The Actias system: supervised multi-strategy learning paradigm using categorical logic

TL;DR

The Actias system introduces a supervised multi-strategy learning framework that leverages collaborative data mining and graphical logic to efficiently build and integrate knowledge bases for Business Information Systems.

Contribution

It presents the Actias system, a novel approach combining collaborative data mining with graphical logic for knowledge integration in knowledge base construction.

Findings

Enables collaborative knowledge acquisition from heterogeneous data models

Uses graphical sketches language for knowledge integration

Improves speed and quality of knowledge base development

Abstract

One of the most difficult problems in the development of intelligent systems is the construction of the underlying knowledge base. As a consequence, the rate of progress in the development of this type of system is directly related to the speed with which knowledge bases can be assembled, and on its quality. We attempt to solve the knowledge acquisition problem, for a Business Information System, developing a supervised multistrategy learning paradigm. This paradigm is centred on a collaborative data mining strategy, where groups of experts collaborate using data-mining process on the supervised acquisition of new knowledge extracted from heterogeneous machine learning data models. The Actias system is our approach to this paradigm. It is the result of applying the graphic logic based language of sketches to knowledge integration. The system is a data mining collaborative workplace, where the Information System knowledge base is an algebraic structure. It results from the integration of background knowledge with new insights extracted from data models, generated for specific data modelling tasks, and represented as rules using the sketches language.