Using Machine Learning Algorithms for Heart Rate Time Series Classification
DOI:
https://doi.org/10.70705/ppp.bioai.2024.v03.i01.pp27-30Keywords:
Classification, Machine learning, Time series, Decision tree algorithm, SVM algorithmAbstract
The electrocardiogram (ECG) is a vital tool for the detection of cardiac problems. Doctors are busier than usual due to the
high volume of cardiac patients. An automated computer detection method is required to lessen their workload. This research
presents a computer system that can categorize electrocardiogram (ECG) data. Analyses are conducted using the MIT-BIH
ECG arrhythmia database. Data feature extraction follows the preprocessing step of making the ECG signal noisy. The feature
extraction process involves building a support vector machine (SVM) and using a decision tree to divide the ECG signal into
two groups. We may call it normal or abnormal. The system successfully categorizes the input ECG signal with a sensitivity level
of 90%, according to the findings.
