Abstract
Several algorithms have been proposed for offline multi-label classification. However, applications in areas such as traffic monitoring, social networks, and sensors produce data continuously, the so called data streams, posing challenges to batch multi-label learning. With the lack of stationarity in the distribution of data streams, new algorithms are needed to online adapt to such changes (concept drift). Also, in realistic applications, changes occur in scenarios with infinitely delayed labels, where the true classes of the arrival instances are never available. We propose an online unsupervised incremental method based on self-organizing maps for multi-label stream classification in scenarios with infinitely delayed labels. We consider the existence of an initial set of labeled instances to train a self-organizing map for each label. The learned models are then used and adapted in an evolving stream to classify new instances, considering that their classes will never be available. We adapt to incremental concept drifts by online updating the weight vectors of winner neurons and the dataset label cardinality. Predictions are obtained using the Bayes rule and the outputs of each neuron, adapting the prior probabilities and conditional probabilities of the classes in the stream. Experiments using synthetic and real datasets show that our method is highly competitive with several ones from the literature, in both stationary and concept drift scenarios.

Abstract
We detail a study of the techniques and sealing materials for optical fiber sensors used in dynamic environments with high pressure (>300 bar) and high temperature (>300 °C). The sealing techniques and materials are the key for the robustness of sensors in harsh dynamic environments, such as large combustion engines. The sealing materials and techniques studied in this work are high-temperature epoxies, metallic polymer, metallic solders, glass solder, cement, brazing and electroless nickel plating. Because obtaining high temperature simultaneously with high pressure is very difficult in the same chamber in the laboratory, we developed a new and simple method to test sealed fibers in these conditions in the laboratory. In addition, some sensors using the materials tested in the laboratory were also field tested in real thermoelectric combustion engines. The study also discusses the methods of fabrication and the cost-benefit ratio of each method.

Abstract
A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. Even in the cloud, they suffer from computational and memory limitations, and they cannot be used to model adequately large physical worlds for agents which assume networks with billions of neurons. These issues are addressed in the last few years by the emerging topic of sparse training, which trains sparse networks from scratch. This paper discusses sparse training state-of-the-art, its challenges and limitations while introducing a couple of new theoretical research directions which has the potential of alleviating sparse training limitations to push deep learning scalability well beyond its current boundaries. Nevertheless, the theoretical advancements impact in complex multi-agents settings is discussed from a real-world perspective, using the smart grid case study.

Abstract
Nowadays we are facing the emergence of new challenges, especially focused on environmental behavior and climate change and also the effects and impacts of COVID-19 world pandemic - which can restrain the attainment of the desired sustainability. It is, then, mandatory to reply to all of these challenges through the design of specific paths to attain sustainable development in a collective approach, with the involvement and the commitment of the community and performed in an integrated way. Thus, it is proposed a trans-disciplinary research method based on the European Union title recognition - European Green Capital (EGC) -, directly related to the Circular Economy (CE), together with a Data Envelopment Analysis (DEA). This paper highlights sustainable measures and proposes common managerial strategies and policies, that can support the cities/regions' sustainable practices embedding as well as ensure its overall monitoring to measure if the actions implemented through time are adequate and efficient towards attaining CE and sustainable development. Those are based on the analysis of the best practices of the EGC, which can impact on CE, and using DEA. This approach can follow the city/region evolution and be adapted to the EGC evaluation parameters in order to understand the main characteristics that can contribute to improve governance approaches and help to foster CE into all the cities/regions' ecosystem.

Abstract
Twitter has become a major platform to share ideas and promoting discussion on relevant topics. However, with a large number of users to resort to it as their primary source of information and with an increasing number of accounts spreading newsworthy content, a characterization of the political bias associated with the social network ecosystem becomes necessary. In this work, we aim at analyzing accounts spreading or publishing content from five different classes of the political spectrum. We also look further and study accounts who spread content from both right and left sides. Conclusions show that there is a large presence of accounts which disseminate right bias content although it is the more central classes that have a higher influence on the network. In addition, users who spread content from both sides are more actively spreading right content with opposite content associated with criticism towards left political parties or promoting right political decisions.

Abstract
System flexibility has been introduced as one of the most significant concepts in energy systems, and accordingly it has captured attention. It should be noted that various parameters and equipment, directly and indirectly, affect system flexibility, among which, demand response (DR) programs, distributed energy resources (DERs), and storage systems, are some important examples. In this respect, a comprehensive review of DR and integrated demand response (IDR) programs has been conducted in this chapter, and the impact of such programs on enhancing the flexibility of local energy systems has been thoroughly investigated. The local energy systems, studied in this chapter, include three residential, commercial, and industrial energy hubs, located in a 33-bus network, equipped with renewable energy sources (RES), as well as electrical and thermal energy storage systems. It should be noted that to evaluate the flexibility of the system, the operation problem of energy hubs has been investigated through simulating six different case studies, and the impact of DR/IDR programs, energy storage systems, RESs, and operation mode has been evaluated on operating costs, emissions, and flexibility. The results showed that each of the hubs will have a different reaction to the presence/absence of the mentioned items.