ESTG - Artigos em revistas internacionais
Permanent URI for this collection
Browse
Recent Submissions
- From Knowledge to Action: How Portuguese Higher Education Students Engage with Circular Economy PrinciplesPublication . Pardal, Ana; Moreira, Anabela; Galacho, Cristina; Mateus, Dina; Viegas, Laura; Gaspar, Marcelo; Teixeira, Margarida Ribau; Manteigas, Vitor; Dinis, Maria Alzira PimentaThis study investigates the perceptions and practices of Portuguese higher education students regarding the circular economy (CE), emphasising their knowledge, attitudes, and behaviours toward sustainable resource management. Carried out by the Working Group on Circular Economy and Waste Management of the Portuguese Sustainable Campus Network (RCS), the research used an online survey targeting students from 20 higher education institutions (HEIs), resulting in 400 responses. The findings indicate that while students generally hold positive views of the CE, their understanding of its practical applications, such as waste reduction and resource efficiency, remains limited. Only a small proportion of students reported exposure to CE-related topics in their curriculum, revealing a gap in academic integration. This study also identifies significant demographic variations in CE awareness and practices, influenced by factors such as age, field of study, and employment status. These insights underscore the need for HEIs to strengthen CE education and actively involve students in hands-on sustainability initiatives, fostering a generation equipped to drive the transition toward a circular economy.
- Multi-Class Intrusion Detection in Internet of Vehicles: Optimizing Machine Learning Models on Imbalanced DataPublication . Palma, Ágata; Antunes, Mário; Bernardino, Jorge; Alves, AnaThe Internet of Vehicles (IoV) presents complex cybersecurity challenges, particularly against Denial-of-Service (DoS) and spoofing attacks targeting the Controller Area Network (CAN) bus. This study leverages the CICIoV2024 dataset, comprising six distinct classes of benign traffic and various types of attacks, to evaluate advanced machine learning techniques for instrusion detection systems (IDS). The models XGBoost, Random Forest, AdaBoost, Extra Trees, Logistic Regression, and Deep Neural Network were tested under realistic, imbalanced data conditions, ensuring that the evaluation reflects real-world scenarios where benign traffic dominates. Using hyperparameter optimization with Optuna, we achieved significant improvements in detection accuracy and robustness. Ensemble methods such as XGBoost and Random Forest consistently demonstrated superior performance, achieving perfect accuracy and macro-average F1-scores, even when detecting minority attack classes, in contrast to previous results for the CICIoV2024 dataset. The integration of optimized hyperparameter tuning and a broader methodological scope culminated in an IDS framework capable of addressing diverse attack scenarios with exceptional precision.
- Design of a Video Otoscope Prototype with an Integrated Scanner for Hearing Aid Direct Digital Manufacturing: A Preliminary StudyPublication . Ganhão, Francisco; Santos, António Carvalho; Silva, Carla; Monteiro de Moura, Carla SofiaIn the current landscape of hearing rehabilitation, ear mold manufacturing typically involves the injection of silicone into the external ear canal (EEC) of each patient. This invasive procedure poses several risks, including the potential for silicone residue retention and tympanic membrane perforation, which may necessitate surgical intervention. To mitigate these risks, we present the design of a video otoscope that integrates a scanner capable of capturing high-precision, real-time images of the EEC’s geometry. The developed device allows (i) the generation of a 3D CAD model leading to the direct, quick, and low-cost production of customized hearing aids using 3D printing and (ii) the establishment of medical protocols for carrying out diagnoses and monitoring of hearing pathology evolution using methodologies based on Artificial Intelligence. Furthermore, the use of customized hearing aids that allow the application of Rhythmic Auditory Stimulation (RAS) and music therapy enhances audiology as an alternative and innovative way to treat cognitive and degenerative diseases, as well as pathological disorders.
- Long-Range RFID Indoor Positioning System for an Autonomous WheelchairPublication . Pereira, JoãoA new Radio-Frequency Identification (RFID) indoor positioning system (IPS) has been developed to operate in environments where the Global Positioning System (GPS) is unavailable. Traditional RFID tracking systems, such as anti-theft systems in clothing stores, typically work within close proximity to exit doors. This paper presents a novel RFID IPS capable of locating and tracking passive RFID tags over a larger area with greater precision. These tags, costing approximately EUR 0.10 each, are in the form of small stickers that can be attached to any item requiring tracking. The proposed system is designed for an autonomous wheelchair, built from scratch, which will be identified and monitored using passive RFID tags. Our new RFID IPS, with a 12 m range, is implemented in this “smart” wheelchair.
- Synthetic image generation for effective deep learning model training for ceramic industry applicationsPublication . Gaspar, Fábio; Daniel Carreira; Rodrigues, Nuno; Miragaia, Rolando; Ribeiro, José; Costa, Paulo; Pereira, AntónioIn the rapidly evolving field of machine learning engineering, access to large, high-quality, and well-balanced labeled datasets is indispensable for accurate product classification. This necessity holds particular significance in sectors such as the ceramics industry, in which effective production line activities are paramount and deep learning classification mechanisms are particularly relevant for streamlining processes; but real-world image samples are scarce and difficult to obtain, hindering dataset building and consequently model training and deployment. This paper presents a novel approach for dataset building in the context of the ceramic industry, which involves employing synthetic images for building or complementing datasets for image classification problems. The proposed methodology was implemented in CeramicFlow, an innovative computer graphics rendering pipeline designed to create synthetic images by employing computer-aided design models of ceramic objects and incorporating domain randomization techniques. As a result, a fully synthetic image dataset named Synthetic CeramicNet was created and validated in real-world ceramic classification problems. The results demonstrate that synthetic images provide an adequate basis for datasets and can significantly reduce reliance on real-world data when developing deep learning approaches for image classification problems in the ceramic industry. Furthermore, the proposed approach can potentially be applied to other industrial fields.
- Decrypting messages: Extracting digital evidence from signal desktop for windowsPublication . Paulino, Gonçalo; Negrão, Miguel; Frade, Miguel; Domingues, PatrícioWith growing concerns over the security and privacy of personal conversations, end-to-end encrypted instant messaging applications have become a key focus of forensic research. This study presents a detailed methodology along with an automated Python script for decrypting and analyzing forensic artifacts from Signal Desktop for Windows. The methodology is divided into two phases: i) decryption of locally stored data and ii) analysis and documentation of forensic artifacts. To ensure data integrity, the proposed approach enables retrieval without launching Signal Desktop, preventing potential alterations. Additionally, a reporting module organizes extracted data for forensic investigators, enhancing usability. Our approach is effective in extracting and analyzing encrypted Signal artifacts, providing a reliable method for forensic investigations.
- The performance of the courts in the digital era: The case of insolvency and restructuring proceedingsPublication . Frade, Catarina; Fernando, Paula; Conceição, Ana FilipaThe performance of the courts has been at the center of both political and public debates around the world and is one of the success indicators in the development of public policies on access to law and justice, particularly as regards the right to obtain a decision in reasonable time. The introduction of new information and communication technologies has been essential in extending this access to law and justice in two ways: as a way of making courts function more efficiently; and as an instrument for measuring and assessing the level of compliance with established policy objectives. Anchored in this “computerization of justice” movement, we intend to analyze its role in the overall performance of the courts in an important and central area for the economy and the functioning of the markets: corporate insolvency and restructuring. In order to achieve this purpose, a series of interviews was carried out with several key judicial players and stakeholders. What has been found in this research shows that day-to-day reality is not yet fully in line with policy purposes and legal provisions. Technologies still play an ambivalent role: despite streamlining processes, they raise new difficulties and challenges that require constant improvements.
- A Review of Manufacturing Materials and Production Methods for Frequency-Selective Structures [Wireless Corner]Publication . Ferreira, David; Caldeirinha, Rafael; Cuinas, Inigo; Fernandes, Telmo, Telmo Rui Carvalhinho Cunha, Telmo R.; Rajo-Iglesias, EvaThis article presents a review of frequency-selective structure (FSS) manufacturing materials and production methods ranging from the common printed circuit board (PCB)-based designs to textile, ink, metal, or fluid prototypes. Our work gathers some of the most relevant solutions published by the scientific community and considers several examples depicted for each case. Additionally, the main physical parameters that may have a significant impact on FSS performance have been identified, e.g., electrical conductivity of the FSS conductive element and the relative permittivity and thickness of the FSS dielectric material. Finally, a comparative analysis of the materials and techniques is presented, which highlights the benefits and limitations of each solution.
- Behavior of Rectangular Reinforced-Concrete Columns under Biaxial Cyclic Loading and Variable Axial LoadsPublication . Rodrigues, Hugo; Furtado, André; Arêde, AntónioThe behavior of reinforced-concrete (RC) elements subjected to axial loading variation in conjunction with cyclic biaxial bending is recognized as a very important research topic with a reduced number of experimental results available. Six full-scale RC rectangular columns were tested and analyzed to study the effects of variable axial load on the hysteretic behavior of RC building columns under biaxial horizontal loading. The experimental results are presented and discussed in terms of damage evolution, global hysteretic behavior, stiffness degradation, columns’ capacity, and energy dissipation. The global findings revealed the significant effects of the axial load variation on the hysteretic behavior of RC columns.
- Evaluation of different strengthening techniques’ efficiency for a soft storey buildingPublication . Furtado, André; Rodrigues, Hugo; Varum, Humberto; Costa, AníbalThe assessment of seismic vulnerability and strengthening of existing buildings is a topic of relevant importance and priority, as evidenced in recent earthquakes around the world, particularly in Southern European countries. Some architectural solutions adopted in the decade of 1970, combined with the common design and construction practices at that time, particularly in what regards to the seismic design, influences the seismic vulnerability of these structures. The objective of the present work is to study, based on numerical analyses, different strengthening techniques to adopt into an existing building with the behaviour potentially governed by soft storey mechanism when subjected to seismic actions. The influence of the masonry infill panels will be studied and the seismic safety of the building will be assessed. Also, different strengthening techniques will be tested to fix/eliminate the soft storey like response, namely: RC columns jacketing, addition of steel bracings with and without shear link and addition of RC shear walls. The strengthened buildings results will be compared with the results of the original structure, deducting about the structural efficiency by each type of strengthening technique adopted. The costs associated to each solution will be determined and compared with the market value of the building.