Abstract
A pandemia Covid-19 teve um profundo impacto nos processos pedagógicos das universidades de ensino presencial. O confinamento obrigatório da população universitária implicou a transposição do ensino presencial em sala para as aulas realizadas online, levando a um aumento considerável do uso de sistemas de videoconferência, estabelecendo novas (ou reforçando as existentes) comunidades de aprendizagem online. Estas práticas de aprendizagem online tendem a se manter após o fim da pandemia na medida em que proporcionem alternativas complementares de contacto, partilha e colaboração em rede, determinando formas não estruturadas de modelos pedagógicos híbridos de ensino a distância. Neste artigo descrevemos práticas concretas de ensino online implementadas durante a pandemia em duas universidades de ensino presencial, a Universidade de São José em Macau; e a Universidade de São Paulo, Brasil, procedendo à sua análise crítica à luz da práxis de ensino a distância online em voga na Universidade Aberta, Portugal, uma universidade virtual de ensino a distância, tendo em vista a definição de um modelo pedagógico virtual de cariz geral que possa proporcionar princípios e linhas mestras para o planeamento, organização e implementação de oferta educativa de nível universitário administrável online para os tempos pós-pandémicos suportada nas evidências da pesquisa e tendências emergentes. 

Abstract
This paper reviewed machine learning algorit hms, particularly deep learning architectures applied to end-of-line testing systems in industrial environment. In industry, data is also produced when any product is being manufactured. All this information registered when manufacturing a specific product can be manipulated and interpreted using Machine Learning algorithms. Therefore, it is possible to draw conclusions from data and infer valuable results that can positively impact the future of the production line. The reviewed papers showed that machine learning algorithms play a crucial role in detecting, isolating, and preventing anomalies, helping operators make decisions, and allowing industries to save resources. © International Journal of Emerging Technology and Advanced Engineering.All right reserved.

Abstract
Artificial intelligence is transforming the way chatbots are created and used. The recent boom of artificial intelligence development is creating a whole new generation of intelligent approaches that enable a more efficient and effective design of chatbots. On the other hand, the increasing need and interest from the industry in artificial intelligence based solutions, is guaranteeing the necessary investment and applicational know-how that is pushing such solutions to a new dimension. Some relevant examples are e-commerce, health or education, which is the main focus of this work. This paper studies and analyses the impact that artificial intelligence models and solutions is having on the design and development of chatbots, when compared to the previously used approaches. Some of the most relevant current and future challenges in this domain are highlighted, which include language learning, sentiment interpretation, integration with other services, or data security and privacy issues.

Abstract
Information systems can be useful tools to understand complex agroecological systems. Farmers and extensionists in the Global South may not have access to such information systems due limited resources, skills and opportunities. End-user development (EUD) has the potential to best suit local needs and conditions. This article summarises and furthers a research and development effort targeting communities as well as agroecological extension professionals and organisations in the Serra da Capivara Territory, Piaui, Brazil. In a retrospective ethnographic study we observed information abundance, topdown IS bias, informational competence and digital infrastructure limitations. A set of requirements was identified, with Portuguese syntax and semantics being crucial for an EUD solution. Based on these requirements a multiparadigm controlled natural language is specified and described as well as a prototype implementation and evaluation method. This language should provide a language that enables the end-user to develop IS suitable to their needs and conditions.

Abstract
Technological developments have had a major impact on the intensive use of electronic equipment, networked or connected to the internet, factors that have boosted the emergence and growth of cybercrime. Measures to mitigate and combat the phenomenon, taking into account its complexity and specificity, must involve all public entities with responsibility in the sector, in a global effort to promote digital literacy in the areas of cybersecurity and computer crime prevention. These comprehensive actions should use digital technologies based on artificial intelligence (AI), such as virtual assistants, whose characteristics allow the massification of information transmission, while enhancing the digital inclusion of users. Government entities are engaged in adopting technologies based on chatbots, with their presence in several areas of public administration. Despite the evolution, these resources have not yet been made available by the entities responsible for mitigating computer crime. On the other hand, although there are government programs aimed at increasing the digital skills of citizens, namely regarding the protection of devices, digital content or personal data, they are not designed for the specificities of cybercrime. In this context, a system based on chatbots, implemented in a digital governance context, by law enforcement agencies, with resources shared with other government entities can contribute to the prevention of cybercrime. © 2022 IEEE.

Abstract
New challenges arise with the upsurge of a Big Data era. Huge volumes of data, from the most varied natures, gathered from different sources, collected in different timings, often with high associated uncertainty, make the decision-making process a harsher task. Current methods are not ready to deal with characteristics of the new problems. This paper proposes a novel data selection methodology that filters big volumes of data, so that only the most correlated information is used in the decision-making process in each given context. The proposed methodology uses a clustering algorithm, which creates sub-groups of data according to their correlation. These groups are then used to feed a forecasting process that uses the relevant data for each situation, while discarding data that is not expected to contribute to improving the forecasting results. In this way, a faster, less computationally demanding, and effective forecasting is enabled. A case study is presented, considering the application of the proposed methodology to the filtering of electricity market data used by forecasting approaches. Results show that the data selection increases the forecasting effectiveness of forecasting methods, as well as the computational efficiency of the forecasts, by using less yet more adequate data. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.