DOI: https://doi.org/10.15368/theses.2021.168
Available at: https://digitalcommons.calpoly.edu/theses/2372
Date of Award
12-2021
Degree Name
MS in Biomedical Engineering
Department/Program
Biomedical and General Engineering
College
College of Engineering
Advisor
Robert Szlavik
Advisor Department
Biomedical and General Engineering
Advisor College
College of Engineering
Abstract
Classifying the electrocardiogram is of clinical importance because classification can be used to diagnose patients with cardiac arrhythmias. Many industries utilize machine learning techniques that consist of feature extraction methods followed by Naive- Bayesian classification in order to detect faults within machinery. Machine learning techniques that analyze vibrational machine data in a mechanical application may be used to analyze electrical data in a physiological application. Three of the most common feature extraction methods used to prepare machine vibration data for Naive-Bayesian classification are the Fourier transform, the Hilbert transform, and the Wavelet Packet transform. Each machine learning technique consists of a different feature extraction method to prepare the data for Naive-Bayesian classification. The effectiveness of the different machine learning techniques, when applied to electrocardiogram, is assessed by measuring the sensitivity and specificity of the classifications. Comparing the sensitivity and specificity of each machine learning technique to the other techniques revealed that the Wavelet Packet transform, followed by Naïve-Bayesian classification, is the most effective machine learning technique.
Included in
Bioinformatics Commons, Biomedical Commons, Other Biomedical Engineering and Bioengineering Commons