Rafael Menelau Oliveira e Cruz

Rafael Menelau Oliveira e Cruz

Assistant Professor

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Post

less than 1 minute read

Published:

portfolio

publications

An ensemble classifier for offline cursive character recognition using multiple feature extraction techniques

Published in In the proceedings of The 2010 International Joint Conference on Neural Networks (IJCNN), 2010

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, George Cavalcanti, Tsang Ren, "An ensemble classifier for offline cursive character recognition using multiple feature extraction techniques." In the proceedings of The 2010 International Joint Conference on Neural Networks (IJCNN), 2010.

Handwritten digit recognition using multiple feature extraction techniques and classifier ensemble

Published in In the proceedings of 17th International conference on systems, signals and image processing, 2010

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, George Cavalcanti, Tsang Ren, "Handwritten digit recognition using multiple feature extraction techniques and classifier ensemble." In the proceedings of 17th International conference on systems, signals and image processing, 2010.

A method for dynamic ensemble selection based on a filter and an adaptive distance to improve the quality of the regions of competence

Published in In the proceedings of The 2011 International Joint Conference on Neural Networks, 2011

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, George Cavalcanti, Tsang Ren, "A method for dynamic ensemble selection based on a filter and an adaptive distance to improve the quality of the regions of competence." In the proceedings of The 2011 International Joint Conference on Neural Networks, 2011.

Analyzing dynamic ensemble selection techniques using dissimilarity analysis

Published in In the proceedings of IAPR Workshop on Artificial Neural Networks in Pattern Recognition, 2014

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, Robert Sabourin, George Cavalcanti, "Analyzing dynamic ensemble selection techniques using dissimilarity analysis." In the proceedings of IAPR Workshop on Artificial Neural Networks in Pattern Recognition, 2014.

On meta-learning for dynamic ensemble selection

Published in In the proceedings of 2014 22nd International Conference on Pattern Recognition, 2014

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, Robert Sabourin, George Cavalcanti, "On meta-learning for dynamic ensemble selection." In the proceedings of 2014 22nd International Conference on Pattern Recognition, 2014.

META-DES. H: a dynamic ensemble selection technique using meta-learning and a dynamic weighting approach

Published in In the proceedings of 2015 International Joint Conference on Neural Networks (IJCNN), 2015

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, Robert Sabourin, George Cavalcanti, "META-DES. H: a dynamic ensemble selection technique using meta-learning and a dynamic weighting approach." In the proceedings of 2015 International Joint Conference on Neural Networks (IJCNN), 2015.

Dynamic ensemble selection vs k-nn: why and when dynamic selection obtains higher classification performance?

Published in In the proceedings of 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), 2017

Use Google Scholar for full citation

Recommended citation: Rafael Cruz, Hiba Zakane, Robert Sabourin, George Cavalcanti, "Dynamic ensemble selection vs k-nn: why and when dynamic selection obtains higher classification performance?." In the proceedings of 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), 2017.

On the characterization of the oracle for dynamic classifier selection

Published in In the proceedings of 2017 International Joint Conference on Neural Networks (IJCNN), 2017

Use Google Scholar for full citation

Recommended citation: Mariana Souza, George Cavalcanti, Rafael Cruz, Robert Sabourin, "On the characterization of the oracle for dynamic classifier selection." In the proceedings of 2017 International Joint Conference on Neural Networks (IJCNN), 2017.

An ensemble generation method based on instance hardness

Published in In the proceedings of 2018 international joint conference on neural networks (IJCNN), 2018

Use Google Scholar for full citation

Recommended citation: Felipe Walmsley, George Cavalcanti, Dayvid Oliveira, Rafael Cruz, Robert Sabourin, "An ensemble generation method based on instance hardness." In the proceedings of 2018 international joint conference on neural networks (IJCNN), 2018.

K-nearest oracles borderline dynamic classifier ensemble selection

Published in In the proceedings of 2018 International Joint Conference on Neural Networks (IJCNN), 2018

Use Google Scholar for full citation

Recommended citation: Dayvid Oliveira, George Cavalcanti, Thyago Porpino, Rafael Cruz, Robert Sabourin, "K-nearest oracles borderline dynamic classifier ensemble selection." In the proceedings of 2018 International Joint Conference on Neural Networks (IJCNN), 2018.

On dissimilarity representation and transfer learning for offline handwritten signature verification

Published in In the proceedings of 2019 International Joint Conference on Neural Networks (IJCNN), 2019

Use Google Scholar for full citation

Recommended citation: Victor Souza, Adriano Oliveira, Rafael Cruz, Robert Sabourin, "On dissimilarity representation and transfer learning for offline handwritten signature verification." In the proceedings of 2019 International Joint Conference on Neural Networks (IJCNN), 2019.

On evaluating the online local pool generation method for imbalance learning

Published in In the proceedings of 2019 International Joint Conference on Neural Networks (IJCNN), 2019

Use Google Scholar for full citation

Recommended citation: Mariana Souza, George Cavalcanti, Rafael Cruz, Robert Sabourin, "On evaluating the online local pool generation method for imbalance learning." In the proceedings of 2019 International Joint Conference on Neural Networks (IJCNN), 2019.

An Investigation of Feature Selection and Transfer Learning for Writer-Independent Offline Handwritten Signature Verification

Published in In the proceedings of International Conference on Pattern Recognition (ICPR), 2020

Use Google Scholar for full citation

Recommended citation: Victor Souza, Adriano Oliveira, Rafael Cruz, Robert Sabourin, "An Investigation of Feature Selection and Transfer Learning for Writer-Independent Offline Handwritten Signature Verification." In the proceedings of International Conference on Pattern Recognition (ICPR), 2020.

Improving BPSO-based feature selection applied to offline WI handwritten signature verification through overfitting control

Published in In the proceedings of Genetic and Evolutionary Computation Conference (GECCO), 2020

Use Google Scholar for full citation

Recommended citation: Victor Souza, Adriano Oliveira, Rafael Cruz, Robert Sabourin, "Improving BPSO-based feature selection applied to offline WI handwritten signature verification through overfitting control." In the proceedings of Genetic and Evolutionary Computation Conference (GECCO), 2020.

Multi-label learning for dynamic model type recommendation

Published in In the proceedings of International Joint Conference on Neural Networks, 2020

Use Google Scholar for full citation

Recommended citation: Mariana Souza, Robert Sabourin, George Cavalcanti, Rafael Cruz, "Multi-label learning for dynamic model type recommendation." In the proceedings of International Joint Conference on Neural Networks, 2020.

Contrastive Learning of Handwritten Signature Representations for Writer-Independent Verification

Published in In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022

Use Google Scholar for full citation

Recommended citation: Talles Vianna, Victor Souza, Adriano Oliveira, Rafael MO, Robert Sabourin, "Contrastive Learning of Handwritten Signature Representations for Writer-Independent Verification." In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022.

Dynamic Ensemble Selection Using Fuzzy Hyperboxes

Published in In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022

Use Google Scholar for full citation

Recommended citation: Reza Davtalab, Rafael Cruz, Robert Sabourin, "Dynamic Ensemble Selection Using Fuzzy Hyperboxes." In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022.

Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking

Published in In the proceedings of 2022 International Joint Conference on Neural Networks (IJCNN), 2022

Use Google Scholar for full citation

Recommended citation: Madhu Kiran, Le Nguyen-Meidine, Rajat Sahay, Rafael Cruz, Louis-Antoine Blais-Morin, Eric Granger, "Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking." In the proceedings of 2022 International Joint Conference on Neural Networks (IJCNN), 2022.

Generative Target Update for Adaptive Siamese Tracking

Published in In the proceedings of International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI), 2022

Use Google Scholar for full citation

Recommended citation: Madhu Kiran, Le Nguyen-Meidine, Rajat Sahay, Rafael Cruz, Louis-Antoine Blais-Morin, Eric Granger, "Generative Target Update for Adaptive Siamese Tracking." In the proceedings of International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI), 2022.

Local overlap reduction procedure for dynamic ensemble selection

Published in In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022

Use Google Scholar for full citation

Recommended citation: Mariana Souza, Robert Sabourin, George Cavalcanti, Rafael Cruz, "Local overlap reduction procedure for dynamic ensemble selection." In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022.

talks

Dynamic Classifier Selection: Recent Advances and Perspectives

Published:

Multiple Classifier Systems (MCS) have been widely studied as an alternative for increasing accuracy in pattern recognition. One of the most promising MCS approaches is Dynamic Selection (DS), in which the base classifiers are selected on the fly, according to each new sample to be classified. DS has become an active research topic in the multiple classifier systems literature in past years. This has been due to the fact that more and more works are reporting the superior performance of such techniques over static combination approaches, especially when dealing with small sized datasets, imbalanced problems and noise distributions.

Multiple classifier systems challenges and applications (In Portuguese)

Published:

A escolha de um classificador para resolver um problema de reconhecimento de padrões é uma tarefa difícil, requerendo muita tentativa e error até conseguirmos um modelo apropriado. Mesmo assim, em muitos casos não conseguimos obter o desempenho desejado para resolver o problema utilizando apenas um único classificador. Dentro deste contexto, o uso de múltiplos classificadores é uma estratégia bastante utilizada para aumentar o desempenho de sistemas de reconhecimento de padrões. A ideia é que os erros sejam minimizados através do uso de múltiplos classificadores ao invés de um único classificador, reduzindo assim o problema de selecionar um bom modelo para resolver um problema de reconhecimento de padrões. Sistemas de múltiplos classificadores é amplemente utilizando para resolver problemas difícies como lidar com dados ruídosos, ambientes incertos pela falta de exemplos para treinamento, assim como combinar dados que vem de origens diferentes. Nesta palestra apresentarei os conceitos básicos da área de sistema de múltiplos classificadores, a intuição e os motivos pelo qual considerar uma abordagem de múltiplos classificadores para resolver diversos problemas de reconhecimento de padrões, assim como um overview de diversas aplicações que são ou que podem ser beneficiadas do uso de sistemas de múltiplos classificadores.

teaching