainty handling; BBA; D-S evidence theory; Dempster-Shafer evidence theory; basic belief assignment; decision making; multineural network classifier; pattern recognition; shape recognition; Bayesian methods; Decision making; Electronic mail; Fuzzy logic; Information representation; Intelligent networks; Neural networks; Pattern recognition; Probability; Shape;
Conference_Titel :
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN :
0-7803-8131-9
DOI :
10.1109/ICMLC.2003.1260132
