Around the world Alzheimer’s Disease (AD) is on the rise. Previous studies have shown the default mode network (DMN) sees changes with AD progression as the disease erodes away cortical areas. Aerobic exercise with significant increases to cardiorespiratory fitness could show neuro-protective changes to delay AD. This study will explore if functional connectivity changes in the DMN can be seen in a young adult sample by using group independent component analysis through FSL MELODIC. The young adult sample of 19 were selected from a larger study at the Brain Plasticity and Neuroimaging Laboratory at Boston University. The participants engaged in a twelve-week exercise intervention in either a strength training or aerobic training group. They also completed pre-intervention and post-intervention resting-state fMRI scans to evaluate change in functional connectivity in the default mode network. Cardiorespiratory fitness was assessed using a modified Balke protocol with pre-intervention and post-intervention VO2 max percentiles being used. Through two repeated-measure ANOVA analyses, this study found no significant increase in mean functional connectivity or cardiorespiratory fitness in the young adult sample. While improvements in mean VO2 max percentile and functional connectivity would have been seen with a larger sample size, this study adds to the literature by suggesting if fitness does not improve significantly, neither will functional connectivity in the default mode network.

Orientador: Prof. Dr. Ricardo Suyama / Dissertação (mestrado) - Universidade Federal do ABC, Programa de Pós-Graduação em Engenharia da Informação, 2017. / O metodo estatistico de Independent Component Analysis (ICA) e um dos mais amplamente utilizados para solucionar o problema de Blind Source Separation (BSS) que, junto a outros metodos de processamento de sinais, sao colocados a prova com o aumento do numero das fontes de sinais e amostras disponiveis para processamento, e sao a base de aplicacoes com requisitos de desempenho cada vez maiores. O objetivo deste trabalho e realizar o estudo do metodo ICA e analise dos algoritmos FastICA e Joint Approximate Diagonalization of Eigen-matrices (JADE) implementados em Field-Programmable Gate Array (FPGA) e seu comportamento quando variamos o numero de amostras das misturas e os numeros de iteracoes ou updates. Outros trabalhos de pesquisa ja foram realizados com o objetivo de demonstrar a viabilidade da implementacao de tais algoritmos em FPGA, mas pouco apresentam sobre o metodo utilizado para definir detalhes de implementacao como numero de amostradas utilizados, a razao da representacao numerica escolhida e sobre o thoughtput alcancado. A analise que este trabalho propos realizar, num primeiro momento, passa por demonstrar o comportamento do core dos algoritmos quando implementados utilizando diferentes representacoes numericas de ponto flutuante com precisao simples (32 bits) e ponto fixo com diferentes numeros de amostras e fontes a serem estimadas, por meio de simulacoes. Foi verificada a viabilidade desses serem utilizados para atender aplicacoes que precisam resolver o problema de BSS com boa acuracia, quando comparados com implementacoes dos mesmos algoritmos que se utilizaram de uma representacao numerica de ponto flutuante com precisao dupla (64 bits). Utilizando o Simulink R¿e a biblioteca DSP Builder R¿da Altera R¿para implementar os modelos de cada algoritmo, foi possivel analisar outros aspectos importantes, em busca de demonstrar a possibilidade da utilizacao de tais implementacoes em aplicacoes com requisitos de tempo real, que necessitam de alto desempenho, utilizando FPGA de baixo custo, como: a quantidade de recursos de FPGA necessarios na implementacao de cada algoritmo, principalmente buscando minimizar a utilizacao de blocos DSP, a latencia, e maximizar o throughput de processamento. / Independent Component Analysis (ICA) is one of the most widely used statistical method to solve the problem of Blind Source Separation (BSS), which, along with other signal processing methods, faces new challenges with the increasing the number of signal sources and samples available for processing, being the base of applications with increasing performance requirements. The aim of this work is to study the FastICA and the Joint Approximate Diagonalization of Eigen-matrices (JADE) algorithms and implement them in Field- Programmable Gate Array (FPGA). Other researches have already been carried out with the objective of demonstrating the feasibility of implementing such algorithms in FPGA, but they present little about the methodology used and implementation details such as the number of samples used, why the numerical representation was chosen and the obtained thoughtput. The analysis carried out in this work demonstrates the behavior of the core of the algorithms when implemented using different representations, such as singleprecision floating-point (32 bits) and fixed point with different numbers of samples and sources to be estimated. It was verified these immplementations are able to solve the BSS problem with good accuracy when compared with implementations of the same algorithms that exmploy a double-precision floating-point representation (64 bits). Using the Simulink R¿ and Alterafs R¿ DSP Builder R¿ library to implement the models of each algorithm, it was possible to analyze other important aspects, in order to demonstrate the possibility of using such implementations in applications with real-time requirements that require high performance, using low cost FPGA, such as: the necessary FPGA resources in the implementation of each algorithm, mainly seeking to minimize the use of DSP blocks, latency, and to maximize the processing throughput.

Orientadora: Profa. Dra. Cristiane Otero Reis Salum / Coorientador: Prof. Dr. Francisco José Fraga da Silva / Dissertação (mestrado) - Universidade Federal do ABC, Programa de Pós-Graduação em Neurociência e Cognição, São Bernardo do Campo, 2017. / Pacientes de transtorno bipolar e esquizofrenia apresentam déficits no processamento de informação. Dentre esses déficits está uma disfunção do mecanismo de filtragem sensorial, que pode ser observada através do teste de Inibição Pré-Pulso (IPP), que acessa a inibição das respostas muscular, observada por eletromiografia (EMG) e neural, observada por eletroencefalograma (EEG) através da inibição de potenciais evocados, como o P2-N1. No fenômeno da IPP, é observado que a resposta iniciada por um estímulo de alta intensidade é reduzida quando este é precedido em alguns milissegundos (30-300ms) por outro estímulo de baixa intensidade. Esses estímulos são respectivamente chamados de Pulso (P) e Pré-Pulso (PP). A porcentagem de redução da resposta ao P, quando este é precedido por um PP é calculada em relação à magnitude de resposta que seria evocada pelo P quando este não é precedido por PP algum. O presente estudo visou avaliar o filtro sensorial através do registro simultâneo dos sinais eletromiográficos e eletroencefalográficos em pacientes brasileiros de primeiro episódio psicótico de transtorno bipolar (BP) e esquizofrenia (SZ). Vinte pacientes BP, quinze pacientes SZ e 22 sujeitos sadios participaram do estudo. Pacientes SZ apresentam redução da %IPP observada por EMG em relação a pessoas sadias, ao passo que pacientes do grupo BP não apresentam redução da filtragem sensório-motora. Para a IPP neural, foi observada redução na amplitude de P do grupo BP na região frontal, avaliada pelo eletrodo Fz e redução da amplitude de P e também na %IPP para os grupos BP e SZ na região parietal, avaliada pelo eletrodo Pz. Os resultados indicam que a redução da filtragem sensorial foi observada em diferentes estágios do processamento sensorial. E a divergência entre IPP clássica e IPP neural para o grupo BP sugere que a IPP medida por EMG clássica e medida por EEG refletem filtros sensoriais diferentes e que pacientes de diferentes grupos podem exibir déficits em um desses filtros apenas. O presente trabalho é o pioneiro na utilização de ferramentas de atenuação de artefatos contaminantes do sinal neural no teste de IPP neural. / Patients with bipolar disorder and schizophrenia have deficits in information processing. Among these deficits is a dysfunction of the sensory filtering mechanism, which can be observed through the Prepulse Inhibition (PPI) test, which accesses the inhibition of muscle responses, observed by electromyography (EMG) and neural, observed by electroencephalogram (EEG) through inhibition of evoked potentials, such as P2-N1. In the PPI phenomenon, it is observed that the response initiated by a high intensity stimulus is reduced when it is preceded in a few milliseconds (30-300ms) by another low intensity stimulus. These stimuli are respectively called Pulse (P) and Prepulse (PP). The reduction percentage of the response to P when it is preceded by a PP is calculated in relation to the magnitude of response that would be evoked by P when it is not preceded by any PP. The present study aimed to evaluate the sensory filter through the simultaneous recording of electromyographic and electroencephalographic signals in Brazilian patients with first psychotic episode of bipolar disorder (BP) and schizophrenia (SZ). Twenty BP patients, fifteen SZ patients and 22 healthy subjects participated in the study. SZ patients presented a reduction in the %PPI observed by EMG when compared to healthy individuals, whereas patients in the BP group did not show reduction of sensory-motor filter. For the neural PPI, a reduction in BP group P amplitude was observed in the frontal region, evaluated by the Fz electrode. Also, was observed a reduction in the P amplitude and in the %PPI for the BP and SZ groups in the parietal region, evaluated by the Pz electrode. These results indicate that the reduction of sensorial filtration was observed at different stages of sensorial processing. And the divergence between classical IPP and neural IPP for the BP group suggests that PPI measured by classical EMG and measured by EEG reflect different sensory filters and that patients from different groups may exhibit deficits in one of these filters only. The present work is the pioneer in the use of attenuation tools to reduce contaminating artifacts in PPI test neural signal.

Made available in DSpace on 2016-08-17T14:53:12Z (GMT). No. of bitstreams: 1 Denner Guilhon.pdf: 761750 bytes, checksum: 0100d830816d0600a5ff8aacd65531cb (MD5) Previous issue date: 2006-02-24 / The continuing demand for high performance and low cost electrocardiogram processing systems have required the elaboration of even more efficient and reliable ECG compression techniques. The objective of this work is to evaluate the performance of an electrocardiogram (ECG) compression algorithm based on independent components analysis (ICA). To each of the ECG signal we processed, using ICA, vectorial subspaces composed of its basis functions were obtained, for the signal can be expressed as a linear combination of them. The ECG signal was subdivided into m fixed length windows, and each of them was projected in the subspace, resulting in a vector w of coefficients for each window. A simple quantization process was performed over the m vectors w, according to defined levels of quantization, each one generating different levels of reconstruction error. It was observed that the storage of the coefficients implies the use of less space in memory in comparison to that one used by the corresponding windows of the electrocardiogram signal. The reconstruction error measure traditionally used, the percent root mean-square difference (PRD), was used into the evaluation of the algorithm. The results had been compared with those obtained using the Karhunen Lo´eve transform (KLT). / A demanda contınua de por sistemas de processamento de eletrocardiogramas de alto desempenho e baixo custo tem exigido a elaboração de técnicas de compressão de ECG cada vez mais eficientes e confiáveis. O objetivo deste trabalho é avaliar o desempenho de um algoritmo baseado em análise de componentes independentes (ICA) para a compressão de eletrocardiogramas (ECGs). Para cada um dos sinais de ECG utilizados foram obtidos, através de ICA, subespaços vetoriais construıdos a partir de suas funções base, pois o sinal pode ser expresso como uma combinação linear destas. O sinal de ECG foi subdividido em m janelas de comprimento fixo, e cada uma delas foi projetada no subespaço, resultando em um vetor w de coeficientes para cada janela. Um processo de quantização simples foi executado para os m vetores w, segundo nıveis de quantização definidos, cada um gerando diferentes nıveis de erro de reconstrução. Foi observado que o armazenamento dos coeficientes implica na utilização de um menor espaço em memória em comparação àquele utilizado pelas janelas correspondentes do sinal de eletrocardiograma. A medida tradicionalmente utilizada de erro de reconstrução, diferença média quadrática percentual (PRD), foi empregada para a avaliação do algoritmo. Os resultados foram comparados àqueles obtidos utilizando a transformada de Karhunen Loeve (KLT).

Abstract The goal of this study was to explore preoperative evaluation of patients with intracranial tumours using magnetic resonance imaging (MRI) methods: oedema-attenuated inversion recovery (EDAIR) sequence in low-field MRI, and diffusion-weighted imaging (DWI) and resting-state functional MRI (fMRI) in high-field MRI. The aim was also to increase our knowledge about the effects of brain surgery on eloquent brain cortices using new MRI techniques. The total number of patients in these studies was 50 (24 women). Enhancement of the tumour in ten patients after intravenous administration of gadolinium-based contrast agent in low-field MRI was examined with a new sequence, EDAIR, and compared with more conventionally used partial saturation spin echo sequences. EDAIR may facilitate the perception of small enhancing lesions and is valuable in low-field imaging, where T1-based contrast is inferior to high-field imaging. DWI was performed on 25 patients in order to evaluate the potential of this imaging method to assist in differential diagnosis of intracranial tumours. It was shown that apparent diffusion coefficient values of the tumour and peritumoural oedema produced by DWI were different in benign and malignant tumours. Resting-state blood oxygen level-dependent (BOLD) fMRI was performed on eight patients and ten healthy volunteers to examine if functional sensorimotor areas in the brain could be determined without any task-related activations. It was shown that intracranial tumours do not appear to hamper visualization of the sensorimotor area in resting-state BOLD fMRI when independent component analysis is performed, and this method may be used in preoperative imaging when activation studies cannot be performed. Conventional BOLD fMRI with motor and auditory stimuli was used with seven patients as the effect of brain surgery was studied. The results suggest that resection of a tumour with preoperative oedema probably decreases pressure on the brain and makes the functional cortex transiently more easily detectable in BOLD fMRI. In conclusion, the MRI imaging methods used in this study can give valuable additional information about the tumour, specifically for preoperative imaging and planning for surgery.

To manufacture safe, effective and affordable medicines with greater efficiency, process analytical technology (PAT) has been introduced by the Food and Drug Agency to encourage the pharmaceutical industry to develop and design well-understood processes. PAT requires chemical imaging techniques to be used to collect process variables for real-time process analysis. Multivariate statistical analysis tools and process control tools are important for implementing PAT in the development and manufacture of pharmaceuticals as they enable information to be extracted from the PAT measurements. Multivariate statistical analysis methods such as principal component analysis (PCA) and independent component analysis (ICA) are applied in this thesis to extract information regarding a pharmaceutical tablet. ICA was found to outperform PCA and was able to identify the presence of five different materials and their spatial distribution around the tablet.Another important area for PAT is in improving the control of processes. In the pharmaceutical industry, many of the processes operate in a batch strategy, which introduces difficult control challenges. Near-infrared (NIR) spectroscopy is a non-destructive analytical technique that has been used extensively to extract chemical and physical information from a product sample based on the scattering effect of light. In this thesis, NIR measurements were incorporated as feedback information into several control strategies. Although these controllers performed reasonably well, they could only regulate the NIR spectrum at a number of wavenumbers, rather than over the full spectrum.In an attempt to regulate the entire NIR spectrum, a novel control algorithm was developed. This controller was found to be superior to the only comparable controller and able to regulate the NIR similarly. The benefits of the proposed controller were demonstrated using a benchmark simulation of a batch reactor.

Heart Rate Variability (HRV) analysis has been garnering attention from researchers due to its wide range of applications. Medical researchers have always been interested in Heart Rate (HR) and HRV analysis, but nowadays, investigators from variety of other fields are also probing the subject. For instance, variation in HR and HRV is connected to emotional arousal. Therefore, knowledge from the fields of affective computing and psychology, can be employed to devise machines that understand the emotional states of humans. Recent advancements in non-contact HR and HRV measurement techniques will likely further boost interest in emotional estimation through . Such measurement methods involve the extraction of the photoplethysmography (PPG) signal from the human's face through a camera. The latest approaches apply Independent Component Analysis (ICA) on the color channels of video recordings to extract a PPG signal. Other investigated methods rely on Eulerian Video Magnification (EVM) to detect subtle changes in skin color associated with PPG. The effectiveness of the EVM in HR estimation has well been established. However, to the best of our knowledge, EVM has not been successfully employed to extract HRV feature from a video of a human face. In contrast, ICA based methods have been successfully used for HRV analysis. As we demonstrate in this thesis, these two approaches for HRV feature extraction are highly sensitive to noise. Hence, when we evaluated them in indoor settings, we obtained mean absolute error in the range of 0.012 and 28.4. Therefore, in this thesis, we present two approaches to minimize the error rate when estimating physiological measurements from recorded facial videos using a standard camera. In our first approach which is based on the EVM method, we succeeded in extracting HRV measurements but we could not get rid of high frequency noise, which resulted in a high error percentage for the result of the High frequency (HF) component. Our second proposed approach solved this issue by applying ICA on the red, green and blue (RGB) colors channels and we were able to achieve lower error rates and less noisy signal as compared to previous related works. This was done by using a Buterworth filter with the subject's specific HR range as its Cut-Off. The methods were tested with 12 subjects from the DISCOVER lab at the University of Ottawa, using artificial lights as the only source of illumination. This made it a challenge for us because artificial light produces HF signals which can interfere with the PPG signal. The final results show that our proposed ICA based method has a mean absolute error (MAE) of 0.006, 0.005, 0.34, 0.57 and 0.419 for the mean HR, mean RR, LF, HF and LF/HF respectively. This approach also shows that these physiological parameters are highly correlated with the results taken from the electrocardiography (ECG).

This dissertation explored the way in which bumblebees' visual system helps them discover their first flower. Previous studies found bees have unlearned preferences for parts of a flower, such as its colour and shape. The first study pitted two variables against each other: pattern type: sunburst or bull's eye, versus the location of the pattern: shapes appeared peripherally or centrally. We observed free-flying bees in a flight cage using Radio-Frequency Identification (RFID) tracking. The results show two distinct behavioural preferences: Pattern type predicts landing: bees prefer radial over concentric patterns, regardless of whether the radial pattern is on the perimeter or near the centre of the flower. Pattern location predicts exploration: bees were more likely to explore the inside of artificial flowers if the shapes were displayed near the centre of the flower, regardless of whether the pattern was radial or concentric. As part of the second component, we implemented a mathematical model aimed at explaining how bees come to prefer radial patterns, leafy backgrounds and symmetry. The model was based on unsupervised neural networks used to describe cognitive mechanisms. The results captured with the results of multiple behavioural experiments. The model suggests that bees choose computationally "cheaper" stimuli, those that contain less information. The third study tested the computational load hypothesis generated by the artificial neural networks. Visual properties of symmetry, and spatial frequency were tested. Studying free-flying bees in a flight cage using motion-sensitive video recordings, we found that bees preferred 4-axis symmetrical patterns in both low and high frequency displays.

Orientador: Martin Tygel / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Cientifica / Made available in DSpace on 2018-08-22T06:13:33Z (GMT). No. of bitstreams: 1 CostaFilho_CarlosAlbertoda_M.pdf: 3131395 bytes, checksum: f8687abfc7e346fdd8e6dc40746526e8 (MD5) Previous issue date: 2013 / Resumo: As reflexões de ondas sísmicas na subsuperfície terrestre podem ser colocadas em duas categorias disjuntas: reflexões primárias e múltiplas. Reflexões primárias carregam informações pontuais sobre um refletor específico, enquanto reflexões múltiplas carregam informações sobre interfaces e pontos de reflexão variados. Consequentemente é usual tentar atenuar reflexões múltiplas e trabalhar somente com reflexões primárias. Neste trabalho, a teoria de ondas acústicas é desenvolvida somente a partir da equação da onda. Um resultado que demonstra como a propagação de ondas acústicas pode ser descrita somente com uma única multiplicação por matriz é exposta. Este resultado permite que um algoritmo seja desenvolvido que, em teoria, pode ser usado para remover todas as reflexões múltiplas que refletiram na superfície pelo menos uma vez. Uma implementação prática deste algoritmo é mostrada. Por conseguinte, a teoria de análise de componentes independentes é apresentada. Suas considerações teóricas e práticas são abordadas. Finalmente, ela é usada em conjunção com o método de eliminação de múltiplas de superfície para atenuar múltiplas de quatro dados diferentes. Estes resultados são então analisados e a eficácia do método é avaliada / Abstract: The reflections of seismic waves in the subsurface of the Earth can be placed under two disjoint categories: primary and multiple reflections. Primary reflections carry pointwise information about a specific reflector while multiple reflections carry informations about various interfaces and reflection points. Consequently, it is customary to attempt to attenuate multiple reflections and work solely with primary reflections. In this work, the theory of acoustic waves is developed solely from the wave equation. A result that shows how acoustic wave propagation can be described as a single matrix multiplication is exposed. This result enables one to develop an algorithm that, in theory, can be used to remove all multiple reflections that have reflected on the surface at least once. The practical implementation of this algorithm is shown. Thereafter, the theory of independent component analysis is presented. Its theoretical and practical considerations are addressed. Finally, it is used in conjunction with the surface-related multiple elimination method to attenuate multiples in four different datasets. These results are then analyzed and the efficacy of the method is evaluated / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

[EN] This thesis considers new applications of non-Gaussian mixtures in the framework of statistical signal processing and pattern recognition. The non-Gaussian mixtures were implemented by mixtures of independent component analyzers (ICA). The fundamental hypothesis of ICA is that the observed signals can be expressed as a linear transformation of a set of hidden variables, usually referred to as sources, which are statistically independent. This independence allows factoring the original M-dimensional probability density function (PDF) of the data as a product of one-dimensional probability densities, greatly simplifying the modeling of the data. ICA mixture models (ICAMM) provide further flexibility by alleviating the independency requirement of ICA, thus allowing the model to obtain local projections of the data without compromising its generalization capabilities. Here are explored new possibilities of ICAMM for the purposes of estimation and classification of signals. The thesis makes several contributions to the research in non-Gaussian mixtures: (i) a method for maximum-likelihood estimation of missing data, based on the maximization of the PDF of the data given the ICAMM; (ii) a method for Bayesian estimation of missing data that minimizes the mean squared error and can obtain the confidence interval of the prediction; (iii) a generalization of the sequential dependence model for ICAMM to semi-supervised or supervised learning and multiple chains of dependence, thus allowing the use of multimodal data; and (iv) introduction of ICAMM in diverse novel applications, both for estimation and for classification. The developed methods were validated via an extensive number of simulations that covered multiple scenarios. These tested the sensitivity of the proposed methods with respect to the following parameters: number of values to estimate; kinds of source distributions; correspondence of the data with respect to the assumptions of the model; number of classes in the mixture model; and unsupervised, semi-supervised, and supervised learning. The performance of the proposed methods was evaluated using several figures of merit, and compared with the performance of multiple classical and state-of-the-art techniques for estimation and classification. Aside from the simulations, the methods were also tested on several sets of real data from different types: data from seismic exploration studies; ground penetrating radar surveys; and biomedical data. These data correspond to the following applications: reconstruction of damaged or missing data from ground-penetrating radar surveys of historical walls; reconstruction of damaged or missing data from a seismic exploration survey; reconstruction of artifacted or missing electroencephalographic (EEG) data; diagnosis of sleep disorders; modeling of the brain response during memory tasks; and exploration of EEG data from subjects performing a battery of neuropsychological tests. The obtained results demonstrate the capability of the proposed methods to work on problems with real data. Furthermore, the proposed methods are general-purpose and can be used in many signal processing fields. / [ES] Esta tesis considera nuevas aplicaciones de las mezclas no Gaussianas dentro del marco de trabajo del procesado estadístico de señal y del reconocimiento de patrones. Las mezclas no Gaussianas fueron implementadas mediante mezclas de analizadores de componentes independientes (ICA). La hipótesis fundamental de ICA es que las señales observadas pueden expresarse como una transformación lineal de un grupo de variables ocultas, normalmente llamadas fuentes, que son estadísticamente independientes. Esta independencia permite factorizar la función de densidad de probabilidad (PDF) original M-dimensional de los datos como un producto de densidades unidimensionales, simplificando ampliamente el modelado de los datos. Los modelos de mezclas ICA (ICAMM) aportan una mayor flexibilidad al relajar el requisito de independencia de ICA, permitiendo que el modelo obtenga proyecciones locales de los datos sin comprometer su capacidad de generalización. Aquí se exploran nuevas posibilidades de ICAMM para los propósitos de estimación y clasificación de señales. La tesis realiza varias contribuciones a la investigación en mezclas no Gaussianas: (i) un método de estimación de datos faltantes por máxima verosimilitud, basado en la maximización de la PDF de los datos dado el ICAMM; (ii) un método de estimación Bayesiana de datos faltantes que minimiza el error cuadrático medio y puede obtener el intervalo de confianza de la predicción; (iii) una generalización del modelo de dependencia secuencial de ICAMM para aprendizaje supervisado o semi-supervisado y múltiples cadenas de dependencia, permitiendo así el uso de datos multimodales; y (iv) introducción de ICAMM en varias aplicaciones novedosas, tanto para estimación como para clasificación. Los métodos desarrollados fueron validados mediante un número extenso de simulaciones que cubrieron múltiples escenarios. Éstos comprobaron la sensibilidad de los métodos propuestos con respecto a los siguientes parámetros: número de valores a estimar; tipo de distribuciones de las fuentes; correspondencia de los datos con respecto a las suposiciones del modelo; número de clases en el modelo de mezclas; y aprendizaje supervisado, semi-supervisado y no supervisado. El rendimiento de los métodos propuestos fue evaluado usando varias figuras de mérito, y comparado con el rendimiento de múltiples técnicas clásicas y del estado del arte para estimación y clasificación. Además de las simulaciones, los métodos también fueron probados sobre varios grupos de datos de diferente tipo: datos de estudios de exploración sísmica; exploraciones por radar de penetración terrestre; y datos biomédicos. Estos datos corresponden a las siguientes aplicaciones: reconstrucción de datos dañados o faltantes de exploraciones de radar de penetración terrestre de muros históricos; reconstrucción de datos dañados o faltantes de un estudio de exploración sísmica; reconstrucción de datos electroencefalográficos (EEG) dañados o artefactados; diagnóstico de desórdenes del sueño; modelado de la respuesta del cerebro durante tareas de memoria; y exploración de datos EEG de sujetos durante la realización de una batería de pruebas neuropsicológicas. Los resultados obtenidos demuestran la capacidad de los métodos propuestos para trabajar en problemas con datos reales. Además, los métodos propuestos son de propósito general y pueden utilizarse en muchos campos del procesado de señal. / [CAT] Aquesta tesi considera noves aplicacions de barreges no Gaussianes dins del marc de treball del processament estadístic de senyal i del reconeixement de patrons. Les barreges no Gaussianes van ser implementades mitjançant barreges d'analitzadors de components independents (ICA). La hipòtesi fonamental d'ICA és que els senyals observats poden ser expressats com una transformació lineal d'un grup de variables ocultes, comunament anomenades fonts, que són estadísticament independents. Aquesta independència permet factoritzar la funció de densitat de probabilitat (PDF) original M-dimensional de les dades com un producte de densitats de probabilitat unidimensionals, simplificant àmpliament la modelització de les dades. Els models de barreges ICA (ICAMM) aporten una major flexibilitat en alleugerar el requeriment d'independència d'ICA, permetent així que el model obtinga projeccions locals de les dades sense comprometre la seva capacitat de generalització. Ací s'exploren noves possibilitats d'ICAMM pels propòsits d'estimació i classificació de senyals. Aquesta tesi aporta diverses contribucions a la recerca en barreges no Gaussianes: (i) un mètode d'estimació de dades faltants per màxima versemblança, basat en la maximització de la PDF de les dades donat l'ICAMM; (ii) un mètode d'estimació Bayesiana de dades faltants que minimitza l'error quadràtic mitjà i pot obtenir l'interval de confiança de la predicció; (iii) una generalització del model de dependència seqüencial d'ICAMM per entrenament supervisat o semi-supervisat i múltiples cadenes de dependència, permetent així l'ús de dades multimodals; i (iv) introducció d'ICAMM en diverses noves aplicacions, tant per a estimació com per a classificació. Els mètodes desenvolupats van ser validats mitjançant una extensa quantitat de simulacions que cobriren múltiples situacions. Aquestes van verificar la sensibilitat dels mètodes proposats amb respecte als següents paràmetres: nombre de valors per estimar; mena de distribucions de les fonts; correspondència de les dades amb respecte a les suposicions del model; nombre de classes del model de barreges; i aprenentatge supervisat, semi-supervisat i no-supervisat. El rendiment dels mètodes proposats va ser avaluat mitjançant diverses figures de mèrit, i comparat amb el rendiments de múltiples tècniques clàssiques i de l'estat de l'art per a estimació i classificació. A banda de les simulacions, els mètodes van ser verificats també sobre diversos grups de dades reals de diferents tipus: dades d'estudis d'exploració sísmica; exploracions de radars de penetració de terra; i dades biomèdiques. Aquestes dades corresponen a les següents aplicacions: reconstrucció de dades danyades o faltants d'estudis d'exploracions de radar de penetració de terra sobre murs històrics; reconstrucció de dades danyades o faltants en un estudi d'exploració sísmica; reconstrucció de dades electroencefalogràfiques (EEG) artefactuades o faltants; diagnosi de desordres de la son; modelització de la resposta del cervell durant tasques de memòria; i exploració de dades EEG de subjectes realitzant una bateria de tests neuropsicològics. Els resultats obtinguts han demostrat la capacitat dels mètodes proposats per treballar en problemes amb dades reals. A més, els mètodes proposats són de propòsit general i poden fer-se servir en molts camps del processament de senyal. / Safont Armero, G. (2015). New Insights in Prediction and Dynamic Modeling from Non-Gaussian Mixture Processing Methods [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/53913 / TESIS