This dissertation is a study of artificial intelligence for diagnosing the condition of high voltage bushings. The techniques include neural networks, genetic algorithms, fuzzy set theory, particle swarm optimisation, multi-classifier systems, factor analysis, principal component analysis, multidimensional scaling, data-fusion techniques, automatic relevance determination and autoencoders. The classification is done using Dissolved Gas Analysis (DGA) data based on field experience together with criteria from IEEEc57.104 and IEC60599. A review of current literature showed that common methods for the diagnosis of bushings are: partial discharge, DGA, tan- (dielectric dissipation factor), water content in oil, dielectric strength of oil, acidity level (neutralisation value), visual analysis of sludge in suspension, colour of the oil, furanic content, degree of polymerisation (DP), strength of the insulating paper, interfacial tension or oxygen content tests. All the methods have limitations in terms of time and accuracy in decision making. The fact that making decisions using each of these methods individually is highly subjective, also the huge size of the data base of historical data, as well as the loss of skills due to retirement of experienced technical staff, highlights the need for an automated diagnosis tool that integrates information from the many sensors and recalls the historical decisions and learns from new information. Three classifiers that are compared in this analysis are radial basis functions (RBF), multiple layer perceptrons (MLP) and support vector machines (SVM). In this work 60699 bushings were classified based on ten criteria. Classification was done based on a majority vote. The work proposes the application of neural networks with particle swarm optimisation (PSO) and genetic algorithms (GA) to compensate for missing data in classifying high voltage bushings. The work also proposes the application of fuzzy set theory (FST) to diagnose the condition of high voltage bushings. The relevance and redundancy detection methods were able to prune the redundant measured variables and accurately diagnose the condition of the bushing with fewer variables. Experimental results from bushings that were evaluated in the field verified the simulations. The results of this work can help to develop real-time monitoring and decision making tools that combine information from chemical, electrical and mechanical measurements taken from bushings.

Learning the parts of objects have drawn more attentions in computer science recently, and they have been playing the important role in computer applications such as object recognition, self-driving cars, and image processing, etc… However, the existing research such as traditional non-negative matrix factorization (NMF), principal component analysis (PCA), and vector quantitation (VQ) has not been discovering the ground-truth bases which are basic components representing objects. On this thesis, I am proposed to study on pattern recognition enhancement combined non-negative matrix factorization (NMF) with automatic relevance determination (ARD). The main point of this research is to propose a new technique combining the algorithm Expectation Maximization (EM) with Automatic Relevance Determination (ARD) to discover the ground truth basis of datasets, and then to compare my new proposed technique to the others such as: traditional NMF, sparseness constraint and graph embedding in pattern recognition problems to verify if my method has over performance in accuracy rate than the others. Particularly, the new technique will be tested on variety of datasets from simple to complex one, from synthetic datasets to real ones. To compare the performance, I split these datasets into 10 random partitions as the training and the testing sets called 10-fold cross validation, and then use the technique called Euclidean algorithm to classify them and test their accuracy. As the result, my proposed method has higher accuracy than the others, and it is good to use in pattern recognition problems with missing data.

No description available.

Cette thèse porte sur un problème de calibration d'un modèle électromécanique de cœur, personnalisé à partir de données d'imagerie médicale 3D+t ; et sur celui - en amont - de suivi du mouvement cardiaque. A cette fin, nous adoptons une méthodologie fondée sur l'apprentissage statistique. Pour la calibration du modèle mécanique, nous introduisons une méthode efficace mêlant apprentissage automatique et une description statistique originale du mouvement cardiaque utilisant la représentation des courants 3D+t. Notre approche repose sur la construction d'un modèle statistique réduit reliant l'espace des paramètres mécaniques à celui du mouvement cardiaque. L'extraction du mouvement à partir d'images médicales avec quantification d'incertitude apparaît essentielle pour cette calibration, et constitue l'objet de la seconde partie de cette thèse. Plus généralement, nous développons un modèle bayésien parcimonieux pour le problème de recalage d'images médicales. Notre contribution est triple et porte sur un modèle étendu de similarité entre images, sur l'ajustement automatique des paramètres du recalage et sur la quantification de l'incertitude. Nous proposons une technique rapide d'inférence gloutonne, applicable à des données cliniques 4D. Enfin, nous nous intéressons de plus près à la qualité des estimations d'incertitude fournies par le modèle. Nous comparons les prédictions du schéma d'inférence gloutonne avec celles données par une procédure d'inférence fidèle au modèle, que nous développons sur la base de techniques MCMC. Nous approfondissons les propriétés théoriques et empiriques du modèle bayésien parcimonieux et des deux schémas d'inférence / This thesis focuses on the calibration of an electromechanical model of the heart from patient-specific, image-based data; and on the related task of extracting the cardiac motion from 4D images. Long-term perspectives for personalized computer simulation of the cardiac function include aid to the diagnosis, aid to the planning of therapy and prevention of risks. To this end, we explore tools and possibilities offered by statistical learning. To personalize cardiac mechanics, we introduce an efficient framework coupling machine learning and an original statistical representation of shape & motion based on 3D+t currents. The method relies on a reduced mapping between the space of mechanical parameters and the space of cardiac motion. The second focus of the thesis is on cardiac motion tracking, a key processing step in the calibration pipeline, with an emphasis on quantification of uncertainty. We develop a generic sparse Bayesian model of image registration with three main contributions: an extended image similarity term, the automated tuning of registration parameters and uncertainty quantification. We propose an approximate inference scheme that is tractable on 4D clinical data. Finally, we wish to evaluate the quality of uncertainty estimates returned by the approximate inference scheme. We compare the predictions of the approximate scheme with those of an inference scheme developed on the grounds of reversible jump MCMC. We provide more insight into the theoretical properties of the sparse structured Bayesian model and into the empirical behaviour of both inference schemes