An unsupervised evidential conflict resolution method for data fusion in IoT

Internet of Things (IoT) has gained substantial attention recently and plays a significant role in multiple real-world application deployments. A wide spectrum of such applications strongly depend on data fusion capabilities in the cloud from diverse information sources. In fact, various information sources often provide conflicting and contradictory for the same object, and thus it is important to fuse and resolve any possible information conflict before taking crucial decisions. For this reason, the primary aim of this paper is to provide a new evidential conflict resolution method that is able to automatically solve the problem of contradictory information provided by different sources in IoT applications. This method is based on the belief functions theory which is a powerful mathematical theory that can represent and manipulate various types if information imperfection. The performance of the proposed method was evaluated through simulation experiments. The results from these simulations demonstrated that our method outperforms the state-of-art methods in terms of effectiveness.

I. Introduction

IN RECENT years, the Internet of Things (IoT) has received considerable attention among academic researchers as well as industrial managers. The principal reason behind this consideration is the capabilities that IoT promises to offer. Indeed, IoT technology promises to revolutionize the way people live, work and interact with each other, by providing new opportunities to create a smarter world where all the abundant physical smart objects surrounding us can connect to the Internet and collaborate with one another so as to accomplish a common task with limited human intervention [1].