Home // eKNOW 2015, The Seventh International Conference on Information, Process, and Knowledge Management // View article

Knowledge Intensive Evolutionary Algorithms

Authors:
François de Bertrand de Beuvron
Carlos Catania
Cecilia Zanni-Merk

Keywords: Knowledge engineering, multi-objective optimization problems, evolutionary algorithms

Abstract:
In this paper, we show through the resolution of a real problem, how knowledge engineering techniques can be used to guide the definition of Evolutionary Algorithms (EA) for problems involving a large amount of structured data. Evolutionary Algorithms have proven to be very effective in optimizing intractable problems in many areas. Various representations of the fitness functions (multi-objective EA), the genome and mutation / crossover operators adapted to different types of problems (routing, scheduling, etc. ) have been proposed in the literature. However, real problems including specific constraints (legal restrictions, specific usages, etc.) are often overlooked by the proposed generic models. To ensure that these constraints are effectively taken into account, we propose a methodology based on the structuring of the conceptual model underlying the problem, creating a domain ontology suitable for optimization by EA. The real-world example, that is detailed throughout the article, belongs to the general field of medical assistance. The project focuses on the logistics involved in the transportation of the patients. Although this problem is a specific case of the heavily studied family of Vehicle Routing Problems (VRP), its specificity comes from the amount of data and constraints: in addition to costs, many legal or health considerations must be taken into account. Our approach is based on the development of a multi-objective genetic algorithm, which has to come up with the best itinerary taking all these constraints into account. We will show that a precise definition of the knowledge model with a domain ontology can be used to describe the chromosome, the evaluation functions, the crossover and mutation operators.

Pages: 99 to 105

Copyright: Copyright (c) IARIA, 2015

Publication date: February 22, 2015

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-386-5

Location: Lisbon, Portugal

Dates: from February 22, 2015 to February 27, 2015