The Application Of Rough Set And Wavelet Analysis To Electrocardiogram Auto-analyzing

In this paper, as a generalization of pawalak Rough set model, we introduce the Rough set model over two universes and discuss the properties. And its applications to the ECG signal classified as well. Prior to the ECG signal classified, it is needed to obtain the characteristic of the ECG signal. The detection of R wave laid the foundation for the other characteristic of the ECG signal. So, we try two methods to detect R waves: one is the preprocessing technique of ECG data performing with orthonormal wavelet packets. Wavelet decomposition of signal of the preprocessed signal was obtained by Mallat's pyramidal algorithm. Then we deal with the detail signal of 23 scales, the extremes corresponding with R wave have been considerable increased, the QRS complex detection rate has been improved. The result of ORS detection rate examined by the MIT-BIT arrhythmia database is satisfactory. Another method is that we use Mexican-hat wavelet transform to detect characteristic points of ECG signal based on the characteristic points corresponding with the extremes of Mexican-hat wavelet transform; it offers a new detection means to ECG signal analysis. This method is simple and it was proved to be accurate and reliable. The correct rate of ORS detection rata examined by the MIT-BIT arrhythmia database rises up to 99.9%..