Title :
An artificial-intelligence approach to ECG analysis
Author :
Gang, Ii ; Wenyu, Ye ; Ling, Lin ; Qilian, Yu ; Xuemin, YU
Author_Institution :
Coll. of Precision Instrum. & Photo-Electron. Eng., Tianjin Univ., China
Abstract :
The issue we address in this article is how to reduce the computational burden by using an algorithm based on a linear-approximation distance-thresholding compression technique combined with the backpropagation neural network method. We also address how to improve the training speed. The experimental results found with the MIT-BIH database show that the new algorithm is faster in convergence and more accurate in feature recognition than existing methods.
Keywords :
approximation theory; backpropagation; convergence of numerical methods; data compression; electrocardiography; feature extraction; gradient methods; medical signal processing; neural nets; signal classification; ECG analysis; Gauss-Newton method; Levenberg-Marquardt algorithm; QRS detection; artificial-intelligence approach; backpropagation neural network; data compression; fast convergence; feature recognition; linear-approximation distance-thresholding compression; signal preprocessing; steepest descent rule; training speed; Chromium; Data compression; Educational institutions; Electrocardiography; Neural networks; Pattern analysis; Tin; Utility programs; Algorithms; Arrhythmias, Cardiac; Electrocardiography; Humans; Neural Networks (Computer); Signal Processing, Computer-Assisted;
Journal_Title :
Engineering in Medicine and Biology Magazine, IEEE
