文章基本信息

标题：ARRHYTHMIA DETECTION BASED ON COMBINATION OF FREEMAN CHAIN CODE AND FIRST ORDER TEXTURE FEATURES
本地全文：下载
作者：ZAMEN F. JABR ; RANA H. HUSSAIN ; SHAYMAA R. SALEH 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2019
卷号：97
期号：1
页码：207-214
出版社：Journal of Theoretical and Applied
摘要：This paper presents a novel method of detection and classification an Arrhythmia based on ECG chart using image processing techniques and neural network as classifier tool .The method consist of three major stage firstly preprocessing to prepare the ECG chart image, secondly features extraction stage represent by freeman chain code and first order features which are arranged in vector consist of 14 input each one hold one feature value, finally stage this vector of features entered to BPNN classifier to classify an Arrhythmia type. The system applied on dataset consists of 90 ECG chart images. Two different ratios of train-ing/testing groups which are (30% to 70%,50% to 50%) are applied to the classifiers. The higher system's accuracy in first ratios was100% for training group and 90.5% for testing group while higher system's accu-racy in second ratio was 100% for training group and 97.8% for testing group with time 31.6 second. The system achieved using Matlab.
关键词：ECG chart; Arrhythmia; Freeman chain code; First order features; Artificial neural network