Houses Bombing in Ravixe: a Bench for High Level Fusion Evaluation

Abstract

Many benchmarks exist for the evaluation of algorithms in fields such as numerical optimization, automatic planning, SAT solving, Natural Language Processing, automatic code parallelization, signal processing, machine learning and low level fusion. To the best of our knowledge, however, there is no such bench existing for the evaluation of high level information fusion. In this paper, we describe a benchmark that we developed with the aim of evaluating high level fusion algorithms. The bench is related to a house bombing scenario in a fictive world. The scenario is fictional and takes place in a city, within a context of instability in the population between the members of two different communities. We describe the scenario itself, as well as the different sources of information and the kind of information they provide. The whole set of information available in the bench is described. Starting from a complete version of the bench that contains all the information items exchanged during the scenario, we derived several other benches that contain less or altered information items. This will enable evaluating the robustness of the high level information fusion systems, according to the quality of the information they are provided with and without the imperfection of information extractors exhibiting pieces of information from raw data.