Chu Spaces - a New Approach to Diagnostic Information Fusion
Hung T. Nguyen, Владик Крейнович, Berlin Wu · scholarworks - UTEP (The University of Texas at El Paso) · 1999
This paper is rather theoretical. Its aim is to describe a general algebraic framework, known as Chu spaces, in which different type of information can be transformed into the same form, so that fusion procedures can be investigated in a single general framework. Keywords: Chu spaces, data fusion, fuzziness, probability 1 A Motivating Example Data fusion means that we combine ("fuse") several pieces of information (measurement results, expert estimates) about one or several objects. To describe our new approach to formalizing data fusion, we will start with a physically meaningful (and mathematically simple) example. In order to find the location of distant radio sources, we measure the signals from these sources received on different radiotelescopes, and then fuse the measurement results. The larger the telescope, the more accurate the measurements. Therefore, to achieve maximum accuracy, antennas forming a radiotelescope are placed as far away from each other as possible: ideally, o...