Abstract
The great ambition of using games as the cornerstone of education is hindered by its associated teaching workload. The BEACONING project developed a framework based on an authoring tool for gamified lesson paths, which has been rolled-out in large scale across Europe. It includes stages for planning game-based educational activities, plus their deployment, monitoring, and assessment.

Abstract

Abstract
Human Activity Recognition is a machine learning task for the classification of human physical activities. Applications for that task have been extensively researched in recent literature, specially due to the benefits of improving quality of life. Since wearable technologies and smartphones have become more ubiquitous, a large amount of information about a person’s life has become available. However, since each person has a unique way of performing physical activities, a Human Activity Recognition system needs to be adapted to the characteristics of a person in order to maintain or improve accuracy. Additionally, when smartphones devices are used to collect data, it is necessary to manage its limited resources, so the system can efficiently work for long periods of time. In this paper, we present a semi-supervised ensemble algorithm and an extensive study of the influence of hyperparameter configuration in classification accuracy. We also investigate how the classification accuracy is affected by the person and the activities performed. Experimental results show that it is possible to maintain classification accuracy by adjusting hyperparameters, like window size and window overlap, depending on the person and activity performed. These results motivate the development of a system able to automatically adapt hyperparameter settings for the activity performed by each person. © 2020, Springer Nature Switzerland AG.

Abstract
Background: The short-term benefits of aerobic and resistance exercise in subjects affected by Peripheral Arterial Disease (PAD) are scarcely examined in interaction. This study aimed to identify the effects of combined aerobic and resistance exercise programs on walking performance compared with isolated aerobic exercise or with the usual care in patients with intermittent claudication. Methods: A systematic review was conducted following the PRISMA statement. A total of five electronic databases were searched (until October 2019) for randomized and non-randomized controlled trials. The focus comprised PAD patients with intermittent claudication who performed a combined aerobic and resistance exercise program that assessed the walking performance. Results: Seven studies include combined aerobic and resistance exercise vs. isolated aerobic or vs. usual care. The studies represented a sample size of 337 participants. The follow-up ranged from 4 to 12 weeks, 2 to 5 times-per-week. The risk of bias in the trials was a deemed moderate-to-high risk. After the interventions, the percent change in walking performance outcomes had a large variation. In the combined and isolated aerobic programs, the walking performance always improved, while in the usual care group oscillates between the deterioration and the improvement in all outcomes. Combined exercise and isolated aerobic exercise improved the claudication onset distance from 11 to 396%, and 30 to 422%, the absolute claudication distance from 81 to 197%, and 53 to 121%, and the maximal walking distance around 23 and 10%, respectively. Conclusions: Currently, there is insufficient evidence about the effects of combined aerobic and resistance exercise compared to isolated aerobic exercise or usual care on walking performance. However, despite the low quality of evidence, the combined aerobic and resistance exercise seems to be an effective strategy to improve walking performance in patients with intermittent claudication. These combined exercise modes or isolated aerobic exercise produce positive and significant results on walking performance. The usual care approach has a trend to deteriorate the walking performance. Thus, given the scarcity of data, new randomized controlled trial studies that include assessments of cardiovascular risk factors are urgently required to better determine the effect of this exercise combination.

Abstract
The possibility to engage in autonomous flight through geolocation-based missions turns Unmanned Aerial Vehicles (UAV) into valuable tools that save time and resources in services like deliveries and surveillance. Amazon is already developing a drop-by delivery service, but there are limitations regarding the client’s id, that can be analyzed in three phases: the approach to the potential receiver, the authorization through the client id and the delivery itself. This work shows a solution for the first of these phases. Firstly, the receiver identifies the GPS coordinates where he wants to receive the package. The UAV flights to that place and tries to locate the receiver on the arrival through Computer Vision (CV) techniques, more precisely Deep Neural Networks (DNN), to continue to the next phase, the identification. After the proposal of the system’s architecture and the prototype’s implementation, a test scenario to analyze the feasibility of the proposed techniques was created. The results were quite good considering a system to look for one person in a limited area defined by the destination coordinates, confirming the detection of one person with an up to 92% accuracy from a 10 m height and 5 m horizontal distance in low resolution images. © Springer Nature Switzerland AG 2020.

Abstract