Abstract
Accurate predictions of time series are increasingly required to support judgments in a variety of decisions. Several predictive models are available to support these predictions, depending on how each field offers a data variety with varied behavior. The use of artificial neural networks (ANN) at the beginning of the COVID-19 pandemic was significant since the tool may offer forecasting data for various conditions and hence assist in governing critical choices. In this context, this paper describes a system for predicting the daily number of cases, fatalities, and Intensive Care Unit (ICU) patients for the next 28 days in five European countries: Portugal, the United Kingdom, France, Italy, and Germany. The database selection is based on comparable mitigation processes to analyze the impact of safety procedure flexibilization with the most recent numbers of COVID-19. Additionally, it is intended to check the algorithm's adaptability to different variants throughout time. The network's input data has been normalized to account for the size of the countries in the study and smoothed by seven days. The mean absolute error (MAE) was employed as a comparing criterion of two datasets, one with data from the beginning of the pandemic and another with data from the last year, since all variables (cases, deaths, and ICU patients) may be tendentious in percentage analysis. The best architecture produced a general MAE prediction for the 28 days ahead of 256,53 daily cases, 0,59 daily deaths, and 1,63 ICU patients, all numbers normalized by million people. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
This paper presents an educational resource to support the teaching of Portuguese sign language. This educational resource emerges in response to the significant needs for the development of adequate digital tools to support deaf people in different tasks, especially in the language learning process. This work is motivated by the results and conclusions from previous studies that identify augmented reality as one of the promising solutions to improve the learning and teaching processes, and benefits from the advances already accomplished in the development and application of augmented reality solutions in several domains of the educational environment. The educational resource presented in this work is an augmented reality solution that enables associating hand gestures, representative of Portuguese sign language, to different cards, which represent different letters of the alphabet. In this way, it is possible to associate the alphabet letters with the respective gestures in a visual and straightforward way, facilitating the learning process.

Abstract
The growing importance of the Explainable Artificial Intelligence (XAI) field has led to the proposal of several methods for producing visual heatmaps of the classification decisions of deep learning models. However, visual explanations are not sufficient because different end-users have different backgrounds and preferences. Natural language explanations (NLEs) are inherently understandable by humans and, thus, can complement visual explanations. Therefore, we introduce a novel architecture based on multimodal Transformers to enable the generation of NLEs for image classification tasks. Contrary to the current literature, which models NLE generation as a supervised image captioning problem, we propose to learn to generate these textual explanations without their direct supervision, by starting from image captions and evolving to classification-relevant text. Preliminary experiments on a novel dataset where there is a clear demarcation between captions and NLEs show the potential of the approach and shed light on how it can be improved.

Abstract
The fast-changing behaviour of people in metropolitan areas is creating several challenges to local authorities in managing the urban space. These changes are strongly related to the evolution of technology and its adoption by companies and citizens. Current regulations need, therefore, to be rapidly updated to respond to the new urban dynamics. However, the gap between local authorities and citizens and the communication difficulties are increasing as urban centres grow, creating obstacles to innovation and hindering the deployment of new mobility solutions. The low levels of participation in public consultation actions decrease the quality of new policies, as well as their acceptance by the community. Not only do cities need to be reinvented, but local authorities also need to rethink how to interact with citizens, competing for attention in a digital world. Although digital tools are easily accessible, they are not available to everyone, and municipalities need to consider both digital and non-digital interactions to ensure that all citizens can participate. In this work, we analyse and compare a set of measures that municipalities have been adopting to increase citizens' engagement, and we develop a methodology to help local authorities increase public participation and improve citizens' commitment towards the city.

Abstract
The process of digital transformation is based on horizontal and vertical strategies, along with models and technologies used to share information and analyse data that supports decision making. In this context, sharing information securely and intelligibly using standardized architectures is crucial for the digital transformation journey of the companies. This article describes the International Data Spaces as a disruptive model for sharing information inside a network. This work will be evaluated within marketplaces platforms scope. © 2022 The Author(s).

Abstract
Reservoir computing is a versatile approach for implementing physically Recurrent Neural networks which take advantage of a reservoir, consisting of a set of interconnected neurons with temporal dynamics, whose weights and biases are fixed and do not need to be optimized. Instead, the training takes place only at the output layer towards a specific task. One important requirement for these systems to work is nonlinearity, which in optical setups is usually obtained via the saturation of the detection device. In this work, we explore a distinct approach using a photorefractive crystal as the source of the nonlinearity in the reservoir. Furthermore, by leveraging on the time response of the photorefractive media, one can also have the temporal interaction required for such architecture. If we space out in time the propagation of different states, the temporal interaction is lost, and the system can work as an extreme learning machine. This corresponds to a physical implementation of a Feed-Forward Neural Network with a single hidden layer and fixed random weights and biases. Some preliminary results are presented and discussed. © Published under licence by IOP Publishing Ltd.