ECG Classification using Adaptive Neuro-Fuzzy Inference System

ECG classification using Adaptive Neuro-Fuzzy Inference System (ANFIS), sponsored by Professor Yu, involves the diagnosis of six cardiovascular conditions by analyzing one single neural network. Today’s ECG signal instrumentation does not have the ability to characterize cardiovascular diseases without a doctor’s complete evaluation and diagnosis. Our project gives a promising solution to the inability in the current market’s ECG signal instrumentation to correctly evaluate and diagnose cardiovascular diseases. ECG signal reportings is a non-invasive process that will lead to many more applications of advanced signal processing and data analysis/diagnosis of cardiovascular diseases. The inputs to the ANFIS are annotations of electrocardiograph signals that 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 main goal of this project is to detect important characteristics of an ECG signal to determine the cardiovascular condition of an individual. The testing results from the work indicates an average accuracy of 98.39%, average sensitivity of 92.42%, and average specificity of 99.67%