Greedy algorithms are popular in compressive sensing for their highcomputational efficiency. But the performance of current greedy algorithms canbe degenerated seriously by noise (both multiplicative noise and additivenoise). A robust version of greedy cosparse greedy algorithm (greedy analysispursuit) is presented in this paper. Comparing with previous methods, Theproposed robust greedy analysis pursuit algorithm is based on an optimizationmodel which allows both multiplicative noise and additive noise in the datafitting constraint. Besides, a new stopping criterion that is derived. The newalgorithm is applied to compressive sensing of ECG signals. Numericalexperiments based on real-life ECG signals demonstrate the performanceimprovement of the proposed greedy algorithms.
展开▼
