In-Network Outlier Detection in Wireless Sensor Networks

To address the problem of unsupervised outlier detection in wireless sensor networks, we develop an algorithm that (1) is flexible with respect to the outlier definition, (2) works in-network with communication load proportional to the outcome, (3) reveals its outcome to all of sensors. We examine the algorithm’s performance using simulator and real sensor data streams. Our results demonstrate that the algorithm introduces reasonable communication load and power consumption.

• Type: Conference
• Year: 2006
• Where: ICDCS
• Authors: Joel W. Branch, Boleslaw K. Szymanski, Chris Giannella, Ran Wolff, Hillol Kargupta
• Keywords: Communication Load, Distributed And Parallel Computing, ICDCS 2006, Unsupervised Outlier Detection, Wireless Sensor Networks