Title :
Contribution of evidence-similarity to target classification
Author :
Li, Jian ; Lan, Jinhui
Author_Institution :
Dept. of Instrum. Sci. & Technol., Univ. of Sci. & Technol. Beijing, Beijing, China
Abstract :
To resolve the target classification problem under the condition of interference, the paper presents a target classification method based on the evidence-similarity. Because the results of Dempster-Shafer Theory (DST) and Dezert-Smarandache Theory (DSmT) are used in different conflict condition. In the low conflict situation, the classification by DST has good effect, but the classification by DSmT introduces the focal element, which increase the amount of computation greatly. In the high conflict situation, DSmT can effectively tackle the problem that the contradiction focal element can not be fused in DST, and avoid the DST classification appearing counterintuitive conclusions. Therefore, the two kinds of classification theories are combined by the similarity of evidence in the paper. Experiment results show that the method can effectively improve the accuracy of the target classification under different conflict condition.
Keywords :
inference mechanisms; pattern classification; sensor fusion; uncertainty handling; DST; DSmT; Dempster-Shafer theory; Dezert-Smarandache theory; evidence similarity; target classification; Magnetic sensors; Manganese; Reliability; Vectors; Vehicles; DST; PCR6; evidence-similarity; target classification;
Conference_Titel :
Industrial Electronics and Applications (ICIEA), 2012 7th IEEE Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4577-2118-2
DOI :
10.1109/ICIEA.2012.6361023