Data Fusion for Target Recognition Based on Evidence Theory in IOT Environment
Xiaoning Bo Xiaoning Bo, Jin Wang Xiaoning Bo, Guoqin Li Jin Wang, Yanli Tan Guoqin Li, Yi Tan · 電腦學刊 · 2021
Data fusion using evidence theory in IOT applications has been used extensively to recoginze targets because it offers the advantage of handling uncertainty. But the traditional Dempster’s combination rule cannot deal with highly conflicting information because it often generates counter-intuitive results. In this paper, a new weighted evidence combination approach is proposed to solve this problem. First, two measures, i.e., an uncertainty measure of each evidence and a probabilistic-based dissimilarity measure between two evidences, are introduced to estimate the value of weight of each sensor. Then, when combining conflicting information, reasonable results can be produced by using weighted average of evidences and Dempster’s combination rule. Our experimental results showed that the proposed method has better performance in performance than the existing methods.