MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images

This paper addresses the issue of fully automatic segmentation of a hip CT image with the goal to preserve the joint structure for clinical applications in hip disease diagnosis and treatment. For this purpose, we propose a Multi-Atlas Segmentation Constrained Graph (MASCG) method. The MASCG method uses multi-atlas based mesh fusion results to initialize a bone sheetness based multi-label graph cut for an accurate hip CT segmentation which has the inherent advantage of automatic separation of the pelvic region from the bilateral proximal femoral regions. We then introduce a graph cut constrained graph search algorithm to further improve the segmentation accuracy around the bilateral hip joint regions. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 15-fold cross validation. When the present approach was compared to manual segmentation, an average surface distance error of 0.30 mm, 0.29 mm, and 0.30 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. A further look at the bilateral hip joint regions demonstrated an average surface distance error of 0.16 mm, 0.21 mm and 0.20 mm for the acetabulum, the left femoral head, and the right femoral head, respectively.

Multi-level visualisation using Gaussian process latent variable models

Projection of a high-dimensional dataset onto a two-dimensional space is a useful tool to visualise structures and relationships in the dataset. However, a single two-dimensional visualisation may not display all the intrinsic structure. Therefore, hierarchical/multi-level visualisation methods have been used to extract more detailed understanding of the data. Here we propose a multi-level Gaussian process latent variable model (MLGPLVM). MLGPLVM works by segmenting data (with e.g. K-means, Gaussian mixture model or interactive clustering) in the visualisation space and then fitting a visualisation model to each subset. To measure the quality of multi-level visualisation (with respect to parent and child models), metrics such as trustworthiness, continuity, mean relative rank errors, visualisation distance distortion and the negative log-likelihood per point are used. We evaluate the MLGPLVM approach on the ‘Oil Flow’ dataset and a dataset of protein electrostatic potentials for the ‘Major Histocompatibility Complex (MHC) class I’ of humans. In both cases, visual observation and the quantitative quality measures have shown better visualisation at lower levels.

Novas abordagens para configurações automáticas dos parâmetros de controle em comitês de classificadores

Significant advances have emerged in research related to the topic of Classifier Committees. The models that receive the most attention in the literature are those of the static nature, also known as ensembles. The algorithms that are part of this class, we highlight the methods that using techniques of resampling of the training data: Bagging, Boosting and Multiboosting. The choice of the architecture and base components to be recruited is not a trivial task and has motivated new proposals in an attempt to build such models automatically, and many of them are based on optimization methods. Many of these contributions have not shown satisfactory results when applied to more complex problems with different nature. In contrast, the thesis presented here, proposes three new hybrid approaches for automatic construction for ensembles: Increment of Diversity, Adaptive-fitness Function and Meta-learning for the development of systems for automatic configuration of parameters for models of ensemble. In the first one approach, we propose a solution that combines different diversity techniques in a single conceptual framework, in attempt to achieve higher levels of diversity in ensembles, and with it, the better the performance of such systems. In the second one approach, using a genetic algorithm for automatic design of ensembles. The contribution is to combine the techniques of filter and wrapper adaptively to evolve a better distribution of the feature space to be presented for the components of ensemble. Finally, the last one approach, which proposes new techniques for recommendation of architecture and based components on ensemble, by techniques of traditional meta-learning and multi-label meta-learning. In general, the results are encouraging and corroborate with the thesis that hybrid tools are a powerful solution in building effective ensembles for pattern classification problems.

Avaliação do desempenho energético de um grande edifício de serviços existente

Nesta dissertação pretende-se caracterizar o desempenho energético de um grande edifício de serviços existente, da tipologia ensino, avaliar e identificar potenciais medidas que melhorem aquele desempenho, permitindo, em complemento, determinar a sua classificação energética no âmbito da legislação vigente. A pertinência do estudo prende-se com a avaliação do desempenho energético dos edifícios e com o estudo de medidas de melhoria que permitam incrementar a eficiência energética, por recurso a um programa de simulação energética dinâmica certificado – DesignBuilder e tendo em conta a regulamentação portuguesa em vigor. Inicialmente procedeu-se à modelação do edifício com recurso ao programa DesignBuilder, e, simultaneamente, realizou-se um levantamento de todas as suas características ao nível de geometria, pormenores construtivos, sistemas AVAC e de iluminação e fontes de energia utilizadas. Com vista à caracterização do modo de operação do edifício, foi realizado um levantamento dos perfis reais de utilização em termos de ocupação, iluminação e equipamentos para os vários espaços. Foram realizadas medições de caudais de ar novo e da temperatura do ar, em alguns equipamentos e alguns espaços específicos. Foram realizadas medições em tempo real e leituras de contagens da energia eléctrica utilizada, quer em período de aulas quer em período de férias, que permitiram a desagregação das facturas da energia eléctrica que se apresentam globais para o campus do ISEP. Foram realizadas leituras de contagens de gás natural. Em sequência, foi realizada a simulação energética dinâmica com o intuito de ajustar o modelo criado aos consumos reais e de analisar medidas de melhoria que lhe conferissem um melhor desempenho energético. Essas medidas são agrupadas em quatro tipos: - Medidas de natureza comportamental; - Medidas de melhoria da eficiência energética nos sistemas de iluminação; - Medidas de melhoria de eficiência energética nos sistemas AVAC;- Medidas que visam a introdução de energias de fonte renovável; Em sequência, foi elaborada a simulação nominal e calculados os indicadores de eficiência energética com vista à respectiva classificação energética do edifício, tendo o edifício apresentado uma Classe Energética D de acordo com a escala do SCE. Finalmente, foi avaliado o impacto das diferentes medidas de melhoria identificadas e com potencial de aplicação, isto é, que apresentaram um retorno simples do investimento inferior a oito anos, tanto ao nível do desempenho energético real do edifício, como ao nível da sua classificação energética. De onde se concluiu que existe um potencial de 7% de redução nos consumos energéticos actuais do edifício e de 18% se o funcionamento do edifício for em pleno, ou seja, se todos os seus sistemas estiverem efectivamente em funcionamento, e que terá impacto na classificação energética alcançado uma Classe Energética C.

Structure-function relationships in a glycosyltransferase, a phosphatase and an oxidoreductase

Dissertation presented to obtain the Ph.D degree in Biochemistry

Differences between genders in coping: different strategies or different stressors?

These study analysed gender specificity in coping behaviours by taking into account the types of problem faced by Spanish adolescents attending school. It was focused on the ten problems most frequently reported by participants (828 adolescents, 355 boys, and 473 girls; Mage = 14.07, SD = 1.34), which were classified using a multi-axial classification system. Coping was examined as a two separate measures of approach and avoidance coping, and as a combined measure indicating the predominant use of coping, and total coping effort. A MANCOVA and subsequent univariate tests were conducted to analyse the specificity of coping according to problem and gender, controlled by age. The results showed that the percentage of types of problems reported by adolescents differed according to gender. The influence of gender on coping was scarcely relevant when the type of problem was controlled for. There were no gender differences when the predominant type of coping was considered, but when a total coping effort measure was analysed girls showed more coping efforts than boys to face interpersonal relationship problems and personal illness. Keywords: adolescence, coping, gender differences, stressors.

Finding Methods for Recognizing and Classifying Spare Part Criticality – Case Full Deposit Stripping Machines

The aim of this Master’s thesis is to find a method for classifying spare part criticality in the case company. Several approaches exist for criticality classification of spare parts. The practical problem in this thesis is the lack of a generic analysis method for classifying spare parts of proprietary equipment of the case company. In order to find a classification method, a literature review of various analysis methods is required. The requirements of the case company also have to be recognized. This is achieved by consulting professionals in the company. The literature review states that the analytic hierarchy process (AHP) combined with decision tree models is a common method for classifying spare parts in academic literature. Most of the literature discusses spare part criticality in stock holding perspective. This is relevant perspective also for a customer orientated original equipment manufacturer (OEM), as the case company. A decision tree model is developed for classifying spare parts. The decision tree classifies spare parts into five criticality classes according to five criteria. The criteria are: safety risk, availability risk, functional criticality, predictability of failure and probability of failure. The criticality classes describe the level of criticality from non-critical to highly critical. The method is verified for classifying spare parts of a full deposit stripping machine. The classification can be utilized as a generic model for recognizing critical spare parts of other similar equipment, according to which spare part recommendations can be created. Purchase price of an item and equipment criticality were found to have no effect on spare part criticality in this context. Decision tree is recognized as the most suitable method for classifying spare part criticality in the company.

Priv-C : une politique de confidentialité personnalisable

Les politiques de confidentialité définissent comment les services en ligne collectent, utilisent et partagent les données des utilisateurs. Bien qu’étant le principal moyen pour informer les usagers de l’utilisation de leurs données privées, les politiques de confidentialité sont en général ignorées par ces derniers. Pour cause, les utilisateurs les trouvent trop longues et trop vagues, elles utilisent un vocabulaire souvent difficile et n’ont pas de format standard. Les politiques de confidentialité confrontent également les utilisateurs à un dilemme : celui d’accepter obligatoirement tout le contenu en vue d’utiliser le service ou refuser le contenu sous peine de ne pas y avoir accès. Aucune autre option n’est accordée à l’utilisateur. Les données collectées des utilisateurs permettent aux services en ligne de leur fournir un service, mais aussi de les exploiter à des fins économiques (publicités ciblées, revente, etc). Selon diverses études, permettre aux utilisateurs de bénéficier de cette économie de la vie privée pourrait restaurer leur confiance et faciliter une continuité des échanges sur Internet. Dans ce mémoire, nous proposons un modèle de politique de confidentialité, inspiré du P3P (une recommandation du W3C, World Wide Web Consortium), en élargissant ses fonctionnalités et en réduisant sa complexité. Ce modèle suit un format bien défini permettant aux utilisateurs et aux services en ligne de définir leurs préférences et besoins. Les utilisateurs ont la possibilité de décider de l’usage spécifique et des conditions de partage de chacune de leurs données privées. Une phase de négociation permettra une analyse des besoins du service en ligne et des préférences de l’utilisateur afin d’établir un contrat de confidentialité. La valeur des données personnelles est un aspect important de notre étude. Alors que les compagnies disposent de moyens leur permettant d’évaluer cette valeur, nous appliquons dans ce mémoire, une méthode hiérarchique multicritères. Cette méthode va permettre également à chaque utilisateur de donner une valeur à ses données personnelles en fonction de l’importance qu’il y accorde. Dans ce modèle, nous intégrons également une autorité de régulation en charge de mener les négociations entre utilisateurs et services en ligne, et de générer des recommandations aux usagers en fonction de leur profil et des tendances.

Complex extreme learning machine applications in terahertz pulsed signals feature sets

This paper presents a novel approach to the automatic classification of very large data sets composed of terahertz pulse transient signals, highlighting their potential use in biochemical, biomedical, pharmaceutical and security applications. Two different types of THz spectra are considered in the classification process. Firstly a binary classification study of poly-A and poly-C ribonucleic acid samples is performed. This is then contrasted with a difficult multi-class classification problem of spectra from six different powder samples that although have fairly indistinguishable features in the optical spectrum, they also possess a few discernable spectral features in the terahertz part of the spectrum. Classification is performed using a complex-valued extreme learning machine algorithm that takes into account features in both the amplitude as well as the phase of the recorded spectra. Classification speed and accuracy are contrasted with that achieved using a support vector machine classifier. The study systematically compares the classifier performance achieved after adopting different Gaussian kernels when separating amplitude and phase signatures. The two signatures are presented as feature vectors for both training and testing purposes. The study confirms the utility of complex-valued extreme learning machine algorithms for classification of the very large data sets generated with current terahertz imaging spectrometers. The classifier can take into consideration heterogeneous layers within an object as would be required within a tomographic setting and is sufficiently robust to detect patterns hidden inside noisy terahertz data sets. The proposed study opens up the opportunity for the establishment of complex-valued extreme learning machine algorithms as new chemometric tools that will assist the wider proliferation of terahertz sensing technology for chemical sensing, quality control, security screening and clinic diagnosis. Furthermore, the proposed algorithm should also be very useful in other applications requiring the classification of very large datasets.

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n = 30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Compartimentação fisiográfica aplicada à avaliação de terrenos - subsídio ao planejamento territorial do município de Cananéia - SP

Pós-graduação em Geociências e Meio Ambiente - IGCE

A Cox Model for Biostatistics of the Future

Professor Sir David R. Cox (DRC) is widely acknowledged as among the most important scientists of the second half of the twentieth century. He inherited the mantle of statistical science from Pearson and Fisher, advanced their ideas, and translated statistical theory into practice so as to forever change the application of statistics in many fields, but especially biology and medicine. The logistic and proportional hazards models he substantially developed, are arguably among the most influential biostatistical methods in current practice. This paper looks forward over the period from DRC's 80th to 90th birthdays, to speculate about the future of biostatistics, drawing lessons from DRC's contributions along the way. We consider "Cox's model" of biostatistics, an approach to statistical science that: formulates scientific questions or quantities in terms of parameters gamma in probability models f(y; gamma) that represent in a parsimonious fashion, the underlying scientific mechanisms (Cox, 1997); partition the parameters gamma = theta, eta into a subset of interest theta and other "nuisance parameters" eta necessary to complete the probability distribution (Cox and Hinkley, 1974); develops methods of inference about the scientific quantities that depend as little as possible upon the nuisance parameters (Barndorff-Nielsen and Cox, 1989); and thinks critically about the appropriate conditional distribution on which to base infrences. We briefly review exciting biomedical and public health challenges that are capable of driving statistical developments in the next decade. We discuss the statistical models and model-based inferences central to the CM approach, contrasting them with computationally-intensive strategies for prediction and inference advocated by Breiman and others (e.g. Breiman, 2001) and to more traditional design-based methods of inference (Fisher, 1935). We discuss the hierarchical (multi-level) model as an example of the future challanges and opportunities for model-based inference. We then consider the role of conditional inference, a second key element of the CM. Recent examples from genetics are used to illustrate these ideas. Finally, the paper examines causal inference and statistical computing, two other topics we believe will be central to biostatistics research and practice in the coming decade. Throughout the paper, we attempt to indicate how DRC's work and the "Cox Model" have set a standard of excellence to which all can aspire in the future.

Automatic building detection using the Dempster-Shafer algorithm

An approach and strategy for automatic detection of buildings from aerial images using combined image analysis and interpretation techniques is described in this paper. It is undertaken in several steps. A dense DSM is obtained by stereo image matching and then the results of multi-band classification, the DSM, and Normalized Difference Vegetation Index (NDVI) are used to reveal preliminary building interest areas. From these areas, a shape modeling algorithm has been used to precisely delineate their boundaries. The Dempster-Shafer data fusion technique is then applied to detect buildings from the combination of three data sources by a statistically-based classification. A number of test areas, which include buildings of different sizes, shape, and roof color have been investigated. The tests are encouraging and demonstrate that all processes in this system are important for effective building detection.

Probabilistic resource space model for managing resources in cyber-physical society

Classification is the most basic method for organizing resources in the physical space, cyber space, socio space and mental space. To create a unified model that can effectively manage resources in different spaces is a challenge. The Resource Space Model RSM is to manage versatile resources with a multi-dimensional classification space. It supports generalization and specialization on multi-dimensional classifications. This paper introduces the basic concepts of RSM, and proposes the Probabilistic Resource Space Model, P-RSM, to deal with uncertainty in managing various resources in different spaces of the cyber-physical society. P-RSM’s normal forms, operations and integrity constraints are developed to support effective management of the resource space. Characteristics of the P-RSM are analyzed through experiments. This model also enables various services to be described, discovered and composed from multiple dimensions and abstraction levels with normal form and integrity guarantees. Some extensions and applications of the P-RSM are introduced.

Interactive semantics

Much research pursues machine intelligence through better representation of semantics. What is semantics? People in different areas view semantics from different facets although it accompanies interaction through civilization. Some researchers believe that humans have some innate structure in mind for processing semantics. Then, what the structure is like? Some argue that humans evolve a structure for processing semantics through constant learning. Then, how the process is like? Humans have invented various symbol systems to represent semantics. Can semantics be accurately represented? Turing machines are good at processing symbols according to algorithms designed by humans, but they are limited in ability to process semantics and to do active interaction. Super computers and high-speed networks do not help solve this issue as they do not have any semantic worldview and cannot reflect themselves. Can future cyber-society have some semantic images that enable machines and individuals (humans and agents) to reflect themselves and interact with each other with knowing social situation through time? This paper concerns these issues in the context of studying an interactive semantics for the future cyber-society. It firstly distinguishes social semantics from natural semantics, and then explores the interactive semantics in the category of social semantics. Interactive semantics consists of an interactive system and its semantic image, which co-evolve and influence each other. The semantic worldview and interactive semantic base are proposed as the semantic basis of interaction. The process of building and explaining semantic image can be based on an evolving structure incorporating adaptive multi-dimensional classification space and self-organized semantic link network. A semantic lens is proposed to enhance the potential of the structure and help individuals build and retrieve semantic images from different facets, abstraction levels and scales through time.