Loading...

Intelligent Diagnosis of Cardiovascular Disease using ECG Signals

Baghdadi, Fatemeh | 2018

775 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 51042 (55)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Haj Sadeghi, Khosrow
  7. Abstract:
  8. Cardiovascular diseases (CVDs) have ranked first cause of deaths globally. In 2016, about 17.7 million people died from CVDs representing 31% of all world deaths. So, early intelligent detection of cardiovascular disease could help to save many lives in worldwide. There are several methods to analyze heart activity and to detect any abnormalities including Electrocardiogram, Stress test, Echocardiography, cardiac catheterization and coronary angiography.Among all methods, Electrocardiogram (ECG) is the most common and convenient type where it measures heart electrical activity and records it as a series of pulses. Analyzing these pulses would provide useful information about normal and abnormal heart activities. In this thesis, an intelligent system has been designed to analyze ECG signals and classify them to the related categories of diseases.To do so, ECG signals have been processed to remove primary noises using digital filters in MATLAB. Then, desired features have been extracted from signal using frequency and morphology analysis. Within all these features, the most efficient feature has been selected by appropriate feature selection method and then feature vector has been generated. In the Next phase, the classifier, which is an artificial neural network, has used feature vector as input data and trained the classifier. The performance of classifier has been measured using medical metric such as accuracy, sensitivity and specificity.The proposed system could classify ECG signals into five main categories of disease and achieve 85% accuracy, 90% sensitivity and 96% specificity. The system has shown improvement in performance comparing to previous works which justifies its reliability and novelty.
  9. Keywords:
  10. Feature Extraction ; Artificial Neural Network ; Heart Diseases ; Electrocardiogram ; Radial Basis Function ; Multi-Layer Perceptron (MLP) ; Arrhythmia Recognition

 Digital Object List

 Bookmark

No TOC