Abstract
Automatic medical image segmentation via convolutional neural networks (CNNs) has shown promising results. However, they may not always be robust enough for clinical use. Sub-optimal segmentation would require clinician's to manually delineate the target object, causing frustration. To address this problem, a novel interactive CNN-based segmentation framework is proposed in this work. The aim is to represent the CNN segmentation contour as B-splines by utilising B-spline explicit active surfaces (BEAS). The interactive element of the framework allows the user to precisely edit the contour in real-time, and by utilising BEAS it ensures the final contour is smooth and anatomically plausible. This framework was applied to the task of 2D segmentation of the levator hiatus from 2D ultrasound (US) images, and compared to the current clinical tools used in pelvic floor disorder clinic (4DView, GE Healthcare; Zipf, Austria). Experimental results show that: 1) the proposed framework is more robust than current state-of-the-art CNNs; 2) the perceived workload calculated via the NASA-TLX index was reduced more than half for the proposed approach in comparison to current clinical tools; and 3) the proposed tool requires at least 13 s less user time than the clinical tools, which was significant (p = 0.001).

Abstract
Text mining (TM) is a semi-automatized, multi-step process, able to turn unstructured into structured data. TM relevance has increased upon machine learning (ML) and deep learning (DL) algorithms’ application in its various steps. When applied to biomedical literature, text mining is named biomedical text mining and its specificity lies in both the type of analyzed documents and the language and concepts retrieved. The array of documents that can be used ranges from scientific literature to patents or clinical data, and the biomedical concepts often include, despite not being limited to genes, proteins, drugs, and diseases. This review aims to gather the leading tools for biomedical TM, summarily describing and systematizing them. We also surveyed several resources to compile the most valuable ones for each category. © 2021 by the authors.

Abstract
The adoption of serious games as a complement to traditional classroom training is still an emerging theme, but it offers relevant potentialities for both students and teachers. This study describes the integration process of serious games in an entrepreneurship course over five years (2014-2018). In the first three years, the ENTRExplorer was adopted, while in the last two years the FLIGBY was used. The experience of using entrepreneurship serious games is analyzed according to multiple perspectives, such as complexity, generation of more entrepreneurial or group working skills, engagement, interactivity, learning outcomes, or even the impact on the intention to establish a new venture. The findings allowed a comparative analysis of the two games, indicating significant differences in some of those dimensions. Nevertheless, the learning outcomes provided by each game were considered relevant by the students, showing that both games can be useful in the process of learning and acquiring entrepreneurship competencies.

Abstract
This paper addresses an extension of the flexible job shop scheduling problem by considering that jobs need to be moved around the shop-floor by a set of vehicles. Thus, this problem involves assigning each production operation to one of the alternative machines, finding the sequence of operations for each machine, assigning each transport task to one of the vehicles, and finding the sequence of transport tasks for each vehicle, simultaneously. Transportation is usually neglected in the literature and when considered, an unlimited number of vehicles is, typically, assumed. Here, we propose the first mixed integer linear programming model for this problem and show its efficiency at solving small-sized instances to optimality. In addition, and due to the NP-hard nature of the problem, we propose a local search based heuristic that the computational experiments show to be effective, efficient, and robust.

Abstract
This paper compares the accuracy of a set of 22 methods for short-term hotel demand forecasting for lead times up to 14 days ahead. Machine learning models are compared with methods ranging from seasonal naive to exponential smoothing methods for double seasonality. The machine learning methods considered include a new approach based on arbitrating, in which several forecasting models are dynamically combined to obtain predictions. Arbitrating is a metalearning approach that combines the output of experts according to predictions of the loss that they will incur. Particularly, the dynamic ensemble method is used. The methods were compared using a real time series of daily demand for a four-star hotel located in the south of Europe. The forecasting performance of those methods was assessed using three alternative accuracy measures. Results from extensive empirical experiments led us to conclude that machine learning methods outperform traditional hotel demand forecasting methods. We found that the use of machine learning models can reduce the root mean squared error up to 54% for a 1-day forecast horizon, and up to 45% for a 14-days forecast horizon, when compared with traditional exponential smoothing methods.

Abstract
While it is generally accepted that our fossil fuel-dominated energy systems must undergo a sustainable transition, researchers have often neglected the potential impacts of this on water and land systems. However, if unintended environmental impacts from this process are to be avoided, understanding its implications for land use and water demand is of crucial importance. Moreover, developed countries may induce environmental stress beyond their own borders, for instance through extensive imports of bioenergy. In this paper, Germany serves as an example of a developed country with ambitious energy transformation targets. Results show that in particular, the politically-driven aspiration for more organic farming in Germany results in a higher import quota of biomass, especially biofuels. These imports translate into land demand, which will exceed the area available in Germany for bioenergy by a factor of 3-6.5 by 2050. As this will likely bring about land stress in the respective exporting countries, this effect of the German energy transformation ought to be limited as much as possible. In contrast, domestic water demand for the German energy system is expected to decrease by over 80% through 2050 due to declining numbers of fossil-fuelled power plants. However, possible future irrigation needs for bioenergy may reduce or even counterbalance this decreasing effect. In addition, energy policy targets specific to the transport sector show a high sensitivity to biomass imports. In particular, the sector-specific target for greenhouse gas reductions will seemingly promote biomass imports, leading to the above-described challenges in the pursuit of sustainability.