Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Em uma grande gama de problemas físicos, governados por equações diferenciais, muitas vezes é de interesse obter-se soluções para o regime transiente e, portanto, deve-se empregar técnicas de integração temporal. Uma primeira possibilidade seria a de aplicar-se métodos explícitos, devido à sua simplicidade e eficiência computacional. Entretanto, esses métodos frequentemente são somente condicionalmente estáveis e estão sujeitos a severas restrições na escolha do passo no tempo. Para problemas advectivos, governados por equações hiperbólicas, esta restrição é conhecida como a condição de Courant-Friedrichs-Lewy (CFL). Quando temse a necessidade de obter soluções numéricas para grandes períodos de tempo, ou quando o custo computacional a cada passo é elevado, esta condição torna-se um empecilho. A fim de contornar esta restrição, métodos implícitos, que são geralmente incondicionalmente estáveis, são utilizados. Neste trabalho, foram aplicadas algumas formulações implícitas para a integração temporal no método Smoothed Particle Hydrodynamics (SPH) de modo a possibilitar o uso de maiores incrementos de tempo e uma forte estabilidade no processo de marcha temporal. Devido ao alto custo computacional exigido pela busca das partículas a cada passo no tempo, esta implementação só será viável se forem aplicados algoritmos eficientes para o tipo de estrutura matricial considerada, tais como os métodos do subespaço de Krylov. Portanto, fez-se um estudo para a escolha apropriada dos métodos que mais se adequavam a este problema, sendo os escolhidos os métodos Bi-Conjugate Gradient (BiCG), o Bi-Conjugate Gradient Stabilized (BiCGSTAB) e o Quasi-Minimal Residual (QMR). Alguns problemas testes foram utilizados a fim de validar as soluções numéricas obtidas com a versão implícita do método SPH. / In a wide range of physical problems governed by differential equations, it is often of interest to obtain solutions for the unsteady state and therefore it must be employed temporal integration techniques. One possibility could be the use of an explicit methods due to its simplicity and computational efficiency. However, these methods are often only conditionally stable and are subject to severe restrictions for the time step choice. For advective problems governed by hyperbolic equations, this restriction is known as the Courant-Friedrichs-Lewy (CFL) condition. When there is the need to obtain numerical solutions for long periods of time, or when the computational cost for each time step is high, this condition becomes a handicap. In order to overcome this restriction implicit methods can be used, which are generally unconditionally stable. In this study, some implicit formulations for time integration are used in the Smoothed Particle Hydrodynamics (SPH) method to enable the use of larger time increments and obtain a strong stability in the time evolution process. Due to the high computational cost required by the particles tracking at each time step, the implementation will be feasible only if efficient algorithms were applied for this type of matrix structure such as Krylov subspace methods. Therefore, we carried out a study for the appropriate choice of methods best suited to this problem, and the methods chosen were the Bi-Conjugate Gradient (BiCG), the Bi-Conjugate Gradient Stabilized (BiCGSTAB) and the Quasi-Minimal Residual(QMR). Some test problems were used to validate the numerical solutions obtained with the implicit version of the SPH method.

Dans cette thèse, nous proposons plusieurs nouvelles techniques pour la classification d'images hyperspectrales basées sur l'apprentissage d'ensemble. Le cadre proposé introduit des innovations importantes par rapport aux approches précédentes dans le même domaine, dont beaucoup sont basées principalement sur un algorithme individuel. Tout d'abord, nous proposons d'utiliser la Forêt de Rotation (Rotation Forest) avec différentes techiniques d'extraction de caractéristiques linéaire et nous comparons nos méthodes avec les approches d'ensemble traditionnelles, tels que Bagging, Boosting, Sous-espace Aléatoire et Forêts Aléatoires. Ensuite, l'intégration des machines à vecteurs de support (SVM) avec le cadre de sous-espace de rotation pour la classification de contexte est étudiée. SVM et sous-espace de rotation sont deux outils puissants pour la classification des données de grande dimension. C'est pourquoi, la combinaison de ces deux méthodes peut améliorer les performances de classification. Puis, nous étendons le travail de la Forêt de Rotation en intégrant la technique d'extraction de caractéristiques locales et l'information contextuelle spatiale avec un champ de Markov aléatoire (MRF) pour concevoir des méthodes spatio-spectrale robustes. Enfin, nous présentons un nouveau cadre général, ensemble de sous-espace aléatoire, pour former une série de classifieurs efficaces, y compris les arbres de décision et la machine d'apprentissage extrême (ELM), avec des profils multi-attributs étendus (EMaPS) pour la classification des données hyperspectrales. Six méthodes d'ensemble de sous-espace aléatoire, y compris les sous-espaces aléatoires avec les arbres de décision, Forêts Aléatoires (RF), la Forêt de Rotation (RoF), la Forêt de Rotation Aléatoires (Rorf), RS avec ELM (RSELM) et sous-espace de rotation avec ELM (RoELM), sont construits par multiples apprenants de base. L'efficacité des techniques proposées est illustrée par la comparaison avec des méthodes de l'état de l'art en utilisant des données hyperspectrales réelles dans de contextes différents. / In this thesis, we propose several new techniques for the classification of hyperspectral remote sensing images based on multiple classifier system (MCS). Our proposed framework introduces significant innovations with regards to previous approaches in the same field, many of which are mainly based on an individual algorithm. First, we propose to use Rotation Forests with several linear feature extraction and compared them with the traditional ensemble approaches, such as Bagging, Boosting, Random subspace and Random Forest. Second, the integration of the support vector machines (SVM) with Rotation subspace framework for context classification is investigated. SVM and Rotation subspace are two powerful tools for high-dimensional data classification. Therefore, combining them can further improve the classification performance. Third, we extend the work of Rotation Forests by incorporating local feature extraction technique and spatial contextual information with Markov random Field (MRF) to design robust spatial-spectral methods. Finally, we presented a new general framework, Random subspace ensemble, to train series of effective classifiers, including decision trees and extreme learning machine (ELM), with extended multi-attribute profiles (EMAPs) for classifying hyperspectral data. Six RS ensemble methods, including Random subspace with DT (RSDT), Random Forest (RF), Rotation Forest (RoF), Rotation Random Forest (RoRF), RS with ELM (RSELM) and Rotation subspace with ELM (RoELM), are constructed by the multiple base learners. The effectiveness of the proposed techniques is illustrated by comparing with state-of-the-art methods by using real hyperspectral data sets with different contexts.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Em uma grande gama de problemas físicos, governados por equações diferenciais, muitas vezes é de interesse obter-se soluções para o regime transiente e, portanto, deve-se empregar técnicas de integração temporal. Uma primeira possibilidade seria a de aplicar-se métodos explícitos, devido à sua simplicidade e eficiência computacional. Entretanto, esses métodos frequentemente são somente condicionalmente estáveis e estão sujeitos a severas restrições na escolha do passo no tempo. Para problemas advectivos, governados por equações hiperbólicas, esta restrição é conhecida como a condição de Courant-Friedrichs-Lewy (CFL). Quando temse a necessidade de obter soluções numéricas para grandes períodos de tempo, ou quando o custo computacional a cada passo é elevado, esta condição torna-se um empecilho. A fim de contornar esta restrição, métodos implícitos, que são geralmente incondicionalmente estáveis, são utilizados. Neste trabalho, foram aplicadas algumas formulações implícitas para a integração temporal no método Smoothed Particle Hydrodynamics (SPH) de modo a possibilitar o uso de maiores incrementos de tempo e uma forte estabilidade no processo de marcha temporal. Devido ao alto custo computacional exigido pela busca das partículas a cada passo no tempo, esta implementação só será viável se forem aplicados algoritmos eficientes para o tipo de estrutura matricial considerada, tais como os métodos do subespaço de Krylov. Portanto, fez-se um estudo para a escolha apropriada dos métodos que mais se adequavam a este problema, sendo os escolhidos os métodos Bi-Conjugate Gradient (BiCG), o Bi-Conjugate Gradient Stabilized (BiCGSTAB) e o Quasi-Minimal Residual (QMR). Alguns problemas testes foram utilizados a fim de validar as soluções numéricas obtidas com a versão implícita do método SPH. / In a wide range of physical problems governed by differential equations, it is often of interest to obtain solutions for the unsteady state and therefore it must be employed temporal integration techniques. One possibility could be the use of an explicit methods due to its simplicity and computational efficiency. However, these methods are often only conditionally stable and are subject to severe restrictions for the time step choice. For advective problems governed by hyperbolic equations, this restriction is known as the Courant-Friedrichs-Lewy (CFL) condition. When there is the need to obtain numerical solutions for long periods of time, or when the computational cost for each time step is high, this condition becomes a handicap. In order to overcome this restriction implicit methods can be used, which are generally unconditionally stable. In this study, some implicit formulations for time integration are used in the Smoothed Particle Hydrodynamics (SPH) method to enable the use of larger time increments and obtain a strong stability in the time evolution process. Due to the high computational cost required by the particles tracking at each time step, the implementation will be feasible only if efficient algorithms were applied for this type of matrix structure such as Krylov subspace methods. Therefore, we carried out a study for the appropriate choice of methods best suited to this problem, and the methods chosen were the Bi-Conjugate Gradient (BiCG), the Bi-Conjugate Gradient Stabilized (BiCGSTAB) and the Quasi-Minimal Residual(QMR). Some test problems were used to validate the numerical solutions obtained with the implicit version of the SPH method.

Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2017-04-24T15:04:03Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) mapas-auto-organizaveis2.pdf: 2835656 bytes, checksum: 8836a86bd2cced9353cb25b53383b305 (MD5) / Made available in DSpace on 2017-04-24T15:04:03Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) mapas-auto-organizaveis2.pdf: 2835656 bytes, checksum: 8836a86bd2cced9353cb25b53383b305 (MD5) Previous issue date: 2016-08-16 / Métodos e algoritmos em aprendizado de máquina não supervisionado têm sido empregados em diversos problemas significativos. Uma explosão na disponibilidade de dados de várias fontes e modalidades está correlacionada com os avanços na obtenção, compressão, armazenamento, transferência e processamento de grandes quantidades de dados complexos com alta dimensionalidade, como imagens digitais, vídeos de vigilância e microarranjos de DNA. O agrupamento se torna difícil devido à crescente dispersão desses dados, bem como a dificuldade crescente em discriminar distâncias entre os pontos de dados. Este trabalho apresenta um algoritmo de agrupamento suave em subespaços baseado em um mapa auto-organizável (SOM) com estrutura variante no tempo, o que significa que o agrupamento dos dados pode ser alcançado sem qualquer conhecimento prévio, tais como o número de categorias ou a topologia dos padrões de entrada, nos quais ambos são determinados durante o processo de treinamento. O modelo também atribui diferentes pesos a diferentes dimensões, o que implica que cada dimensão contribui para o descobrimento dos aglomerados de dados. Para validar o modelo, diversos conjuntos de dados reais foram utilizados, considerando uma diversificada gama de contextos, tais como mineração de dados, expressão genética, agrupamento multivista e problemas de visão computacional. Os resultados são promissores e conseguem lidar com dados reais caracterizados pela alta dimensionalidade. / Unsupervised learning methods have been employed on many significant problems. A blast in the availability of data from multiple sources and modalities is correlated with advancements in how to obtain, compress, store, transfer, and process large amounts of complex high-dimensional data, such as digital images, surveillance videos, and DNA microarrays. Clustering becomes challenging due to the increasing sparsity of such data, as well as the increasing difficulty in discriminating distances between data points. This work presents a soft subspace clustering algorithm based on a self-organizing map (SOM) with time-variant structure, meaning that clustering data can be achieved without any prior knowledge such as the number of categories or input data topology, in which both are determined during the training process. The model also assigns different weights to different dimensions, this implies that every dimension contributes to uncover clusters. To validate the model, we used a number of real-world data sets, considering a diverse range of contexts such as data mining, gene expression, multi-view and computer vision problems. The promising results can handle real-world data characterized by high dimensionality.

Cette thèse examine quelques approches aux équations diophantiennes, en particulier les connexions entre l’analyse diophantienne et la théorie des corps cyclotomiques.Tout d’abord, nous proposons une introduction très sommaire et rapide aux méthodes d’analyse diophantienne que nous avons utilisées dans notre travail de recherche. Nous rappelons la notion de hauteur et présentons le PGCD logarithmique.Ensuite, nous attaquons une conjecture, formulée par Skolem en 1937, sur une équation diophantienne exponentielle. Pour cette conjecture, soit K un corps de nombres, α1 ,…, αm , λ1 ,…, λm des éléments non-nuls de K, et S un ensemble fini de places de K (qui contient toutes les places infinies), de telle sorte que l’anneau de S-entiers OS = OK,S = {α ∈ K : |α|v ≤ 1 pour les places v ∈/ S}contienne α1 , . . . , αm , λ1 , . . . , λm α1-1 , . . . , αm-1. Pour chaque n ∈ Z, soit A(n)=λ_1 α_1^n+⋯+λ_m α_m^n∈O_S. Skolem a suggéré [SK1] :Conjecture (principe local-global exponentiel). Supposons que pour chaque idéal non-nul a de l’anneau O_S, il existe n ∈ Z tel que A(n) ≡0 mod a. Alors, il existe n ∈ Z tel que A(n)=0.Soit Γ le groupe multiplicatif engendré par α1 ,…, αm. Alors Γ est le produit d’un groupe abélien fini et d’un groupe libre de rang fini. Nous démontrons que cette conjecture est vraie lorsque le rang de Γ est un.Après cela, nous généralisons un résultat précédent de Mourad Abouzaid ([A]). Soit F (X,Y) ∈ Q[X,Y] un Q-polynôme irréductible. En 2008, Mourad Abouzaid [A] a démontré le théorème suivant:Théorème (Abouzaid). Supposons que (0,0) soit un point non-singulier de la courbe plane F(X,Y) = 0. Soit m = degX F, n = degY F, M = max{m, n}. Soit ε tel que 0 < ε < 1. Alors, pour toute solution (α, β) ∈ Q ̅2 de F(X,Y) = 0, nous avons soit max{h(α), h(β)} ≤ 56M8ε−2hp(F) + 420M10ε−2 log(4M),soitmax{|h(α) − nlgcd(α, β)|,|h(β) − mlgcd(α, β)|} ≤ εmax{h(α), h(β)}++ 742M7ε−1hp(F) + 5762M9ε−1log(2m + 2n)Cependant, il a imposé la condition que (0,0) soit un point non-singulier de la courbe plane F(X,Y) = 0. En utilisant des versions quelque peu différentes du lemme “absolu” de Siegel et du lemme d’Eisenstein, nous avons pu lever la condition et démontrer le théorème de façon générale. Nous démontrons le théorème suivant:Théorème. Soit F(X,Y) ∈ Q ̅[X,Y] un polynôme absolument irréductible qui satisfasse F(0,0)=0. Soit m=degX F, n=degY F et r = min{i+j:(∂^(i+j) F)/(∂^i X∂^j Y)(0,0)≠0}. Soit ε tel que 0 < ε < 1. Alors, pour tout (α, β) ∈ Q ̅2 tel que F(α,β) = 0, nous avons soith(α) ≤ 200ε−2mn6(hp(F) + 5)soit|(lgcd(α,β))/r-h(α)/n|≤1/r (εh(α)+4000ε^(-1) n^4 (h_p (F)+log⁡(mn)+1)+30n^2 m(h_p (F)+log⁡(mn) ))Ensuite, nous donnons un aperçu des outils que nous avons utilisés dans les corps cyclotomiques. Nous tentons de développer une approche systématique pour un certain genre d’équations diophantiennes. Nous proposons quelques résultats sur les corps cyclotomiques, les anneaux de groupe et les sommes de Jacobi, qui nous seront utiles pour ensuite décrire l’approche.Finalement, nous développons une application de l’approche précédemment expliquée. Nous considèrerons l’équation diophantienne(1) Xn − 1 = BZn,où B ∈ Z est un paramètre. Définissons ϕ∗(B) := ϕ(rad (B)), où rad (B) est le radical de B, et supposons que(2) (n, ϕ∗(B)) = 1.Pour B ∈ N_(>1) fixé, soit N(B) = {n ∈ N_(>1) | ∃ k > 0 tel que n|ϕ∗(B)}. Si p est un premier impair, nous appellerons CF les conditions combinéesI La conjecture de Vandiver est vraie pour p, c’est-à-dire que le nombre de classe h+ du sous-corps réel maximal du corps cyclotomique Q[ζp ], n’est pas divisible par p.II Nous avons ir(p) < √p − 1, en d’autre mots, il y a au plus √p − 1 entiers impairs k < p tels que le nombre de Bernouilli Bk ≡ 0 mod p. [...] / This thesis examines some approaches to address Diophantine equations, specifically we focus on the connection between the Diophantine analysis and the theory of cyclotomic fields.First, we propose a quick introduction to the methods of Diophantine approximation we have used in this research work. We remind the notion of height and introduce the logarithmic gcd.Then, we address a conjecture, made by Thoralf Skolem in 1937, on an exponential Diophantine equation. For this conjecture, let K be a number field, α1 ,…, αm , λ1 ,…, λm non-zero elements in K, and S a finite set of places of K (containing all the infinite places) such that the ring of S-integersOS = OK,S = {α ∈ K : |α|v ≤ 1 pour les places v ∈/ S}contains α1 , . . . , αm , λ1 , . . . , λm α1-1 , . . . , αm-1. For each n ∈ Z, let A(n)=λ_1 α_1^n+⋯+λ_m α_m^n∈O_S. Skolem suggested [SK1] :Conjecture (exponential local-global principle). Assume that for every non zero ideal a of the ring O_S, there exists n ∈ Z such that A(n) ≡0 mod a. Then, there exists n ∈ Z such that A(n)=0.Let Γ be the multiplicative group generated by α1 ,…, αm. Then Γ is the product of a finite abelian group and a free abelian group of finite rank. We prove that the conjecture is true when the rank of Γ is one.After that, we generalize a result previously published by Abouzaid ([A]). Let F(X,Y) ∈ Q[X,Y] be an irreducible Q-polynomial. In 2008, Abouzaid [A] proved the following theorem:Theorem (Abouzaid). Assume that (0,0) is a non-singular point of the plane curve F(X,Y) = 0. Let m = degX F, n = degY F, M = max{m, n}. Let ε satisfy 0 < ε < 1. Then for any solution (α,β) ∈ Q ̅2 of F(X,Y) = 0, we have eithermax{h(α), h(β)} ≤ 56M8ε−2hp(F) + 420M10ε−2 log(4M),ormax{|h(α) − nlgcd(α, β)|,|h(β) − mlgcd(α, β)|} ≤ εmax{h(α), h(β)}++ 742M7ε−1hp(F) + 5762M9ε−1log(2m + 2n)However, he imposed the condition that (0, 0) be a non-singular point of the plane curve F(X,Y) = 0. Using a somewhat different version of Siegel’s “absolute” lemma and of Eisenstein’s lemma, we could remove the condition and prove it in full generality. We prove the following theorem:Theorem. Let F(X,Y) ∈ Q ̅[X,Y] be an absolutely irreducible polynomial satisfying F(0,0)=0. Let m=degX F, n=degY F and r = min{i+j:(∂^(i+j) F)/(∂^i X∂^j Y)(0,0)≠0}. Let ε be such that 0 < ε < 1. Then, for all (α, β) ∈ Q ̅2 such that F(α,β) = 0, we have eitherh(α) ≤ 200ε−2mn6(hp(F) + 5)or|(lgcd(α,β))/r-h(α)/n|≤1/r (εh(α)+4000ε^(-1) n^4 (h_p (F)+log⁡(mn)+1)+30n^2 m(h_p (F)+log⁡(mn) ))Then, we give an overview of the tools we have used in cyclotomic fields. We try there to develop a systematic approach to address a certain type of Diophantine equations. We discuss on cyclotomic extensions and give some basic but useful properties, on group-ring properties and on Jacobi sums.Finally, we show a very interesting application of the approach developed in the previous chapter. There, we consider the Diophantine equation(1) Xn − 1 = BZn,where B ∈ Z is understood as a parameter. Define ϕ∗(B) := ϕ(rad (B)), where rad (B) is the radical of B, and assume that (2) (n, ϕ∗(B)) = 1.For a fixed B ∈ N_(>1)we let N(B) = {n ∈ N_(>1) | ∃ k > 0 such that n|ϕ∗(B)}. If p is an odd prime, we shall denote by CF the combined condition requiring thatI The Vandiver Conjecture holds for p, so the class number h+ of the maximal real subfield of the cyclotomic field Q[ζp ] is not divisible by p.II We have ir>(p) < √p − 1, in other words, there is at most √p − 1 odd integers k < p such that the Bernoulli number Bk ≡ 0 mod p. [...]

Dans cette thèse, nous étudions le problème de l'identification d'un système à dynamique linéaire. Dans un premier temps, nous répertorions les différentes méthodes qui ont été développées dans la littérature en nous concentrant plus particulièrement sur les méthodes des observateurs adaptatifs. Dans un second temps nous présentons un premier algorithme qui est une approche mixant les méthodes des sous-espaces et celles des observateurs adaptatifs. Ce nouvel algorithme est d'autant plus intéressant qu'il nous permet d'identifier des réalisations de systèmes MIMO dans une base d'état arbitraire. La convergence de cet algorithme est démontrée en utilisant les notions d'excitation persistantes. Dans un troisième chapitre nous introduisons une nouvelle méthode qui s'appuie sur le concept des observateurs de Luenberger non linéaires développés ces dernières années. Ce nouvel algorithme se différencie des algorithmes existants par sa capacité à produire une estimation simultanée des paramètres et de l'état du système. Nous démontrons alors sa robustesse à des perturbations affectant la dynamique interne ou les mesures. La convergence de cet algorithme est obtenue si les entrées du système satisfont une hypothèse d'excitation différentielle. Tous ces algorithmes sont alors évalués et implémentés sur un banc d'expérimentation / In this thesis, we study the problem of identification of a linear dynamical system. First, we survey various methods that have been developed in the literature. We focus more particularly on methods named adaptive observers. Secondly we present an approach which combines subspace identification methods and adaptive observers. This new method is interesting since it allows us to identify MIMO systems in an arbitrary basis. The convergence of this algorithm is demonstrated using the persistent excitation notions. In the third chapter we introduce a new method that is inspired from nonlinear Luenberger observers developed in recent years. This new algorithm is different from the existing algorithms since the parameters and the systemstatus are estimated simultaneously. We demonstrate the robustness of this approach. The convergence of the algorithm is obtained if the system inputs satisfy a differential excitation hypothesis. All these algorithms are evaluated and implemented on an experimental bench

The classical binary error correcting codes, and subspace codes for error correction in random network coding are two different forms of error control coding. We identify common features between these two forms and study the relations between them using the aid of lattices. Lattices are partial ordered sets where every pair of elements has a least upper bound and a greatest lower bound in the lattice. We shall demonstrate that many questions that connect these forms have a natural motivation from the viewpoint of lattices. We shall show that a lattice framework captures the notion of Singleton bound where the bound is on the size of the code as a function of its parameters. For the most part, we consider a special type of a lattice which has the geometric modular property. We will use a lattice framework to combine the two different forms. And then, in order to demonstrate the utility of this binding view, we shall derive a general version of Singleton bound. We will note that the Singleton bounds behave differently in certain respects because the binary coding framework is associated with a lattice that is distributive. We shall demonstrate that lack of distributive gives rise to a weaker bound. We show that Singleton bound for classical binary codes, subspace codes, rank metric codes and Ferrers diagram rank metric codes can be derived using a common technique. In the literature, Singleton bounds are derived for Ferrers diagram rank metric codes where the rank metric codes are linear. We introduce a generalized version of Ferrers diagram rank metric codes and obtain a Singleton bound for this version. Next, we shall prove a conjecture concerning the constraints of embedding a binary coding framework into a subspace framework. We shall prove a conjecture by Braun, Etzion and Vardy, which states that any such embedding which contains the full space in its range is constrained to have a particular size. Our proof will use a theorem due to Lovasz, a subspace counting theorem for geometric modular lattices, to prove the conjecture. We shall further demonstrate that any code that achieves the conjectured size must be of a particular type. This particular type turns out to be a natural distributive sub-lattice of a given geometric modular lattice.

The subject of this work deals with the problem of channel estimation for CDMA systems. This method of multiple access when individual users share the same full bandwidth simultaneously and are differentiated with any of pseudorandom sequences, is now the most perspective method. That is proved by its wide implementation in mobile networks of the third generation and higher systems. This work describes basic theory principles of spread spectrum, above all DS-CDMA (Direct Sequence-CDMA) and furthermore some phenomena of radio wireless channel that affect changes in transmitted signal in its way from transmitter to receiver. Terms of fading, multipath propagation, loss, refraction, scattering of the wave and Rice and Rayleigh probability density functions are mentioned. The third chapter deals with yet known and used capabilities of channel estimation. Differences, advantages and disadvantages of so-called blind estimation or training-based estimation are discussed. Two algorithms: LS method and sliding correlator are analyzed in more detail. There is also description of their simulations in Matlab and some results of these simulations are discussed. The last chapter deals with comparison of main characteristics and achievable accuracy of wireless channel impulse response estimation by both methods, and their possible utilization in real live.

This thesis compares hand-designed features with features learned by feature learning methods in video classification. The features learned by Principal Component Analysis whitening, Independent subspace analysis and Sparse Autoencoders were tested in a standard Bag of Visual Word classification paradigm replacing hand-designed features (e.g. SIFT, HOG, HOF). The classification performance was measured on Human Motion DataBase and YouTube Action Data Set. Learned features showed better performance than the hand-desined features. The combination of hand-designed features and learned features by Multiple Kernel Learning method showed even better performance, including cases when hand-designed features and learned features achieved not so good performance separately.

Tato práce se zabývá pravděpodobnostními modely pro automatické rozpoznávání řečníka. Podrobně analyzuje zejména pravděpodobnostní lineární diskriminační analýzu (PLDA), která modeluje nízkodimenzionální reprezentace promluv ve formě \acronym{i--vektorů}.  Práce navrhuje dvě rozšíření v současnosti požívaného PLDA modelu. Nově navržený PLDA model s plným posteriorním rozložením  modeluje neurčitost při generování i--vektorů. Práce také navrhuje nový diskriminativní přístup k trénování systému pro verifikaci řečníka, který je založený na PLDA. Pokud srovnáváme původní PLDA s modelem rozšířeným o modelování  neurčitosti i--vektorů, výsledky dosažené s rozšířeným modelem dosahují až 20% relativního zlepšení při testech s krátkými nahrávkami. Pro delší  testovací segmenty  (více než jedna minuta) je zisk v přesnosti  menší, nicméně přesnost nového modelu není nikdy menší než přesnost výchozího systému.  Trénovací data jsou ale obvykle dostupná ve formě dostatečně dlouhých segmentů, proto v těchto případech použití nového modelu neposkytuje žádné výhody při trénování. Při trénování může být použit původní PLDA model a jeho rozšířená verze může být využita pro získání skóre v  případě, kdy se bude provádět testování na krátkých segmentech řeči. Diskriminativní model je založen na klasifikaci dvojic i--vektorů do dvou tříd představujících oprávněný a neoprávněný soud (target a non-target trial). Funkcionální forma pro získání skóre pro každý pár je odvozena z PLDA a trénování je založeno na logistické regresi, která minimalizuje vzájemnou entropii mezi správným označením všech soudů a pravděpodobnostním označením soudů, které navrhuje systém. Výsledky dosažené s diskriminativně trénovaným klasifikátorem jsou podobné výsledkům generativního PLDA, ale diskriminativní systém prokazuje schopnost produkovat lépe kalibrované skóre. Tato schopnost vede k lepší skutečné přesnosti na neviděné evaluační sadě, což je důležitá vlastnost pro reálné použití.