Abstract
The wine industry has a high business volume and adds value to the economy. This chapter intends to predict the wine firm performance of three of the most relevant Portuguese regions, by resorting to data available on the Portuguese Farm Accountancy Data Network (PTFADN, Resultados médios por exploração. Available on http://www.gpp.pt/index.php/rica/rede-de-informacao-de-contabilidades-agricolas-rica. Accessed 13 Mar 2018, 2001–2015). The existing social, economic and environmental parameters allowed us to perform function fitting with MATLAB, in order to attain information about the variable’s behaviour. Through the Agent-Based Model (ABM) simulations, it is possible to realize that, in general, the Alentejo region is substantially well prepared to deal with negative scenarios when compared with North and Central regions. Alternative scenarios can be performed in order to develop overall governmental policy recommendations, so as to ensure the sustainability of the three regions. © 2020, The Author(s).

Abstract
Convolutional Neural Networks, as well as other deep learning methods, have shown remarkable performance on tasks like classification and detection. However, these models largely remain black-boxes. With the widespread use of such networks in real-world scenarios and with the growing demand of the right to explanation, especially in highly-regulated areas like medicine and criminal justice, generating accurate predictions is no longer enough. Machine learning models have to be explainable, i.e., understandable to humans, which entails being able to present the reasons behind their decisions. While most of the literature focuses on post-model methods, we propose an in-model CNN architecture, composed by an explainer and a classifier. The model is trained end-to-end, with the classifier taking as input not only images from the dataset but also the explainer’s resulting explanation, thus allowing for the classifier to focus on the relevant areas of such explanation. We also developed a synthetic dataset generation framework, that allows for automatic annotation and creation of easy-to-understand images that do not require the knowledge of an expert to be explained. Promising results were obtained, especially when using L1 regularisation, validating the potential of the proposed architecture and further encouraging research to improve the proposed architecture’s explainability and performance. © 2019, Springer Nature Switzerland AG.

Abstract
Brazil has been failing to offer the most favorable conditions for the implementation of onshore wind farms, due to the presence of multiple barriers. However, the country has observed a fast and expressive wind energy (WE) diffusion (the installed WE capacity grew 37 times in the last decade). Furthermore, its onshore wind farms have reached impressive capacity factors (with productivity levels much higher than the average around the world) and a very low levelized cost of electricity. This study aims at identifying how wind developers plan onshore wind farms to overcome existing barriers. Based on forty-one interviews with relevant stakeholders of the Brazilian WE sector, the study identified efforts targeted at overcoming twenty-four previously identified barriers. Although most barriers may be overcome directly through developer initiatives, addressing higher level barriers, namely an unstable macroeconomic environment, a poor transmission infrastructure, and inadequate access to capital, depends on government actions.

Abstract
Peer-to-peer communication has increasingly gained prevalence in people’s daily lives, with its widespread adoption being catalysed by technological advances. Although there have been strides for the inclusion of disabled individuals to ease communication between peers, people who suffer hand/arm impairments have scarce support in regular mainstream applications to efficiently communicate privately with other individuals. Additionally, as centralized systems have come into scrutiny regarding privacy and security, development of alternative, decentralized solutions has increased, a movement pioneered by Bitcoin that culminated on the blockchain technology and its variants. Within the inclusivity paradigm, this paper aims to showcase an alternative on human-computer interaction with support for the aforementioned individuals, through the use of an electroencephalography headset and electromyography surface electrodes, for application navigation and text input purposes respectively. Users of the application are inserted in a decentralized system that is designed for secure communication and exchange of data between peers that are both resilient to tampering attacks and central points of failure, with no long-term restrictions regarding scalability prospects. Therefore, being composed of a silent speech and brain-computer interface, users can communicate with other peers, regardless of disability status, with no physical contact with the device. Users utilize a specific user interface design that supports such interaction, doing so securely on a decentralized network that is based on a distributed hash table for better lookup, insert and deletion of data performance. This project is still in early stages of development, having successfully been developed a functional prototype on a closed, testing environment. © 2020, Springer Nature Switzerland AG.

Abstract
Due to the technological evolution on wearable devices, biosignals, such as inter-cardiac beat interval (RR) time series, are being captured in a non-controlled environment. These RR signals, derived from photoplethysmography (PPG), enable health status assessment in a more continuous, non-invasive, non-obstructive way, and fully integrated into the individual’s daily activity. However, PPG is vulnerable to motion artefacts, which can affect the accuracy of the estimated neurophysiological markers. This paper introduces a method for motion artefact characterization in terms of location and relative variation parameters obtained in different common daily activities. The approach takes into consideration interindividual variability. Data was analyzed throughout related-samples Friedman’s test, followed by pairwise comparison with Wilcoxon signed-rank tests with a Bonferroni correction. Results showed that movement, involving only arms, presents more variability in terms of the two analyzed parameters. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
The preoperative localisation of non-palpable lesions guided by breast imaging is an important and required procedure for breast-conserving surgery. We conducted a systematic review and meta-analysis of the literature on the comparative impact of different techniques for guided surgical excision of non-palpable breast lesions from reports of clinical or patient-reported outcomes and costs. A literature search of PubMed, ISI, SCOPUS and Cochrane databases was conducted for relevant publications and their references, along with public documents, national and international guidelines, conference proceedings and presentations. From 5720 retrieved articles screened through title and abstract, 5346 were excluded and 374 assessed for full-text eligibility. For data extraction and quality assessment, 49 studies were included. Results of this review demonstrate that Radioactive Seed Localisation (RSL) and Radioactive Occult Lesion Localisation (ROLL) outperform Wire in terms of involved margins and reoperations. Between RSL and ROLL, there is a tendency to favour RSL. Similarly, Clip-guided localisation seems preferred when compared to ROLL, however further studies are needed. In summary, there seems to exist evidence that RSL and ROLL are better than Wire, representing potential alternatives, with a quick learning curve, better scheduling and management issues. Although, for recent techniques, more research is needed in order to achieve the same level of evidence.