Abstract
PurposeThe current student selection process for short-term mobility actions under the Erasmus + program (i.e. intensive programs and blended intensive programs) is based exclusively on the students' order of enrolment and their grades. This study offers an alternative approach using the analytic hierarchy process based on a four-layer model that collects information about the specificities of each project and the profile of the students and also promotes greater inclusion and homogenization of the project teams.Design/methodology/approachA decision support system was built by decomposing it into three stages: the predesign stage, in which the problem is characterized, and the user requirements are identified; the design stage, in which the models, the database and the interfaces are formulated; and the field stage, in which six test scenarios were built to validate the proposed solution.FindingsThe results show that this model can be applied with various selection criteria among students and consider both their hard and soft skills. It can also be applied to help build teams in which the students' knowledge is aligned with the technical skills required by the projects.Originality/valueThe proposed approach is innovative in that it responds to the emerging challenge of short-term European mobility programs that aim to involve students with multidisciplinary competencies. The solution considers both hard and soft skills in the selection of students, which allows changing the student selection paradigm and obtaining potentially more homogeneous multicultural teams with greater learning potential.

Abstract
Quality of Experience (QoE) in multi-view streaming systems is known to be severely affected by the latency associated with view-switching procedures. Anticipating the navigation intentions of the viewer on the multi-view scene could provide the means to greatly reduce such latency. The research work presented in this article builds on this premise by proposing a new predictive view-selection mechanism. A VGG16-inspired Convolutional Neural Network (CNN) is used to identify the viewer's focus of attention and determine which views would be most suited to be presented in the brief term, i.e., the near-term viewing intentions. This way, those views can be locally buffered before they are actually needed. To this aim, two datasets were used to evaluate the prediction performance and impact on latency, in particular when compared to the solution implemented in the previous version of our multi-view streaming system. Results obtained with this work translate into a generalized improvement in perceived QoE. A significant reduction in latency during view-switching procedures was effectively achieved. Moreover, results also demonstrated that the prediction of the user's visual interest was achieved with a high level of accuracy. An experimental platform was also established on which future predictive models can be integrated and compared with previously implemented models.

Abstract
The increasing complexity of recent Wi-Fi amendments is making the use of traditional algorithms and heuristics unfeasible to address the Rate Adaptation (RA) problem. This is due to the large combination of configuration parameters along with the high variability of the wireless channel. Recently, several works have proposed the usage of Reinforcement Learning (RL) techniques to address the problem. However, the proposed solutions lack sufficient technical explanation. Also, the lack of standard frameworks enabling the reproducibility of results and the limited availability of source code, makes the fair comparison with state of the art approaches a challenge. This paper proposes a framework, named RateRL, that integrates state of the art libraries with the well-known Network Simulator 3 (ns-3) to enable the implementation and evaluation of RL-based RA algorithms. To the best of our knowledge, RateRL is the first tool available to assist researchers during the implementation, validation and evaluation phases of RL-based RA algorithms and enable the fair comparison between competing algorithms.

Abstract
Retailers must have accurate sales forecasts to efficiently and effectively operate their businesses and remain competitive in the marketplace. Global forecasting models like RNNs can be a powerful tool for forecasting in retail settings, where multiple time series are often interrelated and influenced by a variety of external factors. By including covariates in a forecasting model, we can often better capture the various factors that can influence sales in a retail setting. This can help improve the accuracy of our forecasts and enable better decision making for inventory management, purchasing, and other operational decisions. In this study, we investigate how the accuracy of global forecasting models is affected by the inclusion of different potential demand covariates. To ensure the significance of the study's findings, we used the M5 forecasting competition's openly accessible and well-established dataset. The results obtained from DeepAR models trained on different combinations of features indicate that the inclusion of time-, event-, and ID-related features consistently enhances the forecast accuracy. The optimal performance is attained when all these covariates are employed together, leading to a 1.8% improvement in RMSSE and a 6.5% improvement in MASE compared to the baseline model without features. It is noteworthy that all DeepAR models, both with and without covariates, exhibit a significantly superior forecasting performance in comparison to the seasonal naive benchmark.

Abstract
Blindness and visual impairment are commonly associated with social and functional limitations, almost 45 million people in the world have blindness, and 135 million have any visual impairment. This condition has a significant impact on the quality of life and brings many challenges to the individual, one of which is the navigation and positioning tasks. Although there are already apps capable of helping visually impaired people (VIP) for mobility purposes, most of them focus on detecting obstacles and, therefore, on avoiding dangerous situations. However, mobility of VIP involves many more tasks, such as knowing their exact position and staying informed along an entire route. For this purpose, a standalone and customizable solution is proposed that uses traditional visual recognition of landmarks to process the surroundings of the current location of the visually impaired person using a smartphone and informing about the nearby places assuring the user a sense of the site. For feature detection, it used the oriented features from accelerated segment test (FAST) and rotated binary robust-independent elementary feature (BRIEF) (ORB) algorithm, and for feature matching, it used the brute-force method with the k-nearest neighbor (KNN) algorithm. Results show that the proposed solution can analyze pictures in fractions of a second with satisfactory accuracy.

Abstract
O Centro de Estudos Organizacionais e Sociais do Politécnico do Porto (CEOS.PP) juntou-se à iniciativa anual da Comissão Europeia - "Noite Europeia dos Investigadores" – lançada em 2005 - com o Dia do Investigador CEOS [DICEOS23]. O objetivo deste evento, que decorreu no dia 29 de setembro de 2023, foi o de divulgar o trabalho desenvolvido pelos investigadores do CEOS.PP, um momento que contou com um conjunto de atividades para criar sinergias entre os investigadores deste centro de investigação e abrir caminhos para o futuro.