A Weighted Combination Method for Conflicting Evidence in Multi-Sensor Data Fusion.

摘要: Dempster–Shafer evidence theory is widely applied in various fields related to information fusion. However, how avoid the counter-intuitive results an open issue when combining highly conflicting pieces of evidence. In order handle such a problem, weighted combination method for multi-sensor data fusion proposed by considering both interplay between and impacts themselves. First, degree credibility determined on basis modified cosine similarity measure basic probability assignment. Then, adjusted leveraging belief entropy function volume Finally, final weight each piece generated from above steps obtained adopted modify bodies before using Dempster’s rule. A numerical example provided illustrate that reasonable efficient handling addition, applications classification motor rotor fault diagnosis validate practicability with better accuracy.