An automatic classifier of emotions built from entropy of noise

The electrocardiogram (ECG) signal has been widely used to study the physiological substrates of emotion. However, searching for better filtering techniques in order to obtain a signal with better quality and with the maximum relevant information remains an important issue for researchers in this field. Signal processing is largely performed for ECG analysis and interpretation, but this process can be susceptible to error in the delineation phase. In addition, it can lead to the loss of important information that is usually considered as noise and, consequently, discarded from the analysis. The goal of this study was to evaluate if the ECG noise allows for the classification of emotions, while using its entropy as an input in a decision tree classifier. We collected the ECG signal from 25 healthy participants while they were presented with videos eliciting negative (fear and disgust) and neutral emotions. The results indicated that the neutral condition showed a perfect identification (100%), whereas the classification of negative emotions indicated good identification performances (60% of sensitivity and 80% of specificity). These results suggest that the entropy of noise contains relevant information that can be useful to improve the analysis of the physiological correlates of emotion.

Estudo sistemático de estrelas variáveis na era dos grandes surveys

The interest in the systematic analysis of astronomical time series data, as well as development in astronomical instrumentation and automation over the past two decades has given rise to several questions of how to analyze and synthesize the growing amount of data. These data have led to many discoveries in the areas of modern astronomy asteroseismology, exoplanets and stellar evolution. However, treatment methods and data analysis have failed to follow the development of the instruments themselves, although much effort has been done. In present thesis, we propose new methods of data analysis and two catalogs of the variable stars that allowed the study of rotational modulation and stellar variability. Were analyzed the photometric databases fromtwo distinctmissions: CoRoT (Convection Rotation and planetary Transits) and WFCAM (Wide Field Camera). Furthermore the present work describes several methods for the analysis of photometric data besides propose and refine selection techniques of data using indices of variability. Preliminary results show that variability indices have an efficiency greater than the indices most often used in the literature. An efficient selection of variable stars is essential to improve the efficiency of all subsequent steps. Fromthese analyses were obtained two catalogs; first, fromtheWFCAMdatabase we achieve a catalog with 319 variable stars observed in the photometric bands Y ZJHK. These stars show periods ranging between ∼ 0, 2 to ∼ 560 days whose the variability signatures present RR-Lyrae, Cepheids , LPVs, cataclysmic variables, among many others. Second, from the CoRoT database we selected 4, 206 stars with typical signatures of rotationalmodulation, using a supervised process. These stars show periods ranging between ∼ 0, 33 to ∼ 92 days, amplitude variability between ∼ 0, 001 to ∼ 0, 5 mag, color index (J - H) between ∼ 0, 0 to ∼ 1, 4 mag and spectral type CoRoT FGKM. The WFCAM variable stars catalog is being used to compose a database of light curves to be used as template in an automatic classifier for variable stars observed by the project VVV (Visible and Infrared Survey Telescope for Astronomy) moreover it are a fundamental start point to study different scientific cases. For example, a set of 12 young stars who are in a star formation region and the study of RR Lyrae-whose properties are not well established in the infrared. Based on CoRoT results we were able to show, for the first time, the rotational modulation evolution for an wide homogeneous sample of field stars. The results are inagreement with those expected by the stellar evolution theory. Furthermore, we identified 4 solar-type stars ( with color indices, spectral type, luminosity class and rotation period close to the Sun) besides 400 M-giant stars that we have a special interest to forthcoming studies. From the solar-type stars we can describe the future and past of the Sun while properties of M-stars are not well known. Our results allow concluded that there is a high dependence of the color-period diagram with the reddening in which increase the uncertainties of the age-period realized by previous works using CoRoT data. This thesis provides a large data-set for different scientific works, such as; magnetic activity, cataclysmic variables, brown dwarfs, RR-Lyrae, solar analogous, giant stars, among others. For instance, these data will allow us to study the relationship of magnetic activitywith stellar evolution. Besides these aspects, this thesis presents an improved classification for a significant number of stars in the CoRoT database and introduces a new set of tools that can be used to improve the entire process of the photometric databases analysis

Classificação automática de cobertura vegetal em imagens aéreas e orbitais para uso em planejamento energético

Neste trabalho é apresentado um modelo de redes neurais que será utilizado como ferramenta para uso no planejamento energético e na construção de cenários energéticos através da identificação e agrupamento de pixels representativos de classes de água, vegetação e antropização no entorno do reservatório de Tucuruí, Estado do Pará (bacia do rio Tocantins). Para o estudo, foram utilizadas fotografias aéreas ortorretificadas e um recorte da imagem do satélite Landsat, ambos obtidos em agosto de 2001 e classificados utilizando a métrica da mínima distância no software Matlab 7.3.0 (Matrix Laboratory - software de matemática aplicada) e no Arcview 3.2a (programa de Sistemas de Informações Geográficas). Para classificação da área no Matlab, foram utilizadas redes neurais competitivas, mais especificamente as redes de Kohonen que são caracterizadas por realizar um mapeamento de um espaço de dimensão n (número de entradas) para um espaço de dimensão m (número de saídas). Os resultados obtidos no classificador utilizando rede neural e no classificador do Arcview foram semelhantes, mas houve uma divergência no que diz respeito à imagem de alta e média resolução que pode ser justificada pelo fato de que a imagem de alta resolução espacial ocasiona muita variação espectral em algumas feições, gerando dificuldades nas classificações. Esse classificador automático é uma ferramenta importante para identificar oportunidades e potenciais a serem desenvolvidos na construção de cenários energéticos programados. Os resultados deste trabalho confirmam que a imagem de média resolução ainda é a mais indicada para resolver a maioria dos problemas que envolvem identificação de cobertura do solo para utilização em planejamento energético.

An epidemiological evaluation of pediatric long bone fractures - a retrospective cohort study of 2716 patients from two Swiss tertiary pediatric hospitals.

BACKGROUND Children and adolescents are at high risk of sustaining fractures during growth. Therefore, epidemiological assessment is crucial for fracture prevention. The AO Comprehensive Injury Automatic Classifier (AO COIAC) was used to evaluate epidemiological data of pediatric long bone fractures in a large cohort. METHODS Data from children and adolescents with long bone fractures sustained between 2009 and 2011, treated at either of two tertiary pediatric surgery hospitals in Switzerland, were retrospectively collected. Fractures were classified according to the AO Pediatric Comprehensive Classification of Long Bone Fractures (PCCF). RESULTS For a total of 2716 patients (60% boys), 2807 accidents with 2840 long bone fractures (59% radius/ulna; 21% humerus; 15% tibia/fibula; 5% femur) were documented. Children's mean age (SD) was 8.2 (4.0) years (6% infants; 26% preschool children; 40% school children; 28% adolescents). Adolescent boys sustained more fractures than girls (p < 0.001). The leading cause of fractures was falls (27%), followed by accidents occurring during leisure activities (25%), at home (14%), on playgrounds (11%), and traffic (11%) and school accidents (8%). There was boy predominance for all accident types except for playground and at home accidents. The distribution of accident types differed according to age classes (p < 0.001). Twenty-six percent of patients were classed as overweight or obese - higher than data published by the WHO for the corresponding ages - with a higher proportion of overweight and obese boys than in the Swiss population (p < 0.0001). CONCLUSION Overall, differences in the fracture distribution were sex and age related. Overweight and obese patients seemed to be at increased risk of sustaining fractures. Our data give valuable input into future development of prevention strategies. The AO PCCF proved to be useful in epidemiological reporting and analysis of pediatric long bone fractures.

Construção de um classificador automático de severidade de bugs para sistemas open source

Software bug analysis is one of the most important activities in Software Quality. The rapid and correct implementation of the necessary repair influence both developers, who must leave the fully functioning software, and users, who need to perform their daily tasks. In this context, if there is an incorrect classification of bugs, there may be unwanted situations. One of the main factors to be assigned bugs in the act of its initial report is severity, which lives up to the urgency of correcting that problem. In this scenario, we identified in datasets with data extracted from five open source systems (Apache, Eclipse, Kernel, Mozilla and Open Office), that there is an irregular distribution of bugs with respect to existing severities, which is an early sign of misclassification. In the dataset analyzed, exists a rate of about 85% bugs being ranked with normal severity. Therefore, this classification rate can have a negative influence on software development context, where the misclassified bug can be allocated to a developer with little experience to solve it and thus the correction of the same may take longer, or even generate a incorrect implementation. Several studies in the literature have disregarded the normal bugs, working only with the portion of bugs considered severe or not severe initially. This work aimed to investigate this portion of the data, with the purpose of identifying whether the normal severity reflects the real impact and urgency, to investigate if there are bugs (initially classified as normal) that could be classified with other severity, and to assess if there are impacts for developers in this context. For this, an automatic classifier was developed, which was based on three algorithms (Näive Bayes, Max Ent and Winnow) to assess if normal severity is correct for the bugs categorized initially with this severity. The algorithms presented accuracy of about 80%, and showed that between 21% and 36% of the bugs should have been classified differently (depending on the algorithm), which represents somewhere between 70,000 and 130,000 bugs of the dataset.

Improving automatic speaker verification using SVM techniques

Automatic recognition of people is an active field of research with important forensic and security applications. In these applications, it is not always possible for the subject to be in close proximity to the system. Voice represents a human behavioural trait which can be used to recognise people in such situations. Automatic Speaker Verification (ASV) is the process of verifying a persons identity through the analysis of their speech and enables recognition of a subject at a distance over a telephone channel { wired or wireless. A significant amount of research has focussed on the application of Gaussian mixture model (GMM) techniques to speaker verification systems providing state-of-the-art performance. GMM's are a type of generative classifier trained to model the probability distribution of the features used to represent a speaker. Recently introduced to the field of ASV research is the support vector machine (SVM). An SVM is a discriminative classifier requiring examples from both positive and negative classes to train a speaker model. The SVM is based on margin maximisation whereby a hyperplane attempts to separate classes in a high dimensional space. SVMs applied to the task of speaker verification have shown high potential, particularly when used to complement current GMM-based techniques in hybrid systems. This work aims to improve the performance of ASV systems using novel and innovative SVM-based techniques. Research was divided into three main themes: session variability compensation for SVMs; unsupervised model adaptation; and impostor dataset selection. The first theme investigated the differences between the GMM and SVM domains for the modelling of session variability | an aspect crucial for robust speaker verification. Techniques developed to improve the robustness of GMMbased classification were shown to bring about similar benefits to discriminative SVM classification through their integration in the hybrid GMM mean supervector SVM classifier. Further, the domains for the modelling of session variation were contrasted to find a number of common factors, however, the SVM-domain consistently provided marginally better session variation compensation. Minimal complementary information was found between the techniques due to the similarities in how they achieved their objectives. The second theme saw the proposal of a novel model for the purpose of session variation compensation in ASV systems. Continuous progressive model adaptation attempts to improve speaker models by retraining them after exploiting all encountered test utterances during normal use of the system. The introduction of the weight-based factor analysis model provided significant performance improvements of over 60% in an unsupervised scenario. SVM-based classification was then integrated into the progressive system providing further benefits in performance over the GMM counterpart. Analysis demonstrated that SVMs also hold several beneficial characteristics to the task of unsupervised model adaptation prompting further research in the area. In pursuing the final theme, an innovative background dataset selection technique was developed. This technique selects the most appropriate subset of examples from a large and diverse set of candidate impostor observations for use as the SVM background by exploiting the SVM training process. This selection was performed on a per-observation basis so as to overcome the shortcoming of the traditional heuristic-based approach to dataset selection. Results demonstrate the approach to provide performance improvements over both the use of the complete candidate dataset and the best heuristically-selected dataset whilst being only a fraction of the size. The refined dataset was also shown to generalise well to unseen corpora and be highly applicable to the selection of impostor cohorts required in alternate techniques for speaker verification.

Design and development of automatic visual inspection system for PCB manufacturing

Inspection of solder joints has been a critical process in the electronic manufacturing industry to reduce manufacturing cost, improve yield, and ensure product quality and reliability. This paper proposes two inspection modules for an automatic solder joint classification system. The “front-end” inspection system includes illumination normalisation, localisation and segmentation. The “back-end” inspection involves the classification of solder joints using the Log Gabor filter and classifier fusion. Five different levels of solder quality with respect to the amount of solder paste have been defined. The Log Gabor filter has been demonstrated to achieve high recognition rates and is resistant to misalignment. This proposed system does not need any special illumination system, and the images are acquired by an ordinary digital camera. This system could contribute to the development of automated non-contact, non-destructive and low cost solder joint quality inspection systems.

Automatic de-identification of electronic health records : an Australian perspective

We present an approach to automatically de-identify health records. In our approach, personal health information is identified using a Conditional Random Fields machine learning classifier, a large set of linguistic and lexical features, and pattern matching techniques. Identified personal information is then removed from the reports. The de-identification of personal health information is fundamental for the sharing and secondary use of electronic health records, for example for data mining and disease monitoring. The effectiveness of our approach is first evaluated on the 2007 i2b2 Shared Task dataset, a widely adopted dataset for evaluating de-identification techniques. Subsequently, we investigate the robustness of the approach to limited training data; we study its effectiveness on different type and quality of data by evaluating the approach on scanned pathology reports from an Australian institution. This data contains optical character recognition errors, as well as linguistic conventions that differ from those contained in the i2b2 dataset, for example different date formats. The findings suggest that our approach compares to the best approach from the 2007 i2b2 Shared Task; in addition, the approach is found to be robust to variations of training size, data type and quality in presence of sufficient training data.

Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the SNOMED CT ontology

Objective To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. Materials and Methods 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. Result Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. Discussion Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. Conclusion This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

A convolutional neural network for automatic analysis of aerial imagery

This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.

Automatic UAV forced landing site detection using machine learning

The commercialization of aerial image processing is highly dependent on the platforms such as UAVs (Unmanned Aerial Vehicles). However, the lack of an automated UAV forced landing site detection system has been identified as one of the main impediments to allow UAV flight over populated areas in civilian airspace. This article proposes a UAV forced landing site detection system that is based on machine learning approaches including the Gaussian Mixture Model and the Support Vector Machine. A range of learning parameters are analysed including the number of Guassian mixtures, support vector kernels including linear, radial basis function Kernel (RBF) and polynormial kernel (poly), and the order of RBF kernel and polynormial kernel. Moreover, a modified footprint operator is employed during feature extraction to better describe the geometric characteristics of the local area surrounding a pixel. The performance of the presented system is compared to a baseline UAV forced landing site detection system which uses edge features and an Artificial Neural Network (ANN) region type classifier. Experiments conducted on aerial image datasets captured over typical urban environments reveal improved landing site detection can be achieved with an SVM classifier with an RBF kernel using a combination of colour and texture features. Compared to the baseline system, the proposed system provides significant improvement in term of the chance to detect a safe landing area, and the performance is more stable than the baseline in the presence of changes to the UAV altitude.