ICI - GeoBioTec@UBI | Documentos por Auto-Depósito
URI permanente para esta coleção:
A unidade de investigação (UI) GeoBiociências, Geotecnologias e Geoengenharias (GeoBioTec) foi criada em 2007 na Universidade de Aveiro e tem dois polos, um na Universidade da Beira Interior (GeoBioTec@UBI), outro na Universidade Nova de Lisboa (GeoBioTec-NOVA). A investigação é diversificada, envolvendo estudos interdisciplinares sobre recursos geológicos, recursos hídricos e gestão sustentável da água, geotecnia e mecânica dos solos e rochas, geologia estrutural, geomateriais, bacias sedimentares, tecnologias agroindustriais, sistemas ambientais complexos, mobilidade e transportes sustentáveis, deteção remota e sustentabilidade de cidades, comunidades e territórios. A UI está classificada como “Muito Bom” pela FCT e tem como missão conhecer e explorar os processos geológicos, biológicos, físicos e químicos que moldam o ambiente da Terra visando o desenvolvimento sustentável de cidades, comunidades e territórios.
Website GeoBioTec@UBINavegar
Percorrer ICI - GeoBioTec@UBI | Documentos por Auto-Depósito por autor "Almeida, Pedro G."
A mostrar 1 - 4 de 4
Resultados por página
Opções de ordenação
- Assessment of Airport Pavement Condition Index (PCI) Using Machine LearningPublication . Santos, Bertha; Studart, André; Almeida, Pedro G.Pavement condition assessment is a fundamental aspect of airport pavement management systems (APMS) for ensuring safe and efficient airport operations. However, conventional methods, which rely on extensive on-site inspections and complex calculations, are often time-consuming and resource-intensive. In response, Industry 4.0 has introduced machine learning (ML) as a powerful tool to streamline these processes. This study explores five ML algorithms (Linear Regression (LR), Decision Tree (DT), Random Forest (RF), Artificial Neural Network (ANN), and Support Vector Machine (SVM)) for predicting the Pavement Condition Index (PCI). Using basic alphanumeric distress data from three international airports, this study predicts both numerical PCI values (on a 0–100 scale) and categorical PCI values (3 and 7 condition classes). To address data imbalance, random oversampling (SMOTE—Synthetic Minority Oversampling Technique) and undersampling (RUS) were used. This study fills a critical knowledge gap by identifying the most effective algorithms for both numerical and categorical PCI determination, with a particular focus on validating class-based predictions using relatively small data samples. The results demonstrate that ML algorithms, particularly Random Forest, are highly effective at predicting both the numerical and the three-class PCI for the original database. However, accurate prediction of the seven-class PCI required the application of oversampling techniques, indicating that a larger, more balanced database is necessary for this detailed classification. Using 10-fold cross-validation, the successful models achieved excellent performance, yielding Kappa statistics between 0.88 and 0.93, an error rate of less than 7.17%, and an area under the ROC curve greater than 0.93. The approach not only significantly reduces the complexity and time required for PCI calculation, but it also makes the technology accessible, enabling resource-limited airports and smaller management entities to adopt advanced pavement management practices.
- Automated and Intelligent Inspection of Airport Pavements: A Systematic Review of Methods, Accuracy and Validation ChallengesPublication . Feitosa, Ianca; Santos, Bertha; Almeida, Pedro G.; mdpiAirport pavement condition assessment plays a critical role in ensuring operational safety, surface functionality, and long-term infrastructure sustainability. Traditional visual inspection methods, although widely used, are increasingly challenged by limitations in accuracy, subjectivity, and scalability. In response, the field has seen a growing adoption of automated and intelligent inspection technologies, incorporating tools such as unmanned aerial vehicles (UAVs), Laser Crack Measurement Systems (LCMS), and machine learning algorithms. This systematic review aims to identify, categorize, and analyze the main technological approaches applied to functional pavement inspections, with a particular focus on surface distress detection. The study examines data collection techniques, processing methods, and validation procedures used in assessing both flexible and rigid airport pavements. Special emphasis is placed on the precision, applicability, and robustness of automated systems in comparison to traditional approaches. The reviewed literature reveals a consistent trend toward greater accuracy and efficiency in systems that integrate deep learning, photogrammetry, and predictive modeling. However, the absence of standardized validation protocols and statistically robust datasets continues to hinder comparability and broader implementation. By mapping existing technologies, identifying methodological gaps, and proposing strategic research directions, this review provides a comprehensive foundation for the development of scalable, data-driven airport pavement management systems.
- Statistical analysis of an in-vehicle image-based data collection method for assessing airport pavement conditionPublication . Feitosa, Ianca Teixeira ; Santos, Bertha; Gama, Jorge; Almeida, Pedro G.This study presents a comprehensive comparative statistical analysis to validate a novel in-vehicle image-based method for collecting pavement condition data in airport environments. It highlights the method’s potential to address key challenges faced by airport pavement managers, such as the need for continuous maintenance and the demand for fast, effective, and reliable inspection procedures. The in-vehicle system integrates laser scanning systems, image capture, and georeferencing devices to collect pavement distress data, and its accuracy and reliability are evaluated statistically. The primary objective is to validate and enhance this novel inspection approach, which shows strong potential as an effective alternative for comprehensive pavement evaluation, enabling continuous, rapid monitoring and the analysis of trends. Validation was performed by means of a detailed statistical comparison of pavement distress density on the main runway of Amílcar Cabral International Airport, Sal Island, Cape Verde, based on data collected using the proposed in-vehicle and the traditional on-foot inspection methods. Non-parametric repeated measures analysis (nparLD) showed statistically similar results between methods for 9 of 12 distress type-severity combinations (4 types × 3 levels), especially for medium and high severity cases, and that pavement section and method-section factors were significant in 10 and 9 of 12 cases, respectively, indicating spatial variability. Kruskal-Wallis tests were applied to each method separately. Significant section-based differences were found in 11 of 12 cases for the traditional method and in 2 of 12 cases for the in-vehicle image-based method, indicating greater sensitivity of the on-foot inspection to spatial variation in distress distribution. These findings support the statistical validation of the proposed method for practical application in airport pavement management. Furthermore, the comprehensive analysis, which included correlation and autocorrelation studies, revealed a bias in severity level assignment during traditional on-foot inspections. The findings highlight time-efficiency gains with the image-based method and suggest improvements, such as enhancing image quality and providing inspector training to increase the accuracy of severity level classification. These results offer valuable insights for airport pavement managers, contributing to improved safety, operational efficiency, and resilience in the face of growing air traffic demands.
- Use of Unmanned Aerial Vehicles (UAVs) for Transport Pavement InspectionPublication . Santos, Bertha; Gavinhos, Pedro; Almeida, Pedro G.; Nery, Dayane; Rujikiatkamjorn, C.; Xue, J.; Indraratna, B.Technological evolution has allowed the use of unmanned aerial vehicles (UAVs) in an easier and more diversified way, creating opportunities for its application in various fields of engineering, namely in the inspection of transport infrastructures. The present study begins with the analysis of the main practices that resort to the use of UAVs, in order to frame its application in the field of transport pavement inspection. A review of studies and other available literature served as a starting point to define the methodology adopted for the development of the case study presented. The methodology includes the collection of images of a flexible road pavement section, its processing, and the creation of an orthoimage and a 3D model from which it was possible to identify and characterize the distresses present on the pavement surface. The main results obtained point to planimetric and altimetric deviations of less than 2 and 10 mm, respectively, for the images collected by theMavic 2 Pro drone at 3 and 20mhigh.With the collected data, itwas also possible to calculate the global quality index PCI for the inspected pavement section. Under these conditions, it is possible to conclude that the accuracy is very good and suitable for the intended purpose, allowing fast data collection at low cost. This new technological approach supports infrastructure managers in the design of maintenance programs and in the scheduling of interventions, thus contributing to the increase of the durability and safety levels of the inspected pavements.