Automatic analysis of facial actions (AFA) can reveal a person’s emotion, intention, and physical state, and make possible a wide range of applications. To enable reliable, valid, and efficient AFA, this thesis investigates automatic analysis of facial actions through transductive, supervised and unsupervised learning. Supervised learning for AFA is challenging, in part, because of individual differences among persons in face shape and appearance and variation in video acquisition and context. To improve generalizability across persons, we propose a transductive framework, Selective Transfer Machine (STM), which personalizes generic classifiers through joint sample reweighting and classifier learning. By personalizing classifiers, STM offers improved generalization to unknown persons. As an extension, we develop a variant of STM for use when partially labeled data are available. Additional challenges for supervised learning include learning an optimal representation for classification, variation in base rates of action units (AUs), correlation between AUs and temporal consistency. While these challenges could be partly accommodated with an SVM or STM, a more powerful alternative is afforded by an end-to-end supervised framework (i.e., deep learning). We propose a convolutional network with long short-term memory (LSTM) and multi-label sampling strategies. We compared SVM, STM and deep learning approaches with respect to AU occurrence and intensity in and between BP4D+ [282] and GFT [93] databases, which consist of around 0.6 million annotated frames. Annotated video is not always possible or desirable. We introduce an unsupervised Branch-and-Bound framework to discover correlated facial actions in un-annotated video. We term this approach Common Event Discovery (CED). We evaluate CED in video and motion capture data. CED achieved moderate convergence with supervised approaches and enabled discovery of novel patterns occult to supervised approaches.

Este trabalho trata de ambientes de software para a realização de teste e caracterização de dispositivos, componentes ou circuitos eletro-eletrônicos, de forma automatizada. Ênfase especial é dada à problemática relacionada ao teste e caracterização automatizados de dispositivos e circuitos integrados. O assunto é tratado sob dois pontos de vista distintos e complementares: i) Sob o ponto de vista do engenheiro de teste e caracterização, que realiza experimentos físicos, que são as medidas e aquisições de dados, processa, visualiza e analisa dados. ii) Sob o ponto de vista do projetista de ferramentas de software, que desenvolve programas de computador para automatizar as tarefas rotineiramente realizadas durante o teste e a caracterização. Após a analise do assunto em questão, um ambiente de software (Framework), chamado SGC, é proposto e implementado. O SGC foi implementado em ambiente MS-WindowsTM através de um paradigma de orientação a objetos, e pretende atender as necessidades inerentes ao teste e caracterização automatizados, quando tratados sob os dois pontos de vista citados. O ambiente SGC é um sistema aberto, a fim de permitir o fácil acoplamento de novas facilidades, bem como mostra-se um sistema prático para suportar rotinas de teste e caracterização em laboratório. / This work deals with software environments for automatic test and characterization of electro-electronical devices, components and circuits. Special attention is paid to the features of testing and characterizing integrated devices and circuits. The subject is treated in two different and complementary views: i) The needs of the test and characterization engineer are addressed. The test engineer carries out physical experiments, which embody measurements and data acquisitions, data processing, visualization and analysis. ii) The needs of the software tools developer, who develops computer programs for the automation of the procedures that are usually carried out during test and characterization, are also addressed. After the analysis of the subject under study, a software framework, called SGC ("Sistema de Gerenciamento e Controle"), is proposed and implemented. The SGC Framework was implemented under MS-WindowsTm using a object oriented approach. The SGC framework aims to fulfill the needs inherent to the automatic test and characterization, when treated using the approaches mentioned above. The SGC Framework is a open system, supporting the easy integration of new software functions to the environment, as well as a practical system for test and characterization laboratory routines.

Este trabalho trata de ambientes de software para a realização de teste e caracterização de dispositivos, componentes ou circuitos eletro-eletrônicos, de forma automatizada. Ênfase especial é dada à problemática relacionada ao teste e caracterização automatizados de dispositivos e circuitos integrados. O assunto é tratado sob dois pontos de vista distintos e complementares: i) Sob o ponto de vista do engenheiro de teste e caracterização, que realiza experimentos físicos, que são as medidas e aquisições de dados, processa, visualiza e analisa dados. ii) Sob o ponto de vista do projetista de ferramentas de software, que desenvolve programas de computador para automatizar as tarefas rotineiramente realizadas durante o teste e a caracterização. Após a analise do assunto em questão, um ambiente de software (Framework), chamado SGC, é proposto e implementado. O SGC foi implementado em ambiente MS-WindowsTM através de um paradigma de orientação a objetos, e pretende atender as necessidades inerentes ao teste e caracterização automatizados, quando tratados sob os dois pontos de vista citados. O ambiente SGC é um sistema aberto, a fim de permitir o fácil acoplamento de novas facilidades, bem como mostra-se um sistema prático para suportar rotinas de teste e caracterização em laboratório. / This work deals with software environments for automatic test and characterization of electro-electronical devices, components and circuits. Special attention is paid to the features of testing and characterizing integrated devices and circuits. The subject is treated in two different and complementary views: i) The needs of the test and characterization engineer are addressed. The test engineer carries out physical experiments, which embody measurements and data acquisitions, data processing, visualization and analysis. ii) The needs of the software tools developer, who develops computer programs for the automation of the procedures that are usually carried out during test and characterization, are also addressed. After the analysis of the subject under study, a software framework, called SGC ("Sistema de Gerenciamento e Controle"), is proposed and implemented. The SGC Framework was implemented under MS-WindowsTm using a object oriented approach. The SGC framework aims to fulfill the needs inherent to the automatic test and characterization, when treated using the approaches mentioned above. The SGC Framework is a open system, supporting the easy integration of new software functions to the environment, as well as a practical system for test and characterization laboratory routines.

Este trabalho trata de ambientes de software para a realização de teste e caracterização de dispositivos, componentes ou circuitos eletro-eletrônicos, de forma automatizada. Ênfase especial é dada à problemática relacionada ao teste e caracterização automatizados de dispositivos e circuitos integrados. O assunto é tratado sob dois pontos de vista distintos e complementares: i) Sob o ponto de vista do engenheiro de teste e caracterização, que realiza experimentos físicos, que são as medidas e aquisições de dados, processa, visualiza e analisa dados. ii) Sob o ponto de vista do projetista de ferramentas de software, que desenvolve programas de computador para automatizar as tarefas rotineiramente realizadas durante o teste e a caracterização. Após a analise do assunto em questão, um ambiente de software (Framework), chamado SGC, é proposto e implementado. O SGC foi implementado em ambiente MS-WindowsTM através de um paradigma de orientação a objetos, e pretende atender as necessidades inerentes ao teste e caracterização automatizados, quando tratados sob os dois pontos de vista citados. O ambiente SGC é um sistema aberto, a fim de permitir o fácil acoplamento de novas facilidades, bem como mostra-se um sistema prático para suportar rotinas de teste e caracterização em laboratório. / This work deals with software environments for automatic test and characterization of electro-electronical devices, components and circuits. Special attention is paid to the features of testing and characterizing integrated devices and circuits. The subject is treated in two different and complementary views: i) The needs of the test and characterization engineer are addressed. The test engineer carries out physical experiments, which embody measurements and data acquisitions, data processing, visualization and analysis. ii) The needs of the software tools developer, who develops computer programs for the automation of the procedures that are usually carried out during test and characterization, are also addressed. After the analysis of the subject under study, a software framework, called SGC ("Sistema de Gerenciamento e Controle"), is proposed and implemented. The SGC Framework was implemented under MS-WindowsTm using a object oriented approach. The SGC framework aims to fulfill the needs inherent to the automatic test and characterization, when treated using the approaches mentioned above. The SGC Framework is a open system, supporting the easy integration of new software functions to the environment, as well as a practical system for test and characterization laboratory routines.

This doctoral thesis focuses on the problems of IGBT failure prediction in pulse converters using measurable changes of selected parameters (so--called trending variables) being influenced of transistor degradation during aging. Firstly the state--of--the--art in this field is presented in the dizertation. The description of designed and constructed automated measurement stand follows, enabling monitoring and recording of switching processes during accelerated aging. Further the problems of high--bandwidth measurement of electrical quantities during IGBT switching are described. Especially the problems of current sensing are analyzed and the most suitable sensor is selected. The data recorded using the developed apparatus served to identify potential trending variables allowing the failure prediction. Here the dependence of trending variables on aging and on parasitic influences (current, temperature, voltage) had to be distinguished. Finally the evaluation of trending variables is performed. Their insignificant sensitivity on accelerated aging is shown which complicates their practical implementation for the purpose of failure prediction.

The main purpose of the thesis Automatic measurement of induction machine using LabVIEW was to develope an automated measuring system, which is used to perform tests of induction motors. The algorithm of the system is programmed in LabVIEW. In the practical part of this thesis, a measurement of the motor Atas Elektromotory Náchod a.s. T22VT512 is carried out, in order to verificate functions of the algorithm, and to perform tests of the motor to analyse losses. Another part of the work is dedicated to the electromagnetic calculation of the motor T22VT512. For this purpose, two softwares with different principles of calculation have been used. Firstly, the calculation is solved by an analytical based software called RMxprt. Secondly, the software Maxwell 2D is used to make the calculation of electric and magnetic fields by the finite element method.