Home // ICWMC 2012, The Eighth International Conference on Wireless and Mobile Communications // View article

Research on Improving Accuracy of Cardiac Disorder Data Analysis based on Random Forest Classifier

Authors:
HyunJu Lee
DongIl Shin
DongKyoo Shin
HeeWon Park
SooHan Kim

Keywords: ECG; R-R interval; HRV; SVM; MLP; Random Forest; classifier; accuracy.

Abstract:
In order to prove that the improved RF algorithm had higher accuracy, the comparing analysis was conducted adapting ECG data. In pre-processing stage, Band-pass Filter was adapted among Wavelet transform, Median Filter, Finite impulse response and others. As a result, the modified Random Forest classifier showed increased more accuracy than SVM, MLP and other researchers’ results. Thus, continuous studies on the selection of the filters and methods, which can efficiently delete baseline-wandering at pre-processing phase and accurately extract R-R interval, should be taken place.

Pages: 166 to 172

Copyright: Copyright (c) IARIA, 2012

Publication date: June 24, 2012

Published in: conference

ISSN: 2308-4219

ISBN: 978-1-61208-203-5

Location: Venice, Italy

Dates: from June 24, 2012 to June 29, 2012