Cesar Lincoln Cavalcante Mattos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Cesar Lincoln Cavalcante Mattos has a total of 101 co-authors. Here are the top co-authors by number of shared publications:
- Joao Paulo Pordeus Gomes
Federal University of Ceará
12 shared publications - Emanuel Bezerra Rodrigues
Federal University of Ceará
5 shared publications - Francisco R. P. da Ponte
Federal University of Ceará (UFC)
4 shared publications - Paulo Antonio Leal Rego
Federal University of Ceará (UFC), Fortaleza, Brazil
3 shared publications - Amauri Holanda Souza Junior
Federal Institute of Ceara
2 shared publications - Diego Mesquita
School of Applied Mathematics, Getulio Vargas Foundation
2 shared publications
Latest Publications
- 2 October 2026
- Published by Springer Nature
- p. 66-80
Spatio-Temporal Anomaly Detection Using Log-Gaussian Cox Processes with Variational Inference
- 2 October 2026
- Published by Springer Nature
- p. 66-80
Spatio-Temporal Anomaly Detection Using Log-Gaussian Cox Processes with Variational Inference
- 30 September 2026
- Published by Springer Nature
- p. 413-427
Weibull Proportional Hazards Model with Deep Learning for Time-Series Memory Failure Prediction
- 30 September 2026
- Published by Springer Nature
- p. 413-427
Weibull Proportional Hazards Model with Deep Learning for Time-Series Memory Failure Prediction
- 30 September 2026
- Published by Springer Nature
- p. 108-122
HoTHP: Hyperbolic Rotary Position Embedding-Based Transformer Hawkes Process for Length Extrapolation
- 30 September 2026
- Published by Springer Nature
- p. 108-122
HoTHP: Hyperbolic Rotary Position Embedding-Based Transformer Hawkes Process for Length Extrapolation
- Open Access
- 18 June 2026
- Published by Elsevier in SSRN Electronic Journal
Breast Cancer Risk Prediction from Longitudinal Mammography Reports in a Real-World Health System: A Prognostic Modelling Study
Background: Traditional breast cancer screening protocols apply uniform strategies across populations with heterogeneous risk profiles. Leveraging routinely collected electronic health records to improve individual risk stratification has the potential to optimize early detection and better allocate clinical resources.Methods: We developed and validated a population-scale model to estimate individual breast cancer risk after negative or probably benign mammography examinations using longitudinal clinical data from the largest private healthcare system in Brazil, collected between January 2016 and December 2025. We selected BI-RADS 1, 2, and 3 yielding approximately 4.6 million examinations from 1.8 million females (median age 44 years [IQR 35--53]) from more than 200 hospitals and clinics in all five main regions of Brazil. Unlike image-based approaches, the model relied exclusively on radiologist report text and structured clinical data.Findings: The model predicted the occurrence of breast cancer within 5 years with an AUROC of 0.86 (95% CI: 0.85--0.87) and a concordance index of 0.86 (95% CI: 0.85--0.87), with similar performance across shorter prediction horizons. Flagging only the top 3.4% risk percentile identifies 50.1% (95% CI: 48.4%--52.2%) of exams from patients who would develop breast cancer within 5 years. In contrast, in the bottom 47% risk percentile, only 10.0% (95% CI: 8.98%--10.9%) develop cancer in 5 years. An explainability analysis identified surgical history, calcifications, and architectural distortions as the strongest drivers of high-risk predictions, while reassuring radiological findings and other clinical factors were prominent in low-risk predictions.Interpretation: This study demonstrates the feasibility of a state-of-the-art breast cancer risk model based on longitudinal text reports and structured clinical data, rather than raw images. Extracted from a large-scale, diverse, real-world health system, these results offer a practical and scalable tool for enhanced individual risk stratification.
- 18 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessBreast Cancer Risk Prediction from Longitudinal Mammography Reports in a Real-World Health System: A Prognostic Modelling Study
Background: Traditional breast cancer screening protocols apply uniform strategies across populations with heterogeneous risk profiles. Leveraging routinely collected electronic health records to improve individual risk stratification has the potential to optimize early detection and better allocate clinical resources.Methods: We developed and validated a population-scale model to estimate individual breast cancer risk after negative or probably benign mammography examinations using longitudinal clinical data from the largest private healthcare system in Brazil, collected between January 2016 and December 2025. We selected BI-RADS 1, 2, and 3 yielding approximately 4.6 million examinations from 1.8 million females (median age 44 years [IQR 35--53]) from more than 200 hospitals and clinics in all five main regions of Brazil. Unlike image-based approaches, the model relied exclusively on radiologist report text and structured clinical data.Findings: The model predicted the occurrence of breast cancer within 5 years with an AUROC of 0.86 (95% CI: 0.85--0.87) and a concordance index of 0.86 (95% CI: 0.85--0.87), with similar performance across shorter prediction horizons. Flagging only the top 3.4% risk percentile identifies 50.1% (95% CI: 48.4%--52.2%) of exams from patients who would develop breast cancer within 5 years. In contrast, in the bottom 47% risk percentile, only 10.0% (95% CI: 8.98%--10.9%) develop cancer in 5 years. An explainability analysis identified surgical history, calcifications, and architectural distortions as the strongest drivers of high-risk predictions, while reassuring radiological findings and other clinical factors were prominent in low-risk predictions.Interpretation: This study demonstrates the feasibility of a state-of-the-art breast cancer risk model based on longitudinal text reports and structured clinical data, rather than raw images. Extracted from a large-scale, diverse, real-world health system, these results offer a practical and scalable tool for enhanced individual risk stratification.
- Open Access
- 9 June 2026
- Published by Associacao Nacional de Pesquisa e Ensino em Transportes in Transportes
- Vol. 34
Uso de aprendizado de máquina probabilístico para avaliação da deformação permanente em misturas asfálticas
A deformação permanente é um defeito que afeta a durabilidade e a qualidade dos pavimentos asfálticos, sendo influenciada pelas propriedades do ligante e dos agregados que compõem as misturas asfálticas usadas em revestimentos. O ensaio uniaxial de carga repetida, cujo resultado é o Flow Number, é usado para avaliar a resistência da mistura à deformação permanente. Uma alternativa a esse ensaio é a aplicação de algoritmos de aprendizado de máquina, uma abordagem que permite prever o nível de tráfego equivalente ao Flow Number a partir de dados de parâmetros das misturas. Outra opção é a aplicação de modelos probabilísticos, que consideram a incerteza das variáveis previstas. Dentre eles, destacam-se os Processos Gaussianos, que se sobressaem com uma pequena quantidade de dados. Este trabalho tem como objetivo avaliar o desempenho de diferentes modelos probabilísticos na classificação de misturas asfálticas com relação à deformação permanente, auxiliando na seleção de materiais e no dimensionamento de pavimentos. Construiu-se um banco de dados com 252 misturas, por meio da coleta de informações de ensaios laboratoriais. Aplicaram-se modelos de regressão e classificação para prever o nível de tráfego equivalente, obtendo resultados que demonstram a viabilidade dessa abordagem, alcançando uma acurácia de até 90%.
- 9 June 2026
- Published by Associacao Nacional de Pesquisa e Ensino em Transportes in Transportes
- Vol. 34
Open AccessUso de aprendizado de máquina probabilístico para avaliação da deformação permanente em misturas asfálticas
A deformação permanente é um defeito que afeta a durabilidade e a qualidade dos pavimentos asfálticos, sendo influenciada pelas propriedades do ligante e dos agregados que compõem as misturas asfálticas usadas em revestimentos. O ensaio uniaxial de carga repetida, cujo resultado é o Flow Number, é usado para avaliar a resistência da mistura à deformação permanente. Uma alternativa a esse ensaio é a aplicação de algoritmos de aprendizado de máquina, uma abordagem que permite prever o nível de tráfego equivalente ao Flow Number a partir de dados de parâmetros das misturas. Outra opção é a aplicação de modelos probabilísticos, que consideram a incerteza das variáveis previstas. Dentre eles, destacam-se os Processos Gaussianos, que se sobressaem com uma pequena quantidade de dados. Este trabalho tem como objetivo avaliar o desempenho de diferentes modelos probabilísticos na classificação de misturas asfálticas com relação à deformação permanente, auxiliando na seleção de materiais e no dimensionamento de pavimentos. Construiu-se um banco de dados com 252 misturas, por meio da coleta de informações de ensaios laboratoriais. Aplicaram-se modelos de regressão e classificação para prever o nível de tráfego equivalente, obtendo resultados que demonstram a viabilidade dessa abordagem, alcançando uma acurácia de até 90%.
- 5 February 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (11) , 127-136
Satellite Eyes on Runway Safety: Predicting Airport Pavement Friction Using Convolutional Neural Networks and Image Processing
Runway safety in landing and takeoff operations is strongly influenced by skid resistance, which may be reduced by rubber buildup from aircraft braking. Conventional friction measurement methods require specialized equipment and operational interruptions, limiting their frequency and increasing costs. This study explores the use of satellite imagery and convolutional neural networks (CNNs) as a non-intrusive and cost-effective alternative for classifying runway friction coefficients. A dataset of about 7,000 Google Earth images of Brazilian aerodrome runways was matched with measured friction coefficients. Three preprocessing techniques (contrast limited adaptive histogram equalization [CLAHE], Gaussian filter, and wavelet) and five CNN architectures (simple CNN, ResNet50, DenseNet121, InceptionV3, and VGG16) were evaluated. The best performance was obtained with CLAHE + Gaussian preprocessing and DenseNet121, achieving over 74% accuracy in cross-validation. External validation with unseen satellite images confirmed robustness, while tests with unmanned aerial vehicle imagery showed limited generalization across visual domains. The results indicate that deep learning combined with remote sensing can support airport pavement management. The proposed approach complements direct friction monitoring, offering a scalable, low-cost, and non-intrusive tool to identify critical areas, guide preventive maintenance, and enhance operational safety.
- 5 February 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (11) , 127-136
Satellite Eyes on Runway Safety: Predicting Airport Pavement Friction Using Convolutional Neural Networks and Image Processing
Runway safety in landing and takeoff operations is strongly influenced by skid resistance, which may be reduced by rubber buildup from aircraft braking. Conventional friction measurement methods require specialized equipment and operational interruptions, limiting their frequency and increasing costs. This study explores the use of satellite imagery and convolutional neural networks (CNNs) as a non-intrusive and cost-effective alternative for classifying runway friction coefficients. A dataset of about 7,000 Google Earth images of Brazilian aerodrome runways was matched with measured friction coefficients. Three preprocessing techniques (contrast limited adaptive histogram equalization [CLAHE], Gaussian filter, and wavelet) and five CNN architectures (simple CNN, ResNet50, DenseNet121, InceptionV3, and VGG16) were evaluated. The best performance was obtained with CLAHE + Gaussian preprocessing and DenseNet121, achieving over 74% accuracy in cross-validation. External validation with unseen satellite images confirmed robustness, while tests with unmanned aerial vehicle imagery showed limited generalization across visual domains. The results indicate that deep learning combined with remote sensing can support airport pavement management. The proposed approach complements direct friction monitoring, offering a scalable, low-cost, and non-intrusive tool to identify critical areas, guide preventive maintenance, and enhance operational safety.
- 30 January 2026
- Published by Springer Nature
- p. 555-570
Extending the Minimal Learning Machine for Classification and Regression on Interval-Valued Data
- 30 January 2026
- Published by Springer Nature
- p. 555-570
Extending the Minimal Learning Machine for Classification and Regression on Interval-Valued Data
- 30 January 2026
- Published by Springer Nature
- p. 539-554
Evaluation of Explainable Artificial Intelligence Methods for Deep Time Series Classification of Biosignals
- 30 January 2026
- Published by Springer Nature
- p. 539-554
Evaluation of Explainable Artificial Intelligence Methods for Deep Time Series Classification of Biosignals
- Open Access
- 20 January 2026
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1)
Portfolio-based Active Learning with Gaussian Processes for Vulnerabilities Risk Classification
Effective vulnerability management is essential for cybersecurity, particularly as the demand for skilled professionals often exceeds supply. This paper investigates the application of Gaussian Processes (GPs) integrated with Active Learning (AL) techniques to classify security vulnerabilities based on their risk of exploitation. The main objective is to optimize the labeling process, thereby reducing the amount of labeled data necessary for training an effective classifier. The proposed methodology combines the uncertainty predictions provided by GP models with five established data selection strategies, utilizing a portfolio-based approach. The portfolio avoids the need of choosing a single strategy and leverages the strengths of each technique. This approach enhances adaptability and balances exploration versus exploitation in complex optimization scenarios, ultimately improving the diversity of labeled samples and contributing to the development of better classifiers trained with less examples. Experiments were conducted using the CVEjoin dataset, which encompasses over 200,000 vulnerabilities, across three distinct evaluation scenarios. The different setups consider equivalent volumes of labeled data, but varying Active Learning iterations. When considering a single strategy, the results indicate that the BSB (best and second best) method consistently outperformed the others in terms of accuracy and F1 score, particularly with an increased number of labeling iterations. In the scenario where multiple strategies are used in a portfolio, the results indicate gains in all evaluation metrics. This study underscores the usefulness of a portfolio-based Active Learning approach in optimizing the labeling procedure and, ultimately, prioritizing vulnerabilities for remediation. This research lays the groundwork for extending the framework to other areas of cybersecurity, such as vulnerabilities in web applications and cloud environments, thereby improving overall security measures in the digital landscape.
- 20 January 2026
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1)
Open AccessPortfolio-based Active Learning with Gaussian Processes for Vulnerabilities Risk Classification
Effective vulnerability management is essential for cybersecurity, particularly as the demand for skilled professionals often exceeds supply. This paper investigates the application of Gaussian Processes (GPs) integrated with Active Learning (AL) techniques to classify security vulnerabilities based on their risk of exploitation. The main objective is to optimize the labeling process, thereby reducing the amount of labeled data necessary for training an effective classifier. The proposed methodology combines the uncertainty predictions provided by GP models with five established data selection strategies, utilizing a portfolio-based approach. The portfolio avoids the need of choosing a single strategy and leverages the strengths of each technique. This approach enhances adaptability and balances exploration versus exploitation in complex optimization scenarios, ultimately improving the diversity of labeled samples and contributing to the development of better classifiers trained with less examples. Experiments were conducted using the CVEjoin dataset, which encompasses over 200,000 vulnerabilities, across three distinct evaluation scenarios. The different setups consider equivalent volumes of labeled data, but varying Active Learning iterations. When considering a single strategy, the results indicate that the BSB (best and second best) method consistently outperformed the others in terms of accuracy and F1 score, particularly with an increased number of labeling iterations. In the scenario where multiple strategies are used in a portfolio, the results indicate gains in all evaluation metrics. This study underscores the usefulness of a portfolio-based Active Learning approach in optimizing the labeling procedure and, ultimately, prioritizing vulnerabilities for remediation. This research lays the groundwork for extending the framework to other areas of cybersecurity, such as vulnerabilities in web applications and cloud environments, thereby improving overall security measures in the digital landscape.
- Open Access
- 25 November 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (12) , 289
Minimal learning machine for multi-label learning
Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.
- 25 November 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (12) , 289
Open AccessMinimal learning machine for multi-label learning
Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.