This work develops optimal assembly sequences for modular building blocks. The underlying concept is that an automated device could take a virtual shape such as a CAD file, and automatically decide how to physically build the shape using simple, identical building blocks. This entails deciding where to place blocks inside the shape and generating an efficient assembly sequence that a robot could use to build the shape. The blocks are defined in a general, parameterized manner such that the model can be easily modified in the future. The primary focus of this work is the development of methods for generating assembly sequences in a time-feasible manner that ensure static stability at each step of the assembly. Most existing research focuses on complete enumeration of every possible assembly sequence and evaluation of many possible sequences. This, however, is not practical for systems with a large number of parts for two reasons: (1) the number of possible assembly sequences is exponential in the number of parts, and (2) each static stability test is very time-consuming. The approach proposed here is to develop a multi-hierarchical rule-based approach to assembly sequences. This is accomplished by formalizing and justifying both high-level and mid-level assembly rules based on static considerations. Application of these rules helps develop assembly sequences rapidly. The assembly sequence is developed in a time-feasible manner according to the geometry of the structure, rather than evaluating statics along the way. This work only evaluates the static stability of each step of the assembly once. The behavior of the various rules is observed both numerically and through theory, and guidelines are developed to suggest which rules to apply. A secondary focus of this work is to introduce methods by which the inside of the structure can be optimized. This structure optimization research is implemented by genetic algorithms that solve the multi-objective optimization problem in two dimensions, and can be extended to three dimensions.

A necessidade de suportar serviços multimídia impulsiona o desenvolvimento das redes sem fio. Com isso, torna-se importante fornecer confiabilidade na transmissão de dados em um ambiente sujeito a variações espaciais, temporais e de freqüência, causadas por fenômenos físicos que, geralmente, causam erros nos dados transmitidos. Esses erros são basicamente de dois tipos: erros em rajada e erros aleatórios (Additive White Gaussian Noise - AWGN). Simular o comportamento dos canais sem fio afetados por erros é objeto de pesquisa há diversos anos. Entretanto, grande parte das pesquisas não considera a aplicação dos dois tipos de erros simultaneamente, o que pode gerar imprecisões nos resultados das simulações. Sendo assim, este trabalho propõe um injetor capaz de gerar tanto seqüências de erros em rajada quanto AWGN, além de propor um modelo de erros híbrido que considera a injeção de ambos os tipos de erros para simular o comportamento de um canal sem fio. O injetor de erros proposto é empregado em um estudo de caso referente à análise de desempenho do mecanismo de codificação de canal em redes que seguem o padrão IEEE 802.16, tanto nomádicas (fixas) quanto móveis. É avaliada a capacidade de correção dos codificadores Forward Error Correction (FEC), de emprego obrigatório de acordo com o referido padrão. Além disso, estuda-se o impacto causado pela aplicação de técnicas que consistem na adição de diversidade temporal à transmissão, em cenários cuja ocorrência dos erros é em rajada, e em cenários cujos erros são modelados de acordo com seqüências AWGN. Finalmente, realiza-se um estudo teórico sobre a vazão que pode ser atingida nos cenários nomádicos e móveis, além de uma discussão sobre os avanços tecnológicos trazidos pela multiplexação de canal baseada em Orthogonal Frequency Division Multiple Access (OFDMA), empregado em redes IEEE 802.16 móveis. / The demand for providing multimedia services is increasing the development of wireless networks. Therefore, an important issue is to guarantee correct transmissions over channels that are affected by time and frequency variant conditions caused by physical impairments that lead to the occurrence of errors during the transmission. These errors are basically of two types: burst errors and random errors, typically modeled as Additive White Gaussian Noise (AWGN). Simulating the behavior of wireless channels affected by physical impairments has been subject of several investigations in the past years. Nevertheless, part of the current researches does not consider the occurrence of both errors at the same time. This approach may lead to imprecisions on the results obtained through simulations. This work proposea an error sequence generator which is able of generating both burst and AWGN error models. Moreover, the proposed model can generate hybrid errors sequences composed of both error types simultaneously. The proposed error sequence generator is applied to a case study that aims to evaluate the performance of the channel encoder of nomadic (fixed) and mobile IEEE 802.16 networks. In this context, we evaluate the error correction capability of FEC encoders which are mandatory according to IEEE 802.16 standard. Furthermore, we study the impact caused by the application of time diversity techniques on the transmission, considering scenarios affected by burst errors and AWGN. We also present a study about the theoretical throughput that can be reached by nomadic and mobile technologies. Finally, we discuss the technological advances brought by Orthogonal Frequency Division Multiple Access (OFDMA) channel multiplexing technique, which is employed in IEEE 802.16 mobile networks.

A necessidade de suportar serviços multimídia impulsiona o desenvolvimento das redes sem fio. Com isso, torna-se importante fornecer confiabilidade na transmissão de dados em um ambiente sujeito a variações espaciais, temporais e de freqüência, causadas por fenômenos físicos que, geralmente, causam erros nos dados transmitidos. Esses erros são basicamente de dois tipos: erros em rajada e erros aleatórios (Additive White Gaussian Noise - AWGN). Simular o comportamento dos canais sem fio afetados por erros é objeto de pesquisa há diversos anos. Entretanto, grande parte das pesquisas não considera a aplicação dos dois tipos de erros simultaneamente, o que pode gerar imprecisões nos resultados das simulações. Sendo assim, este trabalho propõe um injetor capaz de gerar tanto seqüências de erros em rajada quanto AWGN, além de propor um modelo de erros híbrido que considera a injeção de ambos os tipos de erros para simular o comportamento de um canal sem fio. O injetor de erros proposto é empregado em um estudo de caso referente à análise de desempenho do mecanismo de codificação de canal em redes que seguem o padrão IEEE 802.16, tanto nomádicas (fixas) quanto móveis. É avaliada a capacidade de correção dos codificadores Forward Error Correction (FEC), de emprego obrigatório de acordo com o referido padrão. Além disso, estuda-se o impacto causado pela aplicação de técnicas que consistem na adição de diversidade temporal à transmissão, em cenários cuja ocorrência dos erros é em rajada, e em cenários cujos erros são modelados de acordo com seqüências AWGN. Finalmente, realiza-se um estudo teórico sobre a vazão que pode ser atingida nos cenários nomádicos e móveis, além de uma discussão sobre os avanços tecnológicos trazidos pela multiplexação de canal baseada em Orthogonal Frequency Division Multiple Access (OFDMA), empregado em redes IEEE 802.16 móveis. / The demand for providing multimedia services is increasing the development of wireless networks. Therefore, an important issue is to guarantee correct transmissions over channels that are affected by time and frequency variant conditions caused by physical impairments that lead to the occurrence of errors during the transmission. These errors are basically of two types: burst errors and random errors, typically modeled as Additive White Gaussian Noise (AWGN). Simulating the behavior of wireless channels affected by physical impairments has been subject of several investigations in the past years. Nevertheless, part of the current researches does not consider the occurrence of both errors at the same time. This approach may lead to imprecisions on the results obtained through simulations. This work proposea an error sequence generator which is able of generating both burst and AWGN error models. Moreover, the proposed model can generate hybrid errors sequences composed of both error types simultaneously. The proposed error sequence generator is applied to a case study that aims to evaluate the performance of the channel encoder of nomadic (fixed) and mobile IEEE 802.16 networks. In this context, we evaluate the error correction capability of FEC encoders which are mandatory according to IEEE 802.16 standard. Furthermore, we study the impact caused by the application of time diversity techniques on the transmission, considering scenarios affected by burst errors and AWGN. We also present a study about the theoretical throughput that can be reached by nomadic and mobile technologies. Finally, we discuss the technological advances brought by Orthogonal Frequency Division Multiple Access (OFDMA) channel multiplexing technique, which is employed in IEEE 802.16 mobile networks.

A necessidade de suportar serviços multimídia impulsiona o desenvolvimento das redes sem fio. Com isso, torna-se importante fornecer confiabilidade na transmissão de dados em um ambiente sujeito a variações espaciais, temporais e de freqüência, causadas por fenômenos físicos que, geralmente, causam erros nos dados transmitidos. Esses erros são basicamente de dois tipos: erros em rajada e erros aleatórios (Additive White Gaussian Noise - AWGN). Simular o comportamento dos canais sem fio afetados por erros é objeto de pesquisa há diversos anos. Entretanto, grande parte das pesquisas não considera a aplicação dos dois tipos de erros simultaneamente, o que pode gerar imprecisões nos resultados das simulações. Sendo assim, este trabalho propõe um injetor capaz de gerar tanto seqüências de erros em rajada quanto AWGN, além de propor um modelo de erros híbrido que considera a injeção de ambos os tipos de erros para simular o comportamento de um canal sem fio. O injetor de erros proposto é empregado em um estudo de caso referente à análise de desempenho do mecanismo de codificação de canal em redes que seguem o padrão IEEE 802.16, tanto nomádicas (fixas) quanto móveis. É avaliada a capacidade de correção dos codificadores Forward Error Correction (FEC), de emprego obrigatório de acordo com o referido padrão. Além disso, estuda-se o impacto causado pela aplicação de técnicas que consistem na adição de diversidade temporal à transmissão, em cenários cuja ocorrência dos erros é em rajada, e em cenários cujos erros são modelados de acordo com seqüências AWGN. Finalmente, realiza-se um estudo teórico sobre a vazão que pode ser atingida nos cenários nomádicos e móveis, além de uma discussão sobre os avanços tecnológicos trazidos pela multiplexação de canal baseada em Orthogonal Frequency Division Multiple Access (OFDMA), empregado em redes IEEE 802.16 móveis. / The demand for providing multimedia services is increasing the development of wireless networks. Therefore, an important issue is to guarantee correct transmissions over channels that are affected by time and frequency variant conditions caused by physical impairments that lead to the occurrence of errors during the transmission. These errors are basically of two types: burst errors and random errors, typically modeled as Additive White Gaussian Noise (AWGN). Simulating the behavior of wireless channels affected by physical impairments has been subject of several investigations in the past years. Nevertheless, part of the current researches does not consider the occurrence of both errors at the same time. This approach may lead to imprecisions on the results obtained through simulations. This work proposea an error sequence generator which is able of generating both burst and AWGN error models. Moreover, the proposed model can generate hybrid errors sequences composed of both error types simultaneously. The proposed error sequence generator is applied to a case study that aims to evaluate the performance of the channel encoder of nomadic (fixed) and mobile IEEE 802.16 networks. In this context, we evaluate the error correction capability of FEC encoders which are mandatory according to IEEE 802.16 standard. Furthermore, we study the impact caused by the application of time diversity techniques on the transmission, considering scenarios affected by burst errors and AWGN. We also present a study about the theoretical throughput that can be reached by nomadic and mobile technologies. Finally, we discuss the technological advances brought by Orthogonal Frequency Division Multiple Access (OFDMA) channel multiplexing technique, which is employed in IEEE 802.16 mobile networks.

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-07-30T19:06:38Z No. of bitstreams: 1 CAMILLA FALCONI CRISPIM - DISSERTAÇÃO PPGCC 2013..pdf: 21498692 bytes, checksum: 0ddcf6e67e912aaa0d984982e73f8e76 (MD5) / Made available in DSpace on 2018-07-30T19:06:38Z (GMT). No. of bitstreams: 1 CAMILLA FALCONI CRISPIM - DISSERTAÇÃO PPGCC 2013..pdf: 21498692 bytes, checksum: 0ddcf6e67e912aaa0d984982e73f8e76 (MD5) Previous issue date: 2013-03-15 / Manobras são executadas na rede elétrica para que não haja interrupção no fornecimento de energia, causada por eventos aleatórios, como falha ou sobrecarga de equipamentos; ou para a realização de manutenção preventiva nestes equipamentos. A geração de manobras é normalmente manual e a sua elaboração pode demorar de uma hora e a um dia, dependendo da sua complexidade e do número de equipamentos envolvidos. O pouco tempo para a geração das manobras, principalmente em situações de contingência, aumenta a probabilidade de ocorrência de erros nas manobras elaboradas. Os fatores relacionados à demora na geração, às falhas na análise dos efeitos da manobra na rede elétrica e à alta susceptibilidade de erros, podem afetar negativamente o sistema elétrico e a companhia elétrica, diminuindo a segurança no sistema e aumentando as perdas monetárias associadas principalmente à indisponibilidade de equipamentos e à interrupção do fornecimento de energia. Este trabalho propõe uma nova abordagem para a geração automática de manobras para sistemas eletroenergéticos. Esta abordagem tem as principais características de uma solução ideal para o problema: (i) se baseia na topologia de tempo real da rede elétrica; (ii) usa regras de intertravamento baseadas na configuração topológica da rede e nos princípios elétricos dos dispositivos, garantindo assim a segurança do sistema e do pessoal da companhia elétrica; e (iii) usa algoritmos genéricos que independem dos tipos de arranjos topológicos, bem como do número de equipamentos na subestação. Para verificar a corretude da solução no escopo de uma companhia elétrica real, as manobras geradas automaticamente são comparadas às manobras padrão elaboradas manualmente pelos operadores e/ou supervisores da Companhia Hidroelétrica do São Francisco (CHESF). Ao todo, mais de 1300 roteiros foram comparados. Para a liberação de disjuntor, o percentual de acerto foi de 91,1%; e para a normalização de disjuntor, o percentual de acerto foi de 90,4%. A mediana dos tempos de geração automática destas manobras foram de 14ms e 16ms para liberação e normalização de disjuntor, respectivamente. Estes tempos apontam ganho significativo no tempo gasto para a geração de uma manobra. A outra forma de validação da técnica proposta baseia-se em um sistema prova-de-conceito (SmartSwitch). Esse sistema se destina aos operadores e supervisores da CHESF. Um grupo selecionado de especialistas na geração de manobras é responsável pela avaliação da usabilidade do sistema SmartSwitch e da corretude das manobras geradas automaticamente. A avaliação inicial feita por este grupo mostra que a técnica é capaz de gerar, em situações normais de topologia, operações de seccionamento corretas e seguras do ponto de vista elétrico. Percebeu-se também alto nível de aceitação do sistema SmartSwitch por parte dos operadores e supervisores de operação da CHESF, o que prova a contribuição do sistema para a eficácia do processo de geração de manobras na companhia colaboradora. / Switching sequences executed in the electrical grid aim to prevent electric power provision interruptions, which may be caused by random events, such as equipment faults or overloads; or equipment maintenance. Switching sequence generation is usually manual, and can last between one hour and one day, according to the switching sequence complexity and the number of equipment involved. The limited time for switching sequence generation, especially in contingency circumstances, increases the probability of errors in the resulting switching sequences. Factors such as delay in switching sequence generation, failure in analyzing the switching sequence's effects on the electrical grid, and susceptibility to errors can negatively affect the electric system and the electric power company, decreasing system security, and increasing monetary losses mainly associated with equipment unavailability and electric power provision interruption. This study presents and evaluate a new approach for automatically generating switching sequences in electric substations; the proposal possesses the main characteristics to ideally solve the problem. The technique, for automatically generate switching sequences, (i) is based on the power grid's real-time topology; (ii) uses interlocking rules based on the grid's topological configuration in order to guarantee security for the system and for the workers; (iii) uses algorithms that are independent of the equipment's topological disposition and the substation's size. To verify the correctness of solution in the scope of a real electric company, the automatically generated switching sequences was compared to standard switching sequences made manually by CHESF operation supervisors or operators. In ali, more the 1300 scripts were compared. For switching sequences to release circuit breaker during maintenance periods, the percentage of correct switching sequence was 91,1%; and for switching sequence to restore circuit breaker, the percentage of correct switching sequence was 90,4%. The execution time was 14ms and 16ms, respectively. The second validation stage is based on proof-of-concept system, named SmartSwitch. The system is presented in this work and is intended to be used by CHESF operation supervisors and operators. A selected group of specialists in switching sequence generation is responsible for evaluating the system regarding its usability and correctness. The initial evaluation made by specialists group showed that technique is able to generate, in normal topology, correct and safe switching operations from electric point of view. Also, it was noticed that the tool has a high levei of acceptance by the company's operators and supervisors, due to its low maintenance needs.

Ce travail expose plusieurs études dans les domaines de la reconnaissance de la parole et compréhension du langage parlé. La compréhension sémantique du langage parlé est un sous-domaine important de l'intelligence artificielle. Le traitement de la parole intéresse depuis longtemps les chercheurs, puisque la parole est une des charactéristiques qui definit l'être humain. Avec le développement du réseau neuronal artificiel, le domaine a connu une évolution rapide à la fois en terme de précision et de perception humaine. Une autre étape importante a été franchie avec le développement d'approches bout en bout. De telles approches permettent une coadaptation de toutes les parties du modèle, ce qui augmente ainsi les performances, et ce qui simplifie la procédure d'entrainement. Les modèles de bout en bout sont devenus réalisables avec la quantité croissante de données disponibles, de ressources informatiques et, surtout, avec de nombreux développements architecturaux innovateurs. Néanmoins, les approches traditionnelles (qui ne sont pas bout en bout) sont toujours pertinentes pour le traitement de la parole en raison des données difficiles dans les environnements bruyants, de la parole avec un accent et de la grande variété de dialectes. Dans le premier travail, nous explorons la reconnaissance de la parole hybride dans des environnements bruyants. Nous proposons de traiter la reconnaissance de la parole, qui fonctionne dans un nouvel environnement composé de différents bruits inconnus, comme une tâche d'adaptation de domaine. Pour cela, nous utilisons la nouvelle technique à l'époque de l'adaptation du domaine antagoniste. En résumé, ces travaux antérieurs proposaient de former des caractéristiques de manière à ce qu'elles soient distinctives pour la tâche principale, mais non-distinctive pour la tâche secondaire. Cette tâche secondaire est conçue pour être la tâche de reconnaissance de domaine. Ainsi, les fonctionnalités entraînées sont invariantes vis-à-vis du domaine considéré. Dans notre travail, nous adoptons cette technique et la modifions pour la tâche de reconnaissance de la parole dans un environnement bruyant. Dans le second travail, nous développons une méthode générale pour la régularisation des réseaux génératif récurrents. Il est connu que les réseaux récurrents ont souvent des difficultés à rester sur le même chemin, lors de la production de sorties longues. Bien qu'il soit possible d'utiliser des réseaux bidirectionnels pour une meilleure traitement de séquences pour l'apprentissage des charactéristiques, qui n'est pas applicable au cas génératif. Nous avons développé un moyen d'améliorer la cohérence de la production de longues séquences avec des réseaux récurrents. Nous proposons un moyen de construire un modèle similaire à un réseau bidirectionnel. L'idée centrale est d'utiliser une perte L2 entre les réseaux récurrents génératifs vers l'avant et vers l'arrière. Nous fournissons une évaluation expérimentale sur une multitude de tâches et d'ensembles de données, y compris la reconnaissance vocale, le sous-titrage d'images et la modélisation du langage. Dans le troisième article, nous étudions la possibilité de développer un identificateur d'intention de bout en bout pour la compréhension du langage parlé. La compréhension sémantique du langage parlé est une étape importante vers le développement d'une intelligence artificielle de type humain. Nous avons vu que les approches de bout en bout montrent des performances élevées sur les tâches, y compris la traduction automatique et la reconnaissance de la parole. Nous nous inspirons des travaux antérieurs pour développer un système de bout en bout pour la reconnaissance de l'intention. / This work presents several studies in the areas of speech recognition and understanding. The semantic speech understanding is an important sub-domain of the broader field of artificial intelligence. Speech processing has had interest from the researchers for long time because language is one of the defining characteristics of a human being. With the development of neural networks, the domain has seen rapid progress both in terms of accuracy and human perception. Another important milestone was achieved with the development of end-to-end approaches. Such approaches allow co-adaptation of all the parts of the model thus increasing the performance, as well as simplifying the training procedure. End-to-end models became feasible with the increasing amount of available data, computational resources, and most importantly with many novel architectural developments. Nevertheless, traditional, non end-to-end, approaches are still relevant for speech processing due to challenging data in noisy environments, accented speech, and high variety of dialects. In the first work, we explore the hybrid speech recognition in noisy environments. We propose to treat the recognition in the unseen noise condition as the domain adaptation task. For this, we use the novel at the time technique of the adversarial domain adaptation. In the nutshell, this prior work proposed to train features in such a way that they are discriminative for the primary task, but non-discriminative for the secondary task. This secondary task is constructed to be the domain recognition task. Thus, the features trained are invariant towards the domain at hand. In our work, we adopt this technique and modify it for the task of noisy speech recognition. In the second work, we develop a general method for regularizing the generative recurrent networks. It is known that the recurrent networks frequently have difficulties staying on same track when generating long outputs. While it is possible to use bi-directional networks for better sequence aggregation for feature learning, it is not applicable for the generative case. We developed a way improve the consistency of generating long sequences with recurrent networks. We propose a way to construct a model similar to bi-directional network. The key insight is to use a soft L2 loss between the forward and the backward generative recurrent networks. We provide experimental evaluation on a multitude of tasks and datasets, including speech recognition, image captioning, and language modeling. In the third paper, we investigate the possibility of developing an end-to-end intent recognizer for spoken language understanding. The semantic spoken language understanding is an important step towards developing a human-like artificial intelligence. We have seen that the end-to-end approaches show high performance on the tasks including machine translation and speech recognition. We draw the inspiration from the prior works to develop an end-to-end system for intent recognition.