Sergio Canuto
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
Sergio Canuto has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Marcos André Gonçalves
Federal University of Minas Gerais, Belo Horizonte, Brazil
6 shared publications - Claudio Moisés Valiense de Andrade
Universidade Federal de Minas Gerais (UFMG)
4 shared publications - Felipe Viegas
UFMG
4 shared publications - Ana Claudia de Souza
Hospital Moinhos de Vento
2 shared publications - Ana Paula Beck da Silva Etges
Graduation Program in Epidemiology, Federal University of Rio Grande do Sul, Porto Alegre, Brazil
2 shared publications - Avner Dal Bosco
Pontifical Catholic University of Rio Grande do Sul, PUCRS
2 shared publications
Latest Publications
- Open Access
- 1 January 2024
- Published by FapUNIFESP (SciELO) in Matéria (Rio de Janeiro)
- Vol. 29 (4) , e20240354
Avaliação da presença de fissuras em imagens de estruturas de concreto através do uso de redes neurais profundas
RESUMO Este trabalho se insere no contexto de análise de imagens, visando a extração automática de informações complexas com alta precisão. Este estudo teve como objetivo avaliar o desempenho de redes neurais convolucionais na classificação de imagens de concreto em duas classes: (a) não fissuradas e (b) fissuradas. Para tanto, foram empregadas as redes profundas VGG16, VGG19 e ResNet50 com aprendizagem por transferência por meio de ajuste fino. As redes foram treinadas novamente e testadas usando um banco de dados de 40.000 imagens. Após o treinamento, as redes foram testadas, alcançando uma precisão impressionante entre 99,27% e 99,78%. Este alto nível de precisão inspira confiança no uso destes modelos preditivos. Para avaliar a robustez dos modelos, foram gerados gradientes visuais dos pontos focais de atenção das redes nas imagens, mostrando que os modelos focam e capturam aspectos das fotos que realmente caracterizam as fissuras. Com base nos resultados, pode-se concluir que as redes neurais convolucionais são eficazes na classificação de problemas envolvendo concreto e podem ser aplicadas em inspeções precisas para auxiliar engenheiros com alta confiabilidade quanto aos resultados.
- 1 January 2024
- Published by FapUNIFESP (SciELO) in Matéria (Rio de Janeiro)
- Vol. 29 (4) , e20240354
Open AccessAvaliação da presença de fissuras em imagens de estruturas de concreto através do uso de redes neurais profundas
RESUMO Este trabalho se insere no contexto de análise de imagens, visando a extração automática de informações complexas com alta precisão. Este estudo teve como objetivo avaliar o desempenho de redes neurais convolucionais na classificação de imagens de concreto em duas classes: (a) não fissuradas e (b) fissuradas. Para tanto, foram empregadas as redes profundas VGG16, VGG19 e ResNet50 com aprendizagem por transferência por meio de ajuste fino. As redes foram treinadas novamente e testadas usando um banco de dados de 40.000 imagens. Após o treinamento, as redes foram testadas, alcançando uma precisão impressionante entre 99,27% e 99,78%. Este alto nível de precisão inspira confiança no uso destes modelos preditivos. Para avaliar a robustez dos modelos, foram gerados gradientes visuais dos pontos focais de atenção das redes nas imagens, mostrando que os modelos focam e capturam aspectos das fotos que realmente caracterizam as fissuras. Com base nos resultados, pode-se concluir que as redes neurais convolucionais são eficazes na classificação de problemas envolvendo concreto e podem ser aplicadas em inspeções precisas para auxiliar engenheiros com alta confiabilidade quanto aos resultados.
- Open Access
- 1 January 2024
- Published by Sociedade Brasileira de Computação in Journal on Interactive Systems
- Vol. 15 (1) , 561-575
Pipelining Semantic Expansion and Noise Filtering for Sentiment Analysis of Short Documents – CluSent Method
The challenge of constructing effective sentiment models is exacerbated by a lack of sufficient information, particularly in short texts. Enhancing short texts with semantic relationships becomes crucial for capturing affective nuances and improving model efficacy, albeit with the potential drawback of introducing noise. This article introduces a novel approach, CluSent, designed for customized dataset-oriented sentiment analysis. CluSent capitalizes on the CluWords concept, a proposed powerful representation of semantically related words. To address the issues of information scarcity and noise, CluSent addresses these challenges: (i) leveraging the semantic neighborhood of pre-trained word embedding representations to enrich document representation and (ii) introducing dataset-specific filtering and weighting mechanisms to manage noise. These mechanisms utilize part-of-speech and polarity/intensity information from lexicons. In an extensive experimental evaluation spanning 19 datasets and five state-of-the-art baselines, including modern transformer architectures, CluSent emerged as the superior method in the majority of scenarios (28 out of 38 possibilities), demonstrating noteworthy performance gains of up to 14% over the strongest baselines.
- 1 January 2024
- Published by Sociedade Brasileira de Computação in Journal on Interactive Systems
- Vol. 15 (1) , 561-575
Open AccessPipelining Semantic Expansion and Noise Filtering for Sentiment Analysis of Short Documents – CluSent Method
The challenge of constructing effective sentiment models is exacerbated by a lack of sufficient information, particularly in short texts. Enhancing short texts with semantic relationships becomes crucial for capturing affective nuances and improving model efficacy, albeit with the potential drawback of introducing noise. This article introduces a novel approach, CluSent, designed for customized dataset-oriented sentiment analysis. CluSent capitalizes on the CluWords concept, a proposed powerful representation of semantically related words. To address the issues of information scarcity and noise, CluSent addresses these challenges: (i) leveraging the semantic neighborhood of pre-trained word embedding representations to enrich document representation and (ii) introducing dataset-specific filtering and weighting mechanisms to manage noise. These mechanisms utilize part-of-speech and polarity/intensity information from lexicons. In an extensive experimental evaluation spanning 19 datasets and five state-of-the-art baselines, including modern transformer architectures, CluSent emerged as the superior method in the majority of scenarios (28 out of 38 possibilities), demonstrating noteworthy performance gains of up to 14% over the strongest baselines.
- Open Access
- 23 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 110-118
CluSent – Combining Semantic Expansion and De-Noising for Dataset-Oriented Sentiment Analysis of Short Texts
- 23 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 110-118
Open AccessCluSent – Combining Semantic Expansion and De-Noising for Dataset-Oriented Sentiment Analysis of Short Texts
- Open Access
- 1 November 2021
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 9 (11) , e29120
Stroke Outcome Measurements From Electronic Medical Records: Cross-sectional Study on the Effectiveness of Neural and Nonneural Classifiers
Background: With the rapid adoption of electronic medical records (EMRs), there is an ever-increasing opportunity to collect data and extract knowledge from EMRs to support patient-centered stroke management. Objective: This study aims to compare the effectiveness of state-of-the-art automatic text classification methods in classifying data to support the prediction of clinical patient outcomes and the extraction of patient characteristics from EMRs. Methods: Our study addressed the computational problems of information extraction and automatic text classification. We identified essential tasks to be considered in an ischemic stroke value-based program. The 30 selected tasks were classified (manually labeled by specialists) according to the following value agenda: tier 1 (achieved health care status), tier 2 (recovery process), care related (clinical management and risk scores), and baseline characteristics. The analyzed data set was retrospectively extracted from the EMRs of patients with stroke from a private Brazilian hospital between 2018 and 2019. A total of 44,206 sentences from free-text medical records in Portuguese were used to train and develop 10 supervised computational machine learning methods, including state-of-the-art neural and nonneural methods, along with ontological rules. As an experimental protocol, we used a 5-fold cross-validation procedure repeated 6 times, along with subject-wise sampling. A heatmap was used to display comparative result analyses according to the best algorithmic effectiveness (F1 score), supported by statistical significance tests. A feature importance analysis was conducted to provide insights into the results. Results: The top-performing models were support vector machines trained with lexical and semantic textual features, showing the importance of dealing with noise in EMR textual representations. The support vector machine models produced statistically superior results in 71% (17/24) of tasks, with an F1 score >80% regarding care-related tasks (patient treatment location, fall risk, thrombolytic therapy, and pressure ulcer risk), the process of recovery (ability to feed orally or ambulate and communicate), health care status achieved (mortality), and baseline characteristics (diabetes, obesity, dyslipidemia, and smoking status). Neural methods were largely outperformed by more traditional nonneural methods, given the characteristics of the data set. Ontological rules were also effective in tasks such as baseline characteristics (alcoholism, atrial fibrillation, and coronary artery disease) and the Rankin scale. The complementarity in effectiveness among models suggests that a combination of models could enhance the results and cover more tasks in the future. Conclusions: Advances in information technology capacity are essential for scalability and agility in measuring health status outcomes. This study allowed us to measure effectiveness and identify opportunities for automating the classification of outcomes of specific tasks related to clinical conditions of stroke victims, and thus ultimately assess the possibility of proactively using these machine learning techniques in real-world situations.
- 1 November 2021
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 9 (11) , e29120
Open AccessStroke Outcome Measurements From Electronic Medical Records: Cross-sectional Study on the Effectiveness of Neural and Nonneural Classifiers
Background: With the rapid adoption of electronic medical records (EMRs), there is an ever-increasing opportunity to collect data and extract knowledge from EMRs to support patient-centered stroke management. Objective: This study aims to compare the effectiveness of state-of-the-art automatic text classification methods in classifying data to support the prediction of clinical patient outcomes and the extraction of patient characteristics from EMRs. Methods: Our study addressed the computational problems of information extraction and automatic text classification. We identified essential tasks to be considered in an ischemic stroke value-based program. The 30 selected tasks were classified (manually labeled by specialists) according to the following value agenda: tier 1 (achieved health care status), tier 2 (recovery process), care related (clinical management and risk scores), and baseline characteristics. The analyzed data set was retrospectively extracted from the EMRs of patients with stroke from a private Brazilian hospital between 2018 and 2019. A total of 44,206 sentences from free-text medical records in Portuguese were used to train and develop 10 supervised computational machine learning methods, including state-of-the-art neural and nonneural methods, along with ontological rules. As an experimental protocol, we used a 5-fold cross-validation procedure repeated 6 times, along with subject-wise sampling. A heatmap was used to display comparative result analyses according to the best algorithmic effectiveness (F1 score), supported by statistical significance tests. A feature importance analysis was conducted to provide insights into the results. Results: The top-performing models were support vector machines trained with lexical and semantic textual features, showing the importance of dealing with noise in EMR textual representations. The support vector machine models produced statistically superior results in 71% (17/24) of tasks, with an F1 score >80% regarding care-related tasks (patient treatment location, fall risk, thrombolytic therapy, and pressure ulcer risk), the process of recovery (ability to feed orally or ambulate and communicate), health care status achieved (mortality), and baseline characteristics (diabetes, obesity, dyslipidemia, and smoking status). Neural methods were largely outperformed by more traditional nonneural methods, given the characteristics of the data set. Ontological rules were also effective in tasks such as baseline characteristics (alcoholism, atrial fibrillation, and coronary artery disease) and the Rankin scale. The complementarity in effectiveness among models suggests that a combination of models could enhance the results and cover more tasks in the future. Conclusions: Advances in information technology capacity are essential for scalability and agility in measuring health status outcomes. This study allowed us to measure effectiveness and identify opportunities for automating the classification of outcomes of specific tasks related to clinical conditions of stroke victims, and thus ultimately assess the possibility of proactively using these machine learning techniques in real-world situations.
- Open Access
- 29 March 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Stroke Outcome Measurements From Electronic Medical Records: Cross-sectional Study on the Effectiveness of Neural and Nonneural Classifiers (Preprint)
BACKGROUND With the rapid adoption of electronic medical records (EMRs), there is an ever-increasing opportunity to collect data and extract knowledge from EMRs to support patient-centered stroke management. OBJECTIVE This study aims to compare the effectiveness of state-of-the-art automatic text classification methods in classifying data to support the prediction of clinical patient outcomes and the extraction of patient characteristics from EMRs. METHODS Our study addressed the computational problems of information extraction and automatic text classification. We identified essential tasks to be considered in an ischemic stroke value-based program. The 30 selected tasks were classified (manually labeled by specialists) according to the following value agenda: tier 1 (achieved health care status), tier 2 (recovery process), care related (clinical management and risk scores), and baseline characteristics. The analyzed data set was retrospectively extracted from the EMRs of patients with stroke from a private Brazilian hospital between 2018 and 2019. A total of 44,206 sentences from free-text medical records in Portuguese were used to train and develop 10 supervised computational machine learning methods, including state-of-the-art neural and nonneural methods, along with ontological rules. As an experimental protocol, we used a 5-fold cross-validation procedure repeated 6 times, along with subject-wise sampling. A heatmap was used to display comparative result analyses according to the best algorithmic effectiveness (F1 score), supported by statistical significance tests. A feature importance analysis was conducted to provide insights into the results. RESULTS The top-performing models were support vector machines trained with lexical and semantic textual features, showing the importance of dealing with noise in EMR textual representations. The support vector machine models produced statistically superior results in 71% (17/24) of tasks, with an F1 score >80% regarding care-related tasks (patient treatment location, fall risk, thrombolytic therapy, and pressure ulcer risk), the process of recovery (ability to feed orally or ambulate and communicate), health care status achieved (mortality), and baseline characteristics (diabetes, obesity, dyslipidemia, and smoking status). Neural methods were largely outperformed by more traditional nonneural methods, given the characteristics of the data set. Ontological rules were also effective in tasks such as baseline characteristics (alcoholism, atrial fibrillation, and coronary artery disease) and the Rankin scale. The complementarity in effectiveness among models suggests that a combination of models could enhance the results and cover more tasks in the future. CONCLUSIONS Advances in information technology capacity are essential for scalability and agility in measuring health status outcomes. This study allowed us to measure effectiveness and identify opportunities for automating the classification of outcomes of specific tasks related to clinical conditions of stroke victims, and thus ultimately assess the possibility of proactively using these machine learning techniques in real-world situations.
- 29 March 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessStroke Outcome Measurements From Electronic Medical Records: Cross-sectional Study on the Effectiveness of Neural and Nonneural Classifiers (Preprint)
BACKGROUND With the rapid adoption of electronic medical records (EMRs), there is an ever-increasing opportunity to collect data and extract knowledge from EMRs to support patient-centered stroke management. OBJECTIVE This study aims to compare the effectiveness of state-of-the-art automatic text classification methods in classifying data to support the prediction of clinical patient outcomes and the extraction of patient characteristics from EMRs. METHODS Our study addressed the computational problems of information extraction and automatic text classification. We identified essential tasks to be considered in an ischemic stroke value-based program. The 30 selected tasks were classified (manually labeled by specialists) according to the following value agenda: tier 1 (achieved health care status), tier 2 (recovery process), care related (clinical management and risk scores), and baseline characteristics. The analyzed data set was retrospectively extracted from the EMRs of patients with stroke from a private Brazilian hospital between 2018 and 2019. A total of 44,206 sentences from free-text medical records in Portuguese were used to train and develop 10 supervised computational machine learning methods, including state-of-the-art neural and nonneural methods, along with ontological rules. As an experimental protocol, we used a 5-fold cross-validation procedure repeated 6 times, along with subject-wise sampling. A heatmap was used to display comparative result analyses according to the best algorithmic effectiveness (F1 score), supported by statistical significance tests. A feature importance analysis was conducted to provide insights into the results. RESULTS The top-performing models were support vector machines trained with lexical and semantic textual features, showing the importance of dealing with noise in EMR textual representations. The support vector machine models produced statistically superior results in 71% (17/24) of tasks, with an F1 score >80% regarding care-related tasks (patient treatment location, fall risk, thrombolytic therapy, and pressure ulcer risk), the process of recovery (ability to feed orally or ambulate and communicate), health care status achieved (mortality), and baseline characteristics (diabetes, obesity, dyslipidemia, and smoking status). Neural methods were largely outperformed by more traditional nonneural methods, given the characteristics of the data set. Ontological rules were also effective in tasks such as baseline characteristics (alcoholism, atrial fibrillation, and coronary artery disease) and the Rankin scale. The complementarity in effectiveness among models suggests that a combination of models could enhance the results and cover more tasks in the future. CONCLUSIONS Advances in information technology capacity are essential for scalability and agility in measuring health status outcomes. This study allowed us to measure effectiveness and identify opportunities for automating the classification of outcomes of specific tasks related to clinical conditions of stroke victims, and thus ultimately assess the possibility of proactively using these machine learning techniques in real-world situations.
- 1 October 2019
- Published by Elsevier in Expert Systems with Applications
- Vol. 132, 226-238
Quality assessment of collaboratively-created web content with no manual intervention based on soft multi-view generation
- 1 October 2019
- Published by Elsevier in Expert Systems with Applications
- Vol. 132, 226-238
Quality assessment of collaboratively-created web content with no manual intervention based on soft multi-view generation
- Open Access
- 8 February 2016
- Published by Association for Computing Machinery (ACM)
- p. 53-62
Exploiting New Sentiment-Based Meta-level Features for Effective Sentiment Analysis
In this paper we address the problem of automatically learning to classify the sentiment of short messages/reviews by exploiting information derived from meta-level features i.e., features derived primarily from the original bag-of-words representation. We propose new meta-level features especially designed for the sentiment analysis of short messages such as: (i) information derived from the sentiment distribution among the k nearest neighbors of a given short test document x, (ii) the distribution of distances of x to their neighbors and (iii) the document polarity of these neighbors given by unsupervised lexical-based methods. Our approach is also capable of exploiting information from the neighborhood of document x regarding (highly noisy) data obtained from 1.6 million Twitter messages with emoticons. The set of proposed features is capable of transforming the original feature space into a new one, potentially smaller and more informed. Experiments performed with a substantial number of datasets (nineteen) demonstrate that the effectiveness of the proposed sentiment-based meta-level features is not only superior to the traditional bag-of-word representation (by up to 16%) but is also superior in most cases to state-of-art meta-level features previously proposed in the literature for text classification tasks that do not take into account some idiosyncrasies of sentiment analysis. Our proposal is also largely superior to the best lexicon-based methods as well as to supervised combinations of them. In fact, the proposed approach is the only one to produce the best results in all tested datasets in all scenarios.
- 8 February 2016
- Published by Association for Computing Machinery (ACM)
- p. 53-62
Open AccessExploiting New Sentiment-Based Meta-level Features for Effective Sentiment Analysis
In this paper we address the problem of automatically learning to classify the sentiment of short messages/reviews by exploiting information derived from meta-level features i.e., features derived primarily from the original bag-of-words representation. We propose new meta-level features especially designed for the sentiment analysis of short messages such as: (i) information derived from the sentiment distribution among the k nearest neighbors of a given short test document x, (ii) the distribution of distances of x to their neighbors and (iii) the document polarity of these neighbors given by unsupervised lexical-based methods. Our approach is also capable of exploiting information from the neighborhood of document x regarding (highly noisy) data obtained from 1.6 million Twitter messages with emoticons. The set of proposed features is capable of transforming the original feature space into a new one, potentially smaller and more informed. Experiments performed with a substantial number of datasets (nineteen) demonstrate that the effectiveness of the proposed sentiment-based meta-level features is not only superior to the traditional bag-of-word representation (by up to 16%) but is also superior in most cases to state-of-art meta-level features previously proposed in the literature for text classification tasks that do not take into account some idiosyncrasies of sentiment analysis. Our proposal is also largely superior to the best lexicon-based methods as well as to supervised combinations of them. In fact, the proposed approach is the only one to produce the best results in all tested datasets in all scenarios.