Abstract
Smart4RES is a European Horizon2020 project developing next generation solutions for renewable energy forecasting. This paper presents highlight results obtained during the first year of the project. Data science is used throughout the proposed solutions in order to process the large amount of heterogeneous data available to forecasters, and derive model-free approaches of forecasting and decision-aid tasks. This paper presents a series of solutions addressing relevant for Photovoltaics (PV) and storage applications. High-resolution Numerical Weather Predictions and regional solar irradiance forecasting provide detailed information on local weather conditions and their variability. PV power forecasting benefits from such new data sources, but also the proposed collaborative data exchange. Finally, data-driven methods simplify decision-making for trading in short-term markets and for grid management. © 2021 Energynautics GMBH.

Abstract
The economic sector of tourism has gained significant weight in the economy of many countries, highlighting the weight of this sector in Portugal. However, the inconsistency and seasonality of demand causes companies linked to the sector to encounter difficulties regarding the planning and management of resources allocated to the activity. It is often the case that there are periods of economic loss caused by a small volume of demand that is insufficient to support the costs of the activity. In this context, this article proposes a system that, based on intelligent data analysis, allows a hotel chain to segment customers and enhance exclusive offers to minimize fluctuation and demand gaps in hotel units installed in thermal instances.

Abstract
Despite the current importance of international retirement migration for both academics and practitioners, the extant literature on the topic is still scarce and mostly focused on short-period migration flows from wealthy and northern countries to cheaper and warm-weather destinations. This article aims at shedding light on the role of tourism in prospective migrants' decision-making process, considering the framework provided by the push-pull model, which is often used to explain both migration and tourism. A qualitative study was conducted, comprising ten in-depth interviews with 45+ year-old Brazilian citizens who intend to move to Europe after retirement. Results show that tourism is important for prospective migrants to evaluate possible migration destinations, as some of the most relevant migration pull factors (e.g., safety) are easily assessed during tourism experiences. Participants in this study also carefully plan tourism activities prior to their decision to migrate in order to get a more realistic notion of what the destination is like for residents. Overall, this study demonstrates that tourism is particularly important for several stages of migrants' decision-making process.

Abstract
Small and medium-sized enterprises (SMEs) in Europe risk their competitiveness if they fail to embrace digitalization. Indeed, SMEs are aware of the need to digitalize-more than one in two SMEs are concerned that they may lose competitiveness if they do not adopt new digital technologies. However, a key obstacle is related with decision-makers' lack of awareness concerning digital technologies potential and implications. Some decision-makers renounce digital transition simply because they do not understand how it can be incorporated into the business. Take into account this common reality, especially among SMEs, this research project intends to identify the skills and subjects that need to be addressed and suggests the educational methodology and implementation strategy capable of maximizing its success. Therefore, and supported by a focused group research methodology, an innovative training program, oriented to decision-makers, was designed and implemented. The program was conceived based on a self-directed learning methodology, combining both asynchronous lecture/expositive and active training methodologies, strongly based on state-of-the-art knowledge and supported by reference cases and real applications. It is intended that the trainees/participants become familiar with a comprehensive set of concepts, principles, methodologies, and tools, capable of significantly enhancing decision-making capability at both strategic and tactical level. The proposed programme with a multidisciplinary scope explores different thematic chapters (self-contained) as well as cross-cutting thematic disciplines, oriented to the Industry 4.0 and digital transformation paradigm. Topics related with Digital Maturity Assessment, Smart Factories and Flexible Production Systems, Big Data, and Artificial Intelligence for Smarter Decision-Making in Industry and Smart Materials and Products, as well as new production processes for new business models. Each thematic chapter in turn is structured around a variable set of elementary modules and includes examples and case studies to illustrate the selected topics. A teaching-learning methodology centered on an online platform is proposed, having as a central element, a collection of videos complemented by a set of handouts that organize the set of key messages and take-ways associated with each module. In this paper, we present the design and practice of this training course specifically oriented to decision-makers in SME.

Abstract
Natural disasters in recent years have highlighted the need for enhancing the resilience of the power systems against these events. Dynamic microgrid (MG) formation using distributed energy resources (DERs) is the common approach in restoring the critical loads (CLs). On the other hand, vehicle-to-grid (V2G) and grid-tovehicle (G2V) capabilities in electric vehicles (EVs), as well as the presence of high-powered engine-generators (EGs) embedded in plug-in hybrid electric vehicles (PHEVs) provide a new capability for using electric and fossil energy stored in EVs simultaneously to restore the CLs during an outage. In this regard, the outage management system (OMS) cooperates with aggregators and uses EVs in the form of a public parking lot (PL) or residential parking (RP), besides other resources such as diesel generators and photovoltaic (PV) units. The approach presented in this paper shows the procedure of load restoration and energy management of available resources under a two-stage stochastic framework. Also, a new method is introduced for restoring CLs in the mesh network by using the load control and the master-slave control techniques. The problem is formulated as mixed-integer linear programming (MILP), and simulations are performed on IEEE 123-buses test system and a real distribution network.

Abstract
Lung cancer is the deadliest form of cancer, accounting for 20% of total cancer deaths. It represents a group of histologically and molecularly heterogeneous diseases even within the same histological subtype. Moreover, accurate histological subtype diagnosis influences the specific subtype's target genes, which will help define the treatment plan to target those genes in therapy. Deep learning (DL) models seem to set the benchmarks for the tasks of cancer prediction and subtype classification when using gene expression data; however, these methods do not provide interpretability, which is great concern from the perspective of cancer biology since the identification of the cancer driver genes in an individual provides essential information for treatment and prognosis. In this work, we identify some limitations of previous work that showed efforts to build algorithms to extract feature weights from DL models, and we propose using tree-based learning algorithms that address these limitations. Preliminary results show that our methods outperform those of related research while providing model interpretability.