Abstract
This paper addresses the development of a remote hyperspectral imaging system for detection and characterization of marine litter concentrations in an oceanic environment. The work performed in this paper is the following: (i) an in-situ characterization was conducted in an outdoor laboratory environment with the hyperspectral imaging system to obtain the spatial and spectral response of a batch of marine litter samples; (ii) a real dataset hyperspectral image acquisition was performed using manned and unmanned aerial platforms, of artificial targets composed of the material analyzed in the laboratory; (iii) comparison of the results (spatial and spectral response) obtained in laboratory conditions with the remote observation data acquired during the dataset flights; (iv) implementation of two different supervised machine learning methods, namely Random Forest (RF) and Support Vector Machines (SVM), for marine litter artificial target detection based on previous training. Obtained results show a marine litter automated detection capability with a 70-80% precision rate of detection in all three targets, compared to ground-truth pixels, as well as recall rates over 50%.

Abstract
Due to the pervasiveness of always connected devices, large amounts of heterogeneous data are continuously being collected. Beyond the benefits that accrue for the users, there are private and sensitive information that is exposed. Therefore, Privacy-Preserving Mechanisms (PPMs) are crucial to protect users' privacy. In this paper, we perform a thorough study of the state of the art on the following topics: heterogeneous data types, PPMs, and tools for privacy protection. Building from the achieved knowledge, we propose a privacy taxonomy that establishes a relation between different types of data and suitable PPMs for the characteristics of those data types. Moreover, we perform a systematic analysis of solutions for privacy protection, by presenting and comparing privacy tools. From the performed analysis, we identify open challenges and future directions, namely, in the development of novel PPMs. (C) 2021 The Authors. Published by Elsevier Inc.

Abstract
One of the main decisions that a car rental company has to make regards the definition of the fleet size and mix, i.e., the capacity to meet demand. This demand is highly unpredictable and price-sensitive; thus, the definition of the prices charged influences capacity decisions. Moreover, capacity decisions are also linked to other company strategies to meet demand, such as offering upgrades or transferring empty cars between stations. Typically, these problems are tackled focusing on the maximization of profits, disregarding the environmental impacts associated with these decisions. There is a growing need for models and analytical tools that can support decisions considering the trade-off between profit and environmental impact in mobility. Therefore, this work incorporates environmental concerns into the capacity-pricing problem for car rental, proposing a bi-objective model to tackle the trade-off between profit and environmental impact. The Life Cycle Assessment method is applied not only to vehicles but also to fuel to define environmental parameters accurately. Four types of vehicles are considered: internal combustion engine vehicles, hybrids, hybrids plug-in, and electric vehicles. Solving multi-objective models is a computationally challenging problem, which requires efficient and applicable methods. These methods can support policy and business decisions in a real-world context, running different scenarios and evaluating solutions under varying conditions. Due to its efficiency in solving bi-objective models, an Epsilon-constraint method is developed and applied in diverse situations to retrieve managerial insights. The results obtained enable quantifying the feasible trade-offs, overall showing that, on average, with a decrease of 14.44% in financial results, it is possible to obtain a decrease of 63.41% in environmental impact. Additional insights are also retrieved related to the fleet, fuel, prices and demand.

Abstract
Lung segmentation represents a fundamental step in the development of computer-aided decision systems for the investigation of interstitial lung diseases. In a holistic lung analysis, eliminating background areas from Computed Tomography (CT) images is essential to avoid the inclusion of noise information and spend unnecessary computational resources on non-relevant data. However, the major challenge in this segmentation task relies on the ability of the models to deal with imaging manifestations associated with severe disease. Based on U-net, a general biomedical image segmentation architecture, we proposed a light-weight and faster architecture. In this 2D approach, experiments were conducted with a combination of two publicly available databases to improve the heterogeneity of the training data. Results showed that, when compared to the original U-net, the proposed architecture maintained performance levels, achieving 0.894 +/- 0.060, 4.493 +/- 0.633 and 4.457 +/- 0.628 for DSC, HD and HD-95 metrics, respectively, when using all patients from the ILD database for testing only, while allowing a more efficient computational usage. Quantitative and qualitative evaluations on the ability to cope with high-density lung patterns associated with severe disease were conducted, supporting the idea that more representative and diverse data is necessary to build robust and reliable segmentation tools.

Abstract
This paper reports the development of a power recycling network for a wireless radio-frequency (RF) transmitter combiner. The transmitter makes use of two RF power amplifiers (PAs) in an outphasing architecture, connected at the output by a 180-degree hybrid combiner. In general, to provide isolation between the PAs and prevent nonlinear distortion, an isolation resistor is usually applied at the four-port combiner. However, the main drawback of such approach is the power dissipated at the isolation port, which drastically reduces the overall power efficiency of the outphasing transmitter. In the present work, the isolation port is replaced by an active network that provides the required input impedance for isolation, at the same time it converts the RF signal into dc, feeding it back to the transmitter power supply. Hence, this way, one recycles the power that would be lost in the isolating resistor. The proposed active network comprises a circulator, a resonant rectifier and a dcdc converter that can be regulated by a maximum power point tracking (MPPT) algorithm. Simulation results for this power recycling system are provided, denoting 61-percent maximum efficiency achieved for an increase of 22-percent peak efficiency for QAM signals with a bandwidth of 250-kHz and carrier frequency equal to 250-MHz when operating at 41-miliwatt output power.

Abstract
The rise of smart manufacturing environments, characterized by high quantity of data/information available, contributes to a growing interest and research towards the use of immersive technologies not only in factories but also across entire value chains. New immersive technologies and devices are being developed to improve cooperation within Collaborative Networks (CNs), especially in the human-machine hybrid networks context. The application of these technologies in such complex environments expands substantially the modes how information is delivered and used, which may exacerbate one of the oldest problems of cognitive ergonomics: information overload. Therefore, this work presents applications of immersive technologies in manufacturing into the perspective of "information work" and "immersive human-centered manufacturing systems". A framework is proposed to be developed in a FabLab to understand the worker needs and interactions. This FabLab aims to demonstrate the potential/real application of immersive technologies, towards the enhancement of the human worker cognitive capabilities.