Abstract
E-commerce platforms explore the interaction between users and digital content – user generated streams of events – to build and maintain dynamic user preference models which are used to make mean-ingful recommendations. However, the accuracy of these incremental models is critically affected by the choice of hyper-parameters. So far, the incremental recommendation algorithms used to process data streams rely on human expertise for hyper-parameter tuning. In this work we apply our Self Hyper-Parameter Tuning (SPT) algorithm to incremental recommendation algorithms. SPT adapts the Melder-Mead optimi-sation algorithm to perform hyper-parameter tuning. First, it creates three models with random hyper-parameter values and, then, at dynamic size intervals, assesses and applies the Melder-Mead operators to update their hyper-parameters until the models converge. The main contribu-tion of this work is the adaptation of the SPT method to incremental matrix factorisation recommendation algorithms. The proposed method was evaluated with well-known recommendation data sets. The results show that SPT systematically improves data stream recommendations.

Abstract
This paper summarises the joint efforts of a multinational group of six undergraduate students cooperating within the European Project Semester (EPS) conducted at the Instituto Superior de Engenharia do Porto (ISEP). The EPS@ISEP initiative, made available as a part of the Erasmus+ international students exchange programme, employs the principles of problem-based learning, facing students with—albeit downscaled—real-life scenarios and tasks they may encounter in their future professional practice. Participation in the project initiative outclasses most of the traditional courses through a wide spawn of its learning outcomes. Participants acquire not only hard skills necessary for an appropriate execution of the project, but also broaden their understanding of the approached problem through detailed scientific, management, marketing, sustainability, and ethics analysis—all in the atmosphere of multicultural and interdisciplinary collaboration. The team under consideration, based on personal preferences and predispositions, chose the topic of vertical farming and, in particular, to design a domestic indoor gardening solution, appropriate for space efficient incubation of plants. The paper portrays the process, from research, analysis, formulation of the idea to the design, development and testing of a minimum viable proof of concept prototype of the “Vereatable” solution. © 2019, Springer Nature Switzerland AG.

Abstract
This paper reports the collaborative learning experience of a team of five Erasmus students who participated in EPS@ISEP—the European Project Semester (EPS) at Instituto Superior de Engenharia do Porto (ISEP)—during the spring of 2018. EPS@ISEP is a project-based learning capstone programme for third and fourth year engineering, product design and business students, focussing on teamwork and multidisciplinary problem solving as well as on the development of sustainable and ethical practices. In this context, the Team developed a drifting intelligent buoy to monitor the water quality of urban water spaces. Motivated by the desire to build an intelligent buoy for urban water bodies, the Team conducted several scientific, technical, sustainability, marketing, ethical and deontological analyses. Based on the findings, it has derived the requirements, designed the structure and functional system, selected the list of components and providers and assembled a proof of concept prototype. The result is Aquality, an intelligent drifting buoy prototype, designed for private sustainable pools. Aquality monitors the quality of the pool water by measuring its temperature and turbidity, while interfacing with the user through a mobile application. Considering the EPS@ISEP learning experience, the Team valued the knowledge and skills acquired, and, particularly, the collaborative learning and working component of the project, i.e., working together towards one goal while maintaining high motivation and cohesion. © 2019, Springer Nature Switzerland AG.

Abstract
This paper describes the development of a Multi-purpose Urban Sensing Equipment, named Billy, designed by a multinational and multidisciplinary team enrolled in the European Project Semester (EPS) at Instituto Superior de Engenharia do Porto (ISEP). The project is set to design, develop and test an interactive billboard in compliance with the relevant EU regulation and the allocated budget. The Team benefited from the different background, multidisciplinary skills and the newly acquired skills of the members, like marketing, sustainability and design ethics, in activities both inside and outside of the University. The challenge was to design a multi-purpose urban sensing and displaying equipment to inform citizens of nearby environmental conditions. The Team decided to design a system to monitor and display the temperature, humidity, air pressure and air quality of leisure areas, featured with a proximity detection sensor for energy saving. Billy will not only monitor and display this local information, but also the air quality determined by other billboards placed in other locations, creating a distributed urban sensing network. The system has been successfully prototyped and tested using the ESPduino Wi-Fi enabled micro-controller, different sensors and displays (screen and map-based). The results show not only that the prototype functions according to derived specifications and design, but that the team members were able to learn, together and from each other, how to solve this multidisciplinary problem. © 2019, Springer Nature Switzerland AG.

Abstract
Crowdsourcing has become an essential source of information for tourists and tourism industry. Every day, large volumes of data are exchanged among stakeholders in the form of searches, posts, shares, reviews or ratings. Specifically, this paper explores inter-guest trust and similarity post-filtering, using crowdsourced ratings collected from the Expedia and TripAdvisor platforms, to improve hotel recommendations generated by incremental collaborative filtering. First, the profiles of hotels and guests are created using multi-criteria ratings and inter-guest trust and similarity. Next, incremental model-based collaborative filtering is adopted to predict unknown hotel ratings based on the multi-criteria ratings and, finally, post-recommendation filtering sorts the generated predictions based on the inter-guest trust and similarity. The proposed method was tested both off-line (post-processing) and on-line (real time processing) for performance comparison. The results highlight: (i) the increase of the quality of recommendations with the inter-guest trust and similarity; and (ii) the decrease of the predictive errors with the on-line incremental collaborative filtering. Thus, this work contributes with a novel method, integrating incremental collaborative filtering and inter-guest trust and similarity post-filtering, for on-line hotel recommendation based on multi-criteria crowdsourced rating streams. © 2019, Springer Nature Switzerland AG.

Abstract
Engineering education addresses the development of professional competencies in undergraduates. In this context, the core set of professional competencies includes critical thinking and problem solving, effective communication, collaboration and team building, and creativity and innovation-also known as the four Cs-as well as socio-professional ethics and sustainable development-referred in this paper as the two Ss. While the four Cs were identified by the associates of the American Management Association based on the needs of the society, professional associations, and businesses; this paper proposes the two S extension to ensure that future engineers contribute to the well-being of individuals and the preservation of life on Earth. It proposes a tangible framework-the 4C2S-and an application method to analyse the contributions made by engineering capstone programmes to the development of these core competencies in future engineering professionals. The method is applied to an engineering capstone programme-the European Project Semester (EPS) offered by the Instituto Superior de Engenharia do Porto (ISEP)-and a specific project case-EPS@ISEP Pet Tracker project developed in 2013, constituting, in addition, a road map for the application of the 4C2S framework to engineering capstone programmes. The results show that EPS@ISEP complies with the 4C2S framework.