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

Abstract

Abstract
The knowledge of the Portuguese public regarding smart cities is still limited, such knowledge being more present in the technological and business environments. Portuguese cities are starting to invest in smart issues as a response to their complexity and challenges. The ENABLE Consortium's INTELPARK Solution (fictitious names given for anonymity purposes) described herein is an example of a smart parking solution that, through the combination of hardware and software, provides key information about the parking area being managed (for example, occupancy or vehicle infraction information). This technological solution, focused on optimizing and making the management of parking areas more efficient, will serve everyone involved: from the driver to the manager. This article aims to focus on the prospective user (in this case, the driver who will park his or her vehicle in the parking area), since the consumer/traveller driving a vehicle is the main reason for the success or failure of any product and service, such as this one, in the marketplace. In addition, we are living in times of profound digital transformation in which access to information, oftentimes down to the second, becomes increasingly important for the user as well as the search for solutions that increase well-being, quality of life and comfort. Thus, 209 valid online survey answers were received, with structured questions, responses which were gathered from drivers or end users and in a non-probabilistic sampling research process. The main goal was to know how the mobile application INTELPARK, associated with this smart solution, was perceived by the end user, and to understand the potential interest in it and how frequently it would be used. The data collected was analysed through descriptive statistics and via the chi-squared test, in order to find associations between variables. The research concludes that future end users of this mobile intelligent parking application will have the following profile: they will be older, highly literate and with a higher gross monthly income. Moreover, these results also show that parking is seen to be an issue of citizenship and which promotes quality of life rather than simply being a source of revenue.

Abstract

Abstract
During the last two decades, the first generation of beam combiners at the Very Large Telescope Interferometer has proved the importance of optical interferometry for high-angular resolution astrophysical studies in the near- and mid-infrared. With the advent of 4-beam combiners at the VLTI, the u - v coverage per pointing increases significantly, providing an opportunity to use reconstructed images as powerful scientific tools. Therefore, interferometric imaging is already a key feature of the new generation of VLTI instruments, as well as for other interferometric facilities like CHARA and JWST. It is thus imperative to account for the current image reconstruction capabilities and their expected evolutions in the coming years. Here, we present a general overview of the current situation of optical interferometric image reconstruction with a focus on new wavelength-dependent information, highlighting its main advantages and limitations. As an Appendix we include several cookbooks describing the usage and installation of several state-of-the art image reconstruction packages. To illustrate the current capabilities of the software available to the community, we recovered chromatic images, from simulated MATISSE data, using the MCMC software SQUEEZE. With these images, we aim at showing the importance of selecting good regularization functions and their impact on the reconstruction.