A evolução das tecnologias de rede estão impulsionando o avanço da área da computação pervasiva. O projeto ISAM (Infra-estrutura de Suporte às Aplicações Móveis Distribuídas), em desenvolvimento no IIjUFRGS, tem como foco atender as demandas de pesquisa desta área e tem como premissa uma abordagem integrada na concepção do ambiente de desenvolvimento e do ambiente de execução. O EXEHDA (Execution Environrnent for High Distributed Applications) constitui o ambiente de execução do ISAM, sendo responsável pela gerência do processamento das aplicações pervasivas.Esta dissertação propõe um frarnework de escalonamento denominado TiPS concebido como um módulo do EXEHDA. O escopo de pesquisa do TiPS tem como tônica o escalonamento na computação pervasiva e a sua concepção na forma de um framework permite a utilização de diferentes estratégias de escalonamento, através da troca de seus componentes mesmo durante a execução. A modelagem do TiPS considera o uso de inteligência artificial baseada em redes bayesianas na proposição da heurística de escalonamento a ser empregada no seu framework. A utilização de redes bayesianas tem por objetivo o tratamento das incertezas relacionadas à elevada dinamicidade típica do ambiente de computação pervasiva. O TiPS foi implementado em Java, com suas funcionalidades integradas aos outros serviços do EXEHDA. Neste sentido foi desenvolvido para gerenciar o frmnework do TiPS, um módulo para a ferramenta EXEHDA-AMI, utilizada para gerenciar o EXEHDA como um todo. O TiPS foi comparado com outros dois escalonadores, para tanto foi desenvolvida uma aplicação de teste e um módulo de geração sintética de carga para promover a dinamicidade do contexto de execução. Os resultados obtidos com o T'iPS foram promissores e apontam para a viabilidade do emprego de heurísticas de escalonamento que envolvem técnicas de inteligência artificial na computação pervasiva. / The evolution of the network technologies are strengthening the pervasive computing development. The ISAM (Infm-estrutum de Suporte às Aplicações Pervasivas) is under development in the II/UFRGS and has as it's main focus on assisting the research dernands related to this therne, and its approach is to integrate the development environmellt and the execution environment. The EXEHDA (Executioll Environrnent for High Distributed Applications) constitutes the execution environment of ISAM, being responsib1e for the management of the pervasive applications execution. This dissertation proposes a framework for scheduling called TiPS, which was conceived as an EXEHDA module. The research scope of TiPS has as its tonic the scheduling in the pervasive computing environrnent, and its conception as a framework permits the use of different scheduling strategies, by the exchange of its components even during the execution. The TiPS rnodelillg considers the integration of all artificial illtelligence strategy based on bayesian networks, within the scheduling frarnework. The use of bayesiall networks has the objective to handle the uncertainties related to the highly dynamic behavior, which is typical in the pervasive computing. TiPS was irnplemellted in Java and its functionalities were integrated to other EXEHDA services, in this sense it was also developed a management module to the EXEHDA-AMI tool, which is used to manage EXEHDA. TiPS was compared to two other schedulers, for this comparison it was developed a test application and a synthetic load generator to create dynamics of the execution environment. The results obtained by TiPS points to the viability of the use of scheduling heuristics based on artificial intelligence tools in the pervasive computing.

A evolução das tecnologias de rede estão impulsionando o avanço da área da computação pervasiva. O projeto ISAM (Infra-estrutura de Suporte às Aplicações Móveis Distribuídas), em desenvolvimento no IIjUFRGS, tem como foco atender as demandas de pesquisa desta área e tem como premissa uma abordagem integrada na concepção do ambiente de desenvolvimento e do ambiente de execução. O EXEHDA (Execution Environrnent for High Distributed Applications) constitui o ambiente de execução do ISAM, sendo responsável pela gerência do processamento das aplicações pervasivas.Esta dissertação propõe um frarnework de escalonamento denominado TiPS concebido como um módulo do EXEHDA. O escopo de pesquisa do TiPS tem como tônica o escalonamento na computação pervasiva e a sua concepção na forma de um framework permite a utilização de diferentes estratégias de escalonamento, através da troca de seus componentes mesmo durante a execução. A modelagem do TiPS considera o uso de inteligência artificial baseada em redes bayesianas na proposição da heurística de escalonamento a ser empregada no seu framework. A utilização de redes bayesianas tem por objetivo o tratamento das incertezas relacionadas à elevada dinamicidade típica do ambiente de computação pervasiva. O TiPS foi implementado em Java, com suas funcionalidades integradas aos outros serviços do EXEHDA. Neste sentido foi desenvolvido para gerenciar o frmnework do TiPS, um módulo para a ferramenta EXEHDA-AMI, utilizada para gerenciar o EXEHDA como um todo. O TiPS foi comparado com outros dois escalonadores, para tanto foi desenvolvida uma aplicação de teste e um módulo de geração sintética de carga para promover a dinamicidade do contexto de execução. Os resultados obtidos com o T'iPS foram promissores e apontam para a viabilidade do emprego de heurísticas de escalonamento que envolvem técnicas de inteligência artificial na computação pervasiva. / The evolution of the network technologies are strengthening the pervasive computing development. The ISAM (Infm-estrutum de Suporte às Aplicações Pervasivas) is under development in the II/UFRGS and has as it's main focus on assisting the research dernands related to this therne, and its approach is to integrate the development environmellt and the execution environment. The EXEHDA (Executioll Environrnent for High Distributed Applications) constitutes the execution environment of ISAM, being responsib1e for the management of the pervasive applications execution. This dissertation proposes a framework for scheduling called TiPS, which was conceived as an EXEHDA module. The research scope of TiPS has as its tonic the scheduling in the pervasive computing environrnent, and its conception as a framework permits the use of different scheduling strategies, by the exchange of its components even during the execution. The TiPS rnodelillg considers the integration of all artificial illtelligence strategy based on bayesian networks, within the scheduling frarnework. The use of bayesiall networks has the objective to handle the uncertainties related to the highly dynamic behavior, which is typical in the pervasive computing. TiPS was irnplemellted in Java and its functionalities were integrated to other EXEHDA services, in this sense it was also developed a management module to the EXEHDA-AMI tool, which is used to manage EXEHDA. TiPS was compared to two other schedulers, for this comparison it was developed a test application and a synthetic load generator to create dynamics of the execution environment. The results obtained by TiPS points to the viability of the use of scheduling heuristics based on artificial intelligence tools in the pervasive computing.

A evolução das tecnologias de rede estão impulsionando o avanço da área da computação pervasiva. O projeto ISAM (Infra-estrutura de Suporte às Aplicações Móveis Distribuídas), em desenvolvimento no IIjUFRGS, tem como foco atender as demandas de pesquisa desta área e tem como premissa uma abordagem integrada na concepção do ambiente de desenvolvimento e do ambiente de execução. O EXEHDA (Execution Environrnent for High Distributed Applications) constitui o ambiente de execução do ISAM, sendo responsável pela gerência do processamento das aplicações pervasivas.Esta dissertação propõe um frarnework de escalonamento denominado TiPS concebido como um módulo do EXEHDA. O escopo de pesquisa do TiPS tem como tônica o escalonamento na computação pervasiva e a sua concepção na forma de um framework permite a utilização de diferentes estratégias de escalonamento, através da troca de seus componentes mesmo durante a execução. A modelagem do TiPS considera o uso de inteligência artificial baseada em redes bayesianas na proposição da heurística de escalonamento a ser empregada no seu framework. A utilização de redes bayesianas tem por objetivo o tratamento das incertezas relacionadas à elevada dinamicidade típica do ambiente de computação pervasiva. O TiPS foi implementado em Java, com suas funcionalidades integradas aos outros serviços do EXEHDA. Neste sentido foi desenvolvido para gerenciar o frmnework do TiPS, um módulo para a ferramenta EXEHDA-AMI, utilizada para gerenciar o EXEHDA como um todo. O TiPS foi comparado com outros dois escalonadores, para tanto foi desenvolvida uma aplicação de teste e um módulo de geração sintética de carga para promover a dinamicidade do contexto de execução. Os resultados obtidos com o T'iPS foram promissores e apontam para a viabilidade do emprego de heurísticas de escalonamento que envolvem técnicas de inteligência artificial na computação pervasiva. / The evolution of the network technologies are strengthening the pervasive computing development. The ISAM (Infm-estrutum de Suporte às Aplicações Pervasivas) is under development in the II/UFRGS and has as it's main focus on assisting the research dernands related to this therne, and its approach is to integrate the development environmellt and the execution environment. The EXEHDA (Executioll Environrnent for High Distributed Applications) constitutes the execution environment of ISAM, being responsib1e for the management of the pervasive applications execution. This dissertation proposes a framework for scheduling called TiPS, which was conceived as an EXEHDA module. The research scope of TiPS has as its tonic the scheduling in the pervasive computing environrnent, and its conception as a framework permits the use of different scheduling strategies, by the exchange of its components even during the execution. The TiPS rnodelillg considers the integration of all artificial illtelligence strategy based on bayesian networks, within the scheduling frarnework. The use of bayesiall networks has the objective to handle the uncertainties related to the highly dynamic behavior, which is typical in the pervasive computing. TiPS was irnplemellted in Java and its functionalities were integrated to other EXEHDA services, in this sense it was also developed a management module to the EXEHDA-AMI tool, which is used to manage EXEHDA. TiPS was compared to two other schedulers, for this comparison it was developed a test application and a synthetic load generator to create dynamics of the execution environment. The results obtained by TiPS points to the viability of the use of scheduling heuristics based on artificial intelligence tools in the pervasive computing.

While exploring an unknown environment, an intelligent agent has only its sensors to guide its actions. Each sensor's ability to provide accurate information depends on the environment's characteristics. If the agent does not know these characteristics, how can it determine which sensors to rely on? This problem is exacerbated by sensing anomalies: cases where sensor(s) are working but the readings lead to an incorrect interpretation of the environment, e.g. laser sensors cannot detect glass. This work addresses the following research question: Can an inconsistency-based sensing accuracy indicator, which relies solely on fused sensor readings, be used to detect and characterize sensing anomalies in unknown environments? A novel inconsistency-based approach was investigated for sensing anomaly detection and characterization by a mobile robot using range sensing for mapping. Based on the hypothesis that sensing anomalies manifest as inconsistent sensor readings, the approach employed Dempster-Shafer theory and six metrics from the evidential literature to measure the magnitude of inconsistency. These were applied directly to fused sensor data with a threshold, forming an indicator, used to distinguish minor noise from anomalous readings. Experiments with real sensor data from four indoor and two outdoor environments showed that three of the six evidential inconsistency metrics can partially address the issue of noticing sensing anomalies in unknown environments. Polaroid sonar sensors, SICK laser range finders, and a Canesta range camera were used. Despite extensive training in known environments, the indicators could not reliably detect sensing anomalies, i.e. distinguish them from ordinary noise. However, sensing accuracy could be estimated (correlations with sensor error exceeded 0.8) and regions with suspect readings could be isolated. Trained indicators failed to rank sensors, but improved map quality by resetting suspect regions (up to 57.65%) or guiding sensor selection (up to 75.86%). This work contributes to the robotics and uncertainty in artificial intelligence communities by establishing the use of evidential metrics for adapting a single sensor or identifying the most accurate sensor to optimize the sensing accuracy in unknown environments. Future applications could enable intelligent systems to switch information sources to optimize mission performance and identify the reliability of sources for different environments.

The aim of this dissertation is to contribute to research on pay-as-you-go data integration through the proposal of an approach for targeted feedback collection (TFC), which aims to improve the cost-effectiveness of feedback collection, especially when there is uncertainty associated with characteristics of the integration artefacts. In particular, this dissertation focuses on the data source selection task in data integration. It is shown how the impact of uncertainty about the evaluation of the characteristics of the candidate data sources, also known as data criteria, can be reduced, in a cost-effective manner, thereby improving the solutions to the data source selection problem. This dissertation shows how alternative approaches such as active learning and simple heuristics have drawbacks that throw light into the pursuit of better solutions to the problem. This dissertation describes the resulting TFC strategy and reports on its evaluation against alternative techniques. The evaluation scenarios vary from synthetic data sources with a single criterion and reliable feedback to real data sources with multiple criteria and unreliable feedback (such as can be obtained through crowdsourcing). The results confirm that the proposed TFC approach is cost-effective and leads to improved solutions for data source selection by seeking feedback that reduces uncertainty about the data criteria of the candidate data sources.

Nos últimos 30 anos, a área de aprendizagem de máquina desenvolveu-se de forma comparável com a Física no início do século XX. Esse avanço tornou possível a resolução de problemas do mundo real que anteriormente não poderiam ser solucionados por máquinas, devido à dificuldade de modelos puramente estatísticos ajustarem-se de forma satisfatória aos dados de treinamento. Dentre tais avanços, pode-se citar a utilização de técnicas de aprendizagem de máquina na área de Química Medicinal, envolvendo métodos de análise, representação e predição de informação molecular por meio de recursos computacionais. Os dados utilizados no contexto biológico possuem algumas características particulares que podem influenciar no resultado de sua análise. Dentre estas, pode-se citar a complexidade das informações moleculares, o desbalanceamento das classes envolvidas e a existência de dados incompletos ou rotulados de forma incerta. Tais adversidades podem prejudicar o processo de identificação de compostos candidatos a novos fármacos, se não forem tratadas de forma adequada. Neste trabalho, foi abordada uma técnica de aprendizagem de máquina semi-supervisionada capaz de reduzir o impacto causado pelo problema da incerteza na rotulação dos dados, aplicando um método para estimar rótulos mais confiáveis para os compostos químicos existentes no conjunto de treinamento. Na tentativa de evitar os efeitos causados pelo desbalanceamento dos dados, foi incorporada ao processo de estimação de rótulos uma abordagem sensível ao custo, com o objetivo de evitar o viés em benefício da classe majoritária. Após o tratamento do problema da incerteza na rotulação, classificadores baseados em Máquinas de Aprendizado Extremo foram construídos, almejando boa capacidade de aproximação em um tempo de processamento reduzido em relação a outras abordagens de classificação comumente aplicadas. Por fim, o desempenho dos classificadores construídos foi avaliado por meio de análises dos resultados obtidos, confrontando o cenário com os dados originais e outros com as novas rotulações obtidas durante o processo de estimação semi-supervisionado / In the last 30 years, the area of machine learning has developed in a way comparable to Physics in the early twentieth century. This breakthrough has made it possible to solve real-world problems that previously could not be solved by machines because of the difficulty of purely statistical models to fit satisfactorily with training data. Among these advances, one can cite the use of machine learning techniques in the area of Medicinal Chemistry, involving methods for analysing, representing and predicting molecular information through computational resources. The data used in the biological context have some particular characteristics that can influence the result of its analysis. These include the complexity of molecular information, the imbalance of the classes involved, and the existence of incomplete or uncertainly labeled data. If they are not properly treated, such adversities may affect the process of identifying candidate compounds for new drugs. In this work, a semi-supervised machine learning technique was considered to reduce the impact caused by the problem of uncertainty in the data labeling, by applying a method to estimate more reliable labels for the chemical compounds in the training set. In an attempt to reduce the effects caused by data imbalance, a cost-sensitive approach was incorporated to the label estimation process, in order to avoid bias in favor of the majority class. After addressing the uncertainty problem in labeling, classifiers based on Extreme Learning Machines were constructed, aiming for good approximation ability in a reduced processing time in relation to other commonly applied classification approaches. Finally, the performance of the classifiers constructed was evaluated by analyzing the results obtained, comparing the scenario with the original data and others with the new labeling obtained by the semi-supervised estimation process

Nos últimos 30 anos, a área de aprendizagem de máquina desenvolveu-se de forma comparável com a Física no início do século XX. Esse avanço tornou possível a resolução de problemas do mundo real que anteriormente não poderiam ser solucionados por máquinas, devido à dificuldade de modelos puramente estatísticos ajustarem-se de forma satisfatória aos dados de treinamento. Dentre tais avanços, pode-se citar a utilização de técnicas de aprendizagem de máquina na área de Química Medicinal, envolvendo métodos de análise, representação e predição de informação molecular por meio de recursos computacionais. Os dados utilizados no contexto biológico possuem algumas características particulares que podem influenciar no resultado de sua análise. Dentre estas, pode-se citar a complexidade das informações moleculares, o desbalanceamento das classes envolvidas e a existência de dados incompletos ou rotulados de forma incerta. Tais adversidades podem prejudicar o processo de identificação de compostos candidatos a novos fármacos, se não forem tratadas de forma adequada. Neste trabalho, foi abordada uma técnica de aprendizagem de máquina semi-supervisionada capaz de reduzir o impacto causado pelo problema da incerteza na rotulação dos dados, aplicando um método para estimar rótulos mais confiáveis para os compostos químicos existentes no conjunto de treinamento. Na tentativa de evitar os efeitos causados pelo desbalanceamento dos dados, foi incorporada ao processo de estimação de rótulos uma abordagem sensível ao custo, com o objetivo de evitar o viés em benefício da classe majoritária. Após o tratamento do problema da incerteza na rotulação, classificadores baseados em Máquinas de Aprendizado Extremo foram construídos, almejando boa capacidade de aproximação em um tempo de processamento reduzido em relação a outras abordagens de classificação comumente aplicadas. Por fim, o desempenho dos classificadores construídos foi avaliado por meio de análises dos resultados obtidos, confrontando o cenário com os dados originais e outros com as novas rotulações obtidas durante o processo de estimação semi-supervisionado / In the last 30 years, the area of machine learning has developed in a way comparable to Physics in the early twentieth century. This breakthrough has made it possible to solve real-world problems that previously could not be solved by machines because of the difficulty of purely statistical models to fit satisfactorily with training data. Among these advances, one can cite the use of machine learning techniques in the area of Medicinal Chemistry, involving methods for analysing, representing and predicting molecular information through computational resources. The data used in the biological context have some particular characteristics that can influence the result of its analysis. These include the complexity of molecular information, the imbalance of the classes involved, and the existence of incomplete or uncertainly labeled data. If they are not properly treated, such adversities may affect the process of identifying candidate compounds for new drugs. In this work, a semi-supervised machine learning technique was considered to reduce the impact caused by the problem of uncertainty in the data labeling, by applying a method to estimate more reliable labels for the chemical compounds in the training set. In an attempt to reduce the effects caused by data imbalance, a cost-sensitive approach was incorporated to the label estimation process, in order to avoid bias in favor of the majority class. After addressing the uncertainty problem in labeling, classifiers based on Extreme Learning Machines were constructed, aiming for good approximation ability in a reduced processing time in relation to other commonly applied classification approaches. Finally, the performance of the classifiers constructed was evaluated by analyzing the results obtained, comparing the scenario with the original data and others with the new labeling obtained by the semi-supervised estimation process

The heterogeneity of the environments as well as the diversity of patients' needs and profiles are major constraints that challenge the spread of ambient assistive living (AAL) systems. AAL environments are usually evolving by the introduction or the disappearance of sensors, devices and assistive services to respond to the evolution of patients' conditions and human needs. Therefore, a generic framework that is able to adapt to such dynamic environments and to integrate new sensors, devices and assistive services at runtime is required. Implementing such a dynamic aspect may produce an uncertainty derived from technical problems related to sensors reliability or network problems. Therefore, a notion of uncertain should be introduced in context representation and decision making in order to deal with this problem. During this thesis, I have developed a dynamic and extendible framework able to adapt to different environments and patients' needs. This was achieved based on my proposed approach of semantic Plug&Play mechanism. In order to handle the problem of uncertain information related to technical problems, I have proposed an approach for uncertainty measurement based on intrinsic characteristics of the sensors and their functional behaviors, then I have provided a model of semantic representation and reasoning under uncertainty coupled with the Dempster-Shafer Theory of evidence (DST) for decision making

Cette thèse traite de la gestion du trafic aérien et plus précisément, de l’optimisation globale des plans de vol déposés par les compagnies aériennes sous contrainte du respect de la capacité de l’espace aérien. Une composante importante de ce travail concerne la gestion de l’incertitude entourant les trajectoires des aéronefs. Dans la première partie du travail, nous identifions les principales causes d’incertitude au niveau de la prédiction de trajectoires. Celle-ci est la composante essentielle à l’automatisation des systèmes de gestion du trafic aérien. Nous étudions donc le problème du réglage automatique et en-ligne des paramètres de la prédiction de trajectoires au cours de la phase de montée avec l’algorithme d’optimisation CMA-ES. La principale conclusion, corroborée par d’autres travaux de la littérature, implique que la prédiction de trajectoires des centres de contrôle n’est pas suffisamment précise aujourd’hui pour supporter l’automatisation complète des tâches critiques. Ainsi, un système d’optimisation centralisé de la gestion du traficaérien doit prendre en compte le facteur humain et l’incertitude de façon générale.Par conséquent, la seconde partie traite du développement des modèles et des algorithmes dans une perspective globale. De plus, nous décrivons un modèle stochastique qui capture les incertitudes sur les temps de passage sur des balises de survol pour chaque trajectoire. Ceci nous permet d’inférer l’incertitude engendrée sur l’occupation des secteurs de contrôle par les aéronefs à tout moment.Dans la troisième partie, nous formulons une variante du problème classique du Air Traffic Flow and Capacity Management au cours de la phase tactique. L’intérêt est de renforcer les échanges d’information entre le gestionnaire du réseau et les contrôleurs aériens. Nous définissons donc un problème d’optimisation dont l’objectif est de minimiser conjointement les coûts de retard et de congestion tout en respectant les contraintes de séquencement au cours des phases de décollage et d’attérissage. Pour combattre le nombre de dimensions élevé de ce problème, nous choisissons un algorithme évolutionnaire multiobjectif avec une représentation indirecte du problème en se basant sur des ordonnanceurs gloutons. Enfin, nous étudions les performances et la robustesse de cette approche en utilisant le modèle stochastique défini précédemment. Ce travail est validé à l’aide de problèmes réels obtenus du Central Flow Management Unit en Europe, que l’on a aussi densifiés artificiellement. / In this thesis, we investigate the issue of optimizing the aircraft operators' demand with the airspace capacity by taking into account uncertainty in air traffic management. In the first part of the work, we identify the main causes of uncertainty of the trajectory prediction (TP), the core component underlying automation in ATM systems. We study the problem of online parameter-tuning of the TP during the climbing phase with the optimization algorithm CMA-ES. The main conclusion, corroborated by other works in the literature, is that ground TP is not sufficiently accurate nowadays to support fully automated safety-critical applications. Hence, with the current data sharing limitations, any centralized optimization system in Air Traffic Control should consider the human-in-the-loop factor, as well as other uncertainties. Consequently, in the second part of the thesis, we develop models and algorithms from a network global perspective and we describe a generic uncertainty model that captures flight trajectories uncertainties and infer their impact on the occupancy count of the Air Traffic Control sectors. This usual indicator quantifies coarsely the complexity managed by air traffic controllers in terms of number of flights. In the third part of the thesis, we formulate a variant of the Air Traffic Flow and Capacity Management problem in the tactical phase for bridging the gap between the network manager and air traffic controllers. The optimization problem consists in minimizing jointly the cost of delays and the cost of congestion while meeting sequencing constraints. In order to cope with the high dimensionality of the problem, evolutionary multi-objective optimization algorithms are used with an indirect representation and some greedy schedulers to optimize flight plans. An additional uncertainty model is added on top of the network model, allowing us to study the performances and the robustness of the proposed optimization algorithm when facing noisy context. We validate our approach on real-world and artificially densified instances obtained from the Central Flow Management Unit in Europe.

L’hétérogénéité des environnements ainsi que la diversité des profils et des besoins des patients représentent des contraintes majeures qui remettent en question l’utilisation à grande échelle des systèmes d’assistance à l’autonomie à domicile (AAL). En effet, afin de répondre à l’évolution de l’état des patients et de leurs besoins humains, les environnements AAL sont en évolution continue par l’introduction ou la disparition de capteurs, de dispositifs d’interaction et de services d’assistance. Par conséquent, une plateforme générique et dynamique capable de s’adapter à différents environnements et d’intégrer de nouveaux capteurs, dispositifs d’interaction et services d’assistance est requise. La mise en œuvre d’un tel aspect dynamique peut produire une situation d’incertitude dérivée des problèmes techniques liés à la fiabilité des capteurs ou à des problèmes de réseau. Par conséquent, la notion d’incertitude doit être introduite dans la représentation de contexte et la prise de décision afin de faire face à ce problème. Au cours de cette thèse, j’ai développé une plateforme dynamique et extensible capable de s’adapter à différents environnements et aux besoins des patients. Ceci a été réalisé sur la base de l’approche Plug&Play sémantique que j’ai proposé. Afin de traiter le problème d’incertitude de l’information lié à des problèmes techniques, j’ai proposé une approche de mesure d’incertitude en utilisant les caractéristiques intrinsèques des capteurs et leurs comportements fonctionnels. J’ai aussi fourni un modèle de représentation sémantique et de raisonnement avec incertitude associé avec la théorie de Dempster-Shafer (DST) pour la prise de décision / The heterogeneity of the environments as well as the diversity of patients’ needs and profiles are major constraints that challenge the spread of ambient assistive living (AAL) systems. AAL environments are usually evolving by the introduction or the disappearance of sensors, devices and assistive services to respond to the evolution of patients’ conditions and human needs. Therefore, a generic framework that is able to adapt to such dynamic environments and to integrate new sensors, devices and assistive services at runtime is required. Implementing such a dynamic aspect may produce an uncertainty derived from technical problems related to sensors reliability or network problems. Therefore, a notion of uncertain should be introduced in context representation and decision making in order to deal with this problem. During this thesis, I have developed a dynamic and extendible framework able to adapt to different environments and patients’ needs. This was achieved based on my proposed approach of semantic Plug&Play mechanism. In order to handle the problem of uncertain information related to technical problems, I have proposed an approach for uncertainty measurement based on intrinsic characteristics of the sensors and their functional behaviors, then I have provided a model of semantic representation and reasoning under uncertainty coupled with the Dempster-Shafer Theory of evidence (DST) for decision making