Abstract
We present heuristics for two related two-dimensional non-guillotine packing problems. The first problem aims to pack a set of items into the minimum number of larger identical bins, while the second aims to pack the items that generates most value into one bin. Our approach successively creates sequences of items that defines a packing order considering knowledge obtained from sequences previously generated. Computational experiments demonstrated that the proposed heuristics are very effective in terms of solution quality with small computing times. © 2021, Springer Nature Switzerland AG.

Abstract
This paper presents a heuristic algorithm to reduce the set of equipment candidates for Transmission Expansion Planning (TEP). Since it is a Constructive Heuristic Algorithm (CHA), the MiniEff algorithm aims at reducing the computational burden involved in the optimization process in a quick and satisfactory way. This approach includes two major blocks. The first one uses the minimum-effort calculation based on DC-OPF analysis to reduce the search space of the TEP problem. Then, the reduced list of investment alternatives is input to the AC-TEP formulation to build the final expansion plan using the Evolutionary Particle Swarm Optimization technique (EPSO). The tests on the developed TEP approach were done using the IEEE 118 Bus System and they demonstrate the gains that were obtained in terms of reducing the computer burden in solving TEP without compromising the quality of the final plans.

Abstract
The so-called fourth industrial revolution brought a disruptive change in the way that communication technologies, distributed systems, intelligent data management, analytics and computational capability and other technologies are integrated to enable new functions and enhance capabilities not only to production systems, but also in many other domains such as education. Mobile Health (m-Health) education is one of these, where the number of applications and tools for m-Health education is extensive. The SARS-Cov2 (Covid-19) pandemic brought to life immense challenges towards education, technology, and the symbiosis with medicine. This paper introduces 31 of the current state-of-the-art m-Health education applications and analyses the results of an an inquiry to students and junior doctors during the confinement, designed to understanding their knowledge, use and trust regarding these apps. The results show that several applications are well perceived by their users and deserved their trust andconfirms a good relation between use and trust on the applications analysed. This analysis open doors to a deeper study to evaluate at which extent improving m-Health education means not only to transmit knowledge but also to developing skills and better practices.

Abstract
Machine learning has emerged as a promising paradigm for enabling connected, automated vehicles to autonomously cruise the streets and react to unexpected situations. Reacting to such situations requires accurate classification for uncommon events, which in turn depends on the selection of large, diverse, and high-quality training data. In fact, the data available at a vehicle (e.g., photos of road signs) may be affected by errors or have different levels of resolution and freshness. To tackle this challenge, we propose an active learning framework that, leveraging the information collected through onboard sensors as well as received from other vehicles, effectively deals with scarce and noisy data. Given the information received from neighboring vehicles, our solution: (i) selects which vehicles can reliably generate high-quality training data, and (ii) obtains a reliable subset of data to add to the training set by trading off between two essential features, i.e., quality and diversity. The results, obtained with different real-world datasets, demonstrate that our framework significantly outperforms state-of-the-art solutions, providing high classification accuracy with a limited bandwidth requirement for the data exchange between vehicles.

Abstract
The global trend guided by the energy systems decarbonization, decentralization and digitalization combined with the increase of distributed Renewable Energy Sources (RES) are allowing prosumers to take a more active role in the electricity markets. In this context, a market structure based on Peer-to-Peer (P2P) transactions is very promising but presents challenges for the network's operation. A critical challenge is to ensure that network constraints are not violated during energy trade between peers. Thus, the main contribution of this paper is the development of a methodology for the optimization of P2P energy transactions, accounting for network operation. The paper proposes a three-step approach (P2PTDF), using Topological Distribution Factors (TDF) to penalize peers responsible for violations that may occur, ensuring a feasible solution. Simulations were performed with the modified IEEE 14-bus system with 19 peers, including the possibility of exchanging energy with an external grid.

Abstract
The automation of typically intelligent and decision-making processes in the maritime industry leads to fewer accidents and more cost-effective operations. However, there are still lots of challenges to solve until fully autonomous systems can be employed. Artificial Intelligence (AI) has played a major role in this paradigm shift and shows great potential for solving some of these challenges, such as the docking process of an autonomous vessel. This work proposes a lightweight volumetric Convolutional Neural Network (vCNN) capable of recognizing different docking-based structures using 3D data in real-time. A synthetic-to-real domain adaptation approach is also proposed to accelerate the training process of the vCNN. This approach makes it possible to greatly decrease the cost of data acquisition and the need for advanced computational resources. Extensive experiments demonstrate an accuracy of over 90% in the recognition of different docking structures, using low resolution sensors. The inference time of the system was about 120ms on average. Results obtained using a real Autonomous Surface Vehicle (ASV) demonstrated that the vCNN trained with the synthetic-to-real domain adaptation approach is suitable for maritime mobile robots. This novel AI recognition method, combined with the utilization of 3D data, contributes to an increased robustness of the docking process regarding environmental constraints, such as rain and fog, as well as insufficient lighting in nighttime operations.