Abstract
Wine is the most important product from the Douro Region, in Portugal. Ampelographs are disappearing, and farmers need new solutions to identify grapevine varieties to ensure high-quality standards. The development of methodology capable of automatically identify grapevine are in need. In the scenario, deep learning based methods are emerging as the state-of-art in grapevines classification tasks. In previous work, we verify the deep learning models would benefit from focus classification patches in leaves images areas. Deep learning segmentation methods can be used to find grapevine leaves areas. This paper presents a methodology to segment grapevines images automatically based on the U-net model. A private dataset was used, composed of 733 grapevines images frames extracted from 236 videos collected in a natural environment. The trained model obtained a Dice of 95.6% and an Intersection over Union of 91.6%, results that fully satisfy the need of localise grapevine leaves.

Abstract
In this work, different weight contents of as-grown carbon nanofibers (CNFs), produced by chemical vapor deposition, were melt-extruded with polypropylene (PP) and their morphologic, structure and dielectric properties examined. The morphologic analysis reveals that the CNFs are randomly distributed in the form of agglomerates within the PP matrix, whereas the structural results depicted by Raman analysis suggest that the degree of disorder of the as-received CNFs was not affected in the PP/CNF composites. The AC conductivity of PP/CNF composites at room temperature evidenced an insulator-conductor transition in the vicinity of 2 wt.%, corresponding to a remarkable rise of the dielectric permittivity up to similar to 12 at 400 Hz, with respect to the neat PP (similar to 2.5). Accordingly, the AC conductivity and dielectric permittivity of PP/CNF 2 wt.% composites were evaluated by using power laws and discussed in the framework of the intercluster polarization model. Finally, the complex impedance and Nyquist plots of the PP/CNF composites are analyzed by using equivalent circuit models, consisting of a constant phase element (CPE). The analysis gathered in here aims at contributing to the better understanding of the enhanced dielectric properties of low-conducting polymer composites filled with carbon nanofibers.

Abstract
<p>The marine boundary layer offers a unique opportunity to investigate the electrical properties of the atmosphere, as the effect of natural radioactivity in driving near surface ionization is significantly reduced over the ocean, and the concentration of aerosols is also typically lower than over land. This work addresses the temporal variability of the atmospheric electric field in the South Atlantic marine boundary layer based on measurements from the SAIL (Space-Atmosphere-Ocean Interactions in the marine boundary Layer) project. The SAIL monitoring campaign took place on board the Portuguese navy tall ship NRP Sagres during its circumnavigation expedition in 2020.  Two identical field mills (CS110, Campbell Scientific) were installed on the same mast but at different heights (about 5 and 22 meters), recording the atmospheric electric field every 1-second. Hourly averages of the atmospheric electric field are analyzed for the ship’s leg from 3<sup>rd</sup> to 25<sup>th</sup> March, between Buenos Aires (South America) and Cape Town (South Africa). The median daily curve of the electric field has a shape compatible with the Carnegie curve, but significant variability is found in the daily pattern of individual days, with only about 30% of the days exhibiting a diurnal pattern consistent with the Carnegie curve.</p>

Abstract

Abstract
The advances in mobile computing and the market demand for new products which meet an increasingly public represent the importance to assure the quality of mobile applications. In this context, automated GUI testing has become highlighted in research. However, studies indicate that there are still limitations to achieve a large number of possible combinations of operations, transitions, functionality coverage, and failures reproduction. In this paper, a Deep Q-Network-based android application GUI testing tool (DeepGUIT) is proposed to test case generation for android mobile apps, guiding the exploration by code coverage value and new activities. The tool was evaluated with 15 open-source mobile applications. The obtained results showed higher code coverage than the state-of-the-art tools Monkey (61% average higher) and Q-testing (47% average higher), in addition, a greater number of failures.

Abstract
Millions of people use public transport on a daily basis. Although most public transport systems use traditional ticketing approaches, based on tickets and smartcards, there are already ticketing alternatives based on smartphones. Most of the mobile ticketing solutions developed and available in the market use technologies such as Near Field Communication (NFC) or Quick Response Codes (QR Codes), and there are practically no studies on the use of Bluetooth Low Energy (BLE) for this purpose. This paper focuses on assessing the feasibility of using BLE beacons for mobile ticketing in urban passenger transport. The study was conducted during the development of a mobile ticketing solution for the Metropolitan Area of Porto (AMP) that takes advantage of the Bluetooth technology present on the passengers' smartphones. It uses BLE beacons to track the passengers' trips from the start to the end, as part of an implementation of a check-in/be-out system. This solution was implemented as a prototype to be tested in the AMP and all the tests performed were made during the course of a pilot test of this prototype. The study consisted of a set of technical tests related with beacons signal monitoring and the gathering and analysis of passengers' feedback who participated in a four months pilot test. The results obtained suggest that the BLE technology is feasible for mobile ticketing in urban passenger transport. The paper also presents the various available deployment alternatives, identifies the main problems found and proposes solutions to solve them, filling an important research gap in the literature. © 2020 The Authors