The purpose of this study was to investigate the characteristics of a qualified e-learning instructor from e-learners&rsquo / perspectives by submitting a questionnaire to e-learners of &ldquo / CSIT444-Online Web Design&rdquo / course offered through the means of distance learning at the Eastern Mediterranean University. The study explored on-line instructor&rsquo / s administrative support, instructional competency, proficiency in applying the systems used in the course, in other words, technical knowledge and skills and on-line instructor&rsquo / s evaluation criteria of the on-line course. The study used the data obtained from 45 students, the instructor and an assistant of Eastern Mediterranean University. For this research, descriptive study was carried out and qualitative results were given at the end of the study. The results investigated students&rsquo / perceptions about the on-line course they were introduced prior to the application of the questionnaire. The results of the questionnaire demonstrated that the course was found effective, interesting and motivating for students with the animations, free lecture notes, forums, chat rooms, links to e-sources, chance for interaction and immediate feedback that enhance student creativity and self study. The findings included the recommendations for teachers in on-line learning environment. The study also provides the framework of the on-line instructors&rsquo / role by means of on-line learning environment. The results were demonstrated at the end of the study.

Orientador: Monica Fürkotter / Banca: Claudia Maria de Lima / Banca: Simão Pedro Pinto Marinho / Resumo: Este trabalho insere-se no contexto da linha de pesquisa "Tecnologias de Informação e Comunicação e Educação" e investiga um processo de formação continuada de professores do ensino superior para o uso do ambiente colaborativo on-line MOODLE para apoiar sua prática docente e a ocorrência da formação de uma rede de aprendizagem on-line após a capacitação. Baseia-se principalmente em pressupostos teóricos que norteiam a formação continuada contextualizada e na perspectiva da simetria invertida, nos conceitos de professor reflexivo e pesquisador, nas competências digitais necessárias para atuação docente, nas redes de aprendizagem on-line e na utilização da EAD para apoiar processos formativos. Utiliza-se da metodologia quanti-qualitativa na abordagem da investigação-formação. Os dados foram coletados no ambiente virtual utilizado durante o período da capacitação docente analisada. Os resultados apontam a possibilidade de se formar uma rede de aprendizagem on-line a partir da formação continuada, cujo foco seja o desenvolvimento das competências docentes necessárias para a mediação pedagógica com as tecnologias digitais. / Abstract: This paper is within the context of the "Information and Communication Technologies and Education" research line and investigates a process of continuous training of higher teachers for the use of on-line collaborative environment MOODLE to support their teaching practice and the occurrence of the formation of a network of on-line learning after the training. It is mainly based on theoretical assumptions that guide the continuing education context and in view of the reverse symmetry, on the concepts of reflective teacher and researcher, on the skills necessary for proper teacher performance in networks of on-line learning and the use of LMS to support training processes. It uses the methodology in the qualitative-quantitative approach to research and training. Data were collected in the virtual environment used during the teacher training examination. The results indicate the possibility of forming a network of on-line learning from continuing education, whose focus is the development of teaching skills necessary to mediation training with digital technologies. / Mestre

Orientadores: Rubens Maciel Filho, Laercio Ender / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Quimica / Made available in DSpace on 2018-08-08T18:03:43Z (GMT). No. of bitstreams: 1 Duarte_ElisRegina_D.pdf: 5707651 bytes, checksum: d1348f1129ff1981af5a94400a0f9040 (MD5) Previous issue date: 2007 / Resumo:0 objetivo deste trabalho foi desenvolver e avaliar diferentes algoritmos de controle para o processo extrativo de fermentação alcoólica contínua. Para isto foram comparados controladores do tipo preditivo e adaptativo. Para o controle preditivo, foi avaliado o Controle por Matriz Dinâmica (DMC) e foi desenvolvido um algoritmo de controle preditivo baseado em modelo usando redes neurais artificiais (MPC Neural) com aprendizagem em tempo real das redes. Para o controle adaptativo, foi proposto o aperfeiçoamento do algoritmo de controle CONDEG (Controle Neural Direto Baseado no Erro Global) Modificado, desenvolvido por Duarte (2004), O algoritmo está baseado em redes neurais artificiais, com aprendizagem em tempo real, de acordo com as alterações que ocorrem no processo. Os parâmetros de penalização das ações de controle, que são parâmetros de projeto do controlador, foram ajustados ao longo do tempo através da aplicação de um algoritmo do Filtro de Kalman. Para o procedimento de investigação foi utilizada a simulação computacional para o qual todos os algoritmos de controle estudados foram implementados em linguagem de programação Fortran 90 e aplicados a um processo extrativo de fermentação alcoólica contínua para produção de etanol desenvolvido por Silva (1999). O modelo matemático utilizado foi desenvolvido por Costa et al(2001). As simulações em malha fechada realizadas utilizando os algoritmos propostos mostraram melhores resultados para os algoritmos de controle usando redes com aprendizagem ao longo do tempo e que o algoritmo de controle CONDEG Modificado usando filtro de Kalman com fator de velocidade associado foi eficiente e robusto, pois apresentou bons resultados em problemas dos tipos servos e regulador. / Abstract: The objective of the present work is to develop and to evaluate the performance of predictive and adaptive controllers, applied to an extractive fermentative process. As predictive controllers the Dynamical Matrix Control (DMC) and a model predictive control based on artificial neural networks with on-line learning were considered. The adaptive controller is an improvement of the Modified Condeg strategy control (Direct Neural Control based on Global Error), developed by Duarte (2004). The strategy is based on artificial neural networks, with on-line learning, according to modifications that occur in the process. The control actions penalization parameters, that are in fact controller design parameters, are on-line adjusted through an algorithm based on Kalman filter. The performance evaluation was carried out through computer simulation with all algorithms implemented in Fortran 90,.As a case study, an extractive fermentation alcoholic process developed by Silva (1999) was taken into account with the mathematical model developed by Costa et. al (2001). The results obtained from closed-loop simulations using the proposed algorithms showed better results for the neural networks with on-line learning. The Modified Condeg wsth Kalman Filter plus velocity factor is efficient and robust for servo and regulatory applications. / Doutorado / Desenvolvimento de Processos Químicos / Doutor em Engenharia Química

La pratique physique a longtemps été perçue comme le déterminant premier de l’apprentissage du mouvement. Souvent exprimée par l’expression « Vingt fois sur le métier remettez votre ouvrage», cette idée se base sur l’observation qu’une grande quantité de pratique est nécessaire pour maîtriser un geste technique complexe. Bien que l’importance de la pratique physique pour l’apprentissage du mouvement demeure indéniable, il a récemment été démontré que les changements neurobiologiques qui constituent les bases de la mémoire prennent place après la pratique. Ces changements, regroupés sous le terme « consolidation », sont essentiels à la mise en mémoire des habiletés motrices. L’objectif de cette thèse est de définir les processus de consolidation en identifiant certains facteurs qui influencent la consolidation d’une habileté motrice. À l’aide d’une tâche d’adaptation visuomotrice comportant deux niveaux de difficulté, nous avons démontré qu’une bonne performance doit être atteinte au cours de la séance de pratique pour enclencher certains processus de consolidation. De plus, nos résultats indiquent que l’évaluation subjective que l’apprenant fait de sa propre performance peut moduler la consolidation. Finalement, nous avons démontré que l’apprentissage par observation peut enclencher certains processus de consolidation, indiquant que la consolidation n’est pas exclusive à la pratique physique. Dans l’ensemble, les résultats des études expérimentales présentées dans cette thèse montrent que la consolidation regroupe plusieurs processus distincts jouant chacun un rôle important pour l’apprentissage du mouvement. Les éducateurs physiques, les entraineurs sportifs et les spécialistes de la réadaptation physique devraient donc planifier des entrainements favorisant non seulement l’acquisition de gestes moteurs mais également leur consolidation. / Physical practice has long been regarded as the single most determinant factor of motor skill acquisition. Often expressed by the old adage “practice makes perfect,” this idea easily relates to the common observation that extensive practice is necessary to master complex motor skills. Although the importance of physical practice for motor skill learning is undeniable, recent evidence demonstrates that the neurobiological changes that constitute the foundation of memory occur after physical practice. Regrouped under the term “consolidation”, these changes are essential for the memory storage of motor skills. The objective of this thesis was to identify factors that influence motor skill consolidation. Using a visuomotor adaptation task with two levels of difficulty, we showed that a good performance must be attained during practice to trigger certain consolidation processes. In addition, our results indicate that the learner’s subjective evaluation of his/her own performance can also modulate consolidation. Finally, we showed that observation triggers consolidation processes, indicating that consolidation is not exclusive to physical practice. Together, the results presented in this thesis demonstrate that consolidation regroups several distinct processes that each plays an important role for motor skill learning. Physical education teachers, athletic coaches and rehabilitation specialists should therefore plan training schedules favoring not only motor skill acquisition but also motor skill consolidation.

La pratique physique a longtemps été perçue comme le déterminant premier de l’apprentissage du mouvement. Souvent exprimée par l’expression « Vingt fois sur le métier remettez votre ouvrage», cette idée se base sur l’observation qu’une grande quantité de pratique est nécessaire pour maîtriser un geste technique complexe. Bien que l’importance de la pratique physique pour l’apprentissage du mouvement demeure indéniable, il a récemment été démontré que les changements neurobiologiques qui constituent les bases de la mémoire prennent place après la pratique. Ces changements, regroupés sous le terme « consolidation », sont essentiels à la mise en mémoire des habiletés motrices. L’objectif de cette thèse est de définir les processus de consolidation en identifiant certains facteurs qui influencent la consolidation d’une habileté motrice. À l’aide d’une tâche d’adaptation visuomotrice comportant deux niveaux de difficulté, nous avons démontré qu’une bonne performance doit être atteinte au cours de la séance de pratique pour enclencher certains processus de consolidation. De plus, nos résultats indiquent que l’évaluation subjective que l’apprenant fait de sa propre performance peut moduler la consolidation. Finalement, nous avons démontré que l’apprentissage par observation peut enclencher certains processus de consolidation, indiquant que la consolidation n’est pas exclusive à la pratique physique. Dans l’ensemble, les résultats des études expérimentales présentées dans cette thèse montrent que la consolidation regroupe plusieurs processus distincts jouant chacun un rôle important pour l’apprentissage du mouvement. Les éducateurs physiques, les entraineurs sportifs et les spécialistes de la réadaptation physique devraient donc planifier des entrainements favorisant non seulement l’acquisition de gestes moteurs mais également leur consolidation. / Physical practice has long been regarded as the single most determinant factor of motor skill acquisition. Often expressed by the old adage “practice makes perfect,” this idea easily relates to the common observation that extensive practice is necessary to master complex motor skills. Although the importance of physical practice for motor skill learning is undeniable, recent evidence demonstrates that the neurobiological changes that constitute the foundation of memory occur after physical practice. Regrouped under the term “consolidation”, these changes are essential for the memory storage of motor skills. The objective of this thesis was to identify factors that influence motor skill consolidation. Using a visuomotor adaptation task with two levels of difficulty, we showed that a good performance must be attained during practice to trigger certain consolidation processes. In addition, our results indicate that the learner’s subjective evaluation of his/her own performance can also modulate consolidation. Finally, we showed that observation triggers consolidation processes, indicating that consolidation is not exclusive to physical practice. Together, the results presented in this thesis demonstrate that consolidation regroups several distinct processes that each plays an important role for motor skill learning. Physical education teachers, athletic coaches and rehabilitation specialists should therefore plan training schedules favoring not only motor skill acquisition but also motor skill consolidation.

Learning to program is acknowledged to be difficult; programming is a complex intellectual activity and cannot be learnt without practice. Research has shown that first year IT students presently struggle with setting up compilers, learning how to use a programming editor and understanding abstract programming concepts. Large introductory class sizes pose a great challenge for instructors in providing timely, individualised feedback and guidance for students when they do their practice. This research investigates the problems and identifies solutions. An interactive and constructive web-based programming environment is designed to help beginning students learn to program in high-level, object-oriented programming languages such as Java and C#. The environment eliminates common starting hurdles for novice programmers and gives them the opportunity to successfully produce working programs at the earliest stage of their study. The environment allows students to undertake programming exercises anytime, anywhere, by "filling in the gaps" of a partial computer program presented in a web page, and enables them to receive guidance in getting their programs to compile and run. Feedback on quality and correctness is provided through a program analysis framework. Students learn by doing, receiving feedback and reflecting - all through the web. A key novel aspect of the environment is its capability in supporting small &quotfill in the gap" programming exercises. This type of exercise places a stronger emphasis on developing students' reading and code comprehension skills than the traditional approach of writing a complete program from scratch. It allows students to concentrate on critical dimensions of the problem to be solved and reduces the complexity of writing programs.

Modelling dialogue management as a reinforcement learning task enables a system to learn to act optimally by maximising a reward function. This reward function is designed to induce the system behaviour required for goal-oriented applications, which usually means fulfilling the user’s goal as efficiently as possible. However, in real-world spoken dialogue systems, the reward is hard to measure, because the goal of the conversation is often known only to the user. Certainly, the system can ask the user if the goal has been satisfied, but this can be intrusive. Furthermore, in practice, the reliability of the user’s response has been found to be highly variable. In addition, due to the sparsity of the reward signal and the large search space, reinforcement learning-based dialogue policy optimisation is often slow. This thesis presents several approaches to address these problems. To better evaluate a dialogue for policy optimisation, two methods are proposed. First, a recurrent neural network-based predictor pre-trained from off-line data is proposed to estimate task success during subsequent on-line dialogue policy learning to avoid noisy user ratings and problems related to not knowing the user’s goal. Second, an on-line learning framework is described where a dialogue policy is jointly trained alongside a reward function modelled as a Gaussian process with active learning. This mitigates the noisiness of user ratings and minimises user intrusion. It is shown that both off-line and on-line methods achieve practical policy learning in real-world applications, while the latter provides a more general joint learning system directly from users. To enhance the policy learning speed, the use of reward shaping is explored and shown to be effective and complementary to the core policy learning algorithm. Furthermore, as deep reinforcement learning methods have the potential to scale to very large tasks, this thesis also investigates the application to dialogue systems. Two sample-efficient algorithms, trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER), are introduced. In addition, a corpus of demonstration data is utilised to pre-train the models prior to on-line reinforcement learning to handle the cold start problem. Combining these two methods, a practical approach is demonstrated to effectively learn deep reinforcement learning-based dialogue policies in a task-oriented information seeking domain. Overall, this thesis provides solutions which allow truly on-line and continuous policy learning in spoken dialogue systems.

Data streams are a recent processing model where data arrive continuously, in large quantities, at high speeds, so that they must be processed on-line. Besides that, several private and public institutions store large amounts of data that also must be processed. Traditional batch classi ers are not well suited to handle huge amounts of data for basically two reasons. First, they usually read the available data several times until convergence, which is impractical in this scenario. Second, they imply that the context represented by data is stable in time, which may not be true. In fact, the context change is a common situation in data streams, and is named concept drift. This thesis presents rcd, a framework that o ers an alternative approach to handle data streams that su er from recurring concept drifts. It creates a new classi er to each context found and stores a sample of the data used to build it. When a new concept drift occurs, rcd compares the new context to old ones using a non-parametric multivariate statistical test to verify if both contexts come from the same distribution. If so, the corresponding classi er is reused. If not, a new classi er is generated and stored. Three kinds of tests were performed. One compares the rcd framework with several adaptive algorithms (among single and ensemble approaches) in arti cial and real data sets, among the most used in the concept drift research area, with abrupt and gradual concept drifts. It is observed the ability of the classi ers in representing each context, how they handle concept drift, and training and testing times needed to evaluate the data sets. Results indicate that rcd had similar or better statistical results compared to the other classi ers. In the real-world data sets, rcd presented accuracies close to the best classi er in each data set. Another test compares two statistical tests (knn and Cramer) in their capability in representing and identifying contexts. Tests were performed using adaptive and batch classi ers as base learners of rcd, in arti cial and real-world data sets, with several rates-of-change. Results indicate that, in average, knn had better results compared to the Cramer test, and was also faster. Independently of the test used, rcd had higher accuracy values compared to their respective base learners. It is also presented an improvement in the rcd framework where the statistical tests are performed in parallel through the use of a thread pool. Tests were performed in three processors with di erent numbers of cores. Better results were obtained when there was a high number of detected concept drifts, the bu er size used to represent each data distribution was large, and there was a high test frequency. Even if none of these conditions apply, parallel and sequential execution still have very similar performances. Finally, a comparison between six di erent drift detection methods was also performed, comparing the predictive accuracies, evaluation times, and drift handling, including false alarm and miss detection rates, as well as the average distance to the drift point and its standard deviation. / Submitted by João Arthur Martins (joao.arthur@ufpe.br) on 2015-03-12T18:02:08Z No. of bitstreams: 2 Tese Paulo Gonçalves Jr..pdf: 2957463 bytes, checksum: de163caadf10cbd5442e145778865224 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) / Made available in DSpace on 2015-03-12T18:02:08Z (GMT). No. of bitstreams: 2 Tese Paulo Gonçalves Jr..pdf: 2957463 bytes, checksum: de163caadf10cbd5442e145778865224 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2013-04-23 / Fluxos de dados s~ao um modelo de processamento de dados recente, onde os dados chegam continuamente, em grandes quantidades, a altas velocidades, de modo que eles devem ser processados em tempo real. Al em disso, v arias institui c~oes p ublicas e privadas armazenam grandes quantidades de dados que tamb em devem ser processadas. Classi cadores tradicionais n~ao s~ao adequados para lidar com grandes quantidades de dados por basicamente duas raz~oes. Primeiro, eles costumam ler os dados dispon veis v arias vezes at e convergirem, o que e impratic avel neste cen ario. Em segundo lugar, eles assumem que o contexto representado por dados e est avel no tempo, o que pode n~ao ser verdadeiro. Na verdade, a mudan ca de contexto e uma situa c~ao comum em uxos de dados, e e chamado de mudan ca de conceito. Esta tese apresenta o rcd, uma estrutura que oferece uma abordagem alternativa para lidar com os uxos de dados que sofrem de mudan cas de conceito recorrentes. Ele cria um novo classi cador para cada contexto encontrado e armazena uma amostra dos dados usados para constru -lo. Quando uma nova mudan ca de conceito ocorre, rcd compara o novo contexto com os antigos, utilizando um teste estat stico n~ao param etrico multivariado para veri car se ambos os contextos prov^em da mesma distribui c~ao. Se assim for, o classi cador correspondente e reutilizado. Se n~ao, um novo classi cador e gerado e armazenado. Tr^es tipos de testes foram realizados. Um compara o rcd com v arios algoritmos adaptativos (entre as abordagens individuais e de agrupamento) em conjuntos de dados arti ciais e reais, entre os mais utilizados na area de pesquisa de mudan ca de conceito, com mudan cas bruscas e graduais. E observada a capacidade dos classi cadores em representar cada contexto, como eles lidam com as mudan cas de conceito e os tempos de treinamento e teste necess arios para avaliar os conjuntos de dados. Os resultados indicam que rcd teve resultados estat sticos semelhantes ou melhores, em compara c~ao com os outros classi cadores. Nos conjuntos de dados do mundo real, rcd apresentou precis~oes pr oximas do melhor classi cador em cada conjunto de dados. Outro teste compara dois testes estat sticos (knn e Cramer) em suas capacidades de representar e identi car contextos. Os testes foram realizados utilizando classi cadores xi xii RESUMO tradicionais e adaptativos como base do rcd, em conjuntos de dados arti ciais e do mundo real, com v arias taxas de varia c~ao. Os resultados indicam que, em m edia, KNN obteve melhores resultados em compara c~ao com o teste de Cramer, al em de ser mais r apido. Independentemente do crit erio utilizado, rcd apresentou valores mais elevados de precis~ao em compara c~ao com seus respectivos classi cadores base. Tamb em e apresentada uma melhoria do rcd onde os testes estat sticos s~ao executadas em paralelo por meio do uso de um pool de threads. Os testes foram realizados em tr^es processadores com diferentes n umeros de n ucleos. Melhores resultados foram obtidos quando houve um elevado n umero de mudan cas de conceito detectadas, o tamanho das amostras utilizadas para representar cada distribui c~ao de dados era grande, e havia uma alta freq u^encia de testes. Mesmo que nenhuma destas condi c~oes se aplicam, a execu c~ao paralela e seq uencial ainda t^em performances muito semelhantes. Finalmente, uma compara c~ao entre seis diferentes m etodos de detec c~ao de mudan ca de conceito tamb em foi realizada, comparando a precis~ao, os tempos de avalia c~ao, manipula c~ao das mudan cas de conceito, incluindo as taxas de falsos positivos e negativos, bem como a m edia da dist^ancia ao ponto de mudan ca e o seu desvio padr~ao.

Data streams are a recent processing model where data arrive continuously, in large quantities, at high speeds, so that they must be processed on-line. Besides that, several private and public institutions store large amounts of data that also must be processed. Traditional batch classi ers are not well suited to handle huge amounts of data for basically two reasons. First, they usually read the available data several times until convergence, which is impractical in this scenario. Second, they imply that the context represented by data is stable in time, which may not be true. In fact, the context change is a common situation in data streams, and is named concept drift. This thesis presents rcd, a framework that o ers an alternative approach to handle data streams that su er from recurring concept drifts. It creates a new classi er to each context found and stores a sample of the data used to build it. When a new concept drift occurs, rcd compares the new context to old ones using a non-parametric multivariate statistical test to verify if both contexts come from the same distribution. If so, the corresponding classi er is reused. If not, a new classi er is generated and stored. Three kinds of tests were performed. One compares the rcd framework with several adaptive algorithms (among single and ensemble approaches) in arti cial and real data sets, among the most used in the concept drift research area, with abrupt and gradual concept drifts. It is observed the ability of the classi ers in representing each context, how they handle concept drift, and training and testing times needed to evaluate the data sets. Results indicate that rcd had similar or better statistical results compared to the other classi ers. In the real-world data sets, rcd presented accuracies close to the best classi er in each data set. Another test compares two statistical tests (knn and Cramer) in their capability in representing and identifying contexts. Tests were performed using adaptive and batch classi ers as base learners of rcd, in arti cial and real-world data sets, with several rates-of-change. Results indicate that, in average, knn had better results compared to the Cramer test, and was also faster. Independently of the test used, rcd had higher accuracy values compared to their respective base learners. It is also presented an improvement in the rcd framework where the statistical tests are performed in parallel through the use of a thread pool. Tests were performed in three processors with di erent numbers of cores. Better results were obtained when there was a high number of detected concept drifts, the bu er size used to represent each data distribution was large, and there was a high test frequency. Even if none of these conditions apply, parallel and sequential execution still have very similar performances. Finally, a comparison between six di erent drift detection methods was also performed, comparing the predictive accuracies, evaluation times, and drift handling, including false alarm and miss detection rates, as well as the average distance to the drift point and its standard deviation. / Submitted by João Arthur Martins (joao.arthur@ufpe.br) on 2015-03-12T19:25:11Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) tese Paulo Mauricio Gonçalves Jr..pdf: 2957463 bytes, checksum: de163caadf10cbd5442e145778865224 (MD5) / Made available in DSpace on 2015-03-12T19:25:11Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) tese Paulo Mauricio Gonçalves Jr..pdf: 2957463 bytes, checksum: de163caadf10cbd5442e145778865224 (MD5) Previous issue date: 2013-04-23 / Fluxos de dados s~ao um modelo de processamento de dados recente, onde os dados chegam continuamente, em grandes quantidades, a altas velocidades, de modo que eles devem ser processados em tempo real. Al em disso, v arias institui c~oes p ublicas e privadas armazenam grandes quantidades de dados que tamb em devem ser processadas. Classi cadores tradicionais n~ao s~ao adequados para lidar com grandes quantidades de dados por basicamente duas raz~oes. Primeiro, eles costumam ler os dados dispon veis v arias vezes at e convergirem, o que e impratic avel neste cen ario. Em segundo lugar, eles assumem que o contexto representado por dados e est avel no tempo, o que pode n~ao ser verdadeiro. Na verdade, a mudan ca de contexto e uma situa c~ao comum em uxos de dados, e e chamado de mudan ca de conceito. Esta tese apresenta o rcd, uma estrutura que oferece uma abordagem alternativa para lidar com os uxos de dados que sofrem de mudan cas de conceito recorrentes. Ele cria um novo classi cador para cada contexto encontrado e armazena uma amostra dos dados usados para constru -lo. Quando uma nova mudan ca de conceito ocorre, rcd compara o novo contexto com os antigos, utilizando um teste estat stico n~ao param etrico multivariado para veri car se ambos os contextos prov^em da mesma distribui c~ao. Se assim for, o classi cador correspondente e reutilizado. Se n~ao, um novo classi cador e gerado e armazenado. Tr^es tipos de testes foram realizados. Um compara o rcd com v arios algoritmos adaptativos (entre as abordagens individuais e de agrupamento) em conjuntos de dados arti ciais e reais, entre os mais utilizados na area de pesquisa de mudan ca de conceito, com mudan cas bruscas e graduais. E observada a capacidade dos classi cadores em representar cada contexto, como eles lidam com as mudan cas de conceito e os tempos de treinamento e teste necess arios para avaliar os conjuntos de dados. Os resultados indicam que rcd teve resultados estat sticos semelhantes ou melhores, em compara c~ao com os outros classi cadores. Nos conjuntos de dados do mundo real, rcd apresentou precis~oes pr oximas do melhor classi cador em cada conjunto de dados. Outro teste compara dois testes estat sticos (knn e Cramer) em suas capacidades de representar e identi car contextos. Os testes foram realizados utilizando classi cadores tradicionais e adaptativos como base do rcd, em conjuntos de dados arti ciais e do mundo real, com v arias taxas de varia c~ao. Os resultados indicam que, em m edia, KNN obteve melhores resultados em compara c~ao com o teste de Cramer, al em de ser mais r apido. Independentemente do crit erio utilizado, rcd apresentou valores mais elevados de precis~ao em compara c~ao com seus respectivos classi cadores base. Tamb em e apresentada uma melhoria do rcd onde os testes estat sticos s~ao executadas em paralelo por meio do uso de um pool de threads. Os testes foram realizados em tr^es processadores com diferentes n umeros de n ucleos. Melhores resultados foram obtidos quando houve um elevado n umero de mudan cas de conceito detectadas, o tamanho das amostras utilizadas para representar cada distribui c~ao de dados era grande, e havia uma alta freq u^encia de testes. Mesmo que nenhuma destas condi c~oes se aplicam, a execu c~ao paralela e seq uencial ainda t^em performances muito semelhantes. Finalmente, uma compara c~ao entre seis diferentes m etodos de detec c~ao de mudan ca de conceito tamb em foi realizada, comparando a precis~ao, os tempos de avalia c~ao, manipula c~ao das mudan cas de conceito, incluindo as taxas de falsos positivos e negativos, bem como a m edia da dist^ancia ao ponto de mudan ca e o seu desvio padr~ao.

Learning to recognize and predict common activities, performed by objects and observed by sensors, is an important and challenging problem related both to artificial intelligence and robotics.In this thesis, the general problem of dynamic adaptive situation awareness is considered and we argue for the need for an on-line bottom-up approach.A candidate for a bottom layer is proposed, which we consider to be capable of future extensions that can bring us closer towards the goal.We present a novel approach to adaptive activity learning, where a mapping between raw data and primitive activity concepts are learned and continuously improved on-line and unsupervised. The approach takes streams of observations of objects as input and learns a probabilistic representation of both the observed spatio-temporal activities and their causal relations. The dynamics of the activities are modeled using sparse Gaussian processes and their causal relations using probabilistic graphs.The learned model supports both estimating the most likely activity and predicting the most likely future (and past) activities. Methods and ideas from a wide range of previous work are combined to provide a uniform and efficient way to handle a variety of common problems related to learning, classifying and predicting activities.The framework is evaluated both by learning activities in a simulated traffic monitoring application and by learning the flight patterns of an internally developed autonomous quadcopter system. The conclusion is that our framework is capable of learning the observed activities in real-time with good accuracy.We see this work as a step towards unsupervised learning of activities for robotic systems to adapt to new circumstances autonomously and to learn new activities on the fly that can be detected and predicted immediately. / Att lära sig känna igen och förutsäga vanliga aktiviteter genom att analysera sensordata från observerade objekt är ett viktigt och utmanande problem relaterat både till artificiell intelligens och robotik. I det här exjobbet studerar vi det generella problemet rörande adaptiv situationsmedvetenhet, och vi argumenterar för behovet av ett angreppssätt som arbetar on-line (direkt på ny data) och från botten upp. Vi föreslår en möjlig lösning som vi anser bereder väg för framtida utökningar som kan ta oss närmare detta mål. Vi presenterar en ny metod för adaptiv aktivitetsinlärning, där en mappning mellan rå-data och grundläggande aktivitetskoncept, samt deras kausala relationer, lärs och är kontinuerligt förfinade utan behov av övervakning. Tillvägagångssättet bygger på användandet av strömmar av observationer av objekt, och inlärning sker av en statistik representation för både de observerade spatio-temporala aktiviteterna och deras kausala relationer. Aktiviteternas dynamik modelleras med hjälp av glesa Gaussiska processer och för att modellera aktiviteternas kausala samband används probabilistiska grafer. Givet observationer av ett objekt så stödjer de inlärda modellerna både skattning av den troligaste aktiviteten och förutsägelser av de mest troliga framtida (och dåtida) aktiviteterna utförda. Metoder och idéer från en rad olika tidigare arbeten kombineras på ett sätt som möjliggör ett enhetligt och effektivt sätt att hantera en mängd vanliga problem relaterade till inlärning, klassificering och förutsägelser av aktiviteter. Ramverket är utvärderat genom att dels inlärning av aktiviteter i en simulerad trafikövervakningsapplikation och dels genom inlärning av flygmönster hos ett  internt utvecklad quadrocoptersystem. Slutsatsen är att vårt ramverk klarar av att lära sig de observerade aktivisterna i realtid med god noggrannhet. Vi ser detta arbete som ett steg mot oövervakad inlärning av aktiviteter för robotsystem, så att dessa kan anpassa sig till nya förhållanden autonomt och lära sig nya aktiviteter direkt och som då dessutom kan börja detekteras och förutsägas omedelbart.