Paulo Victor Ferreira de Souza
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Paulo Victor Ferreira de Souza has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Adam Santos
Federal University of Southern and Southeastern Pará (UNIFESSPA)
2 shared publications - Raimundo Matos Barros Neto
Federal University of Pará (UFPA)
2 shared publications - Angelo Ricardo Balduino
Instituto Tocantinense Presidente Antônio Carlos
1 shared publication - Carlos Renato Lisboa Francês
Federal University of Pará (UFPA)
1 shared publication - Hugo Kuribayashi
Universidade Federal do Sul e Sudeste do Pará
1 shared publication Iury Silva
Federal University of Pará (UFPA)
1 shared publication
Latest Publications
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (1) , 6-14
SMB: Web-Based Dam Monitoring and Data Analysis System
The monitoring and supervision of complex infrastructures, such as the dams and dikes of the Belo Monte Hydroelectric Plant, demand continuous data collection and analysis from various instruments (e.g., piezometers, surface markers, flow meters). In the context of structural health monitoring, recent advances propose the use of machine learning to recognize patterns and detect anomalies in monitoring data. This study presents a web-based application designed to support the early detection of structural anomalies through machine learning algorithms for anomaly detection, coupled with an interactive dashboard for data visualization. The system enables the establishment of baseline structural behavior and the identification of deviations that may indicate potential risks. Models were trained and tested with historical data, and multiple visualization tools were developed to facilitate the interpretation of results by engineers and decision-makers. The outcomes demonstrate that the proposed solution introduces innovative and effective technologies for the structural monitoring domain, contributing to the modernization of diagnostic processes and enhancing safety in critical energy infrastructure.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 24 (1) , 6-14
SMB: Web-Based Dam Monitoring and Data Analysis System
The monitoring and supervision of complex infrastructures, such as the dams and dikes of the Belo Monte Hydroelectric Plant, demand continuous data collection and analysis from various instruments (e.g., piezometers, surface markers, flow meters). In the context of structural health monitoring, recent advances propose the use of machine learning to recognize patterns and detect anomalies in monitoring data. This study presents a web-based application designed to support the early detection of structural anomalies through machine learning algorithms for anomaly detection, coupled with an interactive dashboard for data visualization. The system enables the establishment of baseline structural behavior and the identification of deviations that may indicate potential risks. Models were trained and tested with historical data, and multiple visualization tools were developed to facilitate the interpretation of results by engineers and decision-makers. The outcomes demonstrate that the proposed solution introduces innovative and effective technologies for the structural monitoring domain, contributing to the modernization of diagnostic processes and enhancing safety in critical energy infrastructure.
- 30 June 2021
- Published by Associacao Brasileira de Inteligencia Computacional - ABRICOM in Learning and Nonlinear Models
- Vol. 18 (2) , 4-15
Comparative Analysis of Convolutional Neural Networks Applied in the Detection of Pneumonia Through X-Ray Images of Children
Pneumonia is one of the most common medical problems in clinical practice and is the leading fatal infectious disease worldwide. According to the World Health Organization, pneumonia kills about 2 million children under the age of 5 and is constantly estimated to be the leading cause of infant mortality, killing more children than AIDS, malaria, and measles combined. A key element in the diagnosis is radiographic data, as chest x-rays are routinely obtained as a standard of care and can aid to differentiate the types of pneumonia. However, a rapid radiological interpretation of images is not always available, particularly in places with few resources, where childhood pneumonia has the highest incidence and mortality rates. As an alternative, the application of deep learning techniques for the classification of medical images has grown considerably in recent years. This study presents five implementations of convolutional neural networks (CNNs): ResNet50, VGG-16, InceptionV3, InceptionResNetV2, and ResNeXt50. To support the diagnosis of the disease, these CNNs were applied to solve the classification problem of medical radiographs from people with pneumonia. InceptionResNetV2 obtained the best recall and precision results for the Normal and Pneumonia classes, 93.95% and 97.52% respectively. ResNeXt50 achieved the best precision and f1-score results for the Normal class (94.62% and 94.25% respectively) and the recall and f1-score results for the Pneumonia class (97.80% and 97.65%, respectively).
- 30 June 2021
- Published by Associacao Brasileira de Inteligencia Computacional - ABRICOM in Learning and Nonlinear Models
- Vol. 18 (2) , 4-15
Comparative Analysis of Convolutional Neural Networks Applied in the Detection of Pneumonia Through X-Ray Images of Children
Pneumonia is one of the most common medical problems in clinical practice and is the leading fatal infectious disease worldwide. According to the World Health Organization, pneumonia kills about 2 million children under the age of 5 and is constantly estimated to be the leading cause of infant mortality, killing more children than AIDS, malaria, and measles combined. A key element in the diagnosis is radiographic data, as chest x-rays are routinely obtained as a standard of care and can aid to differentiate the types of pneumonia. However, a rapid radiological interpretation of images is not always available, particularly in places with few resources, where childhood pneumonia has the highest incidence and mortality rates. As an alternative, the application of deep learning techniques for the classification of medical images has grown considerably in recent years. This study presents five implementations of convolutional neural networks (CNNs): ResNet50, VGG-16, InceptionV3, InceptionResNetV2, and ResNeXt50. To support the diagnosis of the disease, these CNNs were applied to solve the classification problem of medical radiographs from people with pneumonia. InceptionResNetV2 obtained the best recall and precision results for the Normal and Pneumonia classes, 93.95% and 97.52% respectively. ResNeXt50 achieved the best precision and f1-score results for the Normal class (94.62% and 94.25% respectively) and the recall and f1-score results for the Pneumonia class (97.80% and 97.65%, respectively).
- Open Access
- 12 August 2020
- Published by Editoriales Iberoamericanos in Natural Resources
- Vol. 10 (3) , 68-76
Diagnosis of the balneability conditions of Beira Rio beach in the municipality of Porto Nacional, Tocantins
The Tocantins River has great water resources and it has been highly sought after for recreational activity, and it is highlighted for the beautiful beaches that are formed in its extension. It is important to remember that primary contact recreation and leisure activities have a specific criterion of sanitary safety for the purpose of balneability. This study evaluated the water quality of Beira Rio Beach in Porto Nacional - Tocantins. Microbiological analyses were performed using the indicators of the total coliform group and Escherichia coli (E. coli). The results of the monitoring were checked with the parameters established for balneability purposes defined by CONAMA Resolution No 274/00. The Colilert technique was used for detections and confirmatory identifications of total coliforms and E. coli. Low concentrations of E. coli were proven, which allowed the final classification in the category of 'excellent', according to CONAMA Resolution No. 274/00. Therefore, the waters of Beira Rio Beach, in the period of analysis and collection of samples, based on the indicator of bacteria of the E. coli group, were found within the accepted standards for balneability (primary contact recreation).
- 12 August 2020
- Published by Editoriales Iberoamericanos in Natural Resources
- Vol. 10 (3) , 68-76
Open AccessDiagnosis of the balneability conditions of Beira Rio beach in the municipality of Porto Nacional, Tocantins
The Tocantins River has great water resources and it has been highly sought after for recreational activity, and it is highlighted for the beautiful beaches that are formed in its extension. It is important to remember that primary contact recreation and leisure activities have a specific criterion of sanitary safety for the purpose of balneability. This study evaluated the water quality of Beira Rio Beach in Porto Nacional - Tocantins. Microbiological analyses were performed using the indicators of the total coliform group and Escherichia coli (E. coli). The results of the monitoring were checked with the parameters established for balneability purposes defined by CONAMA Resolution No 274/00. The Colilert technique was used for detections and confirmatory identifications of total coliforms and E. coli. Low concentrations of E. coli were proven, which allowed the final classification in the category of 'excellent', according to CONAMA Resolution No. 274/00. Therefore, the waters of Beira Rio Beach, in the period of analysis and collection of samples, based on the indicator of bacteria of the E. coli group, were found within the accepted standards for balneability (primary contact recreation).