An eye for an eye: robust motion segmentation by applying the latest in human vision research

Automatically extracting interesting objects from videos is a very challenging task and is applicable to many research areas such robotics, medical imaging, content based indexing and visual surveillance. Automated visual surveillance is a major research area in computational vision and a commonly applied technique in an attempt to extract objects of interest is that of motion segmentation. Motion segmentation relies on the temporal changes that occur in video sequences to detect objects, but as a technique it presents many challenges that researchers have yet to surmount. Changes in real-time video sequences not only include interesting objects, environmental conditions such as wind, cloud cover, rain and snow may be present, in addition to rapid lighting changes, poor footage quality, moving shadows and reflections. The list provides only a sample of the challenges present. This thesis explores the use of motion segmentation as part of a computational vision system and provides solutions for a practical, generic approach with robust performance, using current neuro-biological, physiological and psychological research in primate vision as inspiration.

Measuring the consumer benefits of improving farm animal welfare to inform welfare labelling

Policy makers in the European Union are envisioning the introduction of a community farm animal welfare label which would allow consumers to align their consumption habits with their farm animal welfare preferences. For welfare labelling to be viable the market for livestock products produced to higher welfare standards has to be sufficiently segmented with consumers having sufficiently distinct and behaviourally consistent preferences. The present study investigates consumers’ preferences for meat produced to different welfare standards using a hypothetical welfare score. Data is obtained from a contingent valuation study carried out in Britain. The ordered probit model was estimated using Bayesian inference to obtain mean willingness to pay. We find decreasing marginal WTP as animal welfare levels increase and that people’s preferences for different levels of farm animal welfare are sufficiently differentiated making the introduction of a labelling scheme in the form of a certified rating system appear feasible.

On the environmental valuation of catastrophe: revisiting mining disasters in the United Kingdom, 1851-1962

In the context of environmental valuation of natural disasters, an important component of the evaluation procedure lies in determining the periodicity of events. This paper explores alternative methodologies for determining such periodicity, illustrating the advantages and the disadvantages of the separate methods and their comparative predictions. The procedures employ Bayesian inference and explore recent advances in computational aspects of mixtures methodology. The procedures are applied to the classic data set of Maguire et al (Biometrika, 1952) which was subsequently updated by Jarrett (Biometrika, 1979) and which comprise the seminal investigations examining the periodicity of mining disasters within the United Kingdom, 1851-1962.

Placement of Kuhlmanniodendron Fiaschi & Groppo in Lindackerieae (Achariaceae, Malpighiales) confirmed by analyses of rbcL sequences, with notes on pollen morphology and wood anatomy

The phylogenetic placement of Kuhlmanniodendron Fiaschi & Groppo (Achariaceae) within Malpighiales was investigated with rbcL sequence data. This genus was recently created to accommodate Carpotroche apterocarpa Kuhlm., a poorly known species from the rainforests of Espirito Santo, Brazil. One rbcL sequence was obtained from Kuhlmanniodendron and analyzed with 73 additional sequences from Malpighiales, and 8 from two closer orders, Oxalidales and Celastrales, all of which were available at Genbank. Phylogenetic analyses were carried out with maximum parsimony and Bayesian inference; bootstrap analyses were used in maximum parsimony to evaluate branch support. The results confirmed the placement of Kuhlmanniodendron together with Camptostylus, Lindackeria, Xylotheca, and Caloncoba in a strongly supported clade (posterior probability = 0.99) that corresponds with the tribe Lindackerieae of Achariaceae (Malpighiales). Kuhlmanniodendron also does not appear to be closely related to Oncoba (Salicaceae), an African genus with similar floral and fruit morphology that has been traditionally placed among cyanogenic Flacourtiaceae (now Achariaceae). A picrosodic paper test was performed in herbarium dry leaves, and the presence of cyanogenic glycosides, a class of compounds usually found in Achariaceae, was detected. Pollen morphology and wood anatomy of Kuhlmanniodendron were also investigated, but both pollen (3-colporate and microreticulate) and wood, with solitary to multiple vessels, scalariform perforation plates and other features, do not seem to be useful to distinguish this genus from other members of the Achariaceae and are rather common among the eudicotyledons as a whole. However, perforated ray cells with scalariform plates, an uncommon wood character, present in Kuhlmanniodendron are similar to those found in Kiggelaria africana (Pangieae, Achariaceae), but the occurrence of such cells is not mapped among the angiosperms, and it is not clear how homoplastic this character could be.

Using non-homogeneous Poisson models with multiple change-points to estimate the number of ozone exceedances in Mexico City

In this paper, we consider some non-homogeneous Poisson models to estimate the probability that an air quality standard is exceeded a given number of times in a time interval of interest. We assume that the number of exceedances occurs according to a non-homogeneous Poisson process (NHPP). This Poisson process has rate function lambda(t), t >= 0, which depends on some parameters that must be estimated. We take into account two cases of rate functions: the Weibull and the Goel-Okumoto. We consider models with and without change-points. When the presence of change-points is assumed, we may have the presence of either one, two or three change-points, depending of the data set. The parameters of the rate functions are estimated using a Gibbs sampling algorithm. Results are applied to ozone data provided by the Mexico City monitoring network. In a first instance, we assume that there are no change-points present. Depending on the adjustment of the model, we assume the presence of either one, two or three change-points. Copyright (C) 2009 John Wiley & Sons, Ltd.

Determinants of Accelerated Small Intestinal Transit in Alcohol-Related Chronic Pancreatitis

Patients with chronic pancreatitis may have abnormal gastrointestinal transit, but the factors underlying these abnormalities are poorly understood. Gastrointestinal transit was assessed, in 40 male outpatients with alcohol-related chronic pancreatitis and 18 controls, by scintigraphy after a liquid meal labeled with (99m)technetium-phytate. Blood and urinary glucose, fecal fat excretion, nutritional status, and cardiovascular autonomic function were determined in all patients. The influence of diabetes mellitus, malabsorption, malnutrition, and autonomic neuropathy on abnormal gastrointestinal transit was assessed by univariate analysis and Bayesian multiple regression analysis. Accelerated gastrointestinal transit was found in 11 patients who showed abnormally rapid arrival of the meal marker to the cecum. Univariate and Bayesian analysis showed that diabetes mellitus and autonomic neuropathy had significant influences on rapid transit, which was not associated with either malabsorption or malnutrition. In conclusion, rapid gastrointestinal transit in patients with alcohol-related chronic pancreatitis is related to diabetes mellitus and autonomic neuropathy.

Estimating the number of ozone peaks in Mexico City using a non-homogeneous Poisson model

In this paper, we consider the problem of estimating the number of times an air quality standard is exceeded in a given period of time. A non-homogeneous Poisson model is proposed to analyse this issue. The rate at which the Poisson events occur is given by a rate function lambda(t), t >= 0. This rate function also depends on some parameters that need to be estimated. Two forms of lambda(t), t >= 0 are considered. One of them is of the Weibull form and the other is of the exponentiated-Weibull form. The parameters estimation is made using a Bayesian formulation based on the Gibbs sampling algorithm. The assignation of the prior distributions for the parameters is made in two stages. In the first stage, non-informative prior distributions are considered. Using the information provided by the first stage, more informative prior distributions are used in the second one. The theoretical development is applied to data provided by the monitoring network of Mexico City. The rate function that best fit the data varies according to the region of the city and/or threshold that is considered. In some cases the best fit is the Weibull form and in other cases the best option is the exponentiated-Weibull. Copyright (C) 2007 John Wiley & Sons, Ltd.

Methods of Estimation in Multiple Linear Regression: Application to Clinical Data

Nesse artigo, tem-se o interesse em avaliar diferentes estratégias de estimação de parâmetros para um modelo de regressão linear múltipla. Para a estimação dos parâmetros do modelo foram utilizados dados de um ensaio clínico em que o interesse foi verificar se o ensaio mecânico da propriedade de força máxima (EM-FM) está associada com a massa femoral, com o diâmetro femoral e com o grupo experimental de ratas ovariectomizadas da raça Rattus norvegicus albinus, variedade Wistar. Para a estimação dos parâmetros do modelo serão comparadas três metodologias: a metodologia clássica, baseada no método dos mínimos quadrados; a metodologia Bayesiana, baseada no teorema de Bayes; e o método Bootstrap, baseado em processos de reamostragem.

Jämförelse av europeiska fotbollsklubbars logotyper : En visuell innehållsanalys

Sedan fotbollens början 1863 har sporten idag vuxit till en mångmiljardindustri. Detta innebär att klubbarna framställs mer som företag där den visuella identiteten är en viktig faktor när det kommer till marknadsföring. Syftet med denna studie är att jämföra 98 europeiska fotbollsklubbars logotyper från fem olika ligor för att hitta samband och skillnader i utformningen mellan länder och ligor. Resultatet sammanfattades i form av generiska logotyper för respektive liga. De 98 klubbarna hämtades ur de fem europeiska ligor som 2014 hade störst tv-intäkter. Logotyperna samlades in genom bildsökningar via Google. Logotyperna sorterades efter respektive liga och överskådades för att definiera lämpliga kategorier för en visuell innehållsanalys. Den visuella innehållsanalysen visade att ligorna skiljer sig något vad beträffar logotypernas utformning, men att de har vissa gemensamma grundläggande drag.

Antecipação do movimento do preço da commodity aço em contratos a preço firme no mercado de engenharia industrial no Brasil

Nesta Tese foram apresentadas algumas alternativas de antecipação do preço futuro do aço a partir do emprego de modelos econométricos. Estes modelos foram definidos em função da análise do comportamento, no longo prazo, entre as séries de preços do aço no Brasil vis-à-vis seus respectivos preços no exterior. A verificação deste comportamento de longo prazo foi realizada através do teste de cointegração. A partir da constatação da não cointegração dessas séries, foram definidos dois modelos, cujas previsões, para diversos períodos, foram aqui apresentadas. Foi feita uma análise comparativa, onde foram identificados o melhor modelo e para quais temporalidades de previsão são melhor empregados. Como foi aqui comprovado, o aço é um insumo primordial nos empreendimentos industriais. Considerando que, atualmente, os preços são demandados de forma firme, ou seja, sem possibilidade de alteração, faz-se necessária a identificação de mecanismos de antecipação dos movimentos futuros desta commodity, de modo que se possa considerá-los na definição do preço ofertado, reduzindo assim perdas por suas flutuações inesperadas.

Graphical models and point set matching

Point pattern matching in Euclidean Spaces is one of the fundamental problems in Pattern Recognition, having applications ranging from Computer Vision to Computational Chemistry. Whenever two complex patterns are encoded by two sets of points identifying their key features, their comparison can be seen as a point pattern matching problem. This work proposes a single approach to both exact and inexact point set matching in Euclidean Spaces of arbitrary dimension. In the case of exact matching, it is assured to find an optimal solution. For inexact matching (when noise is involved), experimental results confirm the validity of the approach. We start by regarding point pattern matching as a weighted graph matching problem. We then formulate the weighted graph matching problem as one of Bayesian inference in a probabilistic graphical model. By exploiting the existence of fundamental constraints in patterns embedded in Euclidean Spaces, we prove that for exact point set matching a simple graphical model is equivalent to the full model. It is possible to show that exact probabilistic inference in this simple model has polynomial time complexity with respect to the number of elements in the patterns to be matched. This gives rise to a technique that for exact matching provably finds a global optimum in polynomial time for any dimensionality of the underlying Euclidean Space. Computational experiments comparing this technique with well-known probabilistic relaxation labeling show significant performance improvement for inexact matching. The proposed approach is significantly more robust under augmentation of the sizes of the involved patterns. In the absence of noise, the results are always perfect.

The best are never normal : exploring the distribution of firm performance

Competitive Strategy literature predicts three different mechanisms of performance generation, thus distinguishing between firms that have competitive advantage, firms that have competitive disadvantage or firms that have neither. Nonetheless, previous works in the field have fitted a single normal distribution to model firm performance. Here, we develop a new approach that distinguishes among performance generating mechanisms and allows the identification of firms with competitive advantage or disadvantage. Theorizing on the positive feedback loops by which firms with competitive advantage have facilitated access to acquire new resources, we proposed a distribution we believe data on firm performance should follow. We illustrate our model by assessing its fit to data on firm performance, addressing its theoretical implications and comparing it to previous works.

Modelos dinâmicos e simulação estocástica

This paper presents new methodology for making Bayesian inference about dy~ o!s for exponential famiIy observations. The approach is simulation-based _~t> use of ~vlarkov chain Monte Carlo techniques. A yletropolis-Hastings i:U~UnLlllll 1::; combined with the Gibbs sampler in repeated use of an adjusted version of normal dynamic linear models. Different alternative schemes are derived and compared. The approach is fully Bayesian in obtaining posterior samples for state parameters and unknown hyperparameters. Illustrations to real data sets with sparse counts and missing values are presented. Extensions to accommodate for general distributions for observations and disturbances. intervention. non-linear models and rnultivariate time series are outlined.

Simulation-based smoothing and filtering in factor stochastic volatility models : two econometric applications

In this article we use factor models to describe a certain class of covariance structure for financiaI time series models. More specifical1y, we concentrate on situations where the factor variances are modeled by a multivariate stochastic volatility structure. We build on previous work by allowing the factor loadings, in the factor mo deI structure, to have a time-varying structure and to capture changes in asset weights over time motivated by applications with multi pIe time series of daily exchange rates. We explore and discuss potential extensions to the models exposed here in the prediction area. This discussion leads to open issues on real time implementation and natural model comparisons.