Application of the empirical mode decomposition to ECG and HRV signals for congestive heart failure classification

Patients with congestive heart failure (CHF)] have neurologic complications, and decreased pulmonary flow. This will lead to having nonstationary ECG signal and also its heart rate variability (HRV) signal. In this work, we used the empirical mode decomposition (EMD) to develop a strategy to identify the relevant intrinsic mode functions (IMFs) for classification. The data set includes long-term record (1-Hour) of ECG signals from normal and CHF. K-means clustering technique was used to classify the decomposed IMFs. The percentage of success of classification using ECG signal was 89% with the first four IMFs while with HRV signal was 100% with the first IMF.