- author = "Christian Gagne",
- title = "Algorithmes evolutionnaires appliques a la reconnaissance des formes et a la conception optique",
- school = "Laval University",
- year = "2005",
- address = "Quebec (QC), Canada",
- month = may,
- keywords = "genetic algorithms, genetic programming",
-
URL = "
http://vision.gel.ulaval.ca/en/publications/Id_528/PublDetails.php",
-
URL = "
http://vision.gel.ulaval.ca/~cgagne/pubs/these-cgagne.pdf",
-
URL = "http://www.theses.ulaval.ca/2005/22701/22701.pdf",
- size = "212 pages",
-
abstract = "Evolutionary Algorithms (EA) encompass a family of
robust search algorithms loosely inspired by natural
evolution. These algorithms are particularly useful to
solve problems for which classical algorithms of
optimisation, learning, or automatic design cannot
produce good results. In this thesis, we propose a
common methodological approach for the development of
EA-based intelligent systems. This methodological
approach is based on five principles: 1) to use
algorithms and representations that are problem
specific; 2) to develop hybrids between EA and
heuristics from the application field; 3) to take
advantage of multi-objective evolutionary optimization;
4) to do co-evolution for the simultaneous resolution
of several sub-problems of a common application and for
promoting robustness; and 5) to use generic software
tools for rapid development of unconventional EA. This
methodological approach is illustrated on four
applications of EA to hard problems. Moreover, the
fifth principle is explained in the study on genericity
of EA software tools.
The application of EA to complex problems requires the use of generic software tool, for which we propose six genericity criteria. Many EA software tools are available in the community, but only a few are really generic. Indeed, an evaluation of some popular tools tells us that only three respect all these criteria, of which the framework Open BEAGLE, developed during the Ph.D. Open BEAGLE is organised into three main software layers. The basic layer is made of the object oriented foundations, over which there is the generic framework layer, consisting of the general mechanisms of the tool, and then the final layer, containing several specialised frameworks implementing different EA flavours. The tool also includes two extensions, respectively to distribute the computations over many computers and to visualise results.
Three applications illustrate different approaches for using EA in the context of pattern recognition. First, nearest neighbour classifiers are optimised, with the prototype selection using a genetic algorithm simultaneously to the Genetic Programming (GP) of neighbourhood metrics. We add to this cooperative two species co-evolution a third co-evolving competitive species for selecting test data in order to improve the generalisation capability of solutions. A second application consists in designing representations with GP for handwritten character recognition. This evolutionary engineering is conducted with an automatic positioning of regions in a window of attention, combined with the selection of fuzzy sets for feature extraction. This application is used to automate character representation search, which is usually conducted by human experts with a trial and error process. For the third application in pattern recognition, we propose an extensible system for the hierarchical combination of classifiers into a fuzzy decision tree. In this system, the tree topology is evolved with GP while the numerical parameters of classification units are determined by specialized learning techniques. The system is tested with three simple types of classification units. All of these applications in pattern recognition have been implemented using a two-objective fitness measure in order to minimise classification errors and solutions complexity. The last application demonstrate the efficiency of EA for lens system design. Self-adaptative evolution strategies, hybridised with a specialised local optimisation technique, are used to solve two complex optical design problems. In both cases, the experiments demonstrate that hybridized EA are able to produce results that are comparable or better than those obtained by human experts. These results are encouraging from the standpoint of a fully automated optical design process. An additional experiment is also conducted with a two-objectives fitness measure that tries to maximise image quality while minimising lens system cost.",
- bibsource = "OAI-PMH server at oai.collectionscanada.ca",
- contributor = "Marc Parizeau",
- identifier = "TC-QQLA-22701",
- language = "FR",
- oai = "oai:collectionscanada.ca:QQLA.2005/22701",
- rights = "copyright Christian Gagne, 2005",
-
notes = "Cf posting to GP-list Tue, 11 Oct 2005 09:50:18
+0200
Entirely written in French",
- abstract = "Les algorithmes {\'e}volutionnaires (AE) constituent une famille d{'}algorithmes inspir{\'e}s de l{'}{\'e}volution naturelle. Ces algorithmes sont particuli{\`e}rement utiles pour la r{\'e}solution de probl{\`e}mes o{\`u} les algorithmes classiques d{'}optimisation, d{'}apprentissage ou de conception automatique sont incapables de produire des r{\'e}sultats satisfaisants. On propose dans cette th{\`e}se une approche m{\'e}thodologique pour le d{\'e}veloppement de syst{\`e}mes intelligents bas{\'e}s sur les AE. Cette approche m{\'e}thodologique repose sur cinq principes : 1) utiliser des algorithmes et des repr{\'e}sentations adapt{\'e}s au probl{\`e}me ; 2) d{\'e}velopper des hybrides entre des AE et des heuristiques du domaine d{'}application ; 3) tirer profit de l{'}optimisation {\'e}volutionnaire {\`a} plusieurs objectifs ; 4) faire de la co-{\'e}volution pour r{\'e}soudre simultan{\'e}ment plusieurs sous-probl{\`e}mes d{'}une application ou favoriser la robustesse ; et 5) utiliser un outil logiciel g{\'e}n{\'e}rique pour le d{\'e}veloppement rapide d{'}AE non conventionnels. Cette approche m{\'e}thodologique est illustr{\'e}e par quatre applications des AE {\`a} des probl{\`e}mes difficiles. De plus, le cinqui{\`e}me principe est appuy{\'e} par l{'}{\'e}tude sur la g{\'e}n{\'e}ricit{\'e} dans les outils logiciels d{'}AE. Le d{\'e}veloppement d{'}applications complexes avec les AE exige l{'}utilisation d{'}un outil logiciel g{\'e}n{\'e}rique. Six crit{\`e}res sont propos{\'e}s ici pour {\'e}valuer la g{\'e}n{\'e}ricit{\'e} des outils d{'}AE. De nombreux outils logiciels d{'}AE sont disponibles dans la communaut{\'e}, mais peu d{'}entre eux peuvent {\^e}tre v{\'e}ritablement qualifi{\'e}s de g{\'e}n{\'e}riques. En effet, une {\'e}valuation de quelques outils relativement populaires nous indique que seulement trois satisfont pleinement {\`a} tous ces crit{\`e}res, dont la framework d{'}AE Open BEAGLE, d{\'e}velopp{\'e}e durant le doctorat.",
- abstract = "Open BEAGLE est organis{\'e} en trois couches logicielles principales, avec {\`a} la base les fondations orient{\'e}es objet, sur lesquelles s{'}ajoute une framework g{\'e}n {\'e}rique comprenant les m{\'e}canismes g{\'e}n{\'e}raux de l{'}outil, ainsi que plusieurs frameworks sp{\'e}cialis{\'e}es qui implantent diff{\'e}rentes saveurs d{'}AE. L{'}outil comporte {\'e}galement deux extensions servant {\`a} distribuer des calculs sur plusieurs ordinateurs et {\`a} visualiser des r{\'e}sultats. Ensuite, trois applications illustrent diff{\'e}rentes approches d{'}utilisation des AE dans un contexte de reconnaissance des formes. Premi{\`e}rement, on optimise des classifieurs bas{\'e}s sur la r{\`e}gle du plus proche voisin avec la s{\'e}lection de prototypes BibTeX entry too long. Truncated
