Philosophiae Doctor - PhD / This research investigated the application of recurrent neural networks (RNNs) for recognition of facial expressions based on facial action coding system (FACS). Support vector machines (SVMs) were used to validate the results obtained by RNNs. In this approach, instead of recognizing whole facial expressions, the focus was on the recognition of action units (AUs) that are defined in FACS. Recurrent neural networks are capable of gaining knowledge from temporal data while SVMs, which are time invariant, are known to be very good classifiers. Thus, the research consists of four important components: comparison of the use of image sequences against single static images, benchmarking feature selection and network optimization approaches, study of inter-AU correlations by implementing multiple output RNNs, and study of difference images as an approach for performance improvement. In the comparative studies, image sequences were classified using a combination of Gabor filters and RNNs, while single static images were classified using Gabor filters and SVMs. Sets of 11 FACS AUs were classified by both approaches, where a single RNN/SVM classifier was used for classifying each AU. Results indicated that classifying FACS AUs using image sequences yielded better results than using static images. The average recognition rate (RR) and false alarm rate (FAR) using image sequences was 82.75% and 7.61%, respectively, while the classification using single static images yielded a RR and FAR of 79.47% and 9.22%, respectively. The better performance by the use of image sequences can be at- tributed to RNNs ability, as stated above, to extract knowledge from time-series data. Subsequent research then investigated benchmarking dimensionality reduction, feature selection and network optimization techniques, in order to improve the performance provided by the use of image sequences. Results showed that an optimized network, using weight decay, gave best RR and FAR of 85.38% and 6.24%, respectively. The next study was of the inter-AU correlations existing in the Cohn-Kanade database and their effect on classification models. To accomplish this, a model was developed for the classification of a set of AUs by a single multiple output RNN. Results indicated that high inter-AU correlations do in fact aid classification models to gain more knowledge and, thus, perform better. However, this was limited to AUs that start and reach apex at almost the same time. This suggests the need for availability of a larger database of AUs, which could provide both individual and AU combinations for further investigation. The final part of this research investigated use of difference images to track the motion of image pixels. Difference images provide both noise and feature reduction, an aspect that was studied. Results showed that the use of difference image sequences provided the best results, with RR and FAR of 87.95% and 3.45%, respectively, which is shown to be significant when compared to use of normal image sequences classified using RNNs. In conclusion, the research demonstrates that use of RNNs for classification of image sequences is a new and improved paradigm for facial expression recognition.

This thesis is dedicated to the development of new energy detectors employed in the detection of unknown signals in the presence of non-Gaussian and non-independent noise samples. To this end, an extensive study has been conducted on di erent energy detection structures, and novel techniques have been proposed which are capable of dealing with these problematic situations. The energy detector is proposed as an optimum solution to detect uncorrelated Gaussian signals, or as a generalized likelihood ratio test to detect entirely unknown signals. In both cases, the background noise must be uncorrelated Gaussian. However, energy detectors degrade when the noise does not ful ll these characteristics. Therefore, two extensions are proposed. The rst is the extended energy detector, which deals with the problem of non-Gaussian noise; and the second is the preprocessed extended energy detector, used when the noise also possesses non-independent samples. A generalization of the matched subspace lter is likewise proposed based on a modi cation of the Rao test. In order to evaluate the expected improvement of these extensions with respect to the classical energy detector, a signalto- noise ratio enhancement factor is de ned and employed to illustrate the improvement achieved in detection. Furthermore, we demonstrate how the uncertainty introduced by the unknown signal duration can decrease the performance of the energy detector. In order to improve this behavior, a multiple energy detector, based on successive subdivisions of the original observation interval, is presented. This novel detection technique leads to a layered structure of energy detectors whose observation vectors are matched to di erent intervals of signal duration. The corresponding probabilities of false alarm and detection are derived for a particular subdivision strategy, and the required procedures for their general application to other possible cases are indicated. The experiments reveal the advantages derived from utilizing this novel structure, making it a worthwhile alternative to the single detector when a signi cant mismatch is present between the original observation length and the actual duration of the signal. / Moragues Escrivá, J. (2011). New energy detector extensions with application in sound based surveillance systems [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/11520 / Palancia

[pt] Identificar um indivíduo a partir de uma imagem de face é uma tarefa simples para seres humanos e extremamente difícil para a Visão Computacional. Esta questão tem motivado diversos grupos de pesquisa em todo o mundo, especialmente a partir de 1993. Inúmeros trabalhos realizados até o momento encaram uma imagem digital de n pixels como um vetor num espaço n-dimensional, onde n é em geral muito grande. Imagens de rostos humanos possuem, contudo, grande redundância: todas contém dois olhos, um nariz, uma boca, e etc. É possível, portanto, trabalhar em uma base deste espaço em que faces possam ser adequadamente caracterizadas a partir de um conjunto de p componentes, onde p é muito menor quen. É com este enfoque que o presente trabalho estuda sistemas de reconhecimento de faces que consistem de um estágio de redução de dimensionalidade, realizado pela técnica de Análise de Componentes Principais (PCA), seguido de um modelo classificador. No estágio da PCA, as imagens de n pixels são transformadas em vetores de p características a partir de um conjunto de treinamento. Três classificadores conhecidos na literatura são estudados: os classificadores de distância (EUclideana e de Mahalanobis), a rede neural de Funções Base Radiais (RBF), e o classificador de Fisher. Este trabalho propõe, ainda, um novo classificador que introduz o conceito de Matrizes de Covariança Misturadas (MPM) no classificador gaussiano de Máxima Probabilidade. Os quatros classificadores são avaliados através da variação de seus respectivos parâmetros e utilizam como imagens o banco de faces da Olivetti. Nos experimentos realizados para comparar tais abordagens, o novo classificador proposto atingiu as maiores taxas de reconhecimento e apresentou menorsensibilidade à escolha do conjunto de faces de treinamento. / [en] Identifying an individual based on a face image is a simple task for humans to perform and a very difficult one for Vision Computing. Since 1993, several research groups in all over the world have been studied this problem. Most of the methods proposed for recognizing the identity of an individual represent a n intensity pixel image as a n- dimensional vector, when, in general, n is a very large number value. Face images are highly redundant, since every individual has two eyes, one nose, one mouth and so on. Then, instead of using n intensity values, it is generally possible to characterize an image instance by a set of p features, for p < < n. This work studies face recognition systems consisting of a PCA stage for dimensionality reduction followed by a classifier. The PCA stage takes the n-pixels face images and produces the corresponding p most expensive features, based on the whole available training set. Three classifiers proposed in the literature are studied: the Euclidean and Mahalanobis distances, the RBF neural network, and the Fisher classifier. This work also proposes a new classifier, which introduces the concept of Mixture Covariance Matrices (MPM) in the Minimum Total Probality of Misclassification rule for normal populations. The four classifiers are evaluated using the Olivetti Face Database varying their parameters in a wide range. In the experiments carried out to compare those approaches the new proposed classifier reached the best recognition rates and showed to be less sensitive to the choice of the training set.

abstract: Functional regression models are widely considered in practice. To precisely understand an underlying functional mechanism, a good sampling schedule for collecting informative functional data is necessary, especially when data collection is limited. However, scarce research has been conducted on the optimal sampling schedule design for the functional regression model so far. To address this design issue, efficient approaches are proposed for generating the best sampling plan in the functional regression setting. First, three optimal experimental designs are considered under a function-on-function linear model: the schedule that maximizes the relative efficiency for recovering the predictor function, the schedule that maximizes the relative efficiency for predicting the response function, and the schedule that maximizes the mixture of the relative efficiencies of both the predictor and response functions. The obtained sampling plan allows a precise recovery of the predictor function and a precise prediction of the response function. The proposed approach can also be reduced to identify the optimal sampling plan for the problem with a scalar-on-function linear regression model. In addition, the optimality criterion on predicting a scalar response using a functional predictor is derived when the quadratic relationship between these two variables is present, and proofs of important properties of the derived optimality criterion are also provided. To find such designs, an algorithm that is comparably fast, and can generate nearly optimal designs is proposed. As the optimality criterion includes quantities that must be estimated from prior knowledge (e.g., a pilot study), the effectiveness of the suggested optimal design highly depends on the quality of the estimates. However, in many situations, the estimates are unreliable; thus, a bootstrap aggregating (bagging) approach is employed for enhancing the quality of estimates and for finding sampling schedules stable to the misspecification of estimates. Through case studies, it is demonstrated that the proposed designs outperform other designs in terms of accurately predicting the response and recovering the predictor. It is also proposed that bagging-enhanced design generates a more robust sampling design under the misspecification of estimated quantities. / Dissertation/Thesis / Doctoral Dissertation Statistics 2020

No description available.

京都大学 / 0048 / 新制・論文博士 / 博士(医学) / 乙第13387号 / 論医博第2219号 / 新制||医||1048(附属図書館) / 京都大学大学院医学研究科医学専攻 / (主査)教授 溝脇 尚志, 教授 髙橋 良輔, 教授 渡邉 大 / 学位規則第4条第2項該当 / Doctor of Medical Science / Kyoto University / DFAM

The aim of this study is evaluation of using multi-dimensional statistical analyses methods as a tool for simulations of reliability of distribution network. Prefered methods are a cluster analysis (CLU) and a principal component analysis (PCA). CLU is used for a division of objects on the basis of their signs and a calculation of the distance between objects into groups whose characteristics should be similar. The readout can reveal a secret structure in data. PCA is used for a location of a structure in signs of multi-dimensional matrix data. Signs present separate quantities describing the given object. PCA uses a dissolution of a primary matrix data to structural and noise matrix data. It concerns the transformation of primary matrix data into new grid system of principal components. New conversion data are called a score. Principal components generating orthogonal system of new position. Distribution network from the aspect of reliability can be characterized by a number of new statistical quantities. Reliability indicators might be: interruption numbers, interruption time. Integral reliability indicators might be: system average interruption frequency index (SAIFI) and system average interruption duration index (SAIDI). In conclusion, there is a comparison of performed SAIFI simulation according to negatively binomial division and provided values from a distribution company. It is performed a test at description of sign dependences and outlet divisions.

The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (P-QRS-T cycles) selected from animals orthogonal ECGs were preprocessed and used as the input signals. Spectral features vectors (values of cross spectral coherency), principal component and HRV parameters were derived from the beats. The beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. from 87,2 to 100%. Presented results can be suitable in future studies aimed at automatic classification of ECG.

This semester thesis is focused on automated measurement of ECG signal. The theoretical part describes the rise and options ECG signal. Furthermore, the issue is staged principal components analysis, whose output is used as input signal for seasons. They describe the basic methods used in measurement to ECG signal. The practical part is designed in measurement algorithm for ECG signal that has been tested on basic CSE database. The results are discussed in the conclusion.

This diploma thesis is dealing with the detection of blood vessels pulsation in retinal sequences. The goal is to create an algorithm for objective evaluation of pulsation in retinal video sequences.