Highly Nonlinear Approximations for Sparse Signal Representation
Dimensionality reduction of ECG signals is considered within the framework of sparse representation. The approach constructs the signal model by selecting elementary components from a redundant wavelet dictionary via a greedy strategy. The technical details and algorithms for constructing the distionaries are given in a complemenaty work. The reduced representation of the signal is shown to be suitable for compression at low level distortion. In that regard, compression results are superior to previously reported benchmarks on the MIT-BIH Arrhythmia data set.
by Laura Rebollo-Neira and Dana Cerna