A Communication Efficient Framework for Finding Outliers in Wireless Sensor Networks

Abstract

Outlier detection is a well studied problem in various fields. The unique challenges of wireless sensor networks make this problem especially challenging. Sensors can detect outliers for a plethora of reasons and these reasons need to be inferred in real time. Here, we present a new communication technique to find outliers in a wireless sensor network. Communication is minimized through controlling sensor when sensors are allowed to communicate. At the same time, minimal assumptions are made about the nature of the data set as to minimize the loss of generality in the architecture.