Abstract
The expectations of Machine Learning systems are becoming increasingly demanding, namely in what concerns the diversity of applications, the expected accuracy, and the pressure for results. However, there are cases in which Human experts are needed to label the data, which may have a significant cost in terms of human resources and time. In these cases, it is often best to learn on-the-fly, without expecting for the whole data to be labeled. Often, it is desirable to guide the Human annotators into focusing on the more relevant instances: this constitutes the so-called active learning. In this paper we propose an approach in which a clustering algorithm is used to find groups of similar instances. Then, the procedure is guided with the objective of favoring the annotation of the groups that are under-represented in the labeled dataset. Results show that this approach leads to models that are, over time, more accurate and reliable.

Abstract

Abstract
Robotics is an ever-growing field, used in countless applications, from domestic to industrial, and taught in advanced courses of multiple higher education institutions. Robot Operating System (ROS), the most prominent robotics architecture, integrates several of these, and has recently moved to a new iteration in the form of ROS2. This project aims to design a complete educational package meant for teaching intelligent robotics in ROS1 and ROS2. A foundation for the package was constructed, using a small differential drive robot equipped with camera-based virtual sensors, a representation in the Flatland simulator, and introductory lessons to both ROS versions and Reinforcement Learning (RL) in robotics. To evaluate the package's pertinence, expected learning outcomes were set and the lessons were tested with users from varying backgrounds and levels of robotics experience. Encouraging results were obtained, especially in the ROS1 and ROS2 lessons, while the feedback from the RL lesson provided clear indications for future improvements. Therefore, this work provides solid groundwork for a more comprehensive educational package on robotics and ROS.

Abstract
Smart cities, leveraging IoT technologies, are revolutionizing the quality of life for citizens. However, the massive data generated in these cities also poses significant privacy risks, particularly in de-anonymization and re-identification. This survey focuses on the privacy concerns and commonly used techniques for data protection in smart cities, specifically addressing geolocation data and video surveillance. We categorize the attacks into linking, predictive and inference, and side-channel attacks. Furthermore, we examine the most widely employed de-identification and anonymization techniques, highlighting privacy-preserving techniques and anonymization tools; while these methods can reduce the privacy risks, they are not enough to address all the challenges. In addition, we argue that de-identification must involve properties such as unlikability, selective disclosure and self-sovereignty. This paper concludes by outlining future research challenges in achieving complete de-identification in smart cities.

Abstract
The increasing demand for precise chemical and biological sensing has led to the development of highly efficient plasmonic optical fiber sensors. Therefore, it is essential to optimize and match the operating wavelength region of both the optical fiber configuration and localized surface plasmon resonance of nanoparticles (NPs). This can be achieved by developing NPs that can reach resonance at near-infrared wavelengths, where refractive index sensitivity is enhanced, and silica optical fibers have lower losses. High aspect-ratio bimetallic Au@Ag nanorods and different side-polished fiber structures are tested using numerical simulations. The selected optical fiber configuration was based on a side-polished fiber with a 1 mm polished section. It is compared power losses and power at the NP interface for two configurations: a step-index single-mode fiber (SMF) with core/cladding diameters of 8.2/125 µm and a multimode graded-index fiber (GIF) with 62.5/125 µm at various polishing depths. The results showed that the best performance for both configurations was achieved at similar polishing depths, namely 59.5 and 55.2 µm for the SMF and GIF, respectively. The optical impact of retardation effects due to the proximity with the fiber structure were also observed, which caused a reduction in sensitivity from 1750 nm/RIU to 1500 nm/RIU and a red-shift of around 70 nm. © 2023 SPIE.

Abstract
Grape moths are a significant pest in vineyards, causing damage and losses in wine production. Pheromone traps are used to monitor grape moth populations and determine their developmental status to make informed decisions regarding pest control. Smart pest monitoring systems that employ sensors, cameras, and artificial intelligence algorithms are becoming increasingly popular due to their ability to streamline the monitoring process. In this study, we investigate the effectiveness of using segmentation as a pre-processing step to improve the detection of grape moths in trap images using deep learning models. We train two segmentation models, the U-Net architecture with ResNet18 and InceptionV3 backbonesl, and utilize the segmented and non-segmented images in the YOLOv5s and YOLOv8s detectors to evaluate the impact of segmentation on detection. Our results show that segmentation preprocessing can significantly improve detection by 3% for YOLOv5 and 1.2% for YOLOv8. These findings highlight the potential of segmentation pre-processing for enhancing insect detection in smart pest monitoring systems, paving the way for further exploration of different training methods.