Abstract

Abstract
Climate change affects global temperature and precipitation patterns. These effects, in turn, influence the intensity and, in some cases, the frequency of extreme environmental events, such as forest fires, hurricanes, heat waves, floods, droughts, and storms. In general, these events can be particularly conducive to the appearance of plant pests and diseases. The availability of models and a data collection system is crucial to manage pests and diseases in sustainable agricultural ecosystems. Agricultural ecosystems are known to be complex, multivariable, and unpredictable. It is important to anticipate crop pests and diseases in order to improve its control in a more ecological and economical way (e.g., precision in the use of pesticides). The development of an intelligent monitoring and management platform for the prevention of pests and diseases in olive groves at Trás-os- Montes region will be very beneficial. This platform must: a) integrate data from multiple data sources such as sensory data (e.g., temperature), biological observations (e.g., insect counts), georeferenced data (e.g., altitude) or digital images (e.g., plant images); b) systematize these data into a regional repository; c) provide relevant forecasts for pest and diseases. Convolutional Neural Networks (CNNs) can be a valuable tool for the identification and classification of images acquired by Internet of Things (IoT).

Abstract
Traffic prediction is a vitally important keystone of an intelligent transportation system (ITS). It aims to improve travel route selection, reduce overall carbon emissions, mitigate congestion, and enhance safety. However, efficiently modelling traffic flow is challenging due to its dynamic and non-linear behaviour. With the availability of a vast number of data samples, deep neural network-based models are best suited to solve these challenges. However, conventional network-based models lack robustness and accuracy because of their incapability to capture traffic's spatial and temporal correlations. Besides, they usually require data from adjacent roads to achieve accurate predictions. Hence, this article presents a one-dimensional (1D) convolution neural network (CNN) and long short-term memory (LSTM)-based traffic state prediction model, which was evaluated using the Zenodo and PeMS datasets. The model used three stacked layers of 1D CNN, and LSTM with a logarithmic hyperbolic cosine loss function. The 1D CNN layers extract the features from the data, and the goodness of the LSTM is used to remember the past events to leverage them for the learnt features for traffic state prediction. A comparative performance analysis of the proposed model against support vector regression, standard LSTM, gated recurrent units (GRUs), and CNN and GRU-based models under the same conditions is also presented. The results demonstrate very encouraging performance of the proposed model, improving the mean absolute error, root mean squared error, mean percentage absolute error, and coefficient of determination scores by a mean of 16.97%, 52.1%, 54.15%, and 7.87%, respectively, relative to the baselines under comparison.

Abstract
Reinforcement Learning techniques allow learning complex behaviors to deal with a variety of situations in a matter of hours. This complexity is even more prominent in multi-agent continuous 3D environments. This paper compares how the actions taken by two agents independently trained via a self-play approach differ from the ones taken when they are controlled by the same policy. It also explores the emergence of competitive or collaborative behaviors in a natural game setting. By implementing a 3D simulated version of the Dance Dance Revolution, the acquisition of more specific abilities like equilibrium, balance, and dexterity was tested. The approach achieved very good results learning a predefined sequence of buttons (7 arrows correctly pressed in 20M timesteps), revealing a similar learning behavior to human beings (improving with training and performing better in this kind of sequence than in random ones). The self-play approach also produced some interesting effects by developing cooperative behaviors in theoretically competitive scenarios.

Abstract
Models-at different levels of abstraction and pertaining to different engineering views-are central in the design of railway networks, in particular signalling systems. The design of such systems must follow numerous strict rules, which may vary from project to project and require information from different views. This renders manual verification of railway networks costly and error-prone. This paper presents EVEREST, a tool for automating the verification of railway network models that preserves the loosely coupled nature of the design process. To achieve this goal, EVEREST first combines two different views of a railway network model-the topology provided in signalling diagrams containing the functional infrastructure, and the precise coordinates of the elements provided in technical drawings (CAD)-in a unified model stored in the railML standard format. This railML model is then verified against a set of user-defined infrastructure rules, written in a custom modal logic that simplifies the specification of spatial constraints in the network. The violated rules can be visualized both in the signalling diagrams and technical drawings, where the element(s) responsible for the violation are highlighted. EVEREST is integrated in a long-term effort of EFACEC to implement industry-strong tools to automate and formally verify the design of railway solutions. © 2022 ACM.

Abstract
Purpose This study contributes to the understanding of how cultural organizations are using digital technologies to redesign their business models and enable sustainable and impactful audiovisual digital archives. Design/methodology/approach An inductive multiple case research design was used. Five cases of audiovisual digital archives of independent films were selected. Data collected was based on desk research, onsite visits, interviews with top managers responsible for the digitalization of some of the archives and experimentation with the services provided. Data was collected and analyzed based on a theoretical framework defined from the literature for business models of cultural organizations. Findings The archives analyzed faced the challenge of aligning the commercial viability with a mission of making content available to increase cultural knowledge. A sustainable business model may be achieved by using different revenue models, while guaranteeing to offer a value proposition carefully aligned with stakeholders' expectations. Moreover, an impactful business model, i.e. a business model that enhances the creation of cultural value for customers and reaches wider audiences, requires careful audience management and the use of data analysis about audience behavior to adjust the offering. Finally, the business model must consider the resources, activities and infrastructure that ensure critical capabilities for the business and must be designed to ensure financial resilience of the organization. Originality/value This study contributes with a holistic analysis of business models for the digital transformation of cultural organizations, detailing alternative configurations for the most relevant components of a digital business model for audiovisual archives.