Abstract
Today's climatic proneness to extreme conditions together with human activity have been triggering a series of wildfire-related events that put at risk ecosystems, as well as animal and vegetal patrimony, while threatening dwellers nearby rural or urban areas. When intervention teams-firefighters, civil protection, police-acknowledge these events, usually they have already escalated to proportions hardly controllable mainly due wind gusts, fuel-like solo conditions, among other conditions that propitiate fire spreading. Currently, there is a wide range of camera-capable sensing systems that can be complemented with useful location data-for example, unmanned aerial systems (UAS) integrated cameras and IMU/GPS sensors, stationary surveillance systems-and processing components capable of fostering wildfire events detection and monitoring, thus providing accurate and faithful data for decision support. Precisely in what concerns to detection and monitoring, Deep Learning (DL) has been successfully applied to perform tasks involving classification and/or segmentation of objects of interest in several fields, such as Agriculture, Forestry and other similar areas. Usually, for an effective DL application, more specifically, based on imagery, datasets must rely on heavy and burdensome logistics to gather a representative problem formulation. What if putting together a dataset could be supported in customizable virtual environments, representing faithful situations to train machines, as it already occurs for human training in what regards some particular tasks (rescue operations, surgeries, industry assembling, etc.)? This work intends to propose not only a system to produce faithful virtual environments to complement and/or even supplant the need for dataset gathering logistics while eventually dealing with hypothetical proposals considering climate change events, but also to create tools for synthesizing wildfire environments for DL application. It will therefore enable to extend existing fire datasets with new data generated by human interaction and supervision, viable for training a computational entity. To that end, a study is presented to assess at which extent data virtually generated data can contribute to an effective DL system aiming to identify and segment fire, bearing in mind future developments of active monitoring systems to timely detect fire events and hopefully provide decision support systems to operational teams.

Abstract

Abstract
Wireless capsule endoscopy is a relatively novel technique used for imaging of the gastrointestinal tract. Unlike traditional approaches, it allows painless visualisation of the whole of the gastrointestinal tract, including the small bowel, a region of difficult access. Endoscopic capsules record for about 8h, producing around 60,000 images. These are analysed by an expert that identifies abnormalities present in the frames, a process that is very tedious and prone to errors. Thus there is a clear need to develop systems that automatically analyse this data and detect lesions. Lesion detection achieved a precision of 0.94 and a recall of 0.93 by fmetuning the pre-trained DenseNet-161 model. (C) 2019 The Authors. Published by Elsevier B.V.

Abstract
Mobile applications are proliferating in all business domains. In the tourism sector, that is information intensive, and a global phenomenon, the development of efficient solutions for deliver information and services for "information-starving" tourists is a challenge, and opportunity but mostly a necessity of modern competitive touristic destinations. This paper briefly discusses the role that mobile devices applications have in the support of information and services of Cabo Verde visiting tourists and presents the design and development of a prototype application Android-based that enable important information and services for all Cabo Verde tourists that need to know more about Cabo Verde islands and their important information and services, manly related with their culture, gastronomy, events and hospitality services.

Abstract
Batalha Abbey is a 14th century UNESCO world heritage site that shows signs of decay. During the last years, high resolution geophysical methods have been used to contribute to the knowledge of its construction characteristics and to an informed maintenance and rehabilitation project. Here in it is presented a multimethod high-resolution geophysical investigation of its main tower. A 3D resistivity survey was carried out on the surface around the tower to investigate the ground beneath it. A GPR survey was used on the tower walls surface to investigate its interior. Three frequencies, 250MHz, 500MHz and 800MHz, were used. Finally, a seismic tomography study was done around the tower with both geophones and sources on the tower walls to provide a 3D velocity image of the tower interior. 3D resistivity results give a clear image of the walls foundations and of the ground beneath the tower. GPR 250MHz data provide a complete GPR image across the tower, although of low resolution. Higher resolution GPR results provided clearer information on the constructive elements of the tower. Finally, the seismic tomography results gave, for the first time, a complete image of the tower interior and proved it a compact construction with no voids.

Abstract
Secure and reliable operation is one of the main challenges in restructured power systems. Wind energy has been gaining increasing global attention as a clean and economic energy source, despite the operational challenges its intermittency brings. In this study, we present a formulation for electricity and reserve market clearance in the presence of wind farms. Uncertainties associated with generation and line outages are modeled as different system scenarios. The formulation incorporates the cost of different scenarios in a two-stage short-term (24-hours) clearing process, also considering different types of reserve. The model is then linearized in order to be compatible with standard mixed-integer linear programming solvers, aiming at solving the security constrained unit-commitment problem using as few variables and optimization constraints as possible. As shown, this will expedite the solution of the optimization problem. The model is validated by testing it on a case study based on the IEEE RTS1, for which results are presented and discussed.