Regina Serrão Lanzillotti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Regina Serrão Lanzillotti has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Cristiane Oliveira Faria
Universidade do Estado do Rio de Janeiro (UERJ)
3 shared publications - Pedro Henrique Alves Barros3 shared publications
- Alesson M. Torres
Department of Informatics and Computer Science, Rio de Janeiro State University, Rio de Janeiro, Rio de Janeiro, Brazil
1 shared publication - Andres Giraldo Morales
Department of Informatics and Computer Science, Rio de Janeiro State University, Rio de Janeiro, Rio de Janeiro, Brazil
1 shared publication - Augusto Magalhães Pinto de Mendonça1 shared publication
- Carla Cristina P. Cruz
Department of Informatics and Computer Science, Rio de Janeiro State University, Rio de Janeiro, Rio de Janeiro, Brazil
1 shared publication
Latest Publications
- Open Access
- 2 June 2025
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 18 (6) , e18921
Segmentação de imagens ambientais com algoritmos fuzzy: comparando precisão e eficiência
A intensificação de desastres ambientais ressalta a necessidade de soluções computacionais eficazes para a análise automatizada de imagens em cenários marcados por incerteza. Nesse contexto, algoritmos baseados em LF oferecem recursos promissores para a segmentação de imagens com alta ambiguidade visual e este artigo objetiva comparar o desempenho dos algoritmos Fuzzy C-Means (FCM) e Fuzzy Intuicionista C-Means (FICM) quanto à eficiência na segmentação de imagens ambientais que foram extraídas de uma base pública de dados disponibilizada na plataforma Kaggle com registros visuais de diferentes tipos de desastres. Os algoritmos foram aplicados nos espaços de cor RGB, HSV e CIELAB, e avaliados por meio das métricas de distância Euclidiana, Manhattan, Cosseno e Mahalanobis. A metodologia incluiu a implementação em Python em bibliotecas como NumPy, Pandas e Scikit-learn. Os resultados revelaram que o FICM obteve desempenho superior ao FCM em termos de precisão, especialmente em ambientes de baixa definição, embora com maior custo computacional. Conclui-se que o FICM representa uma estratégia eficaz para a detecção automatizada de regiões críticas para contribuir o aprimoramento de ferramentas de apoio à gestão de riscos e resposta a desastres ambientais.,
- 2 June 2025
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 18 (6) , e18921
Open AccessSegmentação de imagens ambientais com algoritmos fuzzy: comparando precisão e eficiência
A intensificação de desastres ambientais ressalta a necessidade de soluções computacionais eficazes para a análise automatizada de imagens em cenários marcados por incerteza. Nesse contexto, algoritmos baseados em LF oferecem recursos promissores para a segmentação de imagens com alta ambiguidade visual e este artigo objetiva comparar o desempenho dos algoritmos Fuzzy C-Means (FCM) e Fuzzy Intuicionista C-Means (FICM) quanto à eficiência na segmentação de imagens ambientais que foram extraídas de uma base pública de dados disponibilizada na plataforma Kaggle com registros visuais de diferentes tipos de desastres. Os algoritmos foram aplicados nos espaços de cor RGB, HSV e CIELAB, e avaliados por meio das métricas de distância Euclidiana, Manhattan, Cosseno e Mahalanobis. A metodologia incluiu a implementação em Python em bibliotecas como NumPy, Pandas e Scikit-learn. Os resultados revelaram que o FICM obteve desempenho superior ao FCM em termos de precisão, especialmente em ambientes de baixa definição, embora com maior custo computacional. Conclui-se que o FICM representa uma estratégia eficaz para a detecção automatizada de regiões críticas para contribuir o aprimoramento de ferramentas de apoio à gestão de riscos e resposta a desastres ambientais.,
- Open Access
- 2 June 2025
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 18 (6) , e18672
Detecção de inundação na vizinhança de Porto Alegre via abordagem adaptativa do método de Otsu
Os desastres ambientais complicam a gestão em função de fatores coadjuvantes como crescimento desordenado industrial, aumento da poluição, efeito estufa, alterações nas taxas de salubridades, natalidade de espécies, destruição da camada de ozônio pela chuva ácida, toxicidade e enchentes afetam o planeta e reduz a longevidade humana. A motivação desta proposta foi monitorar desastres ambientais durante o período de março a junho de 2024 na região metropolitana do Rio Grande do Sul. Este estudo apresenta uma nova abordagem para interpretação de imagens de satélite de inundações com o uso do método de limiarização de Otsu e posteriormente a aplicação do modelo de regressão linear para discriminar elementos da imagem. Este método fornece resultados de segmentação mais específicos, permitindo uma melhor análise da extensão das inundações e da provável recuperação da vegetação. Os resultados mostram o potencial da abordagem na ocorrência de desastres ambientais e possíveis tomadas de decisão de gestão.
- 2 June 2025
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 18 (6) , e18672
Open AccessDetecção de inundação na vizinhança de Porto Alegre via abordagem adaptativa do método de Otsu
Os desastres ambientais complicam a gestão em função de fatores coadjuvantes como crescimento desordenado industrial, aumento da poluição, efeito estufa, alterações nas taxas de salubridades, natalidade de espécies, destruição da camada de ozônio pela chuva ácida, toxicidade e enchentes afetam o planeta e reduz a longevidade humana. A motivação desta proposta foi monitorar desastres ambientais durante o período de março a junho de 2024 na região metropolitana do Rio Grande do Sul. Este estudo apresenta uma nova abordagem para interpretação de imagens de satélite de inundações com o uso do método de limiarização de Otsu e posteriormente a aplicação do modelo de regressão linear para discriminar elementos da imagem. Este método fornece resultados de segmentação mais específicos, permitindo uma melhor análise da extensão das inundações e da provável recuperação da vegetação. Os resultados mostram o potencial da abordagem na ocorrência de desastres ambientais e possíveis tomadas de decisão de gestão.
- Open Access
- 14 October 2024
- Published by Seven Events
- p. 1-16
DIAGNÓSTICO DA QUALIDADE DA EDUCAÇÃO BÁSICA BRASILEIRA NAS REDES MUNICIPAIS
A motivação pontua a educação básica brasileira nas redes municipais, Saeb (2021). Objetiva-se verificar a proficiência dos valores médios em Matemática, Língua Portuguesa e Taxa de Alfabetização, entre estados nas escolas municipais e privadas, para capital e interior. Calculou-se a média, moda e mediana para avaliar simetria, curtose e coeficiente de variação, tendo o histograma para visualização gráfica. As covariâncias para pares de disciplinas foram obtidas em relação às autarquias e regionalidades tanto na capital quanto interior. O teste de igualdade de covariância aferiu a similaridade no desempenho das disciplinas. O gráfico de dispersão entre Distâncias Euclidiana e Mahalanobis para a Taxa de Alfabetização por estado, mostrou sensibilidade que as regiões Sudeste e Centro Oeste.
- 14 October 2024
- Published by Seven Events
- p. 1-16
Open AccessDIAGNÓSTICO DA QUALIDADE DA EDUCAÇÃO BÁSICA BRASILEIRA NAS REDES MUNICIPAIS
A motivação pontua a educação básica brasileira nas redes municipais, Saeb (2021). Objetiva-se verificar a proficiência dos valores médios em Matemática, Língua Portuguesa e Taxa de Alfabetização, entre estados nas escolas municipais e privadas, para capital e interior. Calculou-se a média, moda e mediana para avaliar simetria, curtose e coeficiente de variação, tendo o histograma para visualização gráfica. As covariâncias para pares de disciplinas foram obtidas em relação às autarquias e regionalidades tanto na capital quanto interior. O teste de igualdade de covariância aferiu a similaridade no desempenho das disciplinas. O gráfico de dispersão entre Distâncias Euclidiana e Mahalanobis para a Taxa de Alfabetização por estado, mostrou sensibilidade que as regiões Sudeste e Centro Oeste.
- Open Access
- 30 September 2024
- Published by Seven Events in ARACÊ
- Vol. 6 (2) , 487-501
DIAGNOSIS OF THE QUALITY OF BRAZILIAN BASIC EDUCATION IN MUNICIPAL NETWORKS
Motivation punctuates Brazilian basic education in municipal networks, Saeb (2021). The objective is to verify the proficiency of the average values in Mathematics, Portuguese Language and Literacy Rate, between states in municipal and private schools, for the capital and interior. The mean, mode, and median were calculated to evaluate symmetry, kurtosis, and coefficient of variation, with the histogram for graphical visualization. Covariances for pairs of disciplines were obtained in relation to autarchies and regionalities both in the capital and in the interior. The test of equality of covariance measured the similarity in the performance of the disciplines. The scatter plot between Euclidean and Mahalanobis Distances for the Literacy Rate by state showed sensitivity that the Southeast and Midwest regions.
- 30 September 2024
- Published by Seven Events in ARACÊ
- Vol. 6 (2) , 487-501
Open AccessDIAGNOSIS OF THE QUALITY OF BRAZILIAN BASIC EDUCATION IN MUNICIPAL NETWORKS
Motivation punctuates Brazilian basic education in municipal networks, Saeb (2021). The objective is to verify the proficiency of the average values in Mathematics, Portuguese Language and Literacy Rate, between states in municipal and private schools, for the capital and interior. The mean, mode, and median were calculated to evaluate symmetry, kurtosis, and coefficient of variation, with the histogram for graphical visualization. Covariances for pairs of disciplines were obtained in relation to autarchies and regionalities both in the capital and in the interior. The test of equality of covariance measured the similarity in the performance of the disciplines. The scatter plot between Euclidean and Mahalanobis Distances for the Literacy Rate by state showed sensitivity that the Southeast and Midwest regions.
- Open Access
- 16 August 2024
- Published by Seven Events
- p. 276-287
Analysis of student performance using the Fuzzy intuitionist model
In the Public Education Network, the Mathematics teacher from the 6th to the 9th grade is faced with the abyss between pedagogical planning and learning. Evaluations plus bonuses for complementary activities can be considered extra-class excesses, as they generate unrealistic results for the education system. The Fuzzy Intuitionist modeling allows the recognition of patterns for the evaluation of learning using degrees of pertinence and non-pertinence as a function of the results of the three mandatory measurements in the course. Personalized assessment would be more coherent with the student's profile, combating the discouragement generated to ''school failure'', formative assessments are suggested, which can provide the student with greater feedback, directing him to structured knowledge. It is vital to help a teacher feel good about himself and his performance, not minimizing the emotional balance and psychological resilience to live with the stress generated by the current building and educational conditions, avoiding psychosomatic effects. In this domain, it is essential that pedagogical processes are in an appropriate position to contribute to functional learning, that is, skills (activities) that encompass self-care, hygiene habits, school attendance, commitment to tasks and interpersonal interaction.
- 16 August 2024
- Published by Seven Events
- p. 276-287
Open AccessAnalysis of student performance using the Fuzzy intuitionist model
In the Public Education Network, the Mathematics teacher from the 6th to the 9th grade is faced with the abyss between pedagogical planning and learning. Evaluations plus bonuses for complementary activities can be considered extra-class excesses, as they generate unrealistic results for the education system. The Fuzzy Intuitionist modeling allows the recognition of patterns for the evaluation of learning using degrees of pertinence and non-pertinence as a function of the results of the three mandatory measurements in the course. Personalized assessment would be more coherent with the student's profile, combating the discouragement generated to ''school failure'', formative assessments are suggested, which can provide the student with greater feedback, directing him to structured knowledge. It is vital to help a teacher feel good about himself and his performance, not minimizing the emotional balance and psychological resilience to live with the stress generated by the current building and educational conditions, avoiding psychosomatic effects. In this domain, it is essential that pedagogical processes are in an appropriate position to contribute to functional learning, that is, skills (activities) that encompass self-care, hygiene habits, school attendance, commitment to tasks and interpersonal interaction.
- Open Access
- 1 February 2024
- Published by Brazilian Journals in OBSERVATÓRIO DE LA ECONOMÍA LATINOAMERICANA
- Vol. 22 (2) , e3216
Analysis of a portfolio selection model at three-moments
This work performs a numerical simulation for an investment portfolio selection model that considers the three first moments of asset returns distribution – mean return, variance, and skewness. The application of the model, based on data collected on the platform of a Brazilian stockbroker, allowed obtaining portfolios of maximum skewness for fixed values of expected return and weighted variance of the portfolio. The results are analyzed and presented graphically, giving rise to an optimal surface for triples of moments associated with portfolios of maximum skewness. Furthermore, this experiment allowed us to confirm the relevance of considering higher-order moments in the selection of investment portfolios and verifying the efficiency of the Three-Moments model, having as reference the Markowitz solution in his Mean-Variance model.
- 1 February 2024
- Published by Brazilian Journals in OBSERVATÓRIO DE LA ECONOMÍA LATINOAMERICANA
- Vol. 22 (2) , e3216
Open AccessAnalysis of a portfolio selection model at three-moments
This work performs a numerical simulation for an investment portfolio selection model that considers the three first moments of asset returns distribution – mean return, variance, and skewness. The application of the model, based on data collected on the platform of a Brazilian stockbroker, allowed obtaining portfolios of maximum skewness for fixed values of expected return and weighted variance of the portfolio. The results are analyzed and presented graphically, giving rise to an optimal surface for triples of moments associated with portfolios of maximum skewness. Furthermore, this experiment allowed us to confirm the relevance of considering higher-order moments in the selection of investment portfolios and verifying the efficiency of the Three-Moments model, having as reference the Markowitz solution in his Mean-Variance model.
- Open Access
- 7 May 2023
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 16 (1) , 1-24
Machine Learning Applied to COVID-19: A Review of the Initial Pandemic Period
Diagnostic and decision-making processes in the 2019 Coronavirus treatment have combined new standards using patient chest images, clinical and laboratory data. This work presents a systematic review aimed at studying the Artificial Intelligence (AI) approaches to the patients’ diagnosis or evolution with Coronavirus 2019. Five electronic databases were searched, from December 2019 to October 2020, considering the beginning of the pandemic when there was no vaccine influencing the exploration of Artificial Intelligence-based techniques. The first search collected 839 papers. Next, the abstracts were reviewed, and 138 remained after the inclusion/exclusion criteria was performed. After thorough reading and review by a second group of reviewers, 64 met the study objectives. These papers were carefully analyzed to identify the AI techniques used to interpret the images, clinical and laboratory data, considering a distribution regarding two variables: (i) diagnosis or outcome and (ii) the type of data: clinical, laboratory, or imaging (chest computed tomography, chest X-ray, or ultrasound). The data type most used was chest CT scans, followed by chest X-ray. The chest CT scan was the only data type that was used for diagnosis, outcome, or both. A few works combine Clinical and Laboratory data, and the most used laboratory tests were C-reactive protein. AI techniques have been increasingly explored in medical image annotation to overcome the need for specialized manual work. In this context, 25 machine learning (ML) techniques with a highest frequency of usage were identified, ranging from the most classic ones, such as Logistic Regression, to the most current ones, such as those that explore Deep Learning. Most imaging works explored convolutional neural networks (CNN), such as VGG and Resnet. Then transfer learning which stands out among the techniques related to deep learning has the second highest frequency of use. In general, classification tasks adopted two or three datasets. COVID-19 related data is present in all papers, while pneumonia is the most common non-COVID-19 class among them.
- 7 May 2023
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 16 (1) , 1-24
Open AccessMachine Learning Applied to COVID-19: A Review of the Initial Pandemic Period
Diagnostic and decision-making processes in the 2019 Coronavirus treatment have combined new standards using patient chest images, clinical and laboratory data. This work presents a systematic review aimed at studying the Artificial Intelligence (AI) approaches to the patients’ diagnosis or evolution with Coronavirus 2019. Five electronic databases were searched, from December 2019 to October 2020, considering the beginning of the pandemic when there was no vaccine influencing the exploration of Artificial Intelligence-based techniques. The first search collected 839 papers. Next, the abstracts were reviewed, and 138 remained after the inclusion/exclusion criteria was performed. After thorough reading and review by a second group of reviewers, 64 met the study objectives. These papers were carefully analyzed to identify the AI techniques used to interpret the images, clinical and laboratory data, considering a distribution regarding two variables: (i) diagnosis or outcome and (ii) the type of data: clinical, laboratory, or imaging (chest computed tomography, chest X-ray, or ultrasound). The data type most used was chest CT scans, followed by chest X-ray. The chest CT scan was the only data type that was used for diagnosis, outcome, or both. A few works combine Clinical and Laboratory data, and the most used laboratory tests were C-reactive protein. AI techniques have been increasingly explored in medical image annotation to overcome the need for specialized manual work. In this context, 25 machine learning (ML) techniques with a highest frequency of usage were identified, ranging from the most classic ones, such as Logistic Regression, to the most current ones, such as those that explore Deep Learning. Most imaging works explored convolutional neural networks (CNN), such as VGG and Resnet. Then transfer learning which stands out among the techniques related to deep learning has the second highest frequency of use. In general, classification tasks adopted two or three datasets. COVID-19 related data is present in all papers, while pneumonia is the most common non-COVID-19 class among them.