RCIPL
Repositório Institucional do Politécnico de Lisboa
Entradas recentes
Standard-based smart card access control architecture for critical infrastructures
Publication . Oliveira, António Filipe Ramic Santos; Dias, Tiago Miguel Braga da Silva; Chaves, Ricardo Jorge Fernandes
Abstract
This thesis proposes an enterprise-centered access control architecture that is technically compatible with widely adopted standards, enabling the convergence of physical and logical access on a single smart card credential while preserving interoperability and enterprise control over identity proofing, registration, and credential issuance. This need is particularly acute for operators of critical infrastructure, who must replace legacy badge-based systems, ensure cross-site and outage resilience, unify access control with support for rapid revocation, generate audit trails, and avoid vendor lock-in through the use of open standards. The proposed architecture was built to meet these needs. The main outcomes of this work are a standards-aligned enterprise architecture for a multisite access control system and a smart card credential with a well-defined, standardized data model and lifecycle. Additionally, this work showcases a proof-of-concept prototype consisting of a Card Management System that personalizes cards and issues Public Key Infrastructure (PKI) credentials. The prototype also features a Java Card applet that implements a standardized data model and command set, supporting asymmetric cryptography-based multi-factor authentication mechanisms. Furthermore, it includes an access control system emulator for testing purposes. Using this stack, it is possible to issue cards and test them by performing strong authentication mechanisms, demonstrating the end-to-end feasibility of the devised solution for both physical and logical access scenarios.
Aplicação para caracterização da voz
Publication . Santos, Pedro Branco; Cordeiro, Hugo Tito
Este projeto propõe uma aplicação simples e intuitiva com a capacidade de se ligar a um servidor, com o foco a melhorar a experiência do utilizador através de dinamismo e modelação. A funcionalidade principal da aplicação é apresentar resultados, numa interface, que caracterizam a fala através da comunicação com o servidor, mantendo sempre a troca de informação segura e que não haja perdas desta. Um dos objetivos principais do projeto foi garantir que a experiência do utilizador seja agradável, removendo qualquer complexidade na interface da aplicação. A arquitetura do servidor está desenhada de modo a garantir que a informação é sempre processada e que o utilizador obtenha sempre os resultados desejados. Este projeto desenvolveu uma aplicação protótipo que permite a extração de parâmetros dos sinais de fala para rastreio de patologias da voz. A aplicação pretende ser dinâmica, nomeadamente através da inclusão de novos algoritmos. A interface de utilizador foi desenvolvida em Unity3D de modo a permitir o uso em múltiplas plataformas. Os algoritmos foram desenvolvidos em Python de modo a tirar partido das bibliotecas de processamento de fala e sinal existentes.
Application of stereoscopy in speleological surveying
Publication . Gonçalves, Martim Augusto Teixeira; Fazenda, Pedro Viçoso; Jorge, Pedro Miguel Torres Mendes
Abstract
Cave topography plays a fundamental role in supporting various fields that require the exploration of underground environments by specialists. However, speleologists rely on traditional techniques which remain labor-intensive and prone to errors. While LiDAR and photogrammetry boast advanced mapping accuracy, high costs, bulk, laborous preparation and operational complexity limit widespread adoption. This study aims to investigate the use of a portable, cost-effective alternative surveying method by leveraging stereoscopy and established tools from the robotics ecosystem consisting on the ZED 2 3D camera and OctoMap framework. Field experiments compared stereoscopic mapping against a traditional compass-and-laser workflow, evaluating accuracy, efficiency and usability. Results demonstrate that stereo-SLAM pipelines produce metrically accurate 3D models in real time, offering an interesting development path to bridge the gap between manual surveys and high-end LiDAR scans. Limitations in portability, environmental conditions and robustness were identified along with future directions to address them. Despite these limitations in the method, it shows promising results by reducing cost and effort in obtaining structured and machine-readable cave representations with applications beyond speleology. These findings may support the development of tools to assist adjacent fields such as archaeology, geology, biology and environmental monitoring. The work establishes a foundation fieldready stereoscopic systems supporting semantic mapping, advanced spatial analysis, and integration with robotic exploration.
Driver profile and drowsiness classification
Publication . Valente, Duarte Faria da Mota Gonçalves; Lourenço, André Ribeiro; Ferreira, Artur Jorge
Abstract
Every day, approximately 3,700 people die in road accidents, totaling 1.35 million fatalities globally each year. The primary causes of these accidents include speeding, distracted driving, drunk driving, nighttime driving, and drowsy driving. Changing human driving habits is extremely challenging, as road safety campaigns alone have shown limited impact on reducing fatalities. However, while influencing behavior is challenging, technological advancements offer promising solutions to mitigate risks and enhance road safety. This thesis explores unsafe driving behaviors, with a particular focus on both dangerous and drowsy driving. Using data from in-car sensors and physiological signals, we investigate ethods to assess driver states and identify patterns associated with an increased risk of accidents. Specifically, we analyze driving behavior metrics, such as speeding, harsh braking, and sudden acceleration, to classify risky driving tendencies. Additionally, we leverage heart rate variability features extracted from electrocardiograms recorded via a sensor-equipped steering wheel to detect signs of driver drowsiness. The results indicate that both behavioral and physiological markers can serve as effective indicators of unsafe driving conditions. In particular, aggressive driving behaviors are strongly linked to accident risk, while prolonged driving and fatigue significantly impair driver performance. Moreover, individual differences in responses to sleep deprivation highlight the need for personalized assessment methods. These insights contribute to the development of intelligent monitoring systems capable of identifying and mitigating unsafe driving conditions in real time, ultimately enhancing road safety.
Electric vehicle X driving range prediction 2 EV X DRP2
Publication . Valido, João Francisco Fidalgo; Ferreira, Artur Jorge; Coutinho, David Pereira
Abstract
The use of Electric Vehicles (EV) has increased in recent years. The autonomy of the EV, expressed as its Driving Range (DR) is a key factor. This autonomy depends on several variables related to the vehicle itself as well as with external conditions. An accurate estimation of the DR value at each moment is a challenging task. In this thesis, we address the DR estimation problem using machine learning techniques. We build a dataset with 11 features, for DR estimation, using publicly available EV data. Then, we discuss the use of Machine Learning (ML) Regression techniques to estimate DR, with Linear Regression (LR), Multilayer Perceptron (MLP), and Radial Basis Function (RBF) neural networks. Moreover, we assess the effect of unsupervised dimensionality reduction techniques using feature selection and feature reduction approaches. The experimental results show that the use of both feature selection and feature reduction are useful at reducing the dimensionality of the data, keeping or improving the performance for DR estimation. This study also identifies the top features for DR estimation. The best feature selection method was the Mean-Median approach, while Principal Component Analysis yielded the best results in terms of feature reduction. Among the regression techniques evaluated, linear regression achieved the best overall performance. However, in real-world scenarios, where a larger number of variables may be present, methods such as MLP or RBF might offer better adaptability and robustness.