Available at: https://digitalcommons.calpoly.edu/theses/2714
Date of Award
12-2023
Degree Name
MS in Electrical Engineering
Department/Program
Electrical Engineering
College
College of Engineering
Advisor
Xiao-Hua (Helen) Yu
Advisor Department
Electrical Engineering
Advisor College
College of Engineering
Abstract
Heart disease is the leading cause of death for men and women in the United States. Deaths from cardiovascular disease jumped globally from 12.1 million in 1990 to 20.5 million in 2021, according to a new report from the World Heart Federation.
The Electrocardiogram (ECG, or EKG) is a non-invasive and efficient test that records the electrical activities of a human heart. In recent years, various approaches based on computational intelligence have been developed and successfully applied to automatic detection of cardiac arrhythmia on ECG signals.
In this thesis, we study the application of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for identification of cardiac irregularities. The two methods are tested on ECG signals with six different heartbeat conditions in the MIT- BIH Arrhythmia database. Computer simulation results show both methods are highly effective with detection rates of close to 98% and 99%, respectively.