Modeling and Classifying Breast Tissue Density in Mammograms

We present a new approach to model and classify breast parenchymal tissue. Given a mammogram, first, we will discover the distribution of the different tissue densities in an unsupervised manner, and second, we will use this tissue distribution to perform the classification. We achieve this using a classifier based on local descriptors and probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature. We studied the influence of different descriptors like texture and SIFT features at the classification stage showing that textons outperform SIFT in all cases. Moreover we demonstrate that pLSA automatically extracts meaningful latent aspects generating a compact tissue representation based on their densities, useful for discriminating on mammogram classification. We show the results of tissue classification over the MIAS and DDSM datasets. We compare our method with approaches that classified these same datasets showing a better performance of our proposal

Espectadroa de la red

Presentación de los barrios de blogs: cómo son, cómo se relacionan, cómo se propaga la información a través de éstos y cómo saber cuáles son los más interesantes.

Forecasting the maximum compensation offer in the automobile BI claims negotiation process

Most motor bodily injury (BI) claims are settled by negotiation, with fewer than 5% of cases going to court. A well-defined negotiation strategy is thus very useful for insurance companies. In this paper we assume that the monetary compensation awarded in court is the upper amount to be offered by the insurer in the negotiation process. Using a real database, a log-linear model is implemented to estimate the maximal offer. Non-spherical disturbances are detected. Correlation occurs when various claims are settled in the same judicial verdict. Group wise heteroscedasticity is due to the influence of the forensic valuation on the final compensation amount. An alternative approximation based on generalized inference theory is applied to estimate confidence intervals on variance components, since classical interval estimates may be unreliable for datasets with unbalanced structures.

Ex-presó. Compromiso social y creación artística desde los estudios de género

La docencia universitaria de los Estudios de Género aplicados a la creación artística ejerce un estímulo del compromiso social. Analizo el proyecto Ex-presó creado a partir de la antigua cárcel de mujeres de les Corts (Barcelona, 1936-1955), lugar actualmente ocupado por unos grandes almacenes. Mediante los códigos Quick Response (QR) el proyecto tiene su eje de acción en un blog donde se centraliza la información histórica. Se construye un memorial en el que, por un instante, todos podamos trasladarnos al pasado para entender y conocer un poco más de nuestra historia y de nuestra realidad. El objetivo es evidenciar lo que no está para evitar el olvido. Mediante esta práctica se cuestiona lo establecido, se incentiva el compromiso social e interactúa con la práctica artística desde la formación universitaria.

Taxation of unhealthy consumption of food and drinks: An updated literature review

By means of a literature review this paper aims at shedding more light on the potentialities of unhealthy food/drink taxation in changing eating patterns and life styles and hence combating the obesity epidemic. One remarkable point that emerges when assessing the set of selected papers is the existence of a wide diversity of objectives, methodologies, settings and datasets, policies implemented and results achieved by all these studies, which undoubtedly adds complexity to any attempt to draw a general conclusion on fast food taxation. Most of the examined studies predict a rather modest fiscal impact on unhealthy food and drinks consumption and/or nutrition intake and consequently a poor result on weight loss and obesity, by the interplay of several factors among them the effects of cross-price elasticities.

Taxation of unhealthy consumption of food and drinks: An updated literature review

By means of a literature review this paper aims at shedding more light on the potentialities of unhealthy food/drink taxation in changing eating patterns and life styles and hence combating the obesity epidemic. One remarkable point that emerges when assessing the set of selected papers is the existence of a wide diversity of objectives, methodologies, settings and datasets, policies implemented and results achieved by all these studies, which undoubtedly adds complexity to any attempt to draw a general conclusion on fast food taxation. Most of the examined studies predict a rather modest fiscal impact on unhealthy food and drinks consumption and/or nutrition intake and consequently a poor result on weight loss and obesity, by the interplay of several factors among them the effects of cross-price elasticities.

Efficient image mosaicing for multi-robot visual underwater mapping

Robotic platforms have advanced greatly in terms of their remote sensing capabilities, including obtaining optical information using cameras. Alongside these advances, visual mapping has become a very active research area, which facilitates the mapping of areas inaccessible to humans. This requires the efficient processing of data to increase the final mosaic quality and computational efficiency. In this paper, we propose an efficient image mosaicing algorithm for large area visual mapping in underwater environments using multiple underwater robots. Our method identifies overlapping image pairs in the trajectories carried out by the different robots during the topology estimation process, being this a cornerstone for efficiently mapping large areas of the seafloor. We present comparative results based on challenging real underwater datasets, which simulated multi-robot mapping

The association between obesity and back pain in nine countries: a cross-sectional study

BACKGROUND: The association between obesity and back pain has mainly been studied in high-income settings with inconclusive results, and data from older populations and developing countries are scarce. The aim of this study was to assess this association in nine countries in Asia, Africa, Europe, and Latin America among older adults using nationally-representative data. METHODS: Data on 42116 individuals ≥50 years who participated in the Collaborative Research on Ageing in Europe (COURAGE) study conducted in Finland, Poland, and Spain in 2011-2012, and the World Health Organization's Study on Global Ageing and Adult Health (SAGE) conducted in China, Ghana, India, Mexico, Russia, and South Africa in 2007-2010 were analysed. Information on measured height and weight available in the two datasets was used to calculate Body Mass Index (BMI). Self-reported back pain occurring in the past 30 days was the outcome. Multivariable logistic regression analysis was used to assess the association between BMI and back pain. RESULTS: The prevalence of back pain ranged from 21.5% (China) to 57.5% (Poland). In the multivariable analysis, compared to BMI 18.5-24.9 kg/m(2), significantly higher odds for back pain were observed for BMI ≥35 kg/m(2) in Finland (OR 3.33), Russia (OR 2.20), Poland (OR 2.03), Spain (OR 1.56), and South Africa (OR 1.48); BMI 30.0-34.0 kg/m(2) in Russia (OR 2.76), South Africa (OR 1.51), and Poland (OR 1.47); and BMI 25.0-29.9 kg/m(2) in Russia (OR 1.51) and Poland (OR 1.40). No significant associations were found in the other countries. CONCLUSIONS: The strength of the association between obesity and back pain may vary by country. Future studies are needed to determine the factors contributing to differences in the associations observed.