Abstract
Abstract The increasing popularity of attention mechanisms in deep learning algorithms for computer vision and natural language processing made these models attractive to other research domains. In healthcare, there is a strong need for tools that may improve the routines of the clinicians and the patients. Naturally, the use of attention-based algorithms for medical applications occurred smoothly. However, being healthcare a domain that depends on high-stake decisions, the scientific community must ponder if these high-performing algorithms fit the needs of medical applications. With this motto, this paper extensively reviews the use of attention mechanisms in machine learning (including Transformers) for several medical applications. This work distinguishes itself from its predecessors by proposing a critical analysis of the claims and potentialities of attention mechanisms presented in the literature through an experimental case study on medical image classification with three different use cases. These experiments focus on the integrating process of attention mechanisms into established deep learning architectures, the analysis of their predictive power, and a visual assessment of their saliency maps generated by post-hoc explanation methods. This paper concludes with a critical analysis of the claims and potentialities presented in the literature about attention mechanisms and proposes future research lines in medical applications that may benefit from these frameworks.

Abstract

Abstract
We study principles and models for reasoning inductively about properties of distributed systems, based on programmed atomic handlers equipped with contracts. We present the Why3-do library, leveraging a state of the art software verifier for reasoning about distributed systems based on our models. A number of examples involving invariants containing existential and nested quantifiers (including Dijsktra's self-stabilizing systems) illustrate how the library promotes contract-based modular development, abstraction barriers, and automated proofs.

Abstract
Crowdsourced social media data has become popular for assessing cultural ecosystem services (CES). Nevertheless, social media data analyses in the context of CES can be time consuming and costly, particularly when based on the manual classification of images or texts shared by people. The potential of deep learning for automating the analysis of crowdsourced social media content is still being explored in CES research. Here, we use freely available deep learning models, i.e., Convolutional Neural Networks, for automating the classification of natural and human (e.g., species and human structures) elements relevant to CES from Flickr and Wikiloc images. Our approach is developed for Peneda-Ger <^>es (Portugal) and then applied to Sierra Nevada (Spain). For Peneda-Ger <^>es, image classification showed promising results (F1-score ca. 80%), highlighting a preference for aesthetics appreciation by social media users. In Sierra Nevada, even though model performance decreased, it was still satisfactory (F1-score ca. 60%), indicating a predominance of people's pursuit for cultural heritage and spiritual enrichment. Our study shows great potential from deep learning to assist in the automated classification of human-nature interactions and elements from social media content and, by extension, for supporting researchers and stakeholders to decode CES distributions, benefits, and values.

Abstract
Unmanned Aerial Vehicles (UAVs) acting as Flying Access Points (FAPs) are being used to provide on-demand wireless connectivity in extreme scenarios. Despite ongoing research, the optimization of UAVs' positions according to dynamic users' traffic demands remains challenging. We propose the Traffic-aware UAV Placement Algorithm (TUPA), which positions a UAV acting as FAP according to the users' traffic demands, in order to maximize the network utility. Using a DRL approach enables the FAP to autonomously learn and adapt to dynamic conditions and requirements of networking scenarios. Moreover, the proposed DRL methodology allows TUPA to generalize knowledge acquired during training to unknown combinations of users' positions and traffic demands, with no additional training. TUPA is trained and evaluated using network simulator ns-3 and ns3-gym framework. The results demonstrate that TUPA increases the network utility, compared to baseline solutions, increasing the average network utility up to 4x in scenarios with heterogeneous traffic demands.

Abstract
Recently, research concerning the navigation of autonomous surface vehicles (ASVs) has been increasing. However, a large-scale implementation of these vessels is still held back by several challenges such as multi-object tracking. Attaining accurate object detection plays a big role in achieving successful tracking. This article presents the development of a detection model with an image-based Con-volutional Neural Network trained through transfer learning, a deep learning tech-nique. To train, test, and validate the detector module, data were collected with the SENSE ASV by sailing through two nearby ports, Leixoes and Viana do Castelo, and recording video frames through its on-board cameras, along with a Light De-tection And Ranging, GPS, and Inertial Measurement Unit data. Images were ex-tracted from the collected data, composing a manually annotated dataset with nine classes of different vessels, along with data from other open-source maritime datasets. The developed model achieved a class mAP@[.5 .95] (mean average precision) of 89.5% and a clear improvement in boat detection compared to a multi-purposed state-of-the-art detector, YOLO-v4, with a 22.9% and 44.3% increase in the mAP with an Intersection over Union threshold of 50% and the mAP@[.5 .95], respectively. It was integrated in a detection and tracking system, being able to continuously detect nearby vessels and provide sufficient informa-tion for simple navigation tasks.