Detection and Classification of Cardiac Arrhythmia from Photoplethysmography Signal

This paper presents the development of an application for classifying cardiac arrhythmia by utilizing photoplethys-mography sensor signals. The Photoplethysmography (PPG) sensor is used as a reader for the cardiovascular system by measuring changes in blood volume in the skin tissue. The PPG sensor captures electrical signals originating from the reflected light source due to changes in blood flow during heart activity. After going through the preprocessing stage, the signals are then extracted into several features that will be classified using the Random Forest algorithm. The results from the Random Forest algorithm will provide a diagnosis based on the detection of arrhythmia. Based on the experimental results, the accuracy achieved using the method and dataset is 72%. The accuracy of the system testing using the smartwatch under normal heart conditions is 88.88%.