Browsing by Author "Pinto, Filipe C."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- The Role of the Smart Citizen in Smart CitiesPublication . Magalhães, Mariana; P. Duarte, Rui; Oliveira, Cátia; Pinto, Filipe C.The exponential growth of the urban population made cities to feel the obligation to guarantee liveable conditions for all citizens who seek them. The creation of new models of cities and the interconnection between the services they offer became a pressing need. With the tech- nological advancements, all this integration lead cities to scale to the concept of Smart City. This paper focuses on the perspective of the citi- zen. When asked about how smart the cities where they live, few citizens know it, and, even more, when asked about how participative they are, the answer is null or ineffective. Their perspective is being neglected in public matters, either governmental or environmental. Therefore, it is essential to carry out a comprehensive study that allows understanding how the citizen becomes an integral element of the city where he lives, studies, works, or visits. Inclusive cities use technological platforms that motivate citizens to stay or visit the city, thus contributing to citizen inclusion. It is crucial to understand the best digital approach to meet citizens’ needs in the city to take advantage of what the city has to offer.
- Weight-Based Dynamic Hybrid Recommendation System for Web Application ContentPublication . Jerónimo, Margarida; Pinto, Filipe C.; P. Duarte, RuiThis paper presents a prototype for a web application recommendation system’s content applied to movies’ recommendations. It learns the pattern of user content consumption, predicting what he will consume in the future based on similar items to those he has shown interest. It considers similarity with neighbor users, thus creating a user model. Content-based filtering, collaborative filtering, and memory-based on hybrid filtering techniques are used. Content-based filtering allows to extract the fundamental features or attributes of the items and select similar items. Moreover, it proposes predicted classifications for the items of interest not yet classified by the active user. Collaborative filtering allows applying the kNN methodology to identify the similarity between the active user located in the neighborhood and propose predicted classifications for items of interest not yet classified. Hybrid filtering combines the two methodologies to overcome their drawbacks. A weighted approach is applied, allowing a dynamic linear combination of collaborative and content-based filtering. The results obtained were empirically relevant in the experimental evaluation, matching with the results presented in similar studies validated with RMSE metrics.