WSN Signal Reconstruction Based on Unknown Sparse Compressed Sensing

Abstract

For the signal reconstruction problem of unknown signal sparsity in compressed sensing, this paper proposes a Sparsity Adaptive Stagewise Orthogonal Matching Pursuit algorithm (SAOMP), which realizes the reconstructed signal under the condition of unknown signal sparsity. The algorithm combines the idea of adaptive thinking, variable step size iteration and piecewise orthogonal thinking. Under the condition of unknown signal sparsity, the number of supporting set atoms is adaptively selected, and finally the signal reconstruction is realized. The experimental results show that the proposed algorithm is better than the Orthogonal Matching Pursuit algorithm, the Regularized Orthogonal Matching Pursuit algorithm and the Stagewise Orthogonal Matching Pursuit algorithm for the 128-bit observation set and the 256-bit length.