A carregar...
157 resultados
Resultados da pesquisa
A mostrar 1 - 10 de 157
- Collaborative Filtering with Semantic Neighbour DiscoveryPublication . Veloso, Bruno; Malheiro, Benedita; Burguillo, Juan CarlosNearest neighbour collaborative filtering (NNCF) algorithms are commonly used in multimedia recommender systems to suggest media items based on the ratings of users with similar preferences. However, the prediction accuracy of NNCF algorithms is affected by the reduced number of items – the subset of items co-rated by both users – typically used to determine the similarity between pairs of users. In this paper, we propose a different approach, which substantially enhances the accuracy of the neighbour selection process – a user-based CF (UbCF) with semantic neighbour discovery (SND). Our neighbour discovery methodology, which assesses pairs of users by taking into account all the items rated at least by one of the users instead of just the set of co-rated items, semantically enriches this enlarged set of items using linked data and, finally, applies the Collinearity and Proximity Similarity metric (CPS), which combines the cosine similarity with Chebyschev distance dissimilarity metric. We tested the proposed SND against the Pearson Correlation neighbour discovery algorithm off-line, using the HetRec data set, and the results show a clear improvement in terms of accuracy and execution time for the predicted recommendations.
- Crowdsourced Data Stream Mining for Tourism RecommendationPublication . Leal, Fátima; Veloso, Bruno; Malheiro, Benedita; Juan Carlos, BurguilloCrowdsourced data streams are continuous flows of data generated at high rate by users, also known as the crowd. These data streams are popular and extremely valuable in several domains. This is the case of tourism, where crowdsourcing platforms rely on tourist and business inputs to provide tailored recommendations to future tourists in real time. The continuous, open and non-curated nature of the crowd-originated data requires robust data stream mining techniques for on-line profiling, recommendation and evaluation. The sought techniques need, not only, to continuously improve profiles and learn models, but also be transparent, overcome biases, prioritise preferences, and master huge data volumes; all in real time. This article surveys the state-of-art in this field, and identifies future research opportunities.
- In-Programme Personalization for Broadcast: IPP4BPublication . Foss, Jeremy; Malheiro, Benedita; Shirley, Ben; Kepplinger, Sara; Ulisses, Alexandre; Armstrong, MikeThe IPP4B workshop assembles a group of researchers from academia and industry – BBC R&D, Ericsson and MOG Technologies – to discuss the state of the art and together envisage future directions for in-programme personalisation in broadcasting. The workshop comprises one invited keynote, two invited presentations together with a paper and discussion sessions.
- THE EPS@ISEP PROGRAMME: A GLOBALISATION AND INTERNATIONALISATION EXPERIENCEPublication . Ferreira, Paulo; Malheiro, Benedita; Silva, Manuel; Guedes, Pedro; JUSTO, Jorge; Castro Ribeiro, Maria Cristina De; Duarte, Abel J.Higher Education Institutions (HEI) design and implement globalisation and internationalisation policies to promote the image, expand influence and increase both the number and quality of staff and students. This is especially important for engineering schools competing for the reduced cohort of motivated Science, Technology, Engineering and Mathematics (STEM) applicants available yearly. Moreover, to train future engineers, engineering education needs to depart from the traditional teacher-centred paradigm. Student-centred learning is central to maintain high student motivation and to drive the development of hard (scientific and technological) and soft (inter-personal) skills. For students to develop these 21st-century engineering skills, today’s curriculums must embed student-centred pedagogical methods, address the design and implementation of solutions guided by ethics and sustainability, and expose undergraduates to multicultural multidisciplinary teamwork, under strong efficiency constraints.The European Project Semester (EPS) is a project-based, international teamwork initiative, that replaces the design capstone semester of undergraduate engineering degrees. It is offered by a network of 19 HEI located in 12 different European countries. The network develops transnational projects together and exchanges students, staff, ideas, and best practices, expanding the influence of the providers. EPS at the Instituto Superior de Engenharia do Porto (EPS@ISEP) runs during the spring semester. It provides 30 European Credit Transfer System Units (ECTU), with 20 ECTU assigned to the project module and 10 ECTU equally divided by five support modules: Energy and Sustainable Development, Ethics and Deontology, Foreign Language and Culture, Marketing and Communication, and Project Management and Teamwork. The programme is offered to international and local students, but during its 12-year existence most students were international. The students are placed in teams considering psychological profiles. The multiculturalism and the diversity of skills within teams also foster a more inclusive and enriching learning experience. The sustainability and ethics objectives are requirements to be considered in the solution design and in the choice of technologies and components for the project implementation. The weekly project meetings between the teams and the coaching panel (7 teachers from 6 different departments), are not only pivotal to the project-based learning process, but promote the internal dialogue between departments and scientific areas. The reduced project budget provides a strong creative stimulus, while reinforcing the sustainability criteria, since turnkey solutions and waste are incompatible with a constrained bill of materials. Besides the positive effect of the programme on student training/education, as shown by the grades and the projects' documentation, EPS@ISEP has strongly influenced the teacher's skills and performance, as attested by the number of programme-related publications and its influence on other courses and modules offered by ISEP. EPS@ISEP is an effective low-cost programme that acts as a testbed and catalyst in the process of bringing engineering education into the 21st century, following sound ethical and sustainability criteria. EPS@ISEP contributes to the globalisation and internationalisation of ISEP as well as to the dissemination and adoption of best practices in engineering education.
- Smart Supermarket Cart - An EPS@ISEP 2023 ProjectPublication . Orós, Miquel; Robu, Marian-Daniel; van Klaveren, Hessel; Gajda, Dominika; Van Dyck, Jelte; Krings, Tobias; Duarte, Abel J.; Malheiro, Benedita; Ribeiro, Cristina; Justo, Jorge; Silva, Manuel F.; Ferreira, Paulo; Guedes, PedroThe technological revolution experienced over the last two decades, together with changes in shopping behaviour, has led supermarkets to consider smart shopping trolleys. Recently, several companies have tested and implemented smart services and devices, such as smart shopping carts with scanners, automatic payment methods, or self-payment locations, to maximise supermarket profits by reducing staff and improving the customer experience. In the spring of 2023, a team of six students enrolled in the European Project Semester at Instituto Superior de Engenharia do Porto (ISEP) proposed FESmarket, an innovative smart shopping cart solution. The user-centred design focused on making the shopping interaction and experience more efficient, comfortable, and satisfactory. Form (balancing aesthetics with innovation), function (selecting functionalities based on the most disruptive technologies), market (fulfilling the identified needs), sustainability (minimising the use of resources), and ethics (respecting human values) are the pillars of the project. FESmarket proposes a smart shopping trolley equipped a built-in touch screen for real-time information on products and their location, cameras for product identification, an audio assistance system, a refrigeration chamber, and a mobile app interface for the customer. Finally, a proof-of-concept prototype was assembled and tested to validate the viability of the designed solution.
- Educating global engineers with EPS@ISEP: The 'pet tracker' project experiencePublication . Borzecka, Aleksandra; Fagerstrom, Anton; Costa, Artur; Gasull, Marti Domenech; Malheiro, Benedita; Castro Ribeiro, Maria Cristina De; Silva, Manuel; Caetano, Nídia; Ferreira, Paulo; Guedes, PedroThe European Project Semester (EPS) is a one-semester capstone project/internship programme offered to engineering, product design and business undergraduates by 18 European engineering schools. EPS aims to prepare future engineers to think and act globally, by adopting project-based learning and teamwork methodologies, fostering the development of complementary skills and addressing sustainability and multiculturalism. Since 2011, the EPS@ISEP programme offers a set of multidisciplinary projects to multicultural teams of students, so that each team element can bring to the project its previous knowledge and background experience. In the spring of 2013, a team choose to develop a pet tracker to provide pet owners with information regarding the whereabouts of their pets and, above all, to reduce the number of pets lost. After analysing related products, the team decided to add extra features for product differentiation. Combining a triple-axis accelerometer, a low cost GPS receiver and the GSM/GPRS communication technology, the team designed a system providing pet location, tracking, map display and activity monitoring services. This paper describes the development process of the Pet Tracker system, comprising a wearable device for pets and a website for pet owners.
- Balcony Greenhouse – An EPS@ISEP 2017 ProjectPublication . Calderon, Alisson; Mota, António; Hopchet, Christophe; Grabulosa, Cristina; Roeper, Mathias; Duarte, Abel José; Malheiro, Benedita; Ribeiro, Maria Cristina; Ferreira, Fernando José; Silva, Manuel; Ferreira, Paulo; Guedes, PedroThis paper presents the development process of a sustainable solution to grow aromatic plants in small houses. The solution is called The GreenHouse and is meant for people who live in small houses or city apartments and want fresh home grown aromatic plants, but have neither the time nor the space to grow them. The solution is intended to be sustainable and appropriate for people concerned with eating healthy, fresh food. The project was developed by a team of five students enrolled in the European Project Semester (EPS) at the Instituto Superior de Engenharia do Porto (ISEP) during the spring of 2017. EPS@ISEP is a project-based learning framework which aims to foster personal, teamwork and multidisciplinary problem-solving skills in engineering, business and product design students. Research and discussions within the team were done to develop the product. The existing solutions for growing fresh food in industrial and domestic applications as well as marketing, sustainability and ethical topics were researched and discussed. This way it was possible to define the requirements of The GreenHouse. The GreenHouse is semi-automatic and requires little interaction from the customer. It has two covers, a winter cover and a summer cover, to be changed depending on the season and weather. Solar energy and rainwater are used to enable the growth of aromatic plants, making this a sustainable system. The support is adaptable and made to fit different support sizes so it can be hanged on balconies or windows.
- Online detection and infographic explanation of spam reviews with data drift adaptationPublication . de Arriba Pérez, Francisco; García Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo, Juan C.Spam reviews are a pervasive problem on online platforms due to its significant impact on reputation. However, research into spam detection in data streams is scarce. Another concern lies in their need for transparency. Consequently, this paper addresses those problems by proposing an online solution for identifying and explaining spam reviews, incorporating data drift adaptation. It integrates (i) incremental profiling, (ii) data drift detection & adaptation, and (iii) identification of spam reviews employing Machine Learning. The explainable mechanism displays a visual and textual prediction explanation in a dashboard. The best results obtained reached up to 87 % spam F-measure.
- Explanation Plug-In for Stream-Based Collaborative FilteringPublication . Leal, Fátima; García-Méndez, Silvia; Malheiro, Benedita; Burguillo, Juan C.Collaborative filtering is a widely used recommendation technique, which often relies on rating information shared by users, i.e., crowdsourced data. These filters rely on predictive algorithms, such as, memory or model based predictors, to build direct or latent user and item profiles from crowdsourced data. To predict unknown ratings, memory-based approaches rely on the similarity between users or items, whereas model-based mechanisms explore user and item latent profiles. However, many of these filters are opaque by design, leaving users with unexplained recommendations. To overcome this drawback, this paper introduces Explug, a local model-agnostic plug-in that works alongside stream-based collaborative filters to reorder and explain recommendations. The explanations are based on incremental user Trust & Reputation profiling and co-rater relationships. Experiments performed with crowdsourced data from TripAdvisor show that Explug explains and improves the quality of stream-based collaborative filter recommendations.
- Analysis and Visualisation of Crowd-sourced Tourism DataPublication . Leal, Fátima; Dias, Joana Matos; Malheiro, Benedita; Burguillo, Juan CarlosThe tourist behaviour has changed significantly over the last decades due to technological advancement (e.g., ubiquitous access to the Web) and Web 2.0 approaches (e.g., Crowdsourcing). Tourism Crowdsourcing includes experience sharing in the form of ratings and reviews (evaluation-based), pages (wiki-based), likes, posts, images or videos (social-network-based). The main contribution of this paper is a tourist-centred off-line and on-line analysis, using hotel ratings and reviews, to discover and present relevant trends and patterns to tourists and businesses. On the one hand, online, we provide a list of the top ten hotels, according to the user query, ordered by the overall rating, price and the ratio between the positive and negative Word Clouds reviews. On the other hand, off-line, we apply Multiple Linear Regression to identify the most relevant ratings that influence the hotel overall rating, and generate hotel clusters based on these ratings.