DREAM: Dynamic data relation extraction using adaptive multi-agent systems

Abstract

Understanding data is the main purpose of data science and how to achieve it is one of data science challenges, especially when dealing with big data. In order to find meaning and relevant information drowned in the data flood, while overcoming big data challenges, one should rely on an analytic tool able to find relations between data, evaluate them and detect their changes and evolution over time. The aim of this paper is to present the DREAM1 tool for dynamic data relations discovery and dynamic display based on a collective artificial intelligence Adaptive Multi-Agent System (AMAS) that uses a new data similarity metric, the Dynamics Correlation. It is currently being applied in the neOCampus operation, the ambient campus of the University of Toulouse III — Paul Sabatier.