Abstract
Semantic segmentation consists of classifying each pixel according to a set of classes. This process is particularly slow for high-resolution images, which are present in many applications, ranging from biomedicine to the automotive industry. In this work, we propose an algorithm targeted to segment high-resolution images based on two stages. During stage 1, a lower-resolution interpolation of the image is the input of a first neural network, whose low-resolution output is resized to the original resolution. Then, in stage 2, the probabilities resulting from stage 1 are divided into contiguous patches, with less confident ones being collected and refined by a second neural network. The main novelty of this algorithm is the aggregation of the low-resolution result from stage 1 with the high-resolution patches from stage 2. We propose the U-Net architecture segmentation, evaluated in six databases. Our method shows similar results to the baseline regarding the Dice coefficient, with fewer arithmetic operations.

Abstract
To encourage customers to take a chance in finding the right product, retailers and marketplaces implement benevolent return policies that allow users to return items for free without a specific reason. These policies contribute to a high rate of returns, which result in high shipping costs for the retailer and a high environmental toll on the planet. This paper shows that these negative impacts can be significantly minimized if inventory is exchanged within the supplier network of marketplaces upon a return. We compare the performance of this proposal to the standard policy where items are always sent to the original supplier. Our results show that our proposal-returning to a closer supplier and using a predictive heuristic for fulfilment-can achieve a 16% cost reduction compared to the standard-returning to the original supplier and using a myopic rule for fulfilment.

Abstract
The advent of 6G networks is anticipated to introduce a myriad of new technology enablers, including heterogeneous radio, RAN softwarization, multi-vendor deployments, and AI-driven network management, which is expected to broaden the existing threat landscape, demanding for more sophisticated security controls. At the same time, privacy forms a fundamental pillar in the EU development activities for 6G. This decentralized and globally connected environment necessitates robust privacy provisions that encompass all layers of the network stack. In this paper, we present PRIVATEER’s approach for enabling “privacy-first” security enablers for 6G networks. PRIVATEER aims to tackle four major privacy challenges associated with 6G security enablers, i.e., i) processing of infrastructure and network usage data, ii) security-aware orchestration, iii) infrastructure and service attestation and iv) cyber threat intelligence sharing. PRIVATEER addresses the above by introducing several innovations, including decentralised robust security analytics, privacy-aware techniques for network slicing and service orchestration and distributed infrastructure and service attestation mechanisms.

Abstract
The Transmission System Operators (TSOs) from Portugal and Spain do not procure Frequency Containment Reserve (FCR) through market mechanisms. A Virtual Power Plant (VPP) aggregating sources such as wind and solar power and hydrogen electrolysers (HEs) would benefit from participation in this ancillary service market. The methodology proposed in this paper allows to quantify the costs of the participation of the Iberian TSOs in the FCR Cooperation as well as the revenues of a VPP that aggregates wind and solar power and HEs. Results are produced using real data from past market sessions. The Portuguese TSO would have paid roughly 10 M€ to participate in this market in 2022. Using data for the same country and year, a VPP (aggregating the HEs expected to be connected by 2025) would have revenues over 2 M€. © 2023 IEEE.

Abstract
Forests worldwide have been suffering from fires damages, provoking incalculable losses in fauna and flora, economic losses, people and animals' deaths, among other problems. To avoid forest fires catastrophes, it is fundamental to develop innovative operations, such as a forest fire monitoring system. This work concentrates efforts on defining the optimum sensor allocation in a forest fires monitoring system based on a wireless sensor network. Thus, a bi-objective mathematical model is developed to solve the problem, in which the first objective consists of minimising the forest fire hazard of a given forest region, and the second objective refers to the sensors spreading into this region. The developed mathematical model was solved by genetic algorithm and the results demonstrated that the methodology was capable of presenting suitable solutions for the problem. © 2023 American Institute of Physics Inc.. All rights reserved.

Abstract
The environmental protection and energy conservation concerns have spurred the development of new solutions in the automotive industry. This has led to the popularity of electric vehicles (EV) and Plugin hybrid electric vehicles (PHEV). On the other hand, this surge in popularity has created a challenge for the development of various new technologies and services, such as charging technology systems and stations. However, unidirectional charging offers hardware simplicity and easier interconnection and enable a G2V model, while bidirectional charging solutions enables G2V and V2G solutions, which can help stabilize AC power by utilizing the energy stored in the battery. This paper presents an EV battery charging system that uses a compact and straightforward bidirectional converter. The system can draw power from either traditional electrical sources or sustainable energy sources like photovoltaic modules, with the option of using lithium rechargeable batteries and supercapacitors as an Energy Storage System (ESS). Several Simulink simulations were conducted to investigate battery behavior under different power sources, and the results show the good effectiveness of the developed system, allowing it to be used in more comprehensive studies in the field of EV charging. © 2023 IEEE.