Query Evaluation and Information Fusion in a Retrieval System for Multimedia Documents

Despite their predominant application in robotics, the utility of methods for information fusion is not limited to sensor-based fusion tasks. The paper presents an information retrieval (IR) system for multimedia weather documents which makes use of linguistic fusion methods and a semantically rich retrieval model based on methods from fuzzy set theory. The computational problem of how to efficiently organize the query evaluation process is solved by object-based mediation and asynchronous parallel invocations both of the document evaluation and fusion methods.