The aim of the diploma project is to find a method through which it will be possibleto classify the selected emotion from speech. At the beginning of the work deals with the description of the human body and their voice-generating operation. Furthermore, the text deals with the problem of the human voice into digital form.Great attention is paid to the parameters of the speech signal with an emphasis on describing the symptoms to help the selected emotion. The work deals with therecognition of emotions and a description of some of them. The main part is finding the best methods to reduce symptoms of segmental and suprasegmental speech utterances. The results of success was achieved by comparing the classification of selected emotions when using multiple methods and compare their results. The most important criterion in assessing the results ofthe reduction parameters of the speech signal, based on previous research in this area.

The aim of this master's thesis is to get familiar with problems of data mining and classification. This thesis also continues with application SUNAR, which is upgraded in practical part with SVM classification of persons passing between cameras. In the conclusion, we discuss ways to improve classification and person recognition in application SUNAR.

The document is discussing the issue of the computer vision with ability to character recignition in the image. Wavelet transform is used for preprocessing the image. Pixel energy feature is firstly used for searchich candidate text pixels. Density region growing method is then used to collect candidate pixels to the separate regions, which will be candidate text regions. Several of the features are calculated over the regions and the SVM classifier is used to derive, if the region is really a text region or not.

This thesis is focused on EEG processing and emotion classification within two-dimensional emotion space. First part consists of theoretical research about emotional responses of human subjects on sound, image and video stimuli. Emotions are examined from aspect of physiology and psychology. Furthermore technical overview of measurement, analysis and emotion classification within two-dimensional emotional space is discussed. Based on gathered knowledge measurement setup with audiovisual stimuli was designed and measured with two independent instruments – EGI GES400MR in laboratory conditions and Emotiv EPOC device in non-laboratory conditions. Signals were processed and emotions were classified based on chosen features. Performance of classifiers in multiple feature selection setups was evaluated.

Thesis focuses on disk arrays, where the goal is to design test scenarios to measure performance of disk array and use predictive analytics tools to train a model that will predict the selected performance parameter on a measured set of data. The implemented web application demonstrates the functionality of the trained model and shows estimate of the disk array performance.

Cette thèse s’intéresse à l’application des méthodes d’apprentissage statistique pour la prédiction de température d’un composant électronique présent dans un radar. On étudie un cas simplifié des systèmes réels, le système étudié se limitant à un seul composant monté sur un système de refroidissement réduit. Le premier chapitre est consacré à la modélisation thermique. Après avoir présenté les principaux modes de transmission de l’agitation thermique, les modèles analytiques et numériques qui en découlent sont étudiés. En utilisant cette connaissance,le deuxième chapitre propose de choisir dans les méthodes de mesures les plus adaptées aux spécifications et aux contraintes de l’application choisie. Une fois que les bases de données ont été établies, nous pouvons utiliser dans le troisième chapitre les techniques de l’apprentissage statistique pour construire un modèle dynamique. Après un bref rappel sur les tenants et les aboutissants de la modélisation statistique, quatre familles de méthodes seront présentées : les modèles linéaires, les réseaux de neurones, les réseaux bayésiens dynamiques et les machines à vecteur support (SVM). Enfin, le quatrième chapitre est l’occasion de présenter une méthode de modélisation originale.En effet, après avoir détaillé la mise en oeuvre des méthodes d’identification de représentation d’état, nous verrons comment prendre en compte des a priori théoriques au cours de l’apprentissage de ce type de modèle, à savoir une contrainte de stabilité. / This thesis is focused on the application of statistical learning methods for the temperature prediction of an electronic component embedded in a radar. We study a simplified case of real systems, the system under study is limited to a single component mounted on a reduced cooling system. The first chapter is devoted to heat transfer modelisation. After presenting the major mechanisms of thermal agitation transmission, analytical and numerical models are studied. Using this knowledge, the second chapter offers a survey on the methods of temperature measurement, choosing the fittest according to the specifications and the constraints of the chosen application.Once databases have been established, we can use in the third chapter statistical learning techniques to build a dynamic model. After a brief reminder about the ins and outs of statistical modeling, four families of methods willbe presented : linear models, neural networks, dynamic bayesian networks and support vector machines (SVM).The fourth chapter is an opportunity to present a novel method of modeling. Indeed, after a presentation of themethods for the identification of state representation, we see how to take into account theoretical apriorism during learning of this model type, ie a stability constraint.

Many software companies use issue tracking systems to organize their work. However, when working on large projects, across multiple teams, a problem of finding the correctteam to solve a certain issue arises. One team might detect a problem, which must be solved by another team. This can take time from employees tasked with finding the correct team and automating the dispatching of these issues can have large benefits for the company. In this thesis, the use of machine learning methods, mainly convolutional neural networks (CNN) for text classification, has been applied to this problem. For natural language processing both word- and character-level representations are commonly used. The results in this thesis suggests that the CNN learns different information based on whether word- or character-level representation is used. Furthermore, it was concluded that the CNN models performed on similar levels as the classical Support Vector Machine for this task. When compared to a human expert, working with dispatching issues, the best CNN model performed on a similar level when given the same information. The high throughput of a computer model, therefore, suggests automation of this task is very much possible.

La quantité d'images disponible sur Internet ne fait que croître, engendrant un besoin d'algorithmes permettant de fouiller ces images et retrouver de l'information. Les systèmes de recherche d'images par le contenu ont été développées dans ce but. Mais les bases de données grandissant, de nouveaux défis sont apparus. Dans cette thèse, la classification à grain fin est étudiée en particulier. Elle consiste à séparer des images qui sont relativement semblables visuellement mais représentent différents concepts, et à regrouper des images qui sont différentes visuellement mais représentent le même concept. Il est montré dans un premier temps que les techniques classiques de recherche d'images par le contenu rencontrent des difficultés à effectuer cette tâche. Même les techniques utilisant les machines à vecteur de support (SVM), qui sont très performants pour la classification, n'y parviennent pas complètement. Ces techniques n'explorent souvent pas assez l'espace de recherche pour résoudre ce problème. D'autres méthodes, comme les algorithmes évolutionnaires sont également étudiées pour leur capacité à identifier des zones intéressantes de l'espace de recherche en un temps raisonnable. Toutefois, leurs performances restent encore limitées. Par conséquent, l'apport de la thèse consiste à proposer un système hybride combinant un algorithme évolutionnaire et un SVM a finalement été développé. L'algorithme évolutionnaire est utilisé pour construire itérativement un ensemble d'apprentissage pour le SVM. Ce système est évalué avec succès sur la base de données Caltech-256 contenant envieront 30000 images réparties en 256 catégories / Given the ever growing amount of visual content available on the Internet, the need for systems able to search through this content has grown. Content based image retrieval systems have been developed to address this need. But with the growing size of the databases, new challenges arise. In this thesis, the fine grained classification problem is studied in particular. It is first shown that existing techniques, and in particular the support vector machines which are one of the best image classification technique, have some difficulties in solving this problem. They often lack of exploration in their process. Then, evolutionary algorithms are considered to solve the problem, for their balance between exploration and exploitation. But their performances are not good enough either. Finally, an hybrid system combining an evolutionary algorithm and a support vector machine is proposed. This system uses the evolutionary algorithm to iteratively feed the support vector machine with training samples. The experiments conducted on Caltech-256, a state of the art database containing around 30000 images, show very encouraging results

Possibilities of object based image analysis for monitoring of meadow vegetation and management in the Krkonoše Mountains National Park Abstract The main aim of the thesis was to evaluate possibilities of Object Based Image Analysis (OBIA) of WorldView-2 satellite image data and aerial optical scanner for meadow vegetation and managment types classification in Krkonoše Mountains National Park. The classification was based on legend prepared by botanist of the national park. The second goal was to compare classification accuracy of Object Based Image Analysis and neural net classification method that was used by Pomahačová (2012) for the same area and the same WorldView-2 data. OBIA for meadow vegetation was conducted using SVM algorithm and "Decision Tree" algorithm. The classification accuracy was estimated using reference points from the field. The thesis puts the requirements (optimal parameters and conditions) for successfull object based classification of mountain meadow vegetation into a new perspective. Key words: Object based classification, meadows, WorldView-2, aerial optical scanner, SVM, KRNAP

Having enough data about the usage of tyre types on the road can lead to a better understanding of the consequences of studded tyres on the environment. This paper is focused on training and testing a machine learning model which can be further integrated into a larger system for automation of the data collection process. Different machine learning algorithms, namely CNN, SVM, and Random Forest, were compared in this experiment. The method used in this paper is an empirical method. First, sound data for studded and none-studded tyres was collected from three different locations in the city of Gävle/Sweden. A total of 760 Mel spectrograms from both classes was generated to train and test a well-known CNN model (AlexNet) on MATLAB. Sound features for both classes were extracted using JAudio to train and test models that use SVM and Random Forest classifi-ers on Weka. Unnecessary features were removed one by one from the list of features to improve the performance of the classifiers. The result shows that CNN achieved accuracy of 84%, SVM has the best performance both with and without removing some audio features (i.e 94% and 92%, respectively), while Random Forest has 89 % accuracy. The test data is comprised of 51% of the studded class and 49% of the none-studded class and the result of the SVM model has achieved more than 94 %. Therefore, it can be considered as an acceptable result that can be used in practice.