Heart Condition Classification Based on Electrocardiograms Using Advanced Learning Algorithms
Abstracts: Observing the condition of the cardiovascular system is a vital task in the medical sector. The electrocardiogram (ECG) is such a tool that can be used to detect cardiovascular abnormalities. The advanced techniques of machine Learning can help us to detect such abnormalities with the help of computers. But to effectively train the machine, we need to extract meaningful features from the ECG signals. instead of using the raw signal as input. In this study, a set of hand crafted features have been extracted after signal processing and used to train a classifier properly. The aim of this paper is to propose an effective technique to classify 17 different classes of ECG signals based on ensembles learning algorithm. To demonstrate the validity of the method, we applied it on the ECG raw data provided by the MIT-BIH database. Employing the ensemble learning algorithm after extracting the raw data signals using a method is Pwelch classify using RF in the first proposed method, the second one is comprised of PMTM and DCT and classify using XGBoost in the second method. The obtained results show that the methods can identify classify with 88% and 85% accuracy respectively.
Result Published: 2021
|Class / Degree
Ananna Rahman [M.Sc. 180903] ]
|6th June, 2019