Cardiovascular Conditions Classification Using Adaptive Neuro-Fuzzy Inference System
Jason N Rivera, Kelsey C Rodriguez, Xiao-Hua Yu · 2019
ECG (electrocardiogram) signals have been widely used to determine the cardiovascular conditions of individuals. In this research, an Adaptive Neuro-Fuzzy Inference System (ANFIS) is designed to identify six different heart conditions: normal sinus rhythm, premature ventricular contraction (PVC), atrial premature contraction (APC), left bundle branch block (LBBB), right bundle branch block (RBBB), and paced beats. The inputs to ANFIS are the seven time-domain features extracted from ECG signals, such as the Q amplitude, the QRS interval, etc. The proposed approach is tested on the ECG signals of MIT-BIH database; and computer simulation results indicate this method is promising with an average accuracy of 98.39%, and an average specificity of 99.67%.