Modeling of distributed visual knowledge discovery from data process

Assigning a set of intelligent agents in each phase of the Knowledge Discovery from Data (KDD) process improves communication and cooperation between the different KDD steps in order to generate relevant results knowledge for decision-making tasks. We aim in particular to simulate the behavior of a KDD system in which specific intelligent agents interact with each other and with their environment. Such environment is characterized by its dynamic, visual and real-time aspects. The proposed approach is applied to develop a prototype for the fight against nosocomial infections in the hospital Intensive Care Units. This paper ends with the evaluation of the prototype usability.