Pas de résumé en français / Pas de résumé en anglais

Submitted by Luis Ricardo Andrade da Silva (lrasilva@uefs.br) on 2017-11-28T22:15:22Z No. of bitstreams: 1 AILINE-corrigida e completa-enviada pgca.pdf: 18819458 bytes, checksum: 1356b2bb4c6c8fbf60dec709646715da (MD5) / Made available in DSpace on 2017-11-28T22:15:22Z (GMT). No. of bitstreams: 1 AILINE-corrigida e completa-enviada pgca.pdf: 18819458 bytes, checksum: 1356b2bb4c6c8fbf60dec709646715da (MD5) Previous issue date: 2017-08-24 / Advances in the acquisition technology of astronomical spectra resulted in an enormous amount of data. Not being more feasible to analyze them using classical approaches, the need for automatic methods arises. Then, in this research is presented, an Intelligent Algorithm for Identifying Spectral Lines, the AILINE (in Portuguese), which utilizes an artificial neural network to identify the emission lines in the optical spectra of galaxies. This method that in the tests carried out has achieved a accuracy higher than 95% is evaluated and faced with other automatic approaches and other machine learning algorithms. / Os avan?os na tecnologia de aquisi??o de espectros astron?micos resultaram em uma enorme quantidade de dados. N?o sendo mais vi?vel analis?-los usando abordagens cl?ssicas, surge a necessidade de m?todos autom?ticos. Ent?o, nesta pesquisa ? apresentado um Algoritmo Inteligente para Identifica??o de Linhas Espectrais, o AILINE, que utiliza uma Rede Neural Artificial para identificar as linhas em emiss?o nos espectros ?pticos de gal?xias. Este m?todo que nos testes realizados alcan?ou uma acur?cia superior a 95%, ? avaliado e confrontado com outras abordagens autom?ticas e outros algoritmos de aprendizado de m?quina.

Les humains communiquent via différents types de canaux: les mots, la voix, les gestes du corps, des émotions, etc. Pour cette raison, un ordinateur doit percevoir ces divers canaux de communication pour pouvoir interagir intelligemment avec les humains, par exemple en faisant usage de microphones et de webcams. Dans cette thèse, nous nous intéressons à déterminer les émotions humaines à partir d’images ou de vidéo de visages afin d’ensuite utiliser ces informations dans différents domaines d’applications. Ce mémoire débute par une brève introduction à l'apprentissage machine en s’attardant aux modèles et algorithmes que nous avons utilisés tels que les perceptrons multicouches, réseaux de neurones à convolution et autoencodeurs. Elle présente ensuite les résultats de l'application de ces modèles sur plusieurs ensembles de données d'expressions et émotions faciales. Nous nous concentrons sur l'étude des différents types d’autoencodeurs (autoencodeur débruitant, autoencodeur contractant, etc) afin de révéler certaines de leurs limitations, comme la possibilité d'obtenir de la coadaptation entre les filtres ou encore d’obtenir une courbe spectrale trop lisse, et étudions de nouvelles idées pour répondre à ces problèmes. Nous proposons également une nouvelle approche pour surmonter une limite des autoencodeurs traditionnellement entrainés de façon purement non-supervisée, c'est-à-dire sans utiliser aucune connaissance de la tâche que nous voulons finalement résoudre (comme la prévision des étiquettes de classe) en développant un nouveau critère d'apprentissage semi-supervisé qui exploite un faible nombre de données étiquetées en combinaison avec une grande quantité de données non-étiquetées afin d'apprendre une représentation adaptée à la tâche de classification, et d'obtenir une meilleure performance de classification. Finalement, nous décrivons le fonctionnement général de notre système de détection d'émotions et proposons de nouvelles idées pouvant mener à de futurs travaux. / Humans communicate via different types of channels: words, voice, body gesture, emotions …etc. For this reason, implementing these channels in computers is inevitable to make them interact intelligently with humans. Using a webcam and a microphone, computers should figure out what we want to tell from our voice, gesture and face emotions. In this thesis we are interested in figuring human emotions from their images or video in order to use that later in different applications. The thesis starts by giving an introduction to machine learning and some of the models and algorithms we used like multilayer perceptron, convolutional neural networks, autoencoders and finally report the results of applying these models on several facial emotion expression datasets. We moreover concentrate on studying different kinds of autoencoders (Denoising Autoencoder , Contractive Autoencoder, …etc.) and identify some limitations like the possibility of obtaining filters co-adaptation and undesirably smooth spectral curve and we investigate new ideas to address these problems. We also overcome the limitations of training autoencoders in a purely unsupervised manner, i.e. without using any knowledge of task we ultimately want to solve (such as predicting class labels) and develop a new semi-supervised training criterion which exploits the knowledge of the few labeled data to train the autoencoder together with a large amount of unlabeled data in order to learn a representation better suited for the classification task, and obtain better classification performance. Finally, we describe the general pipeline for our emotion detection system and suggest new ideas for future work.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-04-24T19:36:29Z No. of bitstreams: 1 lucascorreanettomachado.pdf: 1851458 bytes, checksum: 2a8b67f0adf8343c28d4e1121a757f6d (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-04-25T15:23:10Z (GMT) No. of bitstreams: 1 lucascorreanettomachado.pdf: 1851458 bytes, checksum: 2a8b67f0adf8343c28d4e1121a757f6d (MD5) / Made available in DSpace on 2017-04-25T15:23:10Z (GMT). No. of bitstreams: 1 lucascorreanettomachado.pdf: 1851458 bytes, checksum: 2a8b67f0adf8343c28d4e1121a757f6d (MD5) Previous issue date: 2013-11-22 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Este trabalho apresenta uma técnica para treinamento de Redes Neurais Artificiais (RNA), capaz de obter os parâmetros da rede através dos dados disponíveis para treinamento, sem necessidade de estabelecer a arquitetura da rede a priori, denominado Método de Segmentações Geométricas Sucessivas (MSGS). O MSGS agrupa os dados de cada classe em Hipercaixa (HC) onde cada caixa é alinhada de acordo com os eixos de maior distribuição de seu conjunto de pontos. Sendo as caixas linearmente separáveis, um hiperplano de separação é identificado originando um neurônio. Caso não seja possível a separação por um único hiperplano, uma técnica de quebra é aplicada para dividir os dados em classes menores para obter novas HCs. Para cada subdivisão novos neurônios são adicionados à rede. Os resultados dos testes realizados apontam para um método rápido e com alta taxa de sucesso. / This work presents a technique for Artificial Neural Network (ANN) training, able to get the network parameters from the available data for training, without establishing the network architecture a priori, called Successive Geometric Segmentation Method (SGSM). The SGSM groups the data of each class into hyperboxes (HB) aligned in accordance with the largest axis of its points distribution. If the HB are linearly separable, a separating hyperplane may be identified resulting a neuron. If it is not, a segmentation technique is applied to divide the data into smaller classes for new HB. For each subdivision new neurons are added to the network. The tests show a rapid method with high success rate.

No description available.

No description available.

This study is concerned with using the popular Recurrent Neural Network (RNN) model, and its variants Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM), on the novel problem of Sentiment Forecasting (SF). The goal of SF is to predict what the sentiment of a response will be in a conversation, using only the previous utterance. In more every day terms, we want to be able to predict the sentiment of person B’s response to something person A said, before B has said anything and using only A’s utterance. The RNN models were trained on a Swedish email database containing email conversations, where the task was to predict the average sentiment of the response emails to an initial mass-sent business email. The emails didn’t come with sentiment labels, so the Valence Aware Dictionary and sEntiment Reasoner (VADER) system was used to determine sentiments. Seventy-five training-and-testing experiments were run with varying RNN models and data conditions. The accuracy, precision, recall, and F1 scores were used to determine to what extent the models had been able to solve the problem. In particular, the F1 score of the models were compared to the F1 score of a dummy classifier that only answered with positive sentiment, with the success case being that a model was able to reach a higher F1 score than the dummy. The results led to the findings that the varying RNN models performed worse or comparably to the dummy classifier, with only 5 out of 75 experiments resulting in the RNN model reaching a higher F1 score than the positive classifier, and with the average performance of the rare succeeding models only going 2.6 percentage points over the positive only classifier, which isn’t considered worthwhile in relation to the time and resource investment involved in training RNNs. In the end, the results led to the conclusion that the RNN may not be able to solve the problem on its own, and a different approach might be needed. This conclusion is somewhat limited by the fact that more work could have been done on experimenting with the data and pre-processing techniques. The same experiments on a different dataset may show different results. Some of the observations showed that the RNN, particularly the Deep GRU, might be used as the basis for a more complex model. Complex models built on top of RNNs have been shown to be useful on similar research problems within Sentiment Analysis, so this may prove a valuable avenue of research. / Denna studie handlade om att använda den populära Recurrent Neural Network (RNN) modellen, och dess varianter Gated Recurrent Unit (GRU) och Long- Short Term Memory (LSTM), på det hittils understuderade problemet Sentiment Forecasting (SF). Målet med SF är att förutsäga vad sentimentet av ett svar kommer att vara i en konversation, med endast det tidigare uttalandet. I mer vardagliga termer vill vi kunna förutsäga känslan av person B: s svar på något som person A sagt, innan B har sagt någonting och att vi endast använder A:s yttrande. RNN-modellerna tränades med en svensk e-postdatabas som innehöll epostkonversationer, där uppgiften var att förutsäga den genomsnittliga känslan av svarsmeddelandena till ett initialt utskickat massmeddelande. E-postmeddelandena kom inte med sentimentetiketter, så Valence Aware Dictionary and sEntiment Reasoner (VADER)-systemet användes för att utvinna etiketter. Sjuttio-fem experiment genomfördes med varierande RNN-modeller och dataförhållanden. Accuracy, precision, recall och F1-score användes för att avgöra i vilken utsträckning modellerna hade kunnat lösa problemet. F1- Score:n för modellerna jämfördes med F1-Score:n för en dummy-klassificerare som endast svarade med positivt sentiment, med framgångsfallet att en modell kunde nå en högre F1-poäng än dummy:n. Resultaten ledde till fynden att de olika RNN-modellerna presterade sämre eller jämförbart med dummyklassificeraren, med endast 5 av 75 experiment som resulterade i att RNN-modellen nådde en högre F1-score än den positiva klassificeraren, och den genomsnittliga prestandan för de sällsynta framgångsrika modellerna bara kom 2,6 procentenheter över den positiva klassificeraren, vilket inte anses lönsamt i förhållande till den tid och resursinvestering som är involverad i träning av RNNs. I slutändan ledde resultaten till slutsatsen att RNN och dess varianter inte riktigt kan lösa problemet på egen hand, och en annan metod kan behövas. Denna slutsats begränsas något av det faktum att mer arbete kunde ha gjorts med att experimentera med data och förbehandlingstekniker. En annan databas skulle möjligtvis leda till ett annat resultat. Några av observationerna visade att RNN, särskilt Deep GRU, kan användas som grund för en mer komplex modell. Komplexa modeller bygga ovanpå RNNs har visat goda resultat på liknande forskningsproblem, och kan vara en värdefull forskningsriktning.

This thesis deals with CT data segmentation using convolutional neural nets and describes the problem of training with limited training sets. User interaction is suggested as means of improving segmentation quality for the models trained on small training sets and the possibility of using transfer learning is also considered. All of the chosen methods help improve the segmentation quality in comparison with the baseline method, which is the use of automatic data specific segmentation model. The segmentation has improved by tens of percents in Dice score when trained with very small datasets. These methods can be used, for example, to simplify the creation of a new segmentation dataset.

Neural networks with algorithm back-propagation will be presented in this work. Theoretical background of the algorithm will be explained. The problems with training neural nets will be solving there. The work discuss some techniques of image preprocessing and image extraction features, which is one of main part in classification. Some part of work discuss few experiments with neural nets with chosen image features.