Reconhecimento de voz através de unidades menores do que a palavra, utilizando Wavelet Packet e SVM, em uma nova estrutura hierárquica de decisão

The automatic speech recognition by machine has been the target of researchers in the past five decades. In this period have been numerous advances, such as in the field of recognition of isolated words (commands), which has very high rates of recognition, currently. However, we are still far from developing a system that could have a performance similar to the human being (automatic continuous speech recognition). One of the great challenges of searches for continuous speech recognition is the large amount of pattern. The modern languages such as English, French, Spanish and Portuguese have approximately 500,000 words or patterns to be identified. The purpose of this study is to use smaller units than the word such as phonemes, syllables and difones units as the basis for the speech recognition, aiming to recognize any words without necessarily using them. The main goal is to reduce the restriction imposed by the excessive amount of patterns. In order to validate this proposal, the system was tested in the isolated word recognition in dependent-case. The phonemes characteristics of the Brazil s Portuguese language were used to developed the hierarchy decision system. These decisions are made through the use of neural networks SVM (Support Vector Machines). The main speech features used were obtained from the Wavelet Packet Transform. The descriptors MFCC (Mel-Frequency Cepstral Coefficient) are also used in this work. It was concluded that the method proposed in this work, showed good results in the steps of recognition of vowels, consonants (syllables) and words when compared with other existing methods in literature

Seleção seqüencial de descritores por análise da semântica para recuperação de imagens baseada no conteúdo

With the rapid growth of databases of various types (text, multimedia, etc..), There exist a need to propose methods for ordering, access and retrieve data in a simple and fast way. The images databases, in addition to these needs, require a representation of the images so that the semantic content characteristics are considered. Accordingly, several proposals such as the textual annotations based retrieval has been made. In the annotations approach, the recovery is based on the comparison between the textual description that a user can make of images and descriptions of the images stored in database. Among its drawbacks, it is noted that the textual description is very dependent on the observer, in addition to the computational effort required to describe all the images in database. Another approach is the content based image retrieval - CBIR, where each image is represented by low-level features such as: color, shape, texture, etc. In this sense, the results in the area of CBIR has been very promising. However, the representation of the images semantic by low-level features is an open problem. New algorithms for the extraction of features as well as new methods of indexing have been proposed in the literature. However, these algorithms become increasingly complex. So, doing an analysis, it is natural to ask whether there is a relationship between semantics and low-level features extracted in an image? and if there is a relationship, which descriptors better represent the semantic? which leads us to a new question: how to use descriptors to represent the content of the images?. The work presented in this thesis, proposes a method to analyze the relationship between low-level descriptors and semantics in an attempt to answer the questions before. Still, it was observed that there are three possibilities of indexing images: Using composed characteristic vectors, using parallel and independent index structures (for each descriptor or set of them) and using characteristic vectors sorted in sequential order. Thus, the first two forms have been widely studied and applied in literature, but there were no records of the third way has even been explored. So this thesis also proposes to index using a sequential structure of descriptors and also the order of these descriptors should be based on the relationship that exists between each descriptor and semantics of the users. Finally, the proposed index in this thesis revealed better than the traditional approachs and yet, was showed experimentally that the order in this sequence is important and there is a direct relationship between this order and the relationship of low-level descriptors with the semantics of the users

Análise de Agrupamentos Com Base na Teoria da Informação: Uma Abordagem Representativa

Currently, one of the biggest challenges for the field of data mining is to perform cluster analysis on complex data. Several techniques have been proposed but, in general, they can only achieve good results within specific areas providing no consensus of what would be the best way to group this kind of data. In general, these techniques fail due to non-realistic assumptions about the true probability distribution of the data. Based on this, this thesis proposes a new measure based on Cross Information Potential that uses representative points of the dataset and statistics extracted directly from data to measure the interaction between groups. The proposed approach allows us to use all advantages of this information-theoretic descriptor and solves the limitations imposed on it by its own nature. From this, two cost functions and three algorithms have been proposed to perform cluster analysis. As the use of Information Theory captures the relationship between different patterns, regardless of assumptions about the nature of this relationship, the proposed approach was able to achieve a better performance than the main algorithms in literature. These results apply to the context of synthetic data designed to test the algorithms in specific situations and to real data extracted from problems of different fields

Estimação de componentes de co-variância para pesos corporais do nascimento aos 365 dias de idade de bovinos Guzerá empregando-se modelos de regressão aleatória

Um total de 19.770 pesos corporais de bovinos Guzerá, do nascimento aos 365 dias de idade, pertencentes ao banco de dados da Associação Brasileira dos Criadores de Zebu (ABCZ) foi analisado com os objetivos de comparar diferentes estruturas de variâncias residuais, considerando 1, 18, 28 e 53 classes residuais e funções de variância de ordens quadrática a quíntica; e estimar funções de co-variância de diferentes ordens para os efeitos genético aditivo direto, genético materno, de ambiente permanente de animal e de mãe e parâmetros genéticos para os pesos corporais usando modelos de regressão aleatória. Os efeitos aleatórios foram modelados por regressões polinomiais em escala de Legendre com ordens variando de linear a quártica. Os modelos foram comparados pelo teste de razão de verossimilhança e pelos critérios de Informação de Akaike e de Informação Bayesiano de Schwarz. O modelo com 18 classes heterogêneas foi o que melhor se ajustou às variâncias residuais, de acordo com os testes estatísticos, porém, o modelo com função de variância de quinta ordem também mostrou-se apropriado. Os valores de herdabilidade direta estimados foram maiores que os encontrados na literatura, variando de 0,04 a 0,53, mas seguiram a mesma tendência dos estimados pelas análises unicaracterísticas. A seleção para peso em qualquer idade melhoraria o peso em todas as idades no intervalo estudado.

Identificação não linear usando uma rede fuzzy wavelet neural network modificada

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Caracterização numérica de antenas para aplicações RFID utilizando o método das ondas - WCIP

In recent years, the radio frequency identification technology (RFID) has gained great interest both industrial communities as scientific communities. Its ability to locate and monitor objects, animals and persons with active or passive tags allows easy development, with good cost-benefice and still presents undeniable benefits in applications ranging from logistics to healthcare, robotics, security, among others. Within this aspect what else comes excelling are RFID tags and the antennas used in RFID readers. Most tags have antennas omnidirectional and are usually manufactured as dipoles modified printed. The primary purpose of a project of antenna for tag is to achieve the required input impedance to perform a good marriage impedance with the load impedance of the chip. Already the objective principal in project of antennas for readers is to achieve reduced sizes and structures with good data transmission capacity. This work brings the numerical characterization of antennas for RFID applications, being these divided into tags RFID and antennas for RFID readers. Three tags RFID and two antennas for RFID readers, found in literature, are analyzed. The analysis of these structures is made using the Method of Waves - WCIP. Initial results found in the literature are compared with those obtained through simulations in WCIP with objective to show that the Method of Waves is able to analyze such structures. To illustrate the results obtained in simulations is presented the behavior of electric and magnetic fields. It also performed a literature review on the characteristics and principles of RFID technology. Suggestions for continuity to this work are presented

Balanço energético comparativo para rotas de escoamento de soja

O presente trabalho objetivou analisar o fluxo energético no escoamento de soja da região Centro-Oeste do Brasil, considerando as rotas atualmente existentes, mais precisamente, do município de Rio Verde -GO até o porto de Santos - SP, visto que este é um grande polo exportador de granéis sólidos. Foram selecionadas duas rotas para a análise, uma contemplando a multimodalidade, ou seja, os modais rodoviário, ferroviário e hidroviário, e outra, uma única modalidade, o modal rodoviário. A conversão dos fatores físicos e operacionais em unidades energéticas foi realizada por meio de coeficientes energéticos levantados junto à literatura. Os resultados obtidos indicaram, pela rota 1 multimodal, um gasto energético específico maior para o modal rodoviário (0,50 MJ km-1 t-1), seguido pelo modal ferroviário (0,42 MJ km-1 t-1) e, em terceiro, o modal hidroviário (0,22 MJ km-1 t-1). Pela rota 2, unimodal rodoviário, o resultado indicou 0,50 MJ km-1 t-1. Nas participações de energia apresentadas, comparando as rotas 1 e 2, a que apresentou maior gasto energético específico total foi a rota 2 (0,50 MJ km-1 t-1), seguida pela rota 1 (0,34 MJ km-1 t-1).