Bayesian Outlier Detection in Location-aware Wireless Networks

Paper in proceeding, 2011

Location-aware networks are a rapidly growing area of research with a wide range of applications. The accuracy of localization depends on the reliability of the information exchanged between devices in the network. In practice, devices may fail or maliciously inject false position information into the network. This paper aims to design and test algorithms to verify the location consistency in wireless networks. We propose a new method based on factor graphs. This method is flexible, easily extendible to cooperative networks, and leads to significant performance improvements compared to existing techniques that are based on linear programming.