This paper presents the study of Parallel Multiobjective Evolutionary Algorithms to enable the automation of exterior lighting designs by computers and results in an optimized version of the algorithm. The resulting algorithm basically works with variable length chromosomes and for which intrinsic operators of crossover and mutation were created. The fitness function was determined through a statistical evaluation method (difference of means), thus enabling the comparison of how different options of fitness functions could impact the performance of the proposed parallel multi-objective evolutionary algorithm. The chosen fitness function enables to develop more efficiently automated designs for exterior lighting. Moreover, adding to the proposed evolutionary algorithm, an application was developed in which the user chooses which the heights of the poles, lamps and fixtures to use and also the layout of the area to be illuminated (allowed to be irregular). Within this area, can be defined sub-areas where there are restrictions on the placement of lighting poles. The user must be set average illumination with a respective tolerance range, though. As a case study, the area of an airport parking lot in the city of Uberlândia-MG (Brazil) is presented. Evolved designs present a low coefficient of variation evaluated for 30 runs. This demonstrates that the system is converging on designs for similar metrics. By identifying the worst and the best of designs achieved by the system for those executions, one could note that there are savings regarding installed capacity when compared to the design of reference: 37.5 % for the worst evolved design and 50.0 % for the best evolved design. Also, evolved designs have better lighting uniformity and energy efficiency, as well as their respective quantities of lighting poles have decreased. / Este trabalho apresenta o estudo de um Algoritmo Evolucionário Multiobjetivo Paralelo que viabiliza a criação de projetos de iluminação de áreas externas automatizadas por computador e que resulta em uma versão otimizada desse algoritmo. O algoritmo resultante, essencialmente, trabalha com cromossomos de tamanho variável e para os quais foram criados operadores intrínsecos de cruzamento e mutação. A determinação da função de aptidão ocorreu por meio do método de avaliação estatística (diferença de médias), possibilitando, assim, a comparação de diferentes opções das funções de aptidão no desempenho do algoritmo evolucionário multiobjetivo paralelo proposto. Com a função escolhida, tornou-se possível construir projetos automatizados de iluminação externa de forma mais eficiente. Além disso, por meio do algoritmo evolucionário proposto, foi desenvolvida uma aplicação, pela qual o usuário escolhe quais as alturas dos postes, lâmpadas e luminárias que deseja utilizar e também o layout de área a ser iluminada (mesmo que irregular). Dentro dessa área, podem ser definidas subáreas onde existem restrições quanto à colocação de postes de iluminação. O usuário deve definir a iluminação média associada à sua respectiva tolerância, ou faixa de variação. Como estudo de caso, é apresentada a área de um estacionamento do aeroporto da cidade de Uberlândia, MG. Os projetos desenvolvidos, apresentam um baixo coeficiente de variação calculado a partir de 30 execuções. Isso demonstra que o sistema está convergindo para projetos com métricas similares. Ao identificar o pior e o melhor dos projetos apresentados como solução pelo sistema para essas execuções, pode-se notar que apresentam economia nas potências instaladas quando comparados ao projeto de referência: 37,5% no pior dos projetos e 50% no melhor projeto apresentado. Além disso, constataram-se melhores uniformidades para iluminação e maiores eficiências energéticas, bem como a diminuição das respectivas quantidades de unidades de iluminação. / Doutor em Ciências

Em redes de computadores, para garantir que seja obtido um nível adequado de comunicação fim-a-fim, é importante garantir um roteamento com Qualidade de Serviço (QoS). O problema de roteamento com QoS envolve múltiplos objetivos a serem otimizados ou atendidos simultaneamente. Quando esse roteamento é do tipo multicast, que envolve vários destinatários, a complexidade do problema é ainda maior. Trabalhos anteriores investigam o uso de Algoritmos Evolutivos Multiobjetivos (AEMO) no problema de roteamento multicast com QoS. É sabido que quanto maior é o número de objetivos a serem otimizados, mais complexo se torna o problema multiobjetivo e mais difícil se torna a convergência de AEMOs tradicionais. Por isso, é proposto o uso de um método evolutivo many objective: o AEMMT (Algoritmo Evolutivo Multiobjetivo com Muitas Tabelas). O AEMMT foi especialmente desenvolvido para problemas com um número maior de objetivos e espera-se que ele se comporte mais adequadamente com o aumento do número de objetivos no roteamento multicast com QoS. Com o intuito de forti car a convergência este trabalho propõe um novo many objective baseado nas estratégias do AEMMT, nomeado AEMMD. / In computer networks, to ensure that an adequate level of communication end-to-end is achieved, it is important to ensure a routing with quality of service (QoS). The routing problem with QoS involves multiple objectives to be optimized or serviced simultaneously. When this multicast routing is the kind which involves multiple recipients, the complexity of the problem is even greater. Previous studies investigating the use of evolutionary algorithms Multiobjetivos (AEMO) in multicast routing problem with QoS. It is known that the greater the number of objects to be optimized, the more complex becomes the multiobjective and more difficult problem becomes convergence AEMOs Traditional. Therefore, the use of an evolutionary method many objective is proposed: the AEMMT (Evolutionary Algorithm with Multiobjective Many tables). The AEMMT was specially developed for problems with a large number of objectives and expected it to behave more appropriately with the increasing number of objectives in the multicast routing with QoS. In order to strengthen the convergence this paper proposes a new many objective based on the strategies of AEMMT appointed AEMMD. / Dissertação (Mestrado)

Avec l’avènement du traitement distribué et l’utilisation accrue des services web inter et intra organisationnels alimentée par la disponibilité des connexions réseaux à faibles coûts, les données multisources partagées ont de plus en plus envahi les systèmes d’informations. Ceci a induit, dans un premier temps, le changement de leurs architectures du centralisé au distribué en passant par le coopératif et le fédéré ; et dans un deuxième temps, une panoplie de problèmes d’exploitation allant du traitement des incohérences des données doubles à la synchronisation des données distribuées. C’est le cas des bases de prospection marketing où les données sont enrichies par des fichiers provenant de différents fournisseurs.Nous nous intéressons au cadre particulier de construction de fichiers de prospection pour la réalisation de campagnes marketing B-to-B, tâche traitée manuellement par les experts métier. Nous visons alors à modéliser le raisonnement de brokers humains, afin d’optimiser et d’automatiser la sélection du « plan fichier » à partir d’un ensemble de données d’enrichissement multisources. L’optimisation en question s’exprimera en termes de gain (coût, qualité) des données sélectionnées, le coût se limitant à l’unique considération du prix d’utilisation de ces données.Ce mémoire présente une triple contribution quant à la gestion des bases de données multisources. La première contribution concerne l’évaluation rigoureuse de la qualité des données multisources. La deuxième contribution porte sur la modélisation et l’agrégation préférentielle des critères d’évaluation qualité par l’intégrale de Choquet. La troisième contribution concerne BrokerACO, un prototype d’automatisation et d’optimisation du brokering multisources basé sur l’algorithme heuristique d’optimisation par les colonies de fourmis (ACO) et dont la Pareto-optimalité de la solution est assurée par l’utilisation de la fonction d’agrégation des préférences des utilisateurs définie dans la deuxième contribution. L’efficacité du prototype est montrée par l’analyse de campagnes marketing tests effectuées sur des données réelles de prospection. / In Business-to-Business (B-to-B) marketing campaigns, manufacturing “the highest volume of sales at the lowest cost” and achieving the best return on investment (ROI) score is a significant challenge. ROI performance depends on a set of subjective and objective factors such as dialogue strategy, invested budget, marketing technology and organisation, and above all data and, particularly, data quality. However, data issues in marketing databases are overwhelming, leading to insufficient target knowledge that handicaps B-to-B salespersons when interacting with prospects. B-to-B prospection data is indeed mainly structured through a set of independent, heterogeneous, separate and sometimes overlapping files that form a messy multisource prospect selection environment. Data quality thus appears as a crucial issue when dealing with prospection databases. Moreover, beyond data quality, the ROI metric mainly depends on campaigns costs. Given the vagueness of (direct and indirect) cost definition, we limit our focus to price considerations.Price and quality thus define the fundamental constraints data marketers consider when designing a marketing campaign file, as they typically look for the "best-qualified selection at the lowest price". However, this goal is not always reachable and compromises often have to be defined. Compromise must first be modelled and formalized, and then deployed for multisource selection issues. In this thesis, we propose a preference-driven selection approach for multisource environments that aims at: 1) modelling and quantifying decision makers’ preferences, and 2) defining and optimizing a selection routine based on these preferences. Concretely, we first deal with the data marketer’s quality preference modelling by appraising multisource data using robust evaluation criteria (quality dimensions) that are rigorously summarized into a global quality score. Based on this global quality score and data price, we exploit in a second step a preference-based selection algorithm to return "the best qualified records bearing the lowest possible price". An optimisation algorithm, BrokerACO, is finally run to generate the best selection result.

Land use changes have become a major contributor to the anthropogenic global change. The ongoing dispersion and concentration of the human species, being at their orders unprecedented, have indisputably altered Earth’s surface and atmosphere. The effects are so salient and irreversible that a new geological epoch, following the interglacial Holocene, has been announced: the Anthropocene. While its onset is by some scholars dated back to the Neolithic revolution, it is commonly referred to the late 18th century. The rapid development since the industrial revolution and its implications gave rise to an increasing awareness of the extensive anthropogenic land change and led to an urgent need for sustainable strategies for land use and land management. By preserving of landscape and settlement patterns at discrete points in time, archival geospatial data sources such as remote sensing imagery and historical geotopographic maps, in particular, could give evidence of the dynamic land use change during this crucial period. In this context, this thesis set out to explore the potentials of retrospective geoinformation for monitoring, communicating, modeling and eventually understanding the complex and gradually evolving processes of land cover and land use change. Currently, large amounts of geospatial data sources such as archival maps are being worldwide made online accessible by libraries and national mapping agencies. Despite their abundance and relevance, the usage of historical land use and land cover information in research is still often hindered by the laborious visual interpretation, limiting the temporal and spatial coverage of studies. Thus, the core of the thesis is dedicated to the computational acquisition of geoinformation from archival map sources by means of digital image analysis. Based on a comprehensive review of literature as well as the data and proposed algorithms, two major challenges for long-term retrospective information acquisition and change detection were identified: first, the diversity of geographical entity representations over space and time, and second, the uncertainty inherent to both the data source itself and its utilization for land change detection. To address the former challenge, image segmentation is considered a global non-linear optimization problem. The segmentation methods and parameters are adjusted using a metaheuristic, evolutionary approach. For preserving adaptability in high level image analysis, a hybrid model- and data-driven strategy, combining a knowledge-based and a neural net classifier, is recommended. To address the second challenge, a probabilistic object- and field-based change detection approach for modeling the positional, thematic, and temporal uncertainty adherent to both data and processing, is developed. Experimental results indicate the suitability of the methodology in support of land change monitoring. In conclusion, potentials of application and directions for further research are given.

Le but de ce doctorat est de déterminer dans quelle mesure les algorithmes issus de l’intelligence artificielle, principalement les Algorithmes Evolutionnaires et la Programmation Génétique, pourraient aider les algorithmes de l’automatique classique afin de permettre aux engins autonomes de disposer de capacités bien supérieures, et ce dans les domaines de l’identification, de la planification de trajectoire, du pilotage et de la navigation.De nouveaux algorithmes ont été développés, dans les domaines de l’identification, de la planification de trajectoire, de la navigation et du contrôle, et ont été testés sur des systèmes de simulation et des aéronefs du monde réel (Oktokopter du ST2I, Bebop.Drone de la société Parrot, Twin Otter et F-16 de la NASA) de manière à évaluer les apports de ces nouvelles approches par rapport à l’état de l’art.La plupart de ces nouvelles approches ont permis d’obtenir de très bons résultats comparés à l’état de l’art, notamment dans le domaine de l’identification et de la commande, et un approfondissement des travaux devraient être engagé afin de développer le potentiel applicatifs de certains algorithmes. / The object of this PhD has consisted in elaborating evolutionary computing algorithms to find interesting solutions to important problems in several domains of automation science, applied to aircrafts mission conduction and to understand what could be the advantages of using such approaches, compared to the state-of-the-art, in terms of efficiency, robustness, and effort of implementation.New algorithms have been developed, in Identification, Path planning, Navigation and Control and have been tested on simulation and on real world platforms (AR.Drone 3.0 UAV (Parrot), Oktokopter UAV, Twin Otter and military fighter F-16 (NASA LaRC)), to assess the performances improvements, given by the new proposed approaches.Most of these new approaches provide very interesting results; and research work (on control by evolutionary algorithms, identification by genetic programming and relative navigation) should be engaged to plan potential applications in different real world technologies.

La variété des concepts d’aéronef à voilure tournante n’a d’égal que l’étendue de leur champ applicatif. Une question essentielle se pose alors : quel concept est le plus adapté face à un certain nombre de missions et de spécifications ? Pour y répondre il faut pouvoir évaluer les performances de vol et les impacts environnementaux de ces appareils. Le projet de recherche fédérateur C.R.E.A.T.I.O.N. pour « Concepts of Rotorcraft Enhanced Assessment Through Integrated Optimization Network » a pour but de mettre en place une plateforme numérique de calculs multidisciplinaires et multiniveaux de modélisation capable d’évaluer de tels critères. La multidisciplinarité fait écho aux différentes disciplines associées à l’évaluation des giravions tandis que l’aspect multi-niveaux de modélisation reflète la possibilité d’étudier un concept quelque soit l’état des connaissances sur ce dernier. La thèse s’inscrit dans ce projet. Une première implication est le développement de modèles de performances de vol et leur intégration dans des boucles de calculs multidisciplinaires. Au-delà de cet aspect de modélisation physique, la multidisciplinarité touche aussi le champ des mathématiques appliquées. Les méthodes d’optimisation multi objectifs multi paramètres, l’aide à la décision pour la sélection d’un optimum de meilleur compromis, l’exploration de bases de données, la création de modèles réduits sont autant de thématiques explorées dans cette thèse. / On the one hand the diversity of rotorcraft concepts is very rich, on the other hand the extent of their applications is very wide. Then a key question is raising: What is the most suitable concept facing a number of missions and specifications ? For answering, models and methods are required for predicting and evaluating the flight performances and environmental impact of rotorcraft. The project «Concepts of Rotorcraft Enhanced Assessment Through Integrated Optimization Network» (C.R.E.A.T.I.O.N.) aims at developing a multi-disciplinary and multi-level modelling calculation chain. The multi-disciplinary feature comes from the involvement of different disciplines in rotorcraft design. The multi modelling levels are defined to allow the evaluation of any rotorcraft concept whatever the level of details available in the description data. The present thesis is part of this project. First steps are the implementation of statistical models able to initialize the rotorcraft presizing from some specifications, the development of an analytical code that evaluates flight performances and its integration into the multidisciplinary calculation chain. A preliminary design conception chain using multidisciplinary optimization is setup and applied to a practical case showing its efficiency as presizing methodology. For this purpose multi-objectives exploration algorithms and decision aid methods to select a best compromise solution are also studied. The exploration of databases and creating response surface models are other themes explored in this thesis.

Artificial neural networks (ANNs) and logic programs have both been suggested as means of modelling human cognition. While ANNs are adaptable and relatively noise resistant, the information they represent is distributed across various neurons and is therefore difficult to interpret. On the contrary, symbolic systems such as logic programs are interpretable but less adaptable. Human cognition is performed in a network of biological neurons and yet is capable of representing symbols, and therefore an ideal model would combine the strengths of the two approaches. This is the goal of Neural-Symbolic Integration [4, 16, 21, 40], in which ANNs are used to produce interpretable, adaptable representations of logic programs and other symbolic models. One neural-symbolic model of reasoning is SHRUTI [89, 95], argued to exhibit biological plausibility in that it captures some aspects of real biological processes. SHRUTI's original developers also suggest that further biological plausibility can be ascribed to the fact that SHRUTI networks can be represented by a model of genetic development [96, 120]. The aims of this thesis are to support the claims of SHRUTI's developers by producing the first such genetic representation for SHRUTI networks and to explore biological plausibility further by investigating the evolvability of the proposed SHRUTI genome. The SHRUTI genome is developed and evolved using principles from Generative and Developmental Systems and Artificial Development [13, 105], in which genomes use indirect encoding to provide a set of instructions for the gradual development of the phenotype just as DNA does for biological organisms. This thesis presents genomes that develop SHRUTI representations of logical relations and episodic facts so that they are able to correctly answer questions on the knowledge they represent. The evolvability of the SHRUTI genomes is limited in that an evolutionary search was able to discover genomes for simple relational structures that did not include conjunction, but could not discover structures that enabled conjunctive relations or episodic facts to be learned. Experiments were performed to understand the SHRUTI fitness landscape and demonstrated that this landscape is unsuitable for navigation using an evolutionary search. Complex SHRUTI structures require that necessary substructures must be discovered in unison and not individually in order to yield a positive change in objective fitness that informs the evolutionary search of their discovery. The requirement for multiple substructures to be in place before fitness can be improved is probably owed to the localist representation of concepts and relations in SHRUTI. Therefore this thesis concludes by making a case for switching to more distributed representations as a possible means of improving evolvability in the future.

Spotřeba a energetická efektivita se stává jedním z nejdůležitějších parametrů při návrhu počítačových systémů, zejména kvůli omezené kapacitě napájení u zařízení napájených bateriemi a velmi vysoké spotřebě energie rostoucích datacenter a cloudové infrastruktury. Současně jsou uživatelé ochotni do určité míry tolerovat nepřesné nebo chybné výpočty v roustoucím počtu aplikací díky nedokonalostem lidských smyslů, statistické povaze výpočtů, šumu ve vstupních datech apod. Přibližné počítání, nová oblast výzkumu v počítačovém inženýrství, využívá rozvolnění požadavků na funkčnost za účelem zvýšení efektivity počítačových systémů, pokud jde o spotřebu energie, výpočetní výkon či složitost. Aplikace tolerující chyby mohou být implementovány efektivněji a stále sloužit svému účelu se stejnou nebo mírně sníženou kvalitou. Ačkoli se objevují nové metody pro návrh přibližně počítajících výpočetních systémů, je stále nedostatek automatických návrhových metod, které by nabízely velké množství kompromisních řešení dané úlohy. Konvenční metody navíc často produkují řešení, která jsou daleko od optima. Evoluční algoritmy sice přinášejí inovativní řešení složitých optimalizačních a návrhových problémů, nicméně trpí několika nedostatky, např. nízkou škálovatelností či vysokým počtem generací nutných k dosažení konkurenceschopných výsledků. Pro přibližné počítání je vhodný zejména multikriteriální návrh, což existující metody většinou nepodporují. V této práci je představen nový automatický multikriteriální paralelní evoluční algoritmus pro návrh a aproximaci digitálních obvodů. Metoda je založena na kartézském genetickém programování, pro zvýšení škálovatelnosti byla navržena nová vysoce paralelizovaná implementace. Multikriteriální návrh byl založen na principech algoritmu NSGA-II. Výkonnost implementace byla vyhodnocena na několika různých úlohách, konkrétně při návrhu (přibližně počítajících) aritmetických obvodů, Booleovských funkcích s vysokou nelinearitou či přibližných logických obvodů pro tří-modulovou redundanci. V těchto úlohách bylo dosaženo význammých zlepšení ve srovnání se současnými metodami.

The thesis studies selected evolution systems to use in planning of high intensity focused ultrasound surgeries. Considered algorithms are statistically analyzed and compared by appropriate criteria to find the one that adds the most value to the potential real world medical problems.

Tato dizertační práce pojednává o více-kriteriálních optimalizačních algoritmech s proměnným počtem dimenzí. Takový algoritmus umožňuje řešit optimalizační úlohy, které jsou jinak řešitelné jen s použitím nepřirozených zjednodušení. Výzkum optimalizačních method s proměnnou dimenzí si vyžádal vytvoření nového optimalizačního frameworku, který obsahuje vedle zmíněných vícekriteriálních metod s proměnnou dimenzí – VND-GDE3 a VND-MOPSO – i další optimalizační metody různých tříd. Optimalizační framework obsahuje také knihovnu rozličných testovacích problémů. Mezi nimi je také sada více-kriteriálních testovacích problémů s proměnnou dimenzí, které byly navrženy pro nastavení a ověření nových metod s proměnnou dimenzí. Nové metody jsou dále použity k optimalizaci několika různorodých optimalizačních úloh z reálného světa.