Today's business world is very dynamic and organizations have to quickly adjust their internal policies to follow the market changes. Such adjustments must be propagated to the business logic embedded in the organization's information systems, that are often legacy applications not designed to represent and operationalize the business logic independently from the technical aspects of the programming language employed. Consequently, the business logic buried in the system must be discovered and understood before being modified. Unfortunately, such activities slow down the modification of the system to new requirements settled in the organization policies and threaten the consistency and coherency of the organization business. In order to simplify these activities, we provide amodel-based approach to extract and represent the business logic, expressed as a set of business rules, from the behavioral and structural parts of information systems. We implement such approach for Java, COBOL and relational database management systems. The proposed approach is based on Model Driven Engineering,that provides a generic and modular solution adaptable to different languages by offering an abstract and homogeneous representation of the system.

Le monde des affaires d’aujourd’hui est très dynamique, donc les organisations doivent rapidement adapter leurs politiques commerciales afin de suivre les évolutions du marché. Ces ajustements doivent être propagés à la logique métier présente dans les systèmes d’informations des organisations, qui sont souvent des applications héritées non conçues pour représenter et opérationnaliser la logique métier indépendamment des aspects techniques du langage de programmation utilisé. Par conséquent, la logique métier intégrée au sein du système doit être identifiée et comprise avant d’être modifiée. Malheureusement, ces activités ralentissent la mise à jour du système vers de nouvelles exigences établies dans les politiques de l’organisation et menacent la cohérence des activités commerciales de celle-ci. Afin de simplifier ces activités, nous offrons une approche basée sur les modèles pour extraire et représenter la logique métier, exprimée comme un ensemble de règles de gestion, à partir des parties comportementales et structurelles des systèmes d’information. Nous mettons en œuvre cette approche pour les systèmes écrits en Java et COBOL ainsi que pour les systèmes de gestion de bases de données relationnelles. L’approche proposée est basée sur l’Ingénierie Dirigée par les Modèles, qui fournit une solution générique et modulaire adaptable à différents langages en offrant une représentation abstraite et homogène du système. / Today’s business world is very dynamic and organizations have to quickly adjust their internal policies to follow the market changes. Such adjustments must be propagated to the business logic embedded in the organization’s information systems, that are often legacy applications not designed to represent and operationalize the business logic independently from the technical aspects of the programming language employed. Consequently, the business logic buried in the system must be discovered and understood before being modified. Unfortunately, such activities slow down the modification of the system to new requirements settled in the organization policies and threaten the consistency and coherency of the organization business. In order to simplify these activities, we provide amodel-based approach to extract and represent the business logic, expressed as a set of business rules, from the behavioral and structural parts of information systems. We implement such approach for Java, COBOL and relational database management systems. The proposed approach is based on Model Driven Engineering,that provides a generic and modular solution adaptable to different languages by offering an abstract and homogeneous representation of the system.

[pt] Este trabalho tem como principal objetivo propor e desenvolver uma metodologia baseada em modelos fuzzy para a segmentação e caracterização dos segmentos que compõem o mercado bancário, permitindo um amplo conhecimento dos perfis de clientes, melhor adaptação das ofertas ao mercado e, conseqüentemente, melhores retornos financeiros. A metodologia proposta nesta dissertação pode ser dividida em três módulos principais: coleta e tratamento dos dados; definição dos segmentos; e caracterização e classificação dos segmentos. O primeiro módulo, denominado coleta e tratamento dos dados, abrange as pesquisas de marketing utilizadas na coleta dos dados e a aplicação de técnicas de pré-processamento de dados, para a limpeza (remoção de outliers e missing values) e normalização dos dados. O módulo de definição dos segmentos emprega o modelo fuzzy de agrupamento Fuzzy C-Means (FCM) na descoberta de grupos de clientes que apresentem características semelhantes. A escolha deste modelo de agrupamento deve-se à possibilidade de análise dos graus de pertinência de cada cliente em relação aos diferentes grupos, identificando os clientes entre segmentos e, conseqüentemente, elaborando ações efetivas para a sua transição ou manutenção nos segmentos de interesse. O módulo de caracterização e classificação dos segmentos é baseado em um Sistema de Inferência Fuzzy. Na primeira etapa deste módulo são selecionadas as variáveis mais relevantes, do ponto de vista da informação, para sua aplicação no processo de extração de regras. As regras extraídas para a caracterização dos segmentos são posteriormente utilizadas na construção de um sistema de inferência fuzzy dedicado à classificação de novos clientes. Este sistema permite que os analistas de marketing contribuam com novas regras ou modifiquem as já extraídas, tornando o modelo mais robusto e a segmentação de mercado uma ferramenta acessível a todos que dela se servem. A metodologia foi aplicada na segmentação de mercado do Banco da Amazônia, um banco estatal que atua na Amazônia Legal, cujo foco prioritário constitui o fomento da região. Avaliando a aplicação dos modelos fuzzy no estudo de caso, observam-se bons resultados na definição dos segmentos, com médias de valor de silhueta de 0,7, e na classificação da base de clientes, com acurácia de 100%. Adicionalmente, o uso destes modelos na segmentação de mercado possibilitou a análise dos clientes que estão entre segmentos e a caracterização desses segmentos por meio de uma base de regras, ampliando as análises dos analistas de marketing. / [en] The main aim of this work is to propose and develop a methodology base don fuzzy models for segmentation and characterization of segments comprising the bank segment, allowing broad knowledge of client profiles, better suiting market needs, hence offering better financial results. The methodology proposed in this work may be divided into three main modules: data collection and treatment; definition of segments; and characterization and classification of segments. The first module, denominated data collection and treatment, encompasses marketing research used in data collection and application of techniques for pre-processing of data, for data trimming (removal of outliers and missing values) and normalization. The definition of segments adopts the Fuzzy C-Means (FCM) grouping model in identifying groups of clients with similar characteristics. The choice for this grouping model is due to the possibility of analyzing the membership coefficient of each client in connection with the different groups, thus identifying clients among segments and consequently elaborating effective actions for their transition to or maintenance in the segments of interest. The module of characterization and classification of segments is based on a Fuzzy Inference System. In the first stage, the most relevant variables from the information standpoint are selected, for application in the process of rule extraction. The rules extracted are then used in the construction of a fuzzy inference system dedicated to classifying new clients. This system allows marketing analysts to contribute with new rules or modify those already extracted, making the model more robust and the turning market segmentation into a tool accessible to all using it. This methodology was applied in the market segmentation of Banco da Amazônia, stte- contrlled bank acting in the Amazon region, with main focus of which is fostering the region´s development. The application of fuzzy models in the case study generated good results in the definition of segments, with average silhouette value of 0.7, and accuracy of 100% for client base classification. Furthermore, the use of these models in market segmentation allowed the analysis of clients classified between segments and the characterization of those segments by means of a set of rules, improving the analyses made by marketing analysts.

Deux aspects importants de la connaissance qu'un individu a pu acquérir par ses expériences correspondent à la mémoire sémantique (celle des connaissances explicites, comme par exemple l'apprentissage de concepts et de catégories décrivant les objets du monde) et la mémoire procédurale (connaissances relatives à l'apprentissage de règles ou de la syntaxe). Cette "mémoire syntaxique" se construit à partir de l'expérience et notamment de l'observation de séquences, suites d'objets dont l'organisation séquentielle obéit à des règles syntaxiques. Elle doit pouvoir être utilisée ultérieurement pour générer des séquences valides, c'est-à-dire respectant ces règles. Cette production de séquences valides peut se faire de façon explicite, c'est-à-dire en évoquant les règles sous-jacentes, ou de façon implicite, quand l'apprentissage a permis de capturer le principe d'organisation des séquences sans recours explicite aux règles. Bien que plus rapide, plus robuste et moins couteux en termes de charge cognitive que le raisonnement explicite, le processus implicite a pour inconvénient de ne pas donner accès aux règles et de ce fait, de devenir moins flexible et moins explicable. Ces mécanismes mnésiques s'appliquent aussi à l'expertise métier : la capitalisation des connaissances pour toute entreprise est un enjeu majeur et concerne aussi bien celles explicites que celles implicites. Au début, l'expert réalise un choix pour suivre explicitement les règles du métier. Mais ensuite, à force de répétition, le choix se fait automatiquement, sans évocation explicite des règles sous-jacentes. Ce changement d'encodage des règles chez un individu en général et particulièrement chez un expert métier peut se révéler problématique lorsqu'il faut expliquer ou transmettre ses connaissances. Si les concepts métiers peuvent être formalisés, il en va en général de tout autre façon pour l'expertise. Dans nos travaux, nous avons souhaité nous pencher sur les séquences de composants électriques et notamment la problématique d’extraction des règles cachées dans ces séquences, aspect important de l’extraction de l’expertise métier à partir des schémas techniques. Nous nous plaçons dans le domaine connexionniste, et nous avons en particulier considéré des modèles neuronaux capables de traiter des séquences. Nous avons implémenté deux réseaux de neurones récurrents : le modèle de Elman et un modèle doté d’unités LSTM (Long Short Term Memory). Nous avons évalué ces deux modèles sur différentes grammaires artificielles (grammaire de Reber et ses variations) au niveau de l’apprentissage, de leurs capacités de généralisation de celui-ci et leur gestion de dépendances séquentielles. Finalement, nous avons aussi montré qu’il était possible d’extraire les règles encodées (issues des séquences) dans le réseau récurrent doté de LSTM, sous la forme d’automate. Le domaine électrique est particulièrement pertinent pour cette problématique car il est plus contraint avec une combinatoire plus réduite que la planification de tâches dans des cas plus généraux comme la navigation par exemple, qui pourrait constituer une perspective de ce travail. / There are two important aspects of the knowledge that an individual acquires through experience. One corresponds to the semantic memory (explicit knowledge, such as the learning of concepts and categories describing the objects of the world) and the other, the procedural or syntactic memory (knowledge relating to the learning of rules or syntax). This "syntactic memory" is built from experience and particularly from the observation of sequences of objects whose organization obeys syntactic rules.It must have the capability to aid recognizing as well as generating valid sequences in the future, i.e., sequences respecting the learnt rules. This production of valid sequences can be done either in an explicit way, that is, by evoking the underlying rules, or implicitly, when the learning phase has made it possible to capture the principle of organization of the sequences without explicit recourse to the rules. Although the latter is faster, more robust and less expensive in terms of cognitive load as compared to explicit reasoning, the implicit process has the disadvantage of not giving access to the rules and thus becoming less flexible and less explicable. These mnemonic mechanisms can also be applied to business expertise. The capitalization of information and knowledge in general, for any company is a major issue and concerns both the explicit and implicit knowledge. At first, the expert makes a choice to explicitly follow the rules of the trade. But then, by dint of repetition, the choice is made automatically, without explicit evocation of the underlying rules. This change in encoding rules in an individual in general and particularly in a business expert can be problematic when it is necessary to explain or transmit his or her knowledge. Indeed, if the business concepts can be formalized, it is usually in any other way for the expertise which is more difficult to extract and transmit.In our work, we endeavor to observe sequences of electrical components and in particular the problem of extracting rules hidden in these sequences, which are an important aspect of the extraction of business expertise from technical drawings. We place ourselves in the connectionist domain, and we have particularly considered neuronal models capable of processing sequences. We implemented two recurrent neural networks: the Elman model and a model with LSTM (Long Short Term Memory) units. We have evaluated these two models on different artificial grammars (Reber's grammar and its variations) in terms of learning, their generalization abilities and their management of sequential dependencies. Finally, we have also shown that it is possible to extract the encoded rules (from the sequences) in the recurrent network with LSTM units, in the form of an automaton. The electrical domain is particularly relevant for this problem. It is more constrained with a limited combinatorics than the planning of tasks in general cases like navigation for example, which could constitute a perspective of this work.

Face à la complexité significative du domaine mammographique ainsi que l'évolution massive de ses données, le besoin de contextualiser les connaissances au sein d'une modélisation formelle et exhaustive devient de plus en plus impératif pour les experts. C'est dans ce cadre que s'inscrivent nos travaux de recherche qui s'intéressent à unifier différentes sources de connaissances liées au domaine au sein d'une modélisation ontologique cible. D'une part, plusieurs modélisations ontologiques mammographiques ont été proposées dans la littérature, où chaque ressource présente une perspective distincte du domaine d'intérêt. D'autre part, l'implémentation des systèmes d'acquisition des mammographies rend disponible un grand volume d'informations issues des faits passés, dont la réutilisation devient un enjeu majeur. Toutefois, ces fragments de connaissances, présentant de différentes évidences utiles à la compréhension de domaine, ne sont pas interopérables et nécessitent des méthodologies de gestion de connaissances afin de les unifier. C'est dans ce cadre que se situe notre travail de thèse qui s'intéresse à l'enrichissement d'une ontologie de domaine existante à travers l'extraction et la gestion de nouvelles connaissances (concepts et relations) provenant de deux courants scientifiques à savoir: des ressources ontologiques et des bases de données comportant des expériences passées. Notre approche présente un processus de couplage entre l'enrichissement conceptuel et l'enrichissement relationnel d'une ontologie mammographique existante. Le premier volet comporte trois étapes. La première étape dite de pré-alignement d'ontologies consiste à construire pour chaque ontologie en entrée une hiérarchie des clusters conceptuels flous. Le but étant de réduire l'étape d'alignement de deux ontologies entières en un alignement de deux groupements de concepts de tailles réduits. La deuxième étape consiste à aligner les deux structures des clusters relatives aux ontologies cible et source. Les alignements validés permettent d'enrichir l'ontologie de référence par de nouveaux concepts permettant d'augmenter le niveau de granularité de la base de connaissances. Le deuxième processus s'intéresse à l'enrichissement relationnel de l'ontologie mammographique cible par des relations déduites de la base de données de domaine. Cette dernière comporte des données textuelles des mammographies recueillies dans les services de radiologies. Ce volet comporte ces étapes : i) Le prétraitement des données textuelles ii) l'application de techniques relatives à la fouille de données (ou extraction de connaissances) afin d'extraire des expériences de nouvelles associations sous la forme de règles, iii) Le post-traitement des règles générées. Cette dernière consiste à filtrer et classer les règles afin de faciliter leur interprétation et validation par l'expert vi) L'enrichissement de l'ontologie par de nouvelles associations entre les concepts. Cette approche a été mise en 'uvre et validée sur des ontologies mammographiques réelles et des données des patients fournies par les hôpitaux Taher Sfar et Ben Arous. / Facing the significant complexity of the mammography area and the massive changes in its data, the need to contextualize knowledge in a formal and comprehensive modeling is becoming increasingly urgent for experts. It is within this framework that our thesis work focuses on unifying different sources of knowledge related to the domain within a target ontological modeling. On the one hand, there is, nowadays, several mammographic ontological modeling, where each resource has a distinct perspective area of interest. On the other hand, the implementation of mammography acquisition systems makes available a large volume of information providing a decisive competitive knowledge. However, these fragments of knowledge are not interoperable and they require knowledge management methodologies for being comprehensive. In this context, we are interested on the enrichment of an existing domain ontology through the extraction and the management of new knowledge (concepts and relations) derived from two scientific currents: ontological resources and databases holding with past experiences. Our approach integrates two knowledge mining levels: The first module is the conceptual target mammographic ontology enrichment with new concepts extracting from source ontologies. This step includes three main stages: First, the stage of pre-alignment. The latter consists on building for each input ontology a hierarchy of fuzzy conceptual clusters. The goal is to reduce the alignment task from two full ontologies to two reduced conceptual clusters. The second stage consists on aligning the two hierarchical structures of both source and target ontologies. Thirdly, the validated alignments are used to enrich the reference ontology with new concepts in order to increase the granularity of the knowledge base. The second level of management is interested in the target mammographic ontology relational enrichment by novel relations deducted from domain database. The latter includes medical records of mammograms collected from radiology services. This section includes four main steps: i) the preprocessing of textual data ii) the application of techniques for data mining (or knowledge extraction) to extract new associations from past experience in the form of rules, iii) the post-processing of the generated rules. The latter is to filter and classify the rules in order to facilitate their interpretation and validation by expert, vi) The enrichment of the ontology by new associations between concepts. This approach has been implemented and validated on real mammographic ontologies and patient data provided by Taher Sfar and Ben Arous hospitals. The research work presented in this manuscript relates to knowledge using and merging from heterogeneous sources in order to improve the knowledge management process.