In this thesis, we consider a robust state estimation problem for discrete-time, homogeneous, first-order, finite-state finite-alphabet hidden Markov models (HMMs). Based on Kolmogorov's Theorem on the existence of a process, we first present the Kolmogorov model for the HMMs under consideration. A new change of measure is introduced. The statistical properties of the Kolmogorov representation of an HMM are discussed on the canonical probability space. A special Kolmogorov measure is constructed. Meanwhile, the ergodicity of two expanded Markov chains is investigated. In order to describe the uncertainty of HMMs, we study probability distance problems based on the Kolmogorov model of HMMs. Using a change of measure technique, the relative entropy and the relative entropy rate as probability distances between HMMs, are given in terms of the HMM parameters. Also, we obtain a new expression for a probability distance considered in the existing literature such that we can use an information state method to calculate it. Furthermore, we introduce regular conditional relative entropy as an a posteriori probability distance to measure the discrepancy between HMMs when a realized observation sequence is given. A representation of the regular conditional relative entropy is derived based on the Radon-Nikodym derivative. Then a recursion for the regular conditional relative entropy is obtained using an information state method. Meanwhile, the well-known duality relationship between free energy and relative entropy is extended to the case of regular conditional relative entropy given a sub-[special character]-algebra. Finally, regular conditional relative entropy constraints are defined based on the study of the probability distance problem. Using a Lagrange multiplier technique and the duality relationship for regular conditional relative entropy, a finite horizon robust state estimator for HMMs with regular conditional relative entropy constraints is derived. A complete characterization of the solution to the robust state estimation problem is also presented.

In this thesis, we consider a robust state estimation problem for discrete-time, homogeneous, first-order, finite-state finite-alphabet hidden Markov models (HMMs). Based on Kolmogorov's Theorem on the existence of a process, we first present the Kolmogorov model for the HMMs under consideration. A new change of measure is introduced. The statistical properties of the Kolmogorov representation of an HMM are discussed on the canonical probability space. A special Kolmogorov measure is constructed. Meanwhile, the ergodicity of two expanded Markov chains is investigated. In order to describe the uncertainty of HMMs, we study probability distance problems based on the Kolmogorov model of HMMs. Using a change of measure technique, the relative entropy and the relative entropy rate as probability distances between HMMs, are given in terms of the HMM parameters. Also, we obtain a new expression for a probability distance considered in the existing literature such that we can use an information state method to calculate it. Furthermore, we introduce regular conditional relative entropy as an a posteriori probability distance to measure the discrepancy between HMMs when a realized observation sequence is given. A representation of the regular conditional relative entropy is derived based on the Radon-Nikodym derivative. Then a recursion for the regular conditional relative entropy is obtained using an information state method. Meanwhile, the well-known duality relationship between free energy and relative entropy is extended to the case of regular conditional relative entropy given a sub-[special character]-algebra. Finally, regular conditional relative entropy constraints are defined based on the study of the probability distance problem. Using a Lagrange multiplier technique and the duality relationship for regular conditional relative entropy, a finite horizon robust state estimator for HMMs with regular conditional relative entropy constraints is derived. A complete characterization of the solution to the robust state estimation problem is also presented.

Submitted by Jos? Henrique Henrique (jose.neves@ufvjm.edu.br) on 2017-05-09T18:11:27Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) edson_batista_sena.pdf: 2251476 bytes, checksum: 028f563476a851ba89cf53a932fe2ba7 (MD5) / Approved for entry into archive by Rodrigo Martins Cruz (rodrigo.cruz@ufvjm.edu.br) on 2017-05-16T18:51:42Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) edson_batista_sena.pdf: 2251476 bytes, checksum: 028f563476a851ba89cf53a932fe2ba7 (MD5) / Made available in DSpace on 2017-05-16T18:51:42Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) edson_batista_sena.pdf: 2251476 bytes, checksum: 028f563476a851ba89cf53a932fe2ba7 (MD5) Previous issue date: 2016 / Um dos grandes desafios dos dias atuais no desenvolvimento de tecnologias computacionais aplicadas ao processo educacional ? produzir solu??es que sejam capazes de atender corretamente ao processo de ensino e aprendizagem, al?m de definir a forma mais adequada de incorporar esses mecanismos no ambiente escolar. Esta inser??o deve ocorrer de forma que alunos e professores aproveitem ao m?ximo esses instrumentos, e passem a utiliz?-los com o intuito de agregar mais valor aos processos de ensino e aprendizagem. Para que isso ocorra, ? fundamental que os ambientes virtuais forne?am conte?do adequado, objetos de aprendizagem atraentes, al?m de serem din?micos e altamente adapt?veis ?s necessidades e interesses dos estudantes durante as sess?es de aprendizagem, visando a melhoria cont?nua do processo educacional para professores, tutores e estudantes. O presente trabalho tem como objetivo principal apresentar um modelo computacional probabil?stico, que pode ser incorporado ?s estruturas dos ambientes virtuais de aprendizagem, a fim de auxiliar no processo de detec??o autom?tica das tend?ncias e prefer?ncias dos estilos de aprendizagem do estudante, utilizando uma combina??o do modelo proposto por Felder e Silverman para estilos de aprendizagem, o FSLSM, com as t?cnicas de infer?ncia probabil?stica dos modelos ocultos de Markov (HMM). Para a valida??o do modelo, foram realizados experimentos em um simulador computacional capaz de reproduzir parcialmente o processo de intera??o do estudante com o ambiente virtual de aprendizagem, realizando um processo de infer?ncia com base no comportamento do estudante, ao qual foi utilizado o algoritmo de Viterbi para este prop?sito. Ao final, os resultados dos experimentos s?o apresentados e demonstraram um elevado grau de precis?o no processo de infer?ncia do estilo de aprendizagem probabil?stico. / Disserta??o (Mestrado Profissional) ? Programa de P?s-Gradua??o em Educa??o, Universidade Federal dos Vales do Jequitinhonha e Mucuri, 2016. / The great challenges of the present day in the development of computer technologies in educational process is to produce solutions that are able to respond properly to the teaching and learning methods, and define the most appropriate way to incorporate these mechanisms at school. This integration should take place so that students and teachers make the most of these instruments, and start to use them in order to add more value to teaching and learning processes. For this to happen, it is critical that virtual environments provide appropriate content, appealing learning objects, and are dynamic and highly adaptable to the needs and interests of students during the learning sessions, aimed at continuous improvement of the educational process for teachers, tutors and student. This study aims to present a probabilistic computational model, which can be incorporated into the structures of virtual learning environments, auxiliary order in the automatic detection process of the trends and preferences of student learning styles using a combination of the proposed model by Felder and Silverman to learning styles the FSLSM, with the probabilistic inference techniques of hidden Markov models (HMM). To validate the model, experiments were performed on a computer simulator able to partially reproduce the student interaction process with the virtual learning environment, making an inference process based on the student?s behavior, where we used the Viterbi algorithm to this purpose. At the end, the results of the experiments are presented and demonstrated a high degree precision in the process of inference of probabilistic learning style.

Orientador: Fábio Violaro / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-22T07:58:43Z (GMT). No. of bitstreams: 1 Carvalho_SarahNegreirosde_M.pdf: 2350561 bytes, checksum: 950d33430acbd816700ef5de4c78fa5d (MD5) Previous issue date: 2013 / Resumo: Com o contínuo desenvolvimento da tecnologia, há uma demanda crescente por sistemas de síntese de fala que sejam capazes de falar como humanos, para integrá-los nas mais diversas aplicações, seja no âmbito da automação robótica, sejam para acessibilidade de pessoas com deficiências, seja em aplicativos destinados a cultura e lazer. A síntese de fala baseada em modelos ocultos de Markov (HMM) mostra-se promissora em suprir esta necessidade tecnológica. A sua natureza estatística e paramétrica a tornam um sistema flexível, capaz de adaptar vozes artificiais, inserir emoções no discurso e obter fala sintética de boa qualidade usando uma base de treinamento limitada. Esta dissertação apresenta o estudo realizado sobre o sistema de síntese de fala baseado em HMM (HTS), descrevendo as etapas que envolvem o treinamento dos modelos HMMs e a geração do sinal de fala. São apresentados os modelos espectrais, de pitch e de duração que constituem estes modelos HMM dos fonemas dependentes de contexto, considerando as diversas técnicas de estruturação deles. Alguns dos problemas encontrados no HTS, tais como a característica abafada e monótona da fala artificial, são analisados juntamente com algumas técnicas propostas para aprimorar a qualidade final do sinal de fala sintetizado / Abstract: With the continuous development of technology, there is a growing demand for text-to-speech systems that are able to speak like humans, in order to integrate them in the most diverse applications whether in the field of automation and robotics, or for accessibility of people with disabilities, as for culture and leisure activities. Speech synthesis based on hidden Markov models (HMM) shows to be promising in addressing this need. Their statistical and parametric nature make it a flexible system capable of adapting artificial voices, insert emotions in speech and get artificial speech of good quality using a limited amount of speech data for HMM training. This thesis presents the study realized on HMM-based speech synthesis system (HTS), describing the steps that involve the training of HMM models and the artificial speech generation. Spectral, pitch and duration models are presented, which form context-dependent HMM models, and also are considered the various techniques for structuring them. Some of the problems encountered in the HTS, such as the characteristic muffled and monotone of artificial speech, are analyzed along with some of the proposed techniques to improve the final quality of the synthesized speech signal / Mestrado / Telecomunicações e Telemática / Mestra em Engenharia Elétrica

Speech is intuitive, fast and easy to generate, but it is hard to index and easy to forget. What is more, listening to speech is slow. Text is easier to store, process and consume, both for computers and for humans, but writing text is slow and requires some intention. In this thesis, we study speech recognition which allows converting speech into text, making it easier both to create and to use information. Our tool of study is Hidden Markov Models which is one of the most important machine learning models in speech and language processing. The aim of this thesis is to do a rst study in Hidden Markov Models and understand their importance, particularly in speech recognition. We will go through three fundamental problems that come up naturally with Hidden Markov Models: to compute a likelihood of an observation sequence, to nd an optimal state sequence given an observation sequence and the model, and to adjust the model parameters. A solution to each problem will be given together with an example and the corresponding simulations using MatLab. The main importance lies in the last example, in which a rst approach to speech recognition will be done.

The essay presents the basic characteristics of human speech recognition, describes systems for the detection of key words and further deals with the proposal of each decoder blocks divided into three chapters. The first one describes the operations that are performed before the signal distribution of the framework and the segmentation. The second chapter describes the calculation of short-term energy, the number of zero passes and self-correlative, prediction and Mel-frequency cepstral coefficients. The third chapter, which describes the design of the block decoder, describes the method of dynamic time destruction and the method based on hidden Markov model. The final part of the essay describes decoders working with a speech and a proposal for a simple decoder working with isolated words, which was based issued and tested based on the preceding chapters.

Prediction and searching for homologous protein sequences is one of important tasks which are currently being addressed in the area of bioinformatics. According to the determination of homologous sequences of unknown protein sequence it is often possible to determine its structure and function in the organism. For searching homologous sequences, the most frequently used tools are based on direct sequence comparison, profile comparison or on the use of hidden Markov models. There is no universal method better than all others. To satisfy user`s request on needed sequence identity between domains and error rate between founded true positive and false positive pairs, the selection of proper method and its settings is needed. This work is focused to create tool which will help user to choose the best method and its settings according to his requirements. It was created on the basis of the analysis of method results with different settings. In addition, the implemented  application offers the possibility to run this method and show its results.

Protein p53 which is encoded by gene TP53 plays crucial role in cell cycle as a regulator of transcription of genes in cases when cell is under stress. Therefore p53 acts like tumor suppressor. Understanding the pathway of p53 regulation as well as predicting its binding sites on p53 regulated genes is one of the major concerns of modern research in genetics and bioinformatics. In first part of this project we aim to introduce basics from molecular biology to better understand the p53 protein pathway in gene transcription and introduction to analysis of prediction of p53 binding sites. Second part is about implementation and testing of tool which would be able to predict transcription factor binding sites for protein p53.

The goal of this master's thesis is to design and implement a system for recognition of home appliances based on their power consumption characteristics. This system should identify the individual home appliances from measurements of the total household consumption. The acquired data could be used for statistics of usage of a particular appliance and subsequent detection of errors or non-standard behavior of the measured device. An important part of my work is a design and hardware implementation of a unit for measuring and a system for processing the measured signal. The first version of my project uses pulse output of an electrometer to measure the energy. This method does not provide a sufficient sample rate but it's a quick way to obtain data for processing and analysis. The second version monitors the power consumption with a multi-purpose AC converter which measures active and reactive power with the desired sample rate. The data is then processed and recognized by two classifiers - HMM and KNN.

South Africa is currently struggling to deal with a significant poaching and livestock theft problem. This work is concerned with the detection and classification of ground based targets using radar micro- Doppler signatures to aid in the monitoring of borders, nature reserves and farmlands. The research starts of by investigating the state of the art of ground target classification. Different radar systems are investigated with respect to their ability to classify targets at different operating frequencies. Finally, a Gaussian Mixture Model Hidden Markov Model based (GMM-HMM) classification approach is presented and tested in an operational environment. The GMM-HMM method is compared to methods in the literature and is shown to achieve reasonable (up to 95%) classification accuracy, marginally outperforming existing ground target classification methods. / Dissertation (MEng)--University of Pretoria, 2017. / Electrical, Electronic and Computer Engineering / MEng / Unrestricted