Abstract
A method to detect juxta-pleural nodules with radius smaller than 5mm is presented. The intensity difference between nodules and parenchymal tissue as well as the nodules' natural roundness are exploited. Solid nodules are detected by selecting an appropriate threshold over a sliding window, whereas sub-solid/non-solid nodules are enhanced using multi-scale Laplacian-of-Gaussian filters. The 2D-wise outputs are combined to 3D, producing a final candidate list. False positive reduction is achieved with fixed rules and supervised learning. The achieved sensitivity is 57% with 4 false positives/scan, increasing to 62% if only solid nodules are considered. © 2017 SPIE.

Abstract
Software’s structure profoundly affects its development and maintenance costs. Poor software’s structure may lead to well-known design flaws, such as large modules or long methods. A possible ap- proach to reduce a module’s complexity is the Extract Method refactor- ing technique. This technique allows the decomposition of a large and complex method into smaller and simpler ones, while reducing the orig- inal method’s size and improving its readability and comprehension. The OutSystems platform is a low-code platform that allows the de- velopment of web and mobile applications that rely on a set of visual Domain-Specific Languages (DSLs). Even low-code languages when im- properly used can lead to software that has maintenance issues like long methods. Thus, the purpose of this paper is to present the research and devel- opment done to provide the OutSystems platform with a tool that au- tomatically suggests Extract Method refactoring opportunities. The re- search combines program slicing techniques with code complexity metrics to calculate the best refactoring opportunities that preserve programs’ functionality. The proposed approach was tested on typical OutSystems apps and was shown to be able to reduce the overall applications’ complexity.

Abstract
In this work, the self-scheduling problem of a power producer in smart grids is addressed using a stochastic programming approach. Different uncertainties are considered as price uncertainties, forced-outage of the unit as well as generation reallocation. The conditional value-at-risk index is used for modeling of risk. The markets considered in this study are bilateral contracts, day-ahead and ancillary services, including spinning reserve and regulation, and spot market decisions, while an incomplete competitive market is considered. In this sense, an innovative method for bilateral contracts is proposed to increase the profit of the market without ignoring any regulatory rules. The Monte Carlo method is implemented together with a reduction scenario process to generate scenarios.

Abstract
Melanoma is the most dangerous and lethal form of human skin cancer and the early detection is a fundamental key for its successful management. In recent years the use of automatic classification algorithms in the context of Computer Aided Diagnosis (CAD) systems have been an important tool, by improving quantification metrics and also assisting in the decision regarding lesion management. This paper presents a novel and robust textured-based approach to detect melanomas among melanocytic images obtained by dermoscopy, using Local Binary Pattern Variance (LBPV) histograms after the Bidimensional Empirical Mode Decomposition (BEMD) scale-based decomposition methodology. The results show that it is possible to develop a robust CAD system for the classification of dermoscopy images obtained from different databases and acquired in diverse conditions. After the initial texture-scale based classification a post-processing refinement is proposed using reticular pattern and color achieving to 97.83, 94.44 and 96.00 for Sensitivity, Specificity and Accuracy.

Abstract

Abstract
In order to increase sales and profits, it is common that e-commerce website owners resort to several marketing and advertising techniques, attempting to influence user actions. Summarizing and analysing user behaviour is a complex task since it is hard to extrapolate patterns that never occurred before and the causality aspects of the system are not usually taken into consideration. There has been studies about characterizing user behaviour and interactions in e-commerce websites that could be used to improve this process. This paper presents an agent-based framework for simulating models of user behaviour created through data mining processes within an e-commerce context. The purpose of framework is to study the reaction of user to stimuli that influence their actions while navigating the website. Furthermore a scalability analysis is performed on a case-study. © Springer International Publishing AG 2018.