A novel idea for perception of object surfaces is presented by so called "shape descriptors". Such idea is as an abstract level to represent the object surface by some real numbers. It has the similar idea like as the Fourier coefficients of mapping a function f(x) to frequency domain by Fourier transform. The main goal of this thesis is to define some of the key issues in understanding of an object shape and also to find a modeling methodology to create the "shape descriptors". The modeling methodology is designed based on a variational interpolation technique. Such technique is used to generate a group of variational implicit functions with help of radial basis functions. In our modeling methodology, we randomly choose some reference points on a set of related concentric spheres around a 3D point cloud data as known values in variational implicit functions. The "shape descriptors" are found from these implicit functions implementing LU decomposition. We show that the "shape descriptors" are invariant to size and positioning (rotation and translation) changes of a shape and they are also effective tools for matching of two similar objects surfaces.

Depuis plusieurs années, IFPEN développe des adsorbants à base de zéolithe faujasite pour le procédé de séparation des xylènes. Dans ce cadre, cette thèse a permis de rationaliser les origines de la sélectivité des isomères du xylène dans les zéolithes faujasites. Pour ce faire, une nouvelle approche est proposée. L'objectif est d'établir un modèle à la fois explicatif et prédictif qui permet de relier la sélectivité à un certain nombre de paramètres caractéristiques du système, appelés descripteurs. Après la proposition d'un plan d'expériences contenant une soixantaine d'adsorbants, leur préparation et leur test étaient effectués en utilisant des outils adéquats automatisés et parallélisés. L'analyse statistique descriptive faite sur l'ensemble des 43 propriétés d'adsorption évaluées a révélé l'existence de 4 différentes classes d'adsorbants. L'étape de construction du modèle était précédée par l'identification et le calcul des descripteurs. Ceux qui sont retenus caractérisent, essentiellement, l'état de confinement responsable de la sélectivité au sein de la zéolithe. On cite la taille des cations des sites II, l'occupation des sites III ou encore la saturation des sites II. Deux méthodes statistiques étaient utilisées pour construire les relations structures-propriétés. Tout d'abord, la régression linéaire multiple avec comme variables explicatives les 3 descripteurs cités. Le modèle explicatif retenu prédit avec un coefficient de corrélation R² de 0,78. Aussi, l'analyse discriminante était utilisée. Ces mêmes 3 descripteurs ont servi à prédire l'affectation des adsorbants dans les 4 classes identifiées avec un pourcentage de prédiction total de 76% / For several years, IFPEN develops based faujasite adsorbents for the xylene separation process. In this context, this thesis allowed to streamline the selectivity origins of xylene isomers in faujasite zeolites. To do it, a new approach is proposed. The objective is to establish, at the same time, an explanatory and predictive model which allows to relate the selectivity to a number of characteristic parameters of the system, called descriptors. After the proposal of an experimental design containing about sixty adsorbents, their preparation and their test were made by using automated and paralleled adequate tools. A descriptive statistical analysis made on 43 evaluated adsorption properties revealed the existence of 4 various classes of adsorbents. The stage of the model construction was preceded by the identification and the calculation of descriptors. Those who are retained characterize, essentially, the confinement state responsible for the selectivity within the zeolite. We quote the sites II cations size, the sites III occupation or still the sites II saturation. Two statistical methods were used to build the structures-properties relationship. First, a multiple linear regression with, as predictive variables, the 3 quoted descriptors. The retained explanatory model predicts with a correlation coefficient R² = 0,78. So, the discriminant analysis was used. The same 3 descriptors served to predict the affectation of adsorbents in the 4 identified classes with a total prediction percentage of 76 %

Orientadores: Furio Damiani, Romis Ribeiro de Faissol Attux / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-27T01:42:11Z (GMT). No. of bitstreams: 1 FernandesJunior_AntonioCarlosLopes_D.pdf: 3251957 bytes, checksum: 7a047b751489da833ab7c5efd9cd86ee (MD5) Previous issue date: 2015 / Resumo: A deteção de tempo em um sinal musical é uma tarefa muito importante em diversas aplicações. A presente tese apresenta os resultados da detecção de andamento usando uma nova abordagem baseada na extração de atributos de um conjunto de funções de detecção de periodicidade e aprendizado de máquina. Para isto a transformada wavelet foi utilizada para separar o sinal musical em diferentes resoluções e o domínio complexo retificado foi aplicado para a construção de funções de deteccão de onsets. Em seguida, as funções de deteccão de periodicidade para cada nível wavelet foram geradas por operações de autocorrelação. Descritores de áudio clássicos foram adaptados e extraídos de cada função de periodicidade e foram usados como entradas para a máquina de aprendizado que mapeia os descritores para o tempo da música. As máquinas utilizadas foram o perceptron de múltiplas camadas e a máquina de aprendizado extremo, com propostas diferenciadas de configuração. Um método para classificação e avaliação dos descritores foi proposto. Também, neste trabalho, um novo descritor foi proposto. Um método de seleção forward de atributos via Gram-Schmidt foi aplicado para a escolha do melhor subconjunto para o treinamento da máquina. Foi ainda aplicado um método de clustering via K-means para a partilha de observações entre os conjuntos de treinamento, teste e validação, e foi proposto um novo método de seleção de observações via análise de componentes principais denominado de seleção esférica de observações / Abstract: Tempo detection in a music signal is a very important task for many applications. This thesis presents results concerning this task using a new approach based on the extraction of features from a set of periodicity detection functions and on machine learning. The wavelet transform was utilized to separate the musical signal at different resolutions and the rectified complex domain was applied to the construction of onset detection functions. Then, periodicity detection functions for each resolution were generated by autocorrelation operations. Classic audio features were extracted from each periodicity function and were used as inputs to a neural network that maps descriptors to music tempo. The used machines were the multilayer perceptron and an extreme learning machine, with different configuration proposals. A method for classification and evaluation of features has been proposed. Also, in this work, a new descriptor has been proposed. A method of forward selection via Gram-Schmidt was applied to choosing the best subset for the machine training. A K-means clustering method was also applied for partitioning observations between the training sets and a new observation selection method via principal component analysis, called spherical selection of observations, was proposed / Doutorado / Eletrônica, Microeletrônica e Optoeletrônica / Doutor em Engenharia Elétrica

The effects of distortion has been investigated prior to this study, however most of these studies focus on the objective physicalities of a certain type of distortion or they might apply distortion in static amounts to examine effects of loudspeaker distortion. Objectively the varying types of distortion may be different, however there are little explanations on how these types subjectively might sound different. This study aimed to investigate how subjective preference and perception of the timbral attributes warmth and roughness may vary between types of distortion, and if there was a pattern between these using three different types of distortion (zero-crossing, solid state and tube), applied at two different levels (high and low) and to two different instruments (guitar and vocals). The outcome indicated that subjects most prefer tube distortion and that this distortion was considered to provide the most amounts of warmth while also the least amounts of roughness. There were also interaction effects indicating guitar being less sensitive about the level of distortion while being more sensitive about the type of distortion for the measures of preference and amounts of roughness, when compared to vocals.

<div>An improved understanding of energy localization ("hot spots'') is needed to improve the safety and performance of explosives. In this work I establish a variety of experimental and computational methods to aid in the investigation of hot spots. In particular, focus is centered on the implicit relationship between hot spots and energetic material sensitivity. To begin, I propose a technique to visualize and quantify the properties of a dynamic hot spot from within an energetic composite subjected to ultrasonic mechanical excitation. The composite is composed of an optically transparent binder and a countable number of HMX crystals. The evolving temperature field is measured by observing the luminescence from embedded phosphor particles and subsequent application of the intensity ratio method. The spatial temperature precision is less than 2% of the measured absolute temperature in the temperature regime of interest (23-220 C). The temperature field is mapped from within an HMX-binder composite under periodic mechanical excitation.</div><div> </div><div> Following this experimental effort I examine the statistics behind the most prevalent and widely used sensitivity test (at least within the energetic materials community) and suggest adaptions to generalize the approach to bimodal latent distributions. Bimodal latent distributions may occur when manufacturing processes are inconsistent or when competing initiation mechanisms are present.</div><div> </div><div> Moving to simulation work, I investigate how the internal void structure of a solid explosive influences initiation behavior -- specifically the criticality of isolated hot spots -- in response to a shock insult. In the last decade, there has been a significant modeling and simulation effort to investigate the thermodynamic response of a shock induced pore collapse process in energetic materials. However, the majority of these studies largely ignore the geometry of the pore and assume simplistic shapes, typically a sphere. In this work, the influence of pore geometry on the sensitivity of shocked HMX is explored. A collection of pore geometries are retrieved from micrographs of pressed HMX samples via scanning electron microscopy. The shock induced collapse of these geometries are simulated using CTH and the response is reduced to a binary "critical'’ / "sub-critical'' result. The simulation results are used to assign a minimum threshold velocity required to exhibit a critical response to each pore geometry. The pore geometries are subsequently encoded to numerical representations and a functional mapping from pore shape to a threshold velocity is developed using supervised machine-learned models. The resulting models demonstrate good predictive capability and their relative performance is explored. The established models are exposed via a web application to further investigate which shape features most heavily influence sensitivity.</div><div> </div><div> Finally, I develop a convolutional neural network capable of directly parsing the 3D electronic structure of a molecule described by spatial point data for charge density and electrostatic potential represented as a 4D tensor. This method effectively bypasses the need to construct complex representations, or descriptors, of a molecule. This is beneficial because the accuracy of a machine learned model depends on the input representation. Ideally, input descriptors encode the essential physics and chemistry that influence the target property. Thousands of molecular descriptors have been proposed and proper selection of features requires considerable domain expertise or exhaustive and careful statistical downselection. In contrast, deep learning networks are capable of learning rich data representations. This provides a compelling motivation to use deep learning networks to learn molecular structure-property relations from "raw'' data. The convolutional neural network model is jointly trained on over 20,000 molecules that are potentially energetic materials (explosives) to predict dipole moment, total electronic energy, Chapman-Jouguet (C-J) detonation velocity, C-J pressure, C-J temperature, crystal density, HOMO-LUMO gap, and solid phase heat of formation. To my knowledge, this demonstrates the first use of the complete 3D electronic structure for machine learning of molecular properties. </div>

In this Ph.D. thesis, we develop effective techniques for medical image classification, particularly, for histopathological and magnetic resonance images (MRI). Our techniques are capable of handling the high variability in the content of such images. Handcrafted techniques based on texture analysis are used for the classification task. We also use deep learning models but training such models from scratch can be a challenging process, instead, we employ deep features and transfer learning. First, we propose a combined texture-based feature representation that is computed in the complex shearlet domain for histopathological image classification. With complex coefficients, we examine both the magnitude and relative phase of shearlets to form the feature space. Our proposed techniques are successful for histopathological image classification. Furthermore, we investigate their ability to generalize to MRI datasets that present an additional challenge, namely high dimensionality. An MRI sample consists of a large number of slices. Our proposed shearlet-based feature representation for histopathological images cannot be used without adjustment. Therefore, we consider the 3D shearlet transform given the volumetric nature of MRI data. An advantage of the 3D shearlet transform is that it takes into consideration adjacent slices of MRI data. Secondly, we study the classification of histopathological images using pre-trained deep learning models. A pre-trained deep learning model can act as a starting point for datasets with a limited number of samples. Therefore, we used various models either as unsupervised feature extractors, or weight initializers to classify histopathological images. When it comes to MRI samples, fine-tuning a deep learning model is not straightforward. Pre-trained models are trained on RGB images which have a channel size of 3, but an MRI sample has a larger number of slices. Fine-tuning a convolutional neural network (CNN) requires adjusting a model to work with MRI data. We fine-tune pre-trained models and then use them as feature extractors. Thereafter, we demonstrate the effectiveness of fine-tuned deep features with classical machine learning (ML) classifiers, namely a support vector machine and a decision tree bagger. Furthermore, instead of using a classical ML classifier for the MRI sample, we built a custom CNN that takes both the 3D shearlet descriptors and deep features as an input. This custom network processes our feature representation end-to-end and then classifies an MRI sample. Our custom CNN is more effective in comparison to a classical ML on a hidden MRI dataset. It is an indication that our CNN model is less susceptible to over-fitting.

No description available.

No description available.

No description available.

No description available.