Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development

Funder

Organizational Unit

Publications

Lifelong predictive maintenance for railway fault

Publication . Risca, Diogo Ferreira; Figueiredo, Ana Maria Neves Almeida Baptista

The integration of advanced sensor technologies with machine learning algorithms has revolutionized fault diagnosis in railway systems, particularly at the wheel-track interface. Although numerous models have been proposed to detect irregularities such as wheel out-of-roundness, they often fall short in real-world applications due to the dynamic and nonstationary nature of railway operations. This thesis explores the challenges and opportunities of applying continual learning for predictive maintenance in railway systems, where the model’s ability to share knowledge between domains is critical to improving performance over time. By allowing the model to continuously learn and adapt as new data become available, continual learning overcomes the issue of catastrophic forgetting, which often plagues traditional models. The model retains past knowledge while improving predictive accuracy with each new learning episode, leveraging knowledge sharing mechanisms to adapt to evolving operational conditions, such as changes in speed, load, and track irregularities. Techniques such as experience replay and regularization-based strategies enhance model performance across multiple domains, making it particularly suitable for complex real-world environments. The methodology is validated through comprehensive simulations of train-track dynamic interactions, which capture realistic railway operating conditions. The proposed model demonstrates significant improvements in identifying wheel defects and other irregularities, establishing a reliable sequence for maintenance interventions. Future work will focus on field trials to assess the robustness of the approach in real-world railway environments, including challenges posed by track environments such as bridges and tunnels.

2024-10-18Master thesis

Embargoed access

From Data to Action: Exploring AI and IoT-driven Solutions for Smarter Cities

Publication . Dias, Tiago; Fonseca, Tiago; Vitorino, João; Martins, Andreia; Malpique, Sofia; Praça, Isabel

The emergence of smart cities demands harnessing advanced technologies like the Internet of Things (IoT) and Artificial Intelligence (AI) and promises to unlock cities' potential to become more sustainable, efficient, and ultimately livable for their inhabitants. This work introduces an intelligent city management system that provides a data-driven approach to three use cases: (i) analyze traffic information to reduce the risk of traffic collisions and improve driver and pedestrian safety, (ii) identify when and where energy consumption can be reduced to improve cost savings, and (iii) detect maintenance issues like potholes in the city's roads and sidewalks, as well as the beginning of hazards like floods and fires. A case study in Aveiro City demonstrates the system's effectiveness in generating actionable insights that enhance security, energy efficiency, and sustainability, while highlighting the potential of AI and IoT-driven solutions for smart city development.

2023Conference object

Open access

A Comparative Analysis of Machine Learning Techniques for IoT Intrusion Detection

Publication . Vitorino, João; Andrade, Rui; Praça, Isabel; Sousa, Orlando Jorge Coelho Moura; Maia, Eva

The digital transformation faces tremendous security challenges. In particular, the growing number of cyber-attacks targeting Internet of Things (IoT) systems restates the need for a reliable detection of malicious network activity. This paper presents a comparative analysis of supervised, unsupervised and reinforcement learning techniques on nine malware captures of the IoT-23 dataset, considering both binary and multi-class classification scenarios. The developed models consisted of Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Isolation Forest (iForest), Local Outlier Factor (LOF) and a Deep Reinforcement Learning (DRL) model based on a Double Deep Q-Network (DDQIN), adapted to the intrusion detection context. The most reliable performance was achieved by LightGBM. Nonetheless, iForest displayed good anomaly detection results and the DRL model demonstrated the possible benefits of employing this methodology to continuously improve the detection. Overall, the obtained results indicate that the analyzed techniques are well suited for IoT intrusion detection.

2022Book part

Open access

Adversarial Robustness and Feature Impact Analysis for Driver Drowsiness Detection

Publication . Vitorino, João; Rodrigues, Lourenço; Maia, Eva; Praça, Isabel; Lourenço, André

Drowsy driving is a major cause of road accidents, but drivers are dismissive of the impact that fatigue can have on their reaction times. To detect drowsiness before any impairment occurs, a promising strategy is using Machine Learning (ML) to monitor Heart Rate Variability (HRV) signals. This work presents multiple experiments with different HRV time windows and ML models, a feature impact analysis using Shapley Additive Explanations (SHAP), and an adversarial robustness analysis to assess their reliability when processing faulty input data and perturbed HRV signals. The most reliable model was Extreme Gradient Boosting (XGB) and the optimal time window had between 120 and 150 s. Furthermore, the 18 most impactful features were selected and new smaller models were trained, achieving a performance as good as the initial ones. Despite the susceptibility of all models to adversarial attacks, adversarial training enabled them to preserve significantly higher results, so it can be a valuable approach to provide a more robust driver drowsiness detection.

2023Conference object

Open access

Preliminary results of advanced heuristic optimization in the risk-based energy scheduling competition

Publication . Almeida, José; Lezama, Fernando; Soares, João; Vale, Zita; Canizes, Bruno

In this paper, multiple evolutionary algorithms are applied to solve an energy resource management problem in the day-ahead context involving a risk-based analysis corresponding to the proposed 2022 competition on evolutionary computation. We test numerous evolutionary algorithms for a risk-averse day-ahead operation to show preliminary results for the competition. We use evolutionary computation to follow the competition guidelines. Results show that the HyDE algorithm obtains a better solution with lesser costs when compared to the other tested algorithm due to the minimization of worst-scenario impact.

2022Journal article

Open access