A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion

Abstract

Dempster–Shafer theory (DST), which is widely used in information fusion, can process uncertain information without prior information; however, when the evidence to combine is highly conflicting, it may lead to counter-intuitive results. Moreover, the existing methods are not strong enough to process real-time and online conflicting evidence. In order to solve the above problems, a novel information fusion method is proposed in this paper. The proposed method combines the uncertainty of evidence and reinforcement learning (RL). Specifically, we consider two uncertainty degrees: the uncertainty of the original basic probability assignment (BPA) and the uncertainty of its negation. Then, Deng entropy is used to measure the uncertainty of BPAs. Two uncertainty degrees are considered as the condition of measuring information quality. Then, the adaptive conflict processing is performed by RL and the combination two uncertainty degrees. The next step is to compute Dempster’s combination rule (DCR) to achieve multi-sensor information fusion. Finally, a decision scheme based on correlation coefficient is used to make the decision. The proposed method not only realizes adaptive conflict evidence management, but also improves the accuracy of multi-sensor information fusion and reduces information loss. Numerical examples verify the effectiveness of the proposed method.

Research on Mechanical Equipment Fault Diagnosis Method Based on Deep Learning and Information Fusion

“…Arellano-Espitia proposed a diagnosis method on the basis of multiple information source extraction and fusion in electromechanical systems, which can adaptively learn complex relationships in signals to characterize different fault states [ 19 ]. Huang proposed an information fusion method combining uncertain evidence and reinforcement learning, which improves the accuracy of fusion and solves the decision problem with low information, ignoring the decision implementation under the condition of a large amount of information [ 20 ]. Among the methods of real-time fault diagnosis and surveillance, a DS evidence theory combined with the principal component analysis fusion method was proposed by Yao for diagnosing rolling bearing faults and solving the low accuracy problem of fault classification [ 21 ].…”

A RFID-Integrated Framework for Tag Anti-Collision in UAV-Aided VANETs

“…In the past few years, unmanned aerial vehicles (UAVs) have received great attention for their capability to reach places that are not easily accessible by humans, such as remote sensing [1] and monitoring huge spaces as an effective alternative in wide wireless sensor networks [2][3][4]. More recently, UAVs equipped with communication devices have been widely applied to vehicular ad hoc networks (VANETs), such as UAVs, and can be integrated into VANET infrastructures to provide support for vehicle-related services [5,6].…”