Abstract
Healthcare institutions face serious security challenges, namely confidentiality, integrity and availability of patient's data due to the amounts of sensitive data collected on Health Information Systems (HIS) and the complex data management processes in health care. This paper describes scenarios of undue HIS access by staff in healthcare institutions, use cases (UC) that model the activities on HIS and identify the variables on audit trails (AT) logs that can be used to detect illegitimate actions on patients' data. Firstly, a survey was conducted through discussion meetings with Information Systems Director (ISD), Data Protection Officer (DPO) and a jurist to discuss their concerns about patient data access, followed by interviews to professionals from healthcare institutions to gather information about their routines and HIS access practices. Then, undue access scenarios were described and UC of activities on HIS which allow their detection were modelled. Lastly, necessary log variables were identified in order to produce algorithms for illegitimate accesses detection. UC and variables selected were matched with the specific requirements of Ministers Council Resolution (MCR) nr.41/2018 which provides guidelines for technology to be compliant with General Data Protection Regulations (GDPR). Discussions with ISD, DPO and the jurist, and professionals' interviews allowed us to describe nine scenarios of undue access. For each scenario we modelled one UC. 32 variables from different type of logs were identified for illegitimate access detection, of which 14 are mandatory according to MCR nr. 41/2018. Despite we might have some limitations related to poor HIS log quality, the mandatory data that logs must comply will be very useful for the development of UC presented. In addition, it is possible to request systems' vendors the improvement of logs' data to meet the detail we propose for this model, which may be very useful to comply not only with GDPR requirements but also with the Standard "Management of Information" (MOI.11) of Joint Commission International Standards for Hospitals (JCI) certification. As future work, we intend to develop the algorithms for the UC modelled, that will detect suspicious activities and produce alarmistic in their presence, testing them in real environment of a hospital to help Information Systems department and DPO on investigation and prevention of data breaches. (C) 2019 The Authors. Published by Elsevier B.V.

Abstract
Purpose: E-learning has been revealed as an a useful tool among continuing education within health professionals, namely for radiographers or radiologic technologists. Therefore like traditional learning, this teaching approach needs continuous evaluation in order to validate its effectiveness and impact. Kirkpatrick's model has been widely used for this purpose by health information management instructors. Our aim was to assess an E-learning Course on Breast Imaging for radiographers based on the first three levels of Kirkpatrick's framework: reaction, learning and behaviour. Methods and materials: An E-learning course was developed for radiographers in order to provide an easy-to-understand, succinct and current overview in breast imaging, namely mammography technique and image interpretation. The program structure were built based on the guidelines proposed by the European Society of Breast Cancer Specialists (EUSOMA). Learner's satisfaction was assessed through a questionnaire and Knowledge gain was assessed using pre- and post-testing. After 6 months of complying the course, the learners were contacted through a questionnaire in order to give feedback on whether their behaviour changed in workplace. Results: Two editions of the breast imaging course were performed by 64 learners. In general, 97% of the learners stated that the program content was very good and excellent, all learners considered the content was delivered in a very good or excellent way. High percentages of learners stated to be satisfied with the distribution of the content among each module (94%) and 86% of learners stated that your level of dedication was high or very high. Concerning improvement of knowledge, we found an evolution of 4 percentual points between pre and post-tests (p = 0,001). The learners have identified two main changes on their practice, the first one related with patient care, improving communications and positioning skills and the second one related with image interpretation, improving the image processing and analyses. Conclusion: These global results show that e-learning can provide statistically relevant knowledge gains in Radiographers. This course is an important contribution to the improvement of mammography education, impacting on the development of students' and radiographers' skills.

Abstract
With the advent of social media, the boundaries of mainstream journalism and social networks are becoming blurred. User-generated content is increasing, and hence, journalists dedicate considerable time searching platforms such as Facebook and Twitter to announce, spread, and monitor news and crowd check information. Many studies have looked at social networks as news sources, but the relationship and interconnections between this type of platform and news media have not been thoroughly investigated. In this work, we have studied a series of news articles and examined a set of related comments on a social network during a period of six months. Specifically, a sample of articles from generalist Portuguese news sources published on the first semester of 2016 was clustered, and the resulting clusters were then associated with tweets of Portuguese users with the recourse to a similarity measure. Focusing on a subset of clusters, we have performed a temporal analysis by examining the evolution of the two types of documents (articles and tweets) and the timing of when they appeared. It appears that for some stories, namely Brexit and the European Football Cup, the publishing of news articles intensifies on key dates (event-oriented), while the discussion on social media is more balanced throughout the months leading up to those events. Copyright

Abstract
The average ranking method (AR) is one of the simplest and effective algorithms selection methods. This method uses metadata in the form of test results of a given set of algorithms on a given set of datasets and calculates an average rank for each algorithm. The ranks are used to construct the average ranking. In this paper we investigate the problem of how the rankings can be reduced by removing non-competitive and redundant algorithms, thereby reducing the number of tests a user needs to conduct on a new dataset to identify the most suitable algorithm. The method proposed involves two phases. In the first one, the aim is to identify the most competitive algorithms for each dataset used in the past. This is done with the recourse to a statistical test. The second phase involves a covering method whose aim is to reduce the algorithms by eliminating redundant variants. The proposed method differs from one earlier proposal in various aspects. One important one is that it takes both accuracy and time into consideration. The proposed method was compared to the baseline strategy which consists of executing all algorithms from the ranking. It is shown that the proposed method leads to much better performance than the baseline.

Abstract
Recently, soft attention mechanisms have been successfully used in a wide variety of applications such as the generation of image captions, text translation, etc. This mechanism attempts to mimic the visual cortex of a human brain by not analyzing all the objects in a scene equally, but by looking for clues (or salient features) which might give a more compact representation of the environment. In doing so, the human brain can process information more quickly and without overloading. Having learned this lesson, in this paper, we try to make a bridge from the visual to the audio scene classification problem, namely the classification of heart sound signals. To do so, a novel approach merging soft attention mechanisms and recurrent neural nets is proposed. Using the proposed methodology, the algorithm can successfully learn automatically significant audio segments when detecting and classifying abnormal heart sound signals, both improving these classification results and somehow creating a simple justification for them.

Abstract
Information provided by geotagged photos allow us to know where and when people have been, supporting a better understanding about tourist's movement patterns across a destination. The aim of this paper is to study tourists' movement patterns during their staying in Porto through the analysis of geotagged photos in order to fulfill marketing segmentation in an innovative way. For that purpose, the SPADE algorithm was used to find sequence patterns of tourists paths based on the time and location of the photos collected. Then, the K-Mode clustering algorithm was applied to these sequences in order to find identical behaviors in terms of paths followed by tourists. At the same time, in order to understand the influence of the different attractions on tourists' paths, we performed a Social Network Analysis of the touristic attractions (spots, museums, streets, monuments, etc.). Based on the time and location of the photos collected, along with personal information, it was possible to understand tourists' frequent movements across the city and to identify market segments based on a hybrid strategy.