Computational Methods for Identifying Hypertrophic Cardiomyopathy using 12-lead ECG

Hypertrophic cardiomyopathy (HCM) is a cardiovascular disease where the heart muscle is partially thickened and blood flow is - potentially fatally - obstructed. It is one of the leading causes of sudden cardiac death in young people. Electrocardiography (ECG) and Echocardiography (Echo) are the standard tests for identifying HCM and other cardiac abnormalities. The American Heart Association has recommended using a pre-participation questionnaire for young athletes instead of ECG or Echo tests due to considerations of cost and time involved in interpreting the results of these tests by an expert cardiologist. Initially we set out to develop a classifier for automated prediction of young athletes’ heart conditions based on the answers to the questionnaire. Classification results and further in-depth analysis using computational and statistical methods indicated significant shortcomings of the questionnaire in predicting cardiac abnormalities. Automated methods for analyzing ECG signals can help reduce cost and save time in the pre-participation screening process by detecting HCM and other cardiac abnormalities. Therefore, the main goal of this dissertation work is to identify HCM through computational analysis of 12-lead ECG. ECG signals recorded on one or two leads have been analyzed in the past for classifying individual heartbeats into different types of arrhythmia as annotated primarily in the MIT-BIH database. In contrast, we classify complete sequences of 12-lead ECGs to assign patients into two groups: HCM vs. non-HCM. The challenges and issues we address include missing ECG waves in one or more leads and the dimensionality of a large feature-set. We address these by proposing imputation and feature-selection methods. We develop heartbeat-classifiers by employing Random Forests and Support Vector Machines, and propose a method to classify full 12-lead ECGs based on the proportion of heartbeats classified as HCM. The results from our experiments show that the classifiers developed using our methods perform well in identifying HCM. Thus the two contributions of this thesis are the utilization of computational and statistical methods for discovering shortcomings in a current screening procedure and the development of methods to identify HCM through computational analysis of 12-lead ECG signals.

Ultra Compact Inline E-Plane Waveguide Bandpass Filters Using Cross Coupling

This paper presents novel ultra-compact waveguide bandpass filters that exhibit pseudo elliptic responses with ability to place transmission zeros on both sides of the passband to form sharp roll offs. The filters contain E plane extracted pole sections cascaded with cross-coupled filtering blocks. Compactness is achieved by the use of evanescent mode sections and closer arranged resonators modified to shrink in size. The filters containing non-resonating nodes are designed by means of the generalized coupling coefficients (GCC) extraction procedure for the cross-coupled filtering blocks and extracted pole sections. We illustrate the performance of the proposed structures through the design examples of a third and a fourth order filters with center frequencies of 9.2 GHz and 10 GHz respectively. The sizes of the proposed structures suitable for fabricating using the low cost E plane waveguide technology are 38% smaller than ones of the E plane extracted pole filter of the same order.

Deep Head Pose: Gaze-Direction Estimation in Multimodal Video

In this paper we present a convolutional neuralnetwork (CNN)-based model for human head pose estimation inlow-resolution multi-modal RGB-D data. We pose the problemas one of classification of human gazing direction. We furtherfine-tune a regressor based on the learned deep classifier. Next wecombine the two models (classification and regression) to estimateapproximate regression confidence. We present state-of-the-artresults in datasets that span the range of high-resolution humanrobot interaction (close up faces plus depth information) data tochallenging low resolution outdoor surveillance data. We buildupon our robust head-pose estimation and further introduce anew visual attention model to recover interaction with theenvironment. Using this probabilistic model, we show thatmany higher level scene understanding like human-human/sceneinteraction detection can be achieved. Our solution runs inreal-time on commercial hardware

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.

Implementação de classificador de tarefas mentais baseado em EEG

BARBOSA, André F. ; SOUZA, Bryan C. ; PEREIRA JUNIOR, Antônio ; MEDEIROS, Adelardo A. D.de, . Implementação de Classificador de Tarefas Mentais Baseado em EEG. In: CONGRESSO BRASILEIRO DE REDES NEURAIS, 9., 2009, Ouro Preto, MG. Anais... Ouro Preto, MG, 2009

An analysis of facial description in static images and video streams

[ES]This paper describes an analysis performed for facial description in static images and video streams. The still image context is first analyzed in order to decide the optimal classifier configuration for each problem: gender recognition, race classification, and glasses and moustache presence. These results are later applied to significant samples which are automatically extracted in real-time from video streams achieving promising results in the facial description of 70 individuals by means of gender, race and the presence of glasses and moustache.

Hand pose detection for vision-based gesture interfaces

[EN]Vision-based applications designed for humanmachine interaction require fast and accurate hand detection. However, previous works on this field assume different constraints, like a limitation in the number of detected gestures, because hands are highly complex objects to locate. This paper presents an approach which changes the detection target without limiting the number of detected gestures. Using a cascade classifier we detect hands based on their wrists. With this approach, we introduce two main contributions: (1) a reliable segmentation, independently of the gesture being made and (2) a training phase faster than previous cascade classifier based methods. The paper includes experimental evaluations with different video streams that illustrate the efficiency and suitability for perceptual interfaces.

Fast and accurate hand pose detection for human-robot interaction

[EN]Enabling natural human-robot interaction using computer vision based applications requires fast and accurate hand detection. However, previous works in this field assume different constraints, like a limitation in the number of detected gestures, because hands are highly complex objects difficult to locate. This paper presents an approach which integrates temporal coherence cues and hand detection based on wrists using a cascade classifier. With this approach, we introduce three main contributions: (1) a transparent initialization mechanism without user participation for segmenting hands independently of their gesture, (2) a larger number of detected gestures as well as a faster training phase than previous cascade classifier based methods and (3) near real-time performance for hand pose detection in video streams.

Short-term wind power forecast based on cluster analysis and artificial neural networks

[EN]In this paper an architecture for an estimator of short-term wind farm power is proposed. The estimator is made up of a Linear Machine classifier and a set of k Multilayer Perceptrons, training each one for a specific subspace of the input space. The splitting of the input dataset into the k clusters is done using a k-means technique, obtaining the equivalent Linear Machine classifier from the cluster centroids...

Wavelength converters based on four-wave mixing in semiconductor optical amplifiers for advanced modulation formats

Les convertisseurs de longueur d’onde sont essentiels pour la réalisation de réseaux de communications optiques à routage en longueur d’onde. Dans la littérature, les convertisseurs de longueur d’onde basés sur le mélange à quatre ondes dans les amplificateurs optiques à semi-conducteur constituent une solution extrêmement intéressante, et ce, en raison de leurs nombreuses caractéristiques nécessaires à l’implémentation de tels réseaux de communications. Avec l’émergence des systèmes commerciaux de détection cohérente, ainsi qu’avec les récentes avancées dans le domaine du traitement de signal numérique, il est impératif d’évaluer la performance des convertisseurs de longueur d’onde, et ce, dans le contexte des formats de modulation avancés. Les objectifs de cette thèse sont : 1) d’étudier la faisabilité des convertisseurs de longueur d’onde basés sur le mélange à quatre ondes dans les amplificateurs optiques à semi-conducteur pour les formats de modulation avancés et 2) de proposer une technique basée sur le traitement de signal numérique afin d’améliorer leur performance. En premier lieu, une étude expérimentale de la conversion de longueur d’onde de formats de modulation d’amplitude en quadrature (quadrature amplitude modulation - QAM) est réalisée. En particulier, la conversion de longueur d’onde de signaux 16-QAM à 16 Gbaud et 64-QAM à 5 Gbaud dans un amplificateur optique à semi-conducteur commercial est réalisée sur toute la bande C. Les résultats démontrent qu’en raison des distorsions non-linéaires induites sur le signal converti, le point d’opération optimal du convertisseur de longueur d’onde est différent de celui obtenu lors de la conversion de longueur d’onde de formats de modulation en intensité. En effet, dans le contexte des formats de modulation avancés, c’est le compromis entre la puissance du signal converti et les non-linéarités induites qui détermine le point d’opération optimal du convertisseur de longueur d’onde. Les récepteurs cohérents permettent l’utilisation de techniques de traitement de signal numérique afin de compenser la détérioration du signal transmis suite à sa détection. Afin de mettre à profit les nouvelles possibilités offertes par le traitement de signal numérique, une technique numérique de post-compensation des distorsions induites sur le signal converti, basée sur une analyse petit-signal des équations gouvernant la dynamique du gain à l’intérieur des amplificateurs optiques à semi-conducteur, est développée. L’efficacité de cette technique est démontrée à l’aide de simulations numériques et de mesures expérimentales de conversion de longueur d’onde de signaux 16-QAM à 10 Gbaud et 64-QAM à 5 Gbaud. Cette méthode permet d’améliorer de façon significative les performances du convertisseur de longueur d’onde, et ce, principalement pour les formats de modulation avancés d’ordre supérieur tel que 64-QAM. Finalement, une étude expérimentale exhaustive de la technique de post-compensation des distorsions induites sur le signal converti est effectuée pour des signaux 64-QAM. Les résultats démontrent que, même en présence d’un signal à bruité à l’entrée du convertisseur de longueur d’onde, la technique proposée améliore toujours la qualité du signal reçu. De plus, une étude du point d’opération optimal du convertisseur de longueur d’onde est effectuée et démontre que celui-ci varie en fonction des pertes optiques suivant la conversion de longueur d’onde. Dans un réseau de communication optique à routage en longueur d’onde, le signal est susceptible de passer par plusieurs étages de conversion de longueur d’onde. Pour cette raison, l’efficacité de la technique de post-compensation est démontrée, et ce pour la première fois dans la littérature, pour deux étages successifs de conversion de longueur d’onde de signaux 64-QAM à 5 Gbaud. Les résultats de cette thèse montrent que les convertisseurs de longueur d’ondes basés sur le mélange à quatre ondes dans les amplificateurs optiques à semi-conducteur, utilisés en conjonction avec des techniques de traitement de signal numérique, constituent une technologie extrêmement prometteuse pour les réseaux de communications optiques modernes à routage en longueur d’onde.

An investigation of Hebbian phase sequences as assembly graphs

Hebb proposed that synapses between neurons that fire synchronously are strengthened, forming cell assemblies and phase sequences. The former, on a shorter scale, are ensembles of synchronized cells that function transiently as a closed processing system; the latter, on a larger scale, correspond to the sequential activation of cell assemblies able to represent percepts and behaviors. Nowadays, the recording of large neuronal populations allows for the detection of multiple cell assemblies. Within Hebb's theory, the next logical step is the analysis of phase sequences. Here we detected phase sequences as consecutive assembly activation patterns, and then analyzed their graph attributes in relation to behavior. We investigated action potentials recorded from the adult rat hippocampus and neocortex before, during and after novel object exploration (experimental periods). Within assembly graphs, each assembly corresponded to a node, and each edge corresponded to the temporal sequence of consecutive node activations. The sum of all assembly activations was proportional to firing rates, but the activity of individual assemblies was not. Assembly repertoire was stable across experimental periods, suggesting that novel experience does not create new assemblies in the adult rat. Assembly graph attributes, on the other hand, varied significantly across behavioral states and experimental periods, and were separable enough to correctly classify experimental periods (Naïve Bayes classifier; maximum AUROCs ranging from 0.55 to 0.99) and behavioral states (waking, slow wave sleep, and rapid eye movement sleep; maximum AUROCs ranging from 0.64 to 0.98). Our findings agree with Hebb's view that assemblies correspond to primitive building blocks of representation, nearly unchanged in the adult, while phase sequences are labile across behavioral states and change after novel experience. The results are compatible with a role for phase sequences in behavior and cognition.

Sentiment classification with case-base approach

L’augmentation de la croissance des réseaux, des blogs et des utilisateurs des sites d’examen sociaux font d’Internet une énorme source de données, en particulier sur la façon dont les gens pensent, sentent et agissent envers différentes questions. Ces jours-ci, les opinions des gens jouent un rôle important dans la politique, l’industrie, l’éducation, etc. Alors, les gouvernements, les grandes et petites industries, les instituts universitaires, les entreprises et les individus cherchent à étudier des techniques automatiques fin d’extraire les informations dont ils ont besoin dans les larges volumes de données. L’analyse des sentiments est une véritable réponse à ce besoin. Elle est une application de traitement du langage naturel et linguistique informatique qui se compose de techniques de pointe telles que l’apprentissage machine et les modèles de langue pour capturer les évaluations positives, négatives ou neutre, avec ou sans leur force, dans des texte brut. Dans ce mémoire, nous étudions une approche basée sur les cas pour l’analyse des sentiments au niveau des documents. Notre approche basée sur les cas génère un classificateur binaire qui utilise un ensemble de documents classifies, et cinq lexiques de sentiments différents pour extraire la polarité sur les scores correspondants aux commentaires. Puisque l’analyse des sentiments est en soi une tâche dépendante du domaine qui rend le travail difficile et coûteux, nous appliquons une approche «cross domain» en basant notre classificateur sur les six différents domaines au lieu de le limiter à un seul domaine. Pour améliorer la précision de la classification, nous ajoutons la détection de la négation comme une partie de notre algorithme. En outre, pour améliorer la performance de notre approche, quelques modifications innovantes sont appliquées. Il est intéressant de mentionner que notre approche ouvre la voie à nouveaux développements en ajoutant plus de lexiques de sentiment et ensembles de données à l’avenir.

Multiclass Adaboost Based on an Ensemble of Binary Adaboosts

This paper presents a multi-class AdaBoost based on incorporating an ensemble of binary AdaBoosts which is organized as Binary Decision Tree (BDT). It is proved that binary AdaBoost is extremely successful in producing accurate classification but it does not perform very well for multi-class problems. To avoid this performance degradation, the multi-class problem is divided into a number of binary problems and binary AdaBoost classifiers are invoked to solve these classification problems. This approach is tested with a dataset consisting of 6500 binary images of traffic signs. Haar-like features of these images are computed and the multi-class AdaBoost classifier is invoked to classify them. A classification rate of 96.7% and 95.7% is achieved for the traffic sign boarders and pictograms, respectively. The proposed approach is also evaluated using a number of standard datasets such as Iris, Wine, Yeast, etc. The performance of the proposed BDT classifier is quite high as compared with the state of the art and it converges very fast to a solution which indicates it as a reliable classifier.

Designing for User-facing Uncertainty in Everyday Sensing and Prediction

Thesis (Ph.D.)--University of Washington, 2016-07