No description available.

Les systèmes de traduction statistique à base de segments traduisent les phrases un segment à la fois, en plusieurs étapes. À chaque étape, ces systèmes ne considèrent que très peu d’informations pour choisir la traduction d’un segment. Les scores du dictionnaire de segments bilingues sont calculés sans égard aux contextes dans lesquels ils sont utilisés et les modèles de langue ne considèrent que les quelques mots entourant le segment traduit.Dans cette thèse, nous proposons un nouveau modèle considérant la phrase en entier lors de la sélection de chaque mot cible. Notre modèle d’intégration du contexte se différentie des précédents par l’utilisation d’un ppc (perceptron à plusieurs couches). Une propriété intéressante des ppc est leur couche cachée, qui propose une représentation alternative à celle offerte par les mots pour encoder les phrases à traduire. Une évaluation superficielle de cette représentation alter- native nous a montré qu’elle est capable de regrouper certaines phrases sources similaires même si elles étaient formulées différemment. Nous avons d’abord comparé avantageusement les prédictions de nos ppc à celles d’ibm1, un modèle couramment utilisé en traduction. Nous avons ensuite intégré nos ppc à notre système de traduction statistique de l’anglais vers le français. Nos ppc ont amélioré les traductions de notre système de base et d’un deuxième système de référence auquel était intégré IBM1. / Phrase-based statistical machine translation systems translate source sentences one phrase at a time, conditioning the choice of each phrase on very little information. Bilingual phrase table scores are computed regardless of the context in which the phrases are used and language models only look at few words surrounding the target phrases. In this thesis, we propose a novel model to predict words that should appear in a translation given the source sentence as a whole. Our model differs from previous works by its use of mlp (multilayer perceptrons). Our interest in mlp lies in their hidden layer that encodes source sentences in a representation that is only loosely tied to words. We observed that this hidden layer was able to cluster some sentences having similar translations even if they were formulated differently. In a first set of experiments, we compared favorably our mlp to ibm1, a well known model in statistical machine translation. In a second set of experiments, we embedded our ppc in our English to French statistical machine translation system. Our MLP improved translations quality over our baseline system and a second system embedding an IBM1 model.

Student Number : 9811923K - PhD thesis - School of Mechanical Engineering - Faculty of Engineering and the Built Environment / Methods are presented for obtaining models used for predicting welded sample resistance and effective weld current (RMS) for desired weld diameter (weld quality) in the resistance spot welding process. These models were used to design predictive controllers for the welding process. A suitable process model forms an important step in the development and design of process controllers for achieving good weld quality with good reproducibility. Effective current, dynamic resistance and applied electrode force are identified as important input parameters necessary to predict the output weld diameter. These input parameters are used for the process model and design of a predictive controller. A three parameter empirical model with dependent and independent variables was used for curve fitting the nonlinear halfwave dynamic resistance. The estimates of the parameters were used to develop charts for determining overall resistance of samples for any desired weld diameter. Estimating resistance for samples welded in the machines from which dataset obtained were used to plot the chart yielded accurate results. However using these charts to estimate sample resistance for new and unknown machines yielded high estimation error. To improve the prediction accuracy the same set of data generated from the model were used to train four different neural network types. These were the Generalised Feed Forward (GFF) neural network, Multilayer Perceptron (MLP) network, Radial Basis Function (RBF) and Recurrent neural network (RNN). Of the four network types trained, the MLP had the least mean square error for training and cross validation of 0.00037 and 0.00039 respectively with linear correlation coefficient in testing of 0.999 and maximum estimation error range from 0.1% to 3%. A prediction accuracy of about 97% to 99.9%. This model was selected for the design and implementation of the controller for predicting overall sample resistance. Using this predicted overall sample resistance, and applied electrode force, a second model was developed for predicting required effective weld current for any desired weld diameter. The prediction accuracy of this model was in the range of 94% to 99%. The neural network predictive controller was designed using the MLP neural network models. The controller outputs effective current for any desired weld diameter and is observed to track the desired output accurately with same prediction accuracy of the model used which was about 94% to 99%. The controller works by utilizing the neural network output embedded in Microsoft Excel as a digital link library and is able to generate outputs for given inputs on activating the process by the push of a command button.

A busca progressiva no espaço de estados é uma das abordagens mais populares de Planejamento Automatizado. O desempenho dos algoritmos de busca progressiva é influenciado pela heurística independente de domínio utilizada para guiá-lo. Nesse contexto, o foco do presente trabalho consiste em investigar técnicas de aprendizado de máquina supervisionadas que possibilitaram agregar à heurística do plano relaxado, comumente utilizada em abordagens atuais de planejamento, informações sobre o domínio em questão que viessem a ser úteis ao algoritmo de busca. Essas informações foram representadas por meio de um espaço de características do problema de planejamento e uma rede neural MLP foi aplicada para estimar uma nova função heurística para guiar a busca por meio de um processo de regressão não linear. Uma vez que o conjunto de características disponíveis para a construção da nova função heurística é grande, foi necessário a definição de um processo de seleção de características capaz de determinar qual conjunto de características de entrada da rede resultaria em melhor desempenho para o modelo de regressão. Portanto, para a seleção de características, aplicou-se uma abordagem de algoritmos genéticos. Como principal resultado, tem-se uma análise comparativa do desempenho entre a utilização da heurística proposta neste trabalho e a utilização da heurística do plano relaxado para guiar o algoritmo de busca na tarefa de planejamento. Para a análise empírica foram utilizados domínios de diferentes complexidades disponibilizados pela Competições Internacionais de Planejamento. Além dos resultados empíricos e análises comparativas, as contribuições deste trabalho envolvem o desenvolvimento de um novo planejador independente de domínio, denominado LearnInPlanner. Esse planejador utiliza a nova função heurística estimada por meio do processo de aprendizado e o algoritmo de Busca Gulosa para solucionar os problemas de planejamento. / The forward state-space search is one of the most popular Automated Planning approaches. The performance of forward search algorithms is affected by the domain-independent heuristic being used. In this context, the focus of this work consisted on investigating techniques of supervised machine learning that make possible to agregate to the relaxed plan heuristic, commonly used in current planning approaches, information about the domain which could be useful to the search algorithm. This information has been represented through a feature space of planning problem and a MLP neural network has been applied to estimate a new heuristic function for guiding the search through a non-linear regression process. Once the set of features available for the construction of the new heuristic function is large, it was necessary to define a feature selection process capable of determining which set of neural network input features would result in the best performance for the regression model. Therefore, for selecting features, an approach of genetic algorithms has been applied. As the main result, one has obtained a comparative performance analysis between the use of heuristic proposed in this work and the use of the relaxed plan heuristic to guide the search algorithm in the planning task. For the empirical analysis were used domains with different complexities provided by the International Planning Competitions. In addition to the empirical results and comparative analysis, the contributions of this work involves the development of a new domain-independent planner, named LearnInPlanner. This planner uses the new heuristic function estimated by the learning process and the Greedy Best-First search algorithm to solve planning problems.

Made available in DSpace on 2017-07-21T14:19:35Z (GMT). No. of bitstreams: 1 Rodrigo Viecheneski.pdf: 2517433 bytes, checksum: edab7bfbbad98ea4871ef9dbb71009d3 (MD5) Previous issue date: 2012-09-24 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This dissertation presents the development of a computational system called System for Treatment of Agrometeorological weather Series (STST Agrometeorológicas), with the objective of treating agrometeorological data in order to correct time weather. For the development of the study some data were collected from the agrometeorological stations, provided by Fundação ABC. The stations were located in the state of Paraná, in the cities of Ponta Grossa (long - 49.95025733, lat - 25.30156819) and Castro (long -49.8672, lat -24.6752). The computational system that has been suggested made use of the technology of Artificial Neural Networks on the type of Multilayer Perceptron and the backpropagation training algorithm of backpropagation error. It was developed with the Object Pascal programming language, using the integrated development environment Embarcadero Delphi 2009. To validate the proposed method we conducted six case studies, and the one which presented the best result for agrometeorological variable average temperature was the first case study of Castro's weather station, with a hit percentage between the treated registers and the registers without failure of 96.5%, a Pearson correlation coefficient of 0.98 and a simple average of the errors obtained from the training the neural network of 0.026406. The average errors of the neural networks was calculated between the values of errors obtained in each training during a period of correction failure. For the agrometeorological variable relative humidity, the best result was found in the case study 5 of Castro’s weather station, with a hit percentage of 95.7%, a Pearson correlation coefficient of 0.97 and the simple average of the errors obtained from the training the neural network of 0,094298. Given this context, it was revealed that the STST Agrometeorological is a viable alternative in the treatment of meteorological variables such as temperature and relative humidity, since there were results with hit percentage greater than 95% in the treatments of fails of the weather series studied. / Esta dissertação apresenta o desenvolvimento de um sistema computacional deno-minado Sistema para Tratamento de Séries Temporais Agrometeorológicas (STST Agrometeorológicas), com o objetivo de tratar dados agrometeorológicos visando a correção de séries temporais. Para o desenvolvimento dos estudos foram utilizados dados de estações agrometeorológicas disponibilizados pela Fundação ABC, situa-da no estado do Paraná, nas cidades de Ponta Grossa (long -49.95025733, lat -25.30156819) e Castro (long -49.8672, lat -24.6752). O sistema computacional pro-posto fez uso da tecnologia de Redes Neurais Artificiais do tipo Perceptron de Múlti-plas Camadas e do algoritmo backpropagation de treinamento de retropropagação do erro. E foi desenvolvido com a linguagem de programação Object Pascal, utili-zando o ambiente de desenvolvimento integrado Embarcadero Delphi 2009. Para validar o método proposto, foram realizados seis estudos de caso, dentre os quais, o que apresentou o melhor resultado para variável agrometeorológica temperatura média foi o estudo de caso 1 da estação agrometeorológica de Castro, com um per-centual de acerto entre os registros tratados e os registros sem falha de 96,5%, um coeficiente de correlação de Pearson de 0,98 e uma média simples entre os erros obtidos nos treinamentos da rede neural de 0,026406. A média dos erros das redes neurais foi calculada entre os valores dos erros obtidos em cada treinamento, duran-te a correção de um determinado período de falha. Para variável agrometeorológica umidade relativa do ar, o melhor resultado encontrado foi o estudo de caso 5 da es-tação agrometeorológica de Castro, com um percentual de acerto de 95,7%, um coe-ficiente de correlação de Pearson de 0,97 e a média simples dos erros da rede neu-ral de 0,094298. Diante desse contexto, foi possível perceber que o STST Agrome-teorológicas é uma alternativa viável no tratamento das variáveis agrometeorológicas temperatura média e umidade relativa do ar, uma vez que, houve resultados com percentual de acerto superior a 95% no tratamento de falhas das séries temporais estudadas.

A tarefa de encontrar faces em imagens é extremamente complexa, pois pode ocorrer variação de luminosidade, fundos extremamente complexos e objetos que podem se sobrepor parcialmente à face que será localizada, entre outros problemas. Com o avanço na área de visão computacional técnicas mais recentes de processamento de imagens e inteligência artificial têm sido combinadas para desenvolver algoritmos mais eficientes para a tarefa de detecção de faces. Este trabalho apresenta uma metodologia de visão computacional que utiliza redes neurais MLP (Perceptron Multicamadas) para segmentar a cor da pele e a textura da face, de outros objetos presentes em uma imagem de fundo complexo. A imagem resultante é dividida em regiões, e para cada região são extraídas características que são aplicadas em outra rede neural MLP para identificar se naquela região contem face ou não. Para avaliação do software implementado foram utilizados dois banco de imagens, um com imagens padronizadas (Banco AR) e outro banco com imagens adquiridas na Internet contendo faces com diferentes tons de pele e fundo complexo. Os resultados finais obtidos foram de 83% de faces detectadas para o banco de imagens da Internet e 88% para o Banco AR, evidenciando melhores resultados para as imagens deste banco, pelo fato de serem padronizadas, não conterem faces inclinadas e fundo complexo. A etapa de segmentação apesar de reduzir a quantidade de informação a ser processada para os demais módulos foi a que contribuiu para o maior número de falsos negativos. / The task of finding faces in images is extremely complex, as there is variation in brightness, backgrounds and highly complex objects that may overlap partially in the face to be found, among other problems. With the advancement in the field of computer vision techniques latest image processing and artificial intelligence have been combined to develop more efficient algorithms for the task of face detection. This work presents a methodology for computer vision using neural networks MLP (Multilayer Perceptron) to segment the skin color and texture of the face, from other objects present in a complex background image. The resulting image is divided into regions and from each region are extracted features that are applied in other MLP neural network to identify whether this region contains the face or not. To evaluate the software two sets of images were used, images with a standard database (AR) and another database with images acquired from the Internet, containing faces with different skin tones and complex background. The final results were 83% of faces detected in the internet database of images and 88% for the database AR. These better results for the database AR is due to the fact that they are standardized, are not rotated and do not contain complex background. The segmentation step, despite reducing the amount of information being processed for the other modules contributed to the higher number of false negatives.

A tarefa de encontrar faces em imagens é extremamente complexa, pois pode ocorrer variação de luminosidade, fundos extremamente complexos e objetos que podem se sobrepor parcialmente à face que será localizada, entre outros problemas. Com o avanço na área de visão computacional técnicas mais recentes de processamento de imagens e inteligência artificial têm sido combinadas para desenvolver algoritmos mais eficientes para a tarefa de detecção de faces. Este trabalho apresenta uma metodologia de visão computacional que utiliza redes neurais MLP (Perceptron Multicamadas) para segmentar a cor da pele e a textura da face, de outros objetos presentes em uma imagem de fundo complexo. A imagem resultante é dividida em regiões, e para cada região são extraídas características que são aplicadas em outra rede neural MLP para identificar se naquela região contem face ou não. Para avaliação do software implementado foram utilizados dois banco de imagens, um com imagens padronizadas (Banco AR) e outro banco com imagens adquiridas na Internet contendo faces com diferentes tons de pele e fundo complexo. Os resultados finais obtidos foram de 83% de faces detectadas para o banco de imagens da Internet e 88% para o Banco AR, evidenciando melhores resultados para as imagens deste banco, pelo fato de serem padronizadas, não conterem faces inclinadas e fundo complexo. A etapa de segmentação apesar de reduzir a quantidade de informação a ser processada para os demais módulos foi a que contribuiu para o maior número de falsos negativos. / The task of finding faces in images is extremely complex, as there is variation in brightness, backgrounds and highly complex objects that may overlap partially in the face to be found, among other problems. With the advancement in the field of computer vision techniques latest image processing and artificial intelligence have been combined to develop more efficient algorithms for the task of face detection. This work presents a methodology for computer vision using neural networks MLP (Multilayer Perceptron) to segment the skin color and texture of the face, from other objects present in a complex background image. The resulting image is divided into regions and from each region are extracted features that are applied in other MLP neural network to identify whether this region contains the face or not. To evaluate the software two sets of images were used, images with a standard database (AR) and another database with images acquired from the Internet, containing faces with different skin tones and complex background. The final results were 83% of faces detected in the internet database of images and 88% for the database AR. These better results for the database AR is due to the fact that they are standardized, are not rotated and do not contain complex background. The segmentation step, despite reducing the amount of information being processed for the other modules contributed to the higher number of false negatives.

Recommender systems are an advanced form of software applications, more specifically decision-support systems, that efficiently assist the users in finding items of their interest. Recommender systems have been applied to many domains from music to e-commerce, movies to software services delivery and tourism to news by exploiting available information to predict and provide recommendations to end user. The suggestions generated by recommender systems tend to narrow down the list of items which a user may overlook due to the huge variety of similar items or users’ lack of experience in the particular domain of interest. While the performance of traditional recommender systems, which rely on relatively simpler information such as content and users’ filters, is widely accepted, their predictive capability perfomrs poorly when local context of the user and situated actions have significant role in the final decision. Therefore, acceptance and incorporation of context of the user as a significant feature and development of recommender systems utilising the premise becomes an active area of research requiring further investigation of the underlying algorithms and methodology. This thesis focuses on categorisation of contextual and non-contextual features within the domain of context-aware recommender system and their respective evaluation. Further, application of the Multilayer Perceptron Model (MLP) for generating predictions and ratings from the contextual and non-contextual features for contextual recommendations is presented with support from relevant literature and empirical evaluation. An evaluation of specifically employing artificial neural networks (ANNs) in the proposed methodology is also presented. The work emphasizes on both algorithms and methodology with three points of consideration: contextual features and ratings of particular items/movies are exploited in several representations to improve the accuracy of recommendation process using artificial neural networks (ANNs), context features are combined with user-features to further improve the accuracy of a context-aware recommender system and lastly, a combination of the item/movie features are investigated within the recommendation process. The proposed approach is evaluated on the LDOS-CoMoDa dataset and the results are compared with state-of-the-art approaches from relevant published literature.

Os sistemas automáticos são normalmente empregados na indústria com o objetivo de otimizar a produção. Na agro-indústria, estes sistemas são usados com o mesmo propósito, sendo que dentre estes sistemas é possível destacar os que empregam a visão computacional, pois esta tem sido usada para inspeção de lavouras, colheita mecanizada, guiagem de veículos e robôs entre outras aplicações. No presente trabalho, técnicas de visão computacional foram utilizadas para segmentar e classificar elementos presentes em imagens obtidas de pomares de laranjeiras. Uma arquitetura modular foi utilizada na qual a imagem é segmentada automaticamente e, posteriormente, os segmentos são classificados. Nesta arquitetura, o algoritmo de segmentação e o classificador podem ser alterados sem prejudicar a flexibilidade do sistema implementado. Foram realizados experimentos com um banco de imagens composto por 658 imagens. Estas imagens foram obtidas sob diferentes condições de iluminação durante o período que as frutas estavam maduras. Estes experimentos foram realizados para avaliar, no contexto da arquitetura desenvolvida, o algoritmo de segmentação JSEG, vetores de características derivados dos espaços de cores RGB e HSV, além de três tipos de classificadores: bayesiano, classificador ingênuo de Bayes e classificador baseado no perceptron multicamadas. Finalmente, foram construídos os mapas de classes. As funções de distribuição de probabilidades foram estimadas com o algoritmo de Figueiredo-Jain. Dos resultados obtidos, deve-se destacar que o algoritmo de segmentação mostrou-se adequado aos propósitos deste trabalho e o classificador bayesiano mostrou-se mais prático que o classificador baseado no perceptron multicamadas. Por fim, a arquitetura mostrou-se adequada para o reconhecimento de cenas obtidas em pomares de laranjeiras. / Automation systems are usually used in the industry to optimize the production. In the agroindustry, these systems are used with the same intentions. Among them are systems that use computer vision for inspection, mechanized harvest, vehicles and robots guidance and other applications. Because of this, in the present work, techniques of computer vision were used to segment and classify elements in the images from oranges orchards. A modular architecture was used. The image are automatically segmented and, then the segments are classified. In this architecture, the segmentation algorithm and the classifier can be modified without loss of flexibility. The experiments were carried out with 658 images. These images were acquired under different illumination conditions during the period that the fruits are mature. These experiments were carried out to evaluate, in the context of developed architecture, the segmentation algorithm JSEG, characteristics vectors derived from the colors spaces RGB and HSV and three classifiers: Bayes\'s classifier, Bayes\'s naive classifier and multilayer perceptron classifier. Finally, the class maps were constructed. The Figueiredo-Jain algorithm was used to estimate the probability distribution functions. The results show that the segmentation algorithm is adequate to this work and the Bayes classifier is more practical that the multilayer perceptron classifier. Finally, the architecture is adequate for recognition of images acquired in orange orchards.

A busca progressiva no espaço de estados é uma das abordagens mais populares de Planejamento Automatizado. O desempenho dos algoritmos de busca progressiva é influenciado pela heurística independente de domínio utilizada para guiá-lo. Nesse contexto, o foco do presente trabalho consiste em investigar técnicas de aprendizado de máquina supervisionadas que possibilitaram agregar à heurística do plano relaxado, comumente utilizada em abordagens atuais de planejamento, informações sobre o domínio em questão que viessem a ser úteis ao algoritmo de busca. Essas informações foram representadas por meio de um espaço de características do problema de planejamento e uma rede neural MLP foi aplicada para estimar uma nova função heurística para guiar a busca por meio de um processo de regressão não linear. Uma vez que o conjunto de características disponíveis para a construção da nova função heurística é grande, foi necessário a definição de um processo de seleção de características capaz de determinar qual conjunto de características de entrada da rede resultaria em melhor desempenho para o modelo de regressão. Portanto, para a seleção de características, aplicou-se uma abordagem de algoritmos genéticos. Como principal resultado, tem-se uma análise comparativa do desempenho entre a utilização da heurística proposta neste trabalho e a utilização da heurística do plano relaxado para guiar o algoritmo de busca na tarefa de planejamento. Para a análise empírica foram utilizados domínios de diferentes complexidades disponibilizados pela Competições Internacionais de Planejamento. Além dos resultados empíricos e análises comparativas, as contribuições deste trabalho envolvem o desenvolvimento de um novo planejador independente de domínio, denominado LearnInPlanner. Esse planejador utiliza a nova função heurística estimada por meio do processo de aprendizado e o algoritmo de Busca Gulosa para solucionar os problemas de planejamento. / The forward state-space search is one of the most popular Automated Planning approaches. The performance of forward search algorithms is affected by the domain-independent heuristic being used. In this context, the focus of this work consisted on investigating techniques of supervised machine learning that make possible to agregate to the relaxed plan heuristic, commonly used in current planning approaches, information about the domain which could be useful to the search algorithm. This information has been represented through a feature space of planning problem and a MLP neural network has been applied to estimate a new heuristic function for guiding the search through a non-linear regression process. Once the set of features available for the construction of the new heuristic function is large, it was necessary to define a feature selection process capable of determining which set of neural network input features would result in the best performance for the regression model. Therefore, for selecting features, an approach of genetic algorithms has been applied. As the main result, one has obtained a comparative performance analysis between the use of heuristic proposed in this work and the use of the relaxed plan heuristic to guide the search algorithm in the planning task. For the empirical analysis were used domains with different complexities provided by the International Planning Competitions. In addition to the empirical results and comparative analysis, the contributions of this work involves the development of a new domain-independent planner, named LearnInPlanner. This planner uses the new heuristic function estimated by the learning process and the Greedy Best-First search algorithm to solve planning problems.