Diseño de un sistema inteligente para estimación de categorización de grupos de investigación a partir de lineamientos definidos por COLCIENCIAS.

Abstract

This document deals with the design and implementation of a research product recommendation system which is focused on research groups from systems engineering curricular project. After that, a planning of the components to be developed was carried out, as well as the information necessary for the operation of the system, as well as the architecture to be designed and implemented. Then the development of the web scraper, the calculation engine, and its components were started. Finally, the recommendation system was developed, defining four architectures of neural networks, the last being the one used in the implementation. of the recommending system through the creation of a java library with the MATLAB tool, and the creation of the frontend component. For the development of the system, Liferay Portal CE was used for the development of the frontend layer, Mule ESB CE for the development of the services and integration layer, and MySQL as a relational database engine.