文档介绍：Automatic Detection and Localization of Myocardial
Infarction using Back Propagation works
Muhammad Arif Ijaz A. Malagore, Fayyaz A. Afsar
Department of Electrical Engineering, Air University, Department puter and Information Sciences,
Islamabad, Pakistan PIEAS, Nilore, Islamabad, Pakistan.
e-mail: ******@ e-mail: ijazahmad722@, fayyazafsar@
Abstract— This paper presents automatic detection and Infarction in [2] uses ST elevation as an input parameter. The
localization of myocardial infarction (MI) using back accuracy of detecting healthy patients is % and accuracy of
propagation works (BPNN) classifier with features detecting infarction is %.
extracted from 12 lead ECG. Detection of MI aims to classify
healthy and subjects having MI. Localization is the task of
specifying the infarcted region of the heart. The II. MATERIALS AND METHODS
electrocardiogram (ECG) source used is the PTB database PTB ECG database is used which is available free on the
available on Physio-bank. Time domain features of each beat in Physio-Bank [3]. The PTB database contains 549 records from
the ECG signal such as T wave amplitude, Q wave and ST level 294 subjects. Each subject is represented by one to five records.
deviation, which are indicative of MI, are extracted. For The number of patients with myocardial infarction (MI) is 148.
loc