DocumentCode
3378310
Title
Electrocardiogram signal classification based on fractal features
Author
Esgiar, A.N. ; Chakravorty, P.K.
Author_Institution
Univ. of Al Tahadi, Sirte, Libya
fYear
2004
fDate
19-22 Sept. 2004
Firstpage
661
Lastpage
664
Abstract
Atrial fibrillation ECG signals have been classified with fractal features only. The fractal features -fractal dimension, mass dimension and lacunarities were estimated by a new box counting algorithm; called the true box counting method. The classification result and stepwise discriminant analysis for these fractal features were determined. It was seen that lacunarities based on higher mass moments were more important than fractal dimension and mass dimension. The results suggest further investigation of lacunarity features.
Keywords
electrocardiography; fractals; medical signal processing; signal classification; atrial fibrillation; electrocardiogram signal classification; fractal dimension; fractal features; lacunarities; mass dimension; stepwise discriminant analysis; true box counting method; Analog-digital conversion; Atrial fibrillation; Data mining; Electrocardiography; Entropy; Feature extraction; Fractals; Pattern classification; Testing; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Computers in Cardiology, 2004
Print_ISBN
0-7803-8927-1
Type
conf
DOI
10.1109/CIC.2004.1443025
Filename
1443025
Link To Document