An Denoising Method Based on Analysis K-SVD and Disagreement Segment and Its Application on EMI Signal

Abstract

Abstract-Sparse representation plays an important role in signal processing. Recently, the analysis sparse representation has been attracting more and more attention. In this paper, an improved analysis K-SVD denoising algorithm based on disagreement-segment is proposed. A signal is first divided into small redundant segments, and then the signal can be denoised by the analysis K-SVD algorithm. Considering the gap between the local processing and the global signal recovery, we define a disagreement-segment as the difference between the intermediate locally denoised segment and its corresponding part in the final denoised signal. By adding the disagreementsegment to the analysis K-SVD algorithm, the denoising effect of the analysis K-SVD algorithm has a significant improvement. In addition, the experimental results show that the proposed method outperforms the analysis K-SVD algorithm and other advanced methods.