Page Header

A New Approach to an Adaptive Filter High Performance based on Abstract Data Types for Processing ECG Signals

Andrilene MacIel 1, Vieira R. V. 2

Abstract


In this paper, we present a new approach to an adaptive filter high performance based on abstract data types for processing ECG signals, tested in conventional CPU and GPU, evaluated for its efficiency from the samples obtained from the MIT-BIH , arrhythmia database. The algorithm used is based on a compact genetic algorithm that was based on abstract data types, implemented in MATLAB in architecture CUDA. The results shown that the compact genetic algorithm can be implemented in high-performance systems, aiming to improve the health care systems of treatment is provided to patients with cardiovascular problems.

Keywords


Electrocardiogram; Genetic Algorithm; Adaptive Filter; Graphics Processing Unit; Compute Unified Device Architecture

Full Text:

PDF

References


Porto C. C. Doenças do Coração : prevenção e tratamento. Guanabara, 2005.

Mendis S. Global Status Report: on non communicable diseases. WHO Library Cataloguing, 2014.

Oliveira W. J. Pedrosa L. C. Doenças do Coração: Diagnóstico e Tratamento. 1ª edição, Revinter, 536p, São Paulo, 2011.

Moreira D. A. R. Fibrilação Atrial. 2ª edição, Lemos Editorial, 311p. São Paulo, 2005.

Sanches P.,Moffa P. Eletrocardiograma: Uma abordagem didática. 1ª edição, Rocca, 356 p, São Paulo, 2010.

Delbem A.C.B, Casseb M. V. G. at all. Programable logic design of a compact genetic algorithm for phasor estimation in real-time. Elsevier, 109-118, 2014.

Yeh Y., HongJhih L., Chiou C. W. Analyzing ecg for cardic arrhythmia using cluster analysis. expert systems with applications. Elsevier, page 1000:1010, 2012.

Jiang L., Ma L., Ji Z., Li Y., Yu H. Adaptive Lifting Scheme for ecg qrs complexes detection and its fpga implemantation. 3rd International Conference on Biomedical Engineering and Informatics, IEEE, 2010.

Nianqiang L., Guoyi Z., Yongbing W. A preferable method on digital filter in ecg signal processing based on fpga. Third International Symposium on Intelligent Information Technology and Security Informatics, IEEE, 2010.

Gao X. . Diagnosing Abnormal Electrocardiogram (ECG) via Deep Learning. IntechOpen, 2019. Disponível em https://www.intechopen.com/online-first/diagnosing-abnormalelectrocardiogram-ecg-via-deep-learning. Último Acesso: 15/06/2019.

Qiang L., Yao C., Yu H. Application of distributed fir filter based on fpga in the analyzing of ecg signal. International Conference on Intelligent System Design and Engineering Application, IEEE, 2010.

M. N. Iqbal;M. Bomhara, at. all. Real-time signal processing of data from an ECG. IEEE, Wrexham, UK, 2019.

Sato M. Y., Hasegawa N. Acceleration of genetic algorithms for sudoku solution on many-core processors. GECCO-11, Dublin, Ireland. ACM , 12-16., 2011.

Arun Khosla Indu Saini, Dilbag Singh. Qrs detection using k-nearest neighbor algorithm (knn) and evaluation on standard ecg databases. Journal of Advanced Research , Elsevier, 331-344., 2013.

Acharyaa. R. at all. Ecg beat classification using pca, lda, ica and discrete wavelet transform. Biomedical Signal Processing and Control , Elsevier, 437- 448., 2013.

Johannesen L., at all. A wavelet based algorithm for delineation and classification of wave patterns in continuous holter ecg recordings. Computing in Cardiology, 37:979:982, Elsevier, 2010.

Faraji R. and Hamid R. An efficient crossover architecture for hardware parallel implementation of genetic algorithm. Neurocomputing 128, 316-327 p., Elsevier, 2014.

Song G., Long C. X. Z., Lua Y., Guoa M. Architecture-based design and optimization of genetic algorithms on multi-core and many-core systems. Future Generation Computer Systems 38, 75-91 p. Elsevier, 2014.

Holland. J. H. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT Press., 1975.

Vieira R. V. V. Um Algoritmo Genético Baseado em Tipos Abstratos de Dados e sua especificação em Z, Tese de Doutorado, Universidade Federal de Pernambuco, 2003.

Physionet, MIT-BIH Arrhythmia Databases. Disponível em: http://www.physionet.org/physiobank/database/mitdb. Último acesso: 28 de abril de 2019.

Cunha P. C. N. Modelo de eletrocardiógrafo portátil de baixo consumo. Dissertação de Mestrado em Modelagem Computacional de Conhecimento, Universidade Federal de Alagoas, 2012.

Melo B. R. P. An application of a new genetic algorithm to assist the detection of segments of an ecg signals. ISABEL' 11, ACM, Barcelona, Span, 2011.

Melo B. R. P. Melo. Um Sistema Adaptativo para Detecção de Ondas de EletrocardiografiaDissertação de Mestrado do Mestrado em Modelagem Computacional de Conhecimento Dissertação de Mestrado, Universidade Federal de Alagoas, 2011.

Ramos V. W J. Uma aplicação do algoritmo genético baseado em tipos abstratos de dados ao problema de separação cega de fontes com não-linearidade posterior. dissertação de mestrado. Dissertação de Mestrado, Universidade Federal de Alagoas, 2011.

Maciel, A. Um filtro adaptativo de alto desempenho instaciado do algoritmo GAADT para o processamento de sinais de eletrocardiograma, Tese de Doutorado do Centro de Informática da Universidade Federal de Pernambuco, 2015.

NVIDIA CUDA C Programming Guide, Version 4.2,1999.

OpenCL Programming Guide for the CUDA Architecture, V 2.3, 2009.

Math Works - Softwares Matlab R2010, R2012a, R2012b, R2013a e R2014a. URL: http://www.mathworks.com. Último acesso em 20/07/2019.

Darwin, C. The Origin of Species. 1859. Disponível em : http://darwin-online.org.uk/converted/pdf/1861_OriginNY_F382.pdf. Acesso em : 27 de março de 2019.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 Andrilene MacIel 1, Vieira R. V. 2

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.