Design of optimal lifting wavelet filters for data compression

This paper presents a new method to design wavelet filters optimized for time-series data compression. The features of these filters, called signal adapting lifting wavelet filters, are to vanish the wavelet coefficients, adapting to the input signals by tuning free parameters contained in the lifting scheme. Newly constructed filters are almost compactly supported and are perfect reconstruction filters. By using the adaptive filters, we demonstrate an application to electrocardiogram (ECG) data compression and confirm the performance of the proposed method.