Uso de Rede Neural Percéptron Multi-Camadas na Classificação de Patologias Cardíacas
DOI:
https://doi.org/10.5540/tema.2008.09.02.0255Abstract
As doenças cardiovasculares têm sido a maior causa de morte por doença em todo o território nacional. Atualmente, uma das grandes aliadas para a realização de estudo da fisiopatologia de sistemas biológicos no campo das doenças do coração é a técnica conhecida como Variabilidade da Freqüência Cardíaca (HRV). Porém, a HRV apresenta comportamento complexo, o que dificulta a identificação de padrões de doenças específicas. Neste trabalho, utilizamos como diagnóstico dos dados de HRV medidas de complexidade determinadas por meio da Análise de Quantificação de Recorrências (RQA). A classificação dos dados em grupos de patologias é realizada com o uso de redes neurais artificiais do tipo Percéptron de Múltiplas Camadas (MLP). Apresentamos, também, uma discussão sobre as formas e estruturas das redes neurais necessárias para a classificação destes dados.References
[1] G.S. Everton, “Caracteriza¸c˜ao de Sistemas Dinˆamicos Atrav´es de Gr´aficos de Recorrˆencia”, Disserta¸c˜ao de mestrado, UFPR, 2008.
A.C. Guyton, J.E. Hall, “Fisiologia Humana e Mecanismos das Doen¸cas”, Ed. Guanabara Koogan, 1998.
S. Haykin, “Redes Neurais: Princ´ıpios e Pr´atica”, Bookman, 2001.
N. Marwan, N. Wessel, U. Meyerfeldt, A. Schirdewan, J. Kurths, Recurrence plot based measures of complexity and its application to heart rate variability data, Phys. Rev. E, 66, No. 2 (2002), 0267-0282.
N. Marwan et al., Recurrence plots for the analysis of complex systems, Physics Reports, 438, (2007), 237-329.
U. Rajendra Acharay et al., Heart rate variability: a review, Med. Bio. Eng. Comput., 44 (2006), 1031-1051.
C.L. Webber Jr., J.P. Zbilut, Dynamical assessment of physiological systems and states using recurrence plot strategies, J. Appl. Physiol., 76, No. 2 (1994), 965-973.
J.P. Zbilut, C.L. Webber Jr., Embeddings and delays as derived from quantification of recurrence plots, Phys. Lett. A, 171, No. 3-4 (1992), 199-203.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish in this journal agree to the following terms:
Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License that allows the sharing of the work with acknowledgment of authorship and initial publication in this journal.
Authors are authorized to assume additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, publish in an institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
Authors are allowed and encouraged to publish and distribute their work online (eg, in institutional repositories or on their personal page) at any point before or during the editorial process, as this can generate productive changes as well as increase impact and the citation of the published work (See The effect of open access).
This is an open access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the
author. This is in accordance with the BOAI definition of open access
Intellectual Property
All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License under attribution BY.