In this paper, we analyze the performance of electrocardiogram (ECG) signal compression bycomparing original and reconstructed signal on two problems. First, automatic sleep stageclassification based on ECG signal; second, arrhythmia classification. An effective ECG signalcompression method based on two-dimensional wavelet transform which employs set partitioning inhierarchical trees (SPIHT) and beat reordering technique used to compress the ECG signal. Thismethod utilizes the redundancy between adjacent samples and adjacent beats. Beat reorderingrearranges beat order in 2D (2 dimension) ECG array based on the similarity between adjacent beats.The experimental results show that the proposed method yields relatively low distortion at highcompression rate. The experimental results also show that the accuracy of sleep stage classification andarrhythmia classification using reconstructed ECG signal from proposed method is comparable to theoriginal signal. The proposed method preserved signal characteristics for the automatic sleep stage andarrhythmia classification problems.
展开▼