Detection of Electrocardiography Based on Wavelet Transform and Extended Kalman Filter

摘要

This paper combined wavelet transform with extended kalman algorithm. By using wavelet transform which has characteristics of multiresolution to decompose the signal of ECG and then to filter the signal of ECG in each scale. Finally a decision rule is used to determine the QRS wave. The QRS detector has an average sensitivity of Se = 99.34% and a positive predictivity P+= 99.28% by evaluating the algorithm on MIT-BIH Database.