Outlier-Aware Data Aggregation in Sensor Networks

In this paper we discuss a robust aggregation framework that can detect spurious measurements and refrain from incorporating them in the computed aggregate values. Our framework can consider different definitions of an outlier node, based on a specified minimum support. Our experimental evaluation demonstrates the benefits of our approach.

• Type: Conference
• Year: 2008
• Where: ICDE
• Authors: Antonios Deligiannakis, Vassilis Stoumpos, Yannis Kotidis, Vasilis Vassalos, Alex Delis
• Keywords: Computed Aggregate Values, Database, ICDE 2008, Outlier Node, Robust Aggregation Framework