Athena: A Knowledge Fusion Algorithm for the Internet of Things

Abstract

Internet of things (IoT) is envisioned as the interconnection of the Internet with sensing and actuating devices. IoT systems are usually designed to collect massive amounts of data from multiple and possibly conflicting sources. Nevertheless, data must be refined before being stored in a repository, so as information can be correctly extracted for further uses. Knowledge fusion is an important technique to identify and eliminate erroneous data from compromised sources or any mistakes that might have occurred during the extraction process. We propose a new multisensor data fusion algorithm for IoT that supports the knowledge extraction needed to adapt knowledge graphs. This algorithm, named Athena, enhances accuracy when compared to the traditional multisensor data fusion techniques. We also discuss the role of reinforcement learn over integration on a multi-application WSAN.