Abstract
The rapid expansion of Asian hornets poses a high threat for the honey bee survival, as these invaders pray on them. Furthermore, they also pose a threat to people who are allergic, whose sting can lead to death. This study proposes a Decision Support System that uses Computer Vision techniques to automatically detect signs of Vespa velutina through images from GPS equipped camera. The goal of the system is to provide timely information about the presence of these invaders, allowing park managers and beekeepers to act quickly in removing the Vespidae. The proposed methodology obtained an 85% accuracy in the detection of V. velutina using the Mask RCNN architecture, enabling the system to perform detection at 3 FPS. © 2020 MIR Labs.

Abstract
Objectives: Artificial intelligence (AI) is poised to transform breast cancer care. However, most scientists, engineers, and clinicians are not prepared to contribute to the AI revolution in healthcare. In this paper, we describe our experiences teaching a new undergraduate course for American students that aims to prepare the next generation for cross-cultural designthinking, which we believe is crucial for AI to achieve its full potential in breast cancer care. Materials and methods: The key course activities are planning, conducting, and interpreting interviews of healthcare professionals from both Portugal and the United States. Since the course is offered as a short-term faculty-led study abroad program in Portugal, students are able to explore the impact of culture on healthcare delivery and the design of healthcare technologies. Results: The learning assessments demonstrated student growth in several areas pertinent for future development of AI for breast cancer care. With respect to understanding breast cancer care, prior to taking this course, most students had underestimated the impact of cancer and its treatment on women's quality of life and most were unaware of the importance of multidisciplinary care teams. Regarding AI in medicine, students became more mindful of data privacy issues and the need to consider the effect of AI on healthcare professionals. Conclusion: This course illustrates the potential benefits for AI in medicine of introducing future scientists, engineers, and clinicians to cross cultural design-thinking early in their educational experiences. (C) 2020 The Author(s). Published by Elsevier Ltd.

Abstract
The tendency to use renewable energies in DC microgrids (MGs) has been increased in the past decades. Due to the unpredictable behavior of renewable resources, it is vital to utilize energy storage resources in the MG structure. The generation sources and storages in DC MGs should be chosen in order to meet the maximum demand in both grid-connected and islanded mode. Also, penetration of power electronic based devices is essential to connect these resources to the network. The control of these devices are another challenge in this regard. So, a proper configuration along with an efficient control approach is needed for development of DC MGs. In this paper, a new structure for DC MG is presented which includes solar photovoltaic (PV) as generation sources and supercapacitor and battery as storages. Furthermore, an innovative control method based on voltage variations is introduced for the proposed structure. It is shown that simultaneous usage of battery and supercapacitor improves the performance of the MG in handling the abrupt load changes in the both grid-connected and islanded mode operations. To evaluate the performance of the proposed structure and control algorithm, different conditions are simulated in MATLAB/Simulink software and the results are presented. The results confirm a high degree of performance for proposed structure and control method.

Abstract
In the Mediterranean region, climate change is likely to generate an increase in water demand and the deterioration of its quality. The adoption of precision viticulture and the best available techniques aiming at sustainable production, minimizing the impact on natural resources and reducing production costs, has therefore been a goal of winegrowers. In this work, the water footprint (WFP) in the wine sector was evaluated, from the vineyard to the bottle, through the implementation of a methodology based on field experiments and life cycle assessment (LCA) on two Portuguese case studies. Regarding direct water footprint, it ranged from 366 to 899 L/FU (0.75 L bottle), with green water being the most significant component, representing more than 50% of the overall water footprint. The approach used in the current study revealed that although more than 97.5% of the water footprint is associated with vineyard, the winery stage is responsible for more than 75% of the global warming potential indicator. A linear correlation between the carbon footprint and the indirect blue water footprint was also observed for both case studies. Climate change is expected to cause an earlier and prolonged water stress period, resulting in an increase of about 40% to 82% of blue WFP.

Abstract
Internet-of-Things systems are assemblies of highly-distributed and heterogeneous parts that, in orchestration, work to provide valuable services to end-users in many scenarios. These systems depend on the correct operation of sensors, actuators, and third-party services, and the failure of a single one can hinder the proper functioning of the whole system, making error detection and recovery of paramount importance, but often overlooked. By drawing inspiration from other research areas, such as cloud, embedded, and mission-critical systems, we present a set of patterns for self-healing IoT systems. We discuss how their implementation can improve system reliability by providing error detection, error recovery, and health mechanisms maintenance. © 2020 ACM.

Abstract
Cloud computing is omnipresent and plays an important role in today’s world of Internet of Things (IoT). Several IoT devices and their applications already run and communicate through the cloud, easing the configuration burden for their users. With the expected exponential growth on the number of connected IoT devices this centralized approach raises latency, privacy and scalability concerns. This paper proposes the use of fog computing to overcome those concerns. It presents an architecture intended to distribute the communication, computation and storage loads to small gateways, close to the edge of the network, in charge of a group of IoT devices. This approach saves battery on end devices, enables local sensor fusion and fast response to urgent situations while improving user privacy. This architecture was implemented and tested on a project to monitor the level of used cooking oil, stored in barrels, in some restaurants where low cost, battery powered end devices are periodically reporting sensor data. Results show a 93% improvement in end device battery life (by reducing their communication time) and a 75% saving on cloud storage (by processing raw data on the fog device).