Title :
Classifying some cardiac abnormalities using heart rate variability signals
Author :
Obayya, Marwa ; Abou-Chadi, F.
Author_Institution :
Dept. of Electron. & Commun. Eng., Cairo Univ., Giza
Abstract :
In this paper, the heart rate variability signals were utilized to discriminate different cardiac abnormalities. The performance of traditional feature extraction techniques and new complexity estimators was compared using hidden Markov model (HMM). This was done by analyzing data recorded for healthy subjects and patients suffering from congestive heart failure (CHF) and myocardial infarction (MI) diseases. The techniques utilized included time, frequency parameters as well as approximate entropy, sample entropy, detrended fluctuation analysis coefficient, fractal dimension, Poincare plot and largest Lyapunov exponent. Results have shown that using complexity-based estimators gives higher rates for classifying cardiac abnormalities. Classification rate reaches to 98.18%.
Keywords :
cardiology; diseases; feature extraction; hidden Markov models; patient diagnosis; Lyapunov exponent; cardiac abnormalities; complexity estimators; congestive heart failure; feature extraction; fluctuation analysis coefficient; fractal dimension; healthy subjects; heart rate variability signals; hidden Markov model; myocardial infarction diseases; patient diagnosis; sample entropy; Cardiac disease; Cardiovascular diseases; Data analysis; Entropy; Failure analysis; Feature extraction; Frequency; Heart rate variability; Hidden Markov models; Myocardium; Hidden Markov Model (HMM); Lyapunov exponents; entropy; fractal; time and frequency analysis;
Conference_Titel :
Radio Science Conference, 2008. NRSC 2008. National
Conference_Location :
Tanta
Print_ISBN :
978-977-5031-95-2
DOI :
10.1109/NRSC.2008.4542387