ISEL - Engenharia Electrónica, Telecomunicações e Computadores
Permanent URI for this community
Browse
Browsing ISEL - Engenharia Electrónica, Telecomunicações e Computadores by Field of Science and Technology (FOS) "Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática"
Now showing 1 - 10 of 22
Results Per Page
Sort Options
- Aplicações de modelos de linguagem de grande escala na cibersegurançaPublication . Conceição, Tiago Miguel Pestana; Cruz, Nuno Miguel MachadoA crescente complexidade e sofisticação das ameaças no ciberespaço têm impulsionado a procura por soluções inovadoras e eficientes no campo da cibersegurança. Neste contexto, conduziu-se uma investigação com o objetivo de avaliar a viabilidade de Large Language Models (LLMs) no que concerne à automatização da geração de código e configurações no âmbito da cibersegurança. A investigação centrou-se em mecanismos de ciberdefesa e aplicações de educação em cibersegurança, com particular ênfase em soluções de geração de honeypots, malware e exercícios de Capture The Flag (CTF). Foram avaliados sete modelos, incluindo o GPT-4, Gemini Pro e Claude Opus 3. A metodologia de avaliação assentou no desenvolvimento de dois mecanismos de avaliação, sendo o primeiro um novo benchmark Cybersecurity Language Understading (CSLU), baseado no Massive Multitask Language Understanding, constituído por questões de escolha múltipla sobre diversos domínios do conhecimento. As prompts foram concebidas com o intuito de avaliar o estado de conhecimento de cada modelo relativamente aos tópicos supracitados. O segundo mecanismo consistiu na avaliação da consistência, criatividade e adaptabilidade dos modelos referente à geração de artefactos. Os resultados evidenciaram uma notória proeminência referente ao tópico de malware, com quatro destes a alcançarem a pontuação máxima. Por outro lado, o desempenho na tarefa de CTF revelou uma maior variação de resultados. De um modo geral, os modelos GPT- 4, Gemini Pro e Claude 3 Opus demonstraram resultados consistentemente superiores entre os modelos estudados. Num segundo momento, pretendeu-se desenvolver uma ferramenta baseada na web, com o objetivo de fornecer uma prova de conceito dos estudos anterior realizados. A referida ferramenta, recorrendo aos melhores LLMs estudados, permite ao utilizador criar e lançar automaticamente serviços de segurança, como os mencionados honeypots ou exercícios de CTF. De uma perspetiva global, estas descobertas sugerem que a aplicação de LLMs em atividades de cibersegurança pode ser altamente vantajosa.
- Assessing machine learning techniques for intrusion detection in cyber-physical systemsPublication . Santos, Vinicius F.; Albuquerque, Célio; Passos, Diego; Ereno Quincozes, Silvio; Mossé, DanielCyber-physical systems (CPS) are vital to key infrastructures such as Smart Grids and water treatment, and are increasingly vulnerable to a broad spectrum of evolving attacks. Whereas traditional security mechanisms, such as encryption and firewalls, are often inadequate for CPS architectures, the implementation of Intrusion Detection Systems (IDS) tailored for CPS has become an essential strategy for securing them. In this context, it is worth noting the difference between traditional offline Machine Learning (ML) techniques and understanding how they perform under different IDS applications. To answer these questions, this article presents a novel comparison of five offline and three online ML algorithms for intrusion detection using seven CPS-specific datasets, revealing that offline ML is superior when attack signatures are present without time constraints, while online techniques offer a quicker response to new attacks. The findings provide a pathway for enhancing CPS security through a balanced and effective combination of ML techniques.
- An autonomic parallel strategy for exhaustive search tree algorithms on shared or heterogeneous systemsPublication . Gonçalves de Oliveira Passos, Fernanda; Rebello, Vinod E. F.Backtracking branch-and-prune (BP) algorithms and their variants are exhaustive search tree techniques widely employed to solve optimization problems in many scientific areas. However, they characteristically often demand significant amounts of computing power for problem sizes representative of real-world scenarios. Given that their search domains can often be partitioned, these algorithms are frequently designed to execute in parallel by harnessing distributed computing systems. However, to achieve efficient parallel execution times, an effective strategy is required to balance the nonuniform partition workloads across the available resources. Furthermore, with the increasing integration of servers with heterogeneous resources and the adoption of resource sharing, balancing workloads is becoming complex. This paper proposes a strategy to execute parallel BP algorithms more efficiently on even shared or heterogeneous distributed systems. The approach integrates a self-adjusting dynamic partitioning method in the BP algorithm with a dynamic scheduler, provided by an application middleware, which manages the parallel execution while addressing any issues of imbalance. Empirical results indicate better scalability with efficiencies above 90% for instances of an application case study for the discretizable molecular distance geometry problem (DMDGP). Improvements of up to 38% were obtained in execution speed-ups compared to a more traditional parallel BP implementation for DMDGP.
- Bitcoin Anomaly Detection (BAD) - use of machine learning for fraudulent transaction detectionPublication . Gomes, Nuno Gonçalo Rodrigues Cabral; Ferreira, Artur JorgeAbstract The increasing adoption of cryptocurrencies, especially Bitcoin, has significantly altered the financial landscape, enabling decentralised and pseudonymous transactions. While these characteristics foster innovation, they also present serious challenges in detecting fraudulent behaviour, including money laundering and investment scams. This dissertation introduces Bitcoin Anomaly Detection (BAD), a hybrid machine learning framework designed to detect anomalous transactions on the Bitcoin blockchain. The methodology integrates supervised and unsupervised learning techniques, applied to the Elliptic dataset comprising over 200,000 transactions with temporal and graph-based features. Feature engineering, class imbalance handling (e.g., SMOTE + ENN), and dimensionality reduction (PCA, UMAP) are employed. Several models are evaluated, including XGBoost, RF, and GNN, achieving up to 97.5% accuracy, 96.2% recall, and a false positive rate below 4.5%. Graph analysis revealed that illicit transactions tend to form sparsely connected “sink” nodes—receiving many inputs (high in-degree) but sending no outputs (zero out-degree)—a pattern typical of laundering. Semi-supervised learning and association rule mining were used to label unknown data and enhance classification reliability. The final pipeline combines feature selection, class instance sampling, and a hybrid semisupervised learning approach—bridging supervised and unsupervised methods—to classify transactions with high accuracy and robustness. Key challenges addressed include the scarcity of labelled data, severe class imbalance, and the evolving nature of fraud techniques. XAI components were incorporated to ensure interpretability and compliance with regulatory frameworks such as Markets in Crypto-Assets (MiCA) and Financial Action Task Force (FATF). The findings from our experimental evaluation demonstrate the viability of adaptive, interpretable AI solutions for safeguarding decentralised financial ecosystems and supporting efforts in Anti-Money Laundering (AML) and law enforcement.
- Cognitive radio with machine learning to increase spectral efficiency in indoor application on the 2.5 GHz bandPublication . Soares, Marilson Duarte; Passos, Diego; Castellanos, Pedro Vladimir GonzalezDue to the propagation characteristics in the 2.5 GHz band, the signal is significantly degraded by building entry loss (BEL), making coverage in indoor environments in some cases non-existent. Signal degradation inside buildings is a challenge for planning engineers, but it can be seen as a spectrum usage opportunity for a cognitive radio communication system. This work presents a methodology based on statistical modeling of data collected by a spectrum analyzer and the application of machine learning (ML) to leverage the use of those opportunities by autonomous and decentralized cognitive radios (CRs), independent of any mobile operator or external database. The proposed design targets using as few narrowband spectrum sensors as possible in order to reduce the cost of the CRs and sensing time, as well as improving energy efficiency. Those characteristics make our design especially interesting for internet of things (IoT) applications or low-cost sensor networks that may use idle mobile spectrum with high reliability and good recall.
- Deep learning soft-decision GNSS multipath detection and mitigationPublication . Nunes, Fernando; Sousa, FernandoA technique is proposed to detect the presence of the multipath effect in Global Navigation Satellite Signal (GNSS) signals using a convolutional neural network (CNN) as the building block. The network is trained and validated, for a wide range of 𝐶/𝑁0 values, with a realistic dataset constituted by the synthetic noisy outputs of a 2D grid of correlators associated with different Doppler frequencies and code delays (time-domain dataset). Multipath-disturbed signals are generated in agreement with the various scenarios encompassed by the adopted multipath model. It was found that pre-processing the outputs of the correlators grid with the two-dimensional Discrete Fourier Transform (frequency-domain dataset) enables the CNN to improve the accuracy relative to the time-domain dataset. Depending on the kind of CNN outputs, two strategies can then be devised to solve the equation of navigation: either remove the disturbed signal from the equation (hard decision) or process the pseudoranges with a weighted least-squares algorithm, where the entries of the weighting matrix are computed using the analog outputs of the neural network (soft decision).
- Design of a Cardiopulmonary antenna for vital signs monitoring robust to different subjectsPublication . Cardoso, João; Pinho, Pedro; Gouveia, Carolina; Albuquerque, DanielWith the advancement of wireless diagnosis and treatment technologies, antennas deployed close to the human body are now widely used. The use of on-body antennas, along with other technologies, presents itself as an innovative method for detecting and monitoring vital signs. These antennas can be attached directly on the body or on clothes, making it comfortable to use and less invasive when compared to conventional methods, allowing at-home monitoring of elderly patients or high risk workers with a single antenna. In this paper, a robust high bandwidth patch antenna was developed to operate in the dedicated Industrial, Scientific and Medical frequency band, namely at 2.45 GHz, capable of monitoring vital signs in any subject. This work presents the design and results of a robust cardiopulmonary antenna, to be further used to monitor the respiratory rate of five different subjects, each one with different physiognomy.
- Development and evaluation of a mobile application with augmented reality for guiding visitors on hiking trailsPublication . Silva, Rute; Jesus, Rui; Jorge, PedroTourism on the island of Santa Maria, Azores, has been increasing due to its characteristics in terms of biodiversity and geodiversity. This island has several hiking trails; the available information can be consulted in pamphlets and physical placards, whose maintenance and updating is difficult and expensive. Thus, the need to improve the visitors’ experience arises, in this case, by using the technological means currently available to everyone: a smartphone. This paper describes the development and evaluation of the user experience of a mobile application for guiding visitors on said hiking trails, as well as the design principles and main issues observed during this process. The application is based on an augmented reality interaction model providing visitors with an interactive and recreational experience through Augmented Reality in outdoor environments (without additional marks in the physical space and using georeferenced information), helping in navigation during the route and providing updated information with easy maintenance. For the design and evaluation of the application, two studies were carried out with users on-site (Santa Maria, Azores). The first had 77 participants, to analyze users and define the application’s characteristics, and the second had 10 participants to evaluate the user experience. The feedback from participants was obtained through questionnaires. In these questionnaires, an average SUS (System Usability Scale) score of 83 (excellent) and positive results in the UEQ (User Experience Questionnaire) were obtained.
- Drug recommendation system based on symptoms and user sentiment analysis (DRecSys-SUSA)Publication . Pinto, Ana Sofia Simões; Pato, Matilde Pós-de-Mina; Datia, Nuno Miguel SoaresAbstract The rapid growth of user-generated content on multiple online platforms has opened opportunities for improving decision-making across various domains, including healthcare. This dissertation focuses on the development of our Drug Recommendation System based on usergenerated content (DRecSys-SUSA), designed to assist healthcare professionals and patients by providing personalized drug recommendations and supporting informed decision-making. Our research leverages the UCI ML Drug Review dataset as the foundation for developing an advanced recommendation system. Our solution utilizes a combination of modern AI techniques, including Exploratory Data Analysis (EDA), data pre-processing, sentiment analysis (SA), and text generation using a fine-tuned Large Language Model (LLM). We design and propose a recommendation system framework, within which we implement multiple variants of DRecSys-SUSA using different combinations of AI techniques. Each variant generates medically relevant suggestions to user-specific inputs such as age, symptoms, and current medications. Through an iterative process of implementation and evaluation using an LLM-as-judge methodology with AI-generated real-world scenarios, we identify which AI techniques are most beneficial for providing clinically appropriate and user-friendly drug recommendations. The resulting insights contribute to the advancement of AI-driven healthcare tools by establishing effective approaches for leveraging user-generated content in medical recommendation systems.
- Intelligent sports weightsPublication . Duarte, Olga dos Santos; Jacinto, Gustavo; Véstias, Mário; Véstias, Mário; Duarte, Rui Policarpo; Duarte, RuiWeightlifting is a common fitness activity and can be practiced individually without supervision. However, performing regular weightlifting exercises without any form of feedback can lead to serious injuries. To counter this, this work proposes a different approach to automatic weightlifting supervision off-the-person. The proposed embedded system is coupled to the weights and evaluates if they follow the correct trajectory in real time. The system is based on a low-power embedded System-on-a-Chip to perform the classification of the correctness of physical exercises using a Convolutional Neural Network with data from the embedded IMU. It is a low-cost solution and can be adapted to the characteristics of specific exercises to fine-tune the performance of the athlete. Experimental results show real-time monitoring capability with an average accuracy close to 95%. To favor its use, the prototypes have been enclosed on a custom 3D case and validated in an operational environment. All research outputs, developments, and engineering models are publicly available.
- «
- 1 (current)
- 2
- 3
- »