Design of neural network based ECG diagnosing system

مقدم أطروحة جامعية

al-Nuaymi, Ann Fayiq Subayh

الجامعة

الجامعة التكنولوجية

الكلية

-

القسم الأكاديمي

قسم علوم الحاسوب

دولة الجامعة

العراق

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2002

الملخص الإنجليزي

Cardiovascular diseases are the most frequent cause of adult death in industrialized societies, and are increasingly important in developing countries.

The analysis of the electrocardiogram (ECG) can benefit from the wide availability of computing technology as far as features and performances are concerned.

This work presents some results achieved by carrying out the classification tasks of a possible equipment integrating the most common features of the ECG analysis: Arrhythmia, Myocardial Ischema ,Chomic alteratons.

Several Artificial Neural Network (ANN) architectures are implemented, tested, and compared with competing alternatives.

Structure, and learning algorithm of ANN were designed to feature each particular classification task.

The trade-off between the time consuming training of ANN'S and their performance is also explored.

Data pre-and post processing efforts, on the system performance were critically tested.

We tried to investigate the effects of the reduction of the input space dimensions relation to the significance of the input features.

Features from the ECG’s were extracted using principal component analysis, which gives a very good indication for different cases.

The fast Fourier transform (FFT) and cross correlation function are used to perform the above analysis.

The ECG signal has been sampled and digitized in order to be processed in the computer.

(ANNs) proved a very powerful technique for such applications, they can handle almost any nonlinear dependencies.

This work was done on data coming from all the currently available ECG databases, which were previously collected from different fields.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

• القلب
• الأمراض
• الخواص الكهربائية
• الشبكات العصبية(الحاسبات الإلكترونية)
• التشخيص
• تخطيط القلب

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-305786