MSc Caio Carneloz made his Python implementation of the Particle Competition and Cooperation (PCC) model available on GitHub (pycc). Check it out if you want to use the algorithm on your data.
The MATLAB implementation is also available on GitHub, including a version with the main loop compiled in C (MEX) for faster execution.
The Particle Competiton and Cooperation original article is available here, and the accepted manuscript is available here.
Other articles and their respective implementation are available in the Publications section. If you need the code for the algorithms in other articles that are not available yet, please contact me and I’ll do my best to make it available as soon as possible.
Particle Competition and Cooperation (PCC)
Permanent link to this article: https://www.fabriciobreve.com/2019/12/05/particle-competiton-and-cooperation-pcc-python-implementation/
The paper “Auxílio no diagnóstico da doença de Alzheimer a partir de imagens de ressonância magnética utilizando competição e cooperação entre partículas” (“Diagnostic aid for Alzheimer’s disease from magnetic resonance imaging using particle competition and cooperation”) authored by Caio Oliveira Carneloz and Fabricio Aparecido Breve received the award of Best Paper presented at the IX Workshop do Programa de Pós-Graduação em Ciência da Computação da Unesp (WPPGCC 2019), which took place at Bauru-SP last week.
Congratulations Caio! Keep up with the good work!
Permanent link to this article: https://www.fabriciobreve.com/2019/09/13/best-paper-award-wppgcc2019/
Last friday, the MSc student Caio Oliveira Carneloz defended his master’s thesis entitled “Auxílio no diagnóstico da doença de Alzheimer a partir de imagens de ressonância magnética utilizando competição e cooperação entre partículas” (“Diagnostic aid for Alzheimer’s disease from magnetic resonance imaging using particle competition and cooperation”), and he was approved. Congratulations, Caio!
In his work, he presents a semi-supervised approach to classify patients with Alzheimer’s disease from brain imaging, using the particle competition and cooperation model. In order to deal with images, feature extractors from general-purpose descriptors and pre-trained deep learning networks were used. The experiments were performed using the Open Access Series of Imaging Studies (OASIS) database. To evaluate the performance of the particle competition and cooperation model, its results were compared to those achieved by the SVM, kNN, Naive Bayes, Label Propagation and Label Spreading algorithms. The results have shown that this approach is promising and behaves as expected regarding the use of labeled data, i.e., the particle competition and cooperation model needs less labeled data, as it takes advantage of its semi-supervised learning approach.
Thanks to Prof. Dr. João Roberto Bertini Júnior (UNICAMP) and Prof. Dr. Danilo Medeiros Eler (UNESP) for their participation in the examination committee, and their valuable comments and suggestions.
Permanent link to this article: https://www.fabriciobreve.com/2019/09/10/congratulations-caio/
Today, the MSc student Jefferson Antonio Ribeiro Passerini defended his master’s thesis entitled “Segmentação Interativa de Imagens usando Redes Complexas e Competição e Cooperação entre Partículas” (“Interactive Image Segmentation using Complex Networks and Particle Competition and Cooperation”), and he was approved. Congratulations, Jefferson!
In his work, he proposed some improvements on the method to build complex networks representing real-world images. These networks are fed to the particle competition and cooperation model, so it may segment the corresponding images. Jefferson’s method achieves higher accuracy and lower execution times than the original method in interactive image segmentation tasks.
Thanks to Prof. Dr. Fernando Vernal Salina (IFSP) and Prof. Dr. Eraldo Pereira Marinho (UNESP) for their participation in the examination committee, and their valuable comments and suggestions.
Permanent link to this article: https://www.fabriciobreve.com/2019/01/30/congratulations-jefferson/
The paper Interactive image segmentation using label propagation through complex networks, accepted for publication in Expert Systems with Applications, just had its final version published today.
The final version may be downloaded free of charge (no signup nor registration fees) until March, 02, through this link.
Permanent link to this article: https://www.fabriciobreve.com/2019/01/11/interactive-image-segmentation-using-label-propagation-through-complex-networks-final-version-free-access/
My paper Interactive Image Segmentation using Label Propagation through Complex Networks was accepted for publication in the international journal Expert Systems With Applications.
The accepted manuscript is available here. It should appear as an “article in proofs” on ScienceDirect within the next two weeks. The final version should appear in the journal within the next 2~3 months.
Permanent link to this article: https://www.fabriciobreve.com/2019/01/08/paper-accepted-expert-systems-with-applications/
The paper “Segmentação Interativa de Imagens usando Redes Complexas e Competição e Cooperação entre Partículas” authored by Jefferson Antonio Ribeiro Passerini and Fabricio Aparecido Breve received the award of Best Paper at the VIII Workshop do Programa de Pós-Graduação em Ciência da Computação da Unesp (WPPGCC 2018), which took place at Presidente Prudente-SP in November, 2018.
Congratulations Jefferson! Keep up with the good work!
Permanent link to this article: https://www.fabriciobreve.com/2018/12/13/best-paper-award-wppgcc2018/
INSCRIÇÕES ABERTAS ATÉ 30/11/2018
Está aberto o edital de processo seletivo para o Programa de Pós-Graduação em Ciência de Computação (PPGCC) da Universidade Estadual Paulista “Júlio de Mesquita Filho” – UNESP, Mestrado, oferecido em conjunto com o Instituto de Biociências, Letras e Ciências Exatas (São José do Rio Preto), Faculdade de Ciências (Bauru), Faculdade de Ciência e Tecnologia (Presidente Prudente) e Instituto de Geociências e Ciências Exatas (Rio Claro), para início no primeiro semestre de 2019.
As inscrições estarão abertas até o dia 30/11/2018. Mais informações em:
O PPGCC oferece curso de Mestrado em Ciência da Computação em um programa interunidades, em que aulas presenciais e por videoconferência são oferecidas nas quatro unidades que compõem o programa. Atualmente, o PPGCC conta com 29 professores que atuam nas mais variadas áreas de pesquisa, com projetos financiados por instituições públicas e privadas.
Permanent link to this article: https://www.fabriciobreve.com/2018/11/07/processo-seletivo-mestrado-em-ciencia-da-computacao-unesp/
Yesterday and today I took the exams (written exam, didactic exam and oral argument) to achieve the “Livre-Docente em Redes de Computadores” title and become a “Professor Adjunto”, which is equivalent to an “Associate Professor” in the North America system.
The examination committee was composed by Prof. Dr. Carlos Norberto Fischer, Prof. Dr. João Paulo Papa, Profª. Drª. Roseli Aparecida Francelin Romero, Prof. Dr. Renato Tinós, and Prof. Dr. Zhao Liang.
Permanent link to this article: https://www.fabriciobreve.com/2018/06/20/new-title-and-position-livre-docente-associate-professor/
MSc student Claudio Filipe Gonçalves dos Santos defended his master’s dissertation, titled “Optical Character Recognition Using Deep Learning”, yesterday. He was unanimously approved. Congratulations Claudio!
Thanks to Prof. Dr. Ricardo Cerri (UFSCar) and Prof. Dr. João Paulo Papa (UNESP) for agreeing to participate in the examination committee.
Permanent link to this article: https://www.fabriciobreve.com/2018/04/27/optical-character-recognition-using-deep-learning-masters-dissertation/