عنوان المقالة:اكتشاف الاعتلال القلبي باستخدام اشارات تخطيط القلب ARRHYTHMIA DETECTION BASED ON COMBINATION OF FREEMAN CHAIN CODE AND FIRST ORDER TEXTURE FEATURES
يهدف البحث الى اكتشاف تسارع وتباطؤ ضربات القلب باستخدام تقنيات معالجة الصور والذكاء الاصطناعي
الملخص الانجليزي
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 training/
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 accuracy
in second ratio was 100% for training group and 97.8% for testing group with time 31.6 second. The
system achieved using Matlab.
تاريخ النشر
15/01/2019
الناشر
Journal of Theoretical and Applied Information Technology
زمن فاضل جبر | zamen fadhel jabr | 2935