Sparse Bayesian Learning in Compressive Sensing
ثبت نشده
چکیده
Traditional Compressive Sensing (CS) recovery techniques resorts a dictionary matrix to recover a signal. The success of recovery heavily relies on finding a dictionary matrix in which the signal representation is sparse. Achieving a sparse representation does not only depend on the dictionary matrix, but also depends on the data. It is a challenging issue to find an optimal dictionary to recover non-sparse data or to sparsify the data. Instead of finding the optimal dictionary matrix, this paper shows that Bayesian Learning recovery methods can achieve phenomenal results using general dictionary matrices for non-sparse signals. Our empirical results show that when Bayesian Learning is used to recover non-sparse signals it is not necessity to use an optimal dictionary matrix. Our experiments show that Bayesian Learning has superior performance compared to one of the stateof-the-art optimization techniques used in CS, the SPGL1 algorithm. Bayesian Learning outperformed SPGL1 in terms of number of iterations, SNR, and recovery quality.
منابع مشابه
Rice Classification and Quality Detection Based on Sparse Coding Technique
Classification of various rice types and determination of its quality is a major issue in the scientific and commercial fields associated with modern agriculture. In recent years, various image processing techniques are used to identify different types of agricultural products. There are also various color and texture-based features in order to achieve the desired results in this area. In this ...
متن کاملConvolutional Deep Stacking Networks for distributed compressive sensing
This paper addresses the reconstruction of sparse vectors in the Multiple Measurement Vectors (MMV) problem in compressive sensing, where the sparse vectors are correlated. This problem has so far been studied using model based and Bayesian methods. In this paper, we propose a deep learning approach that relies on a Convolutional Deep Stacking Network (CDSN) to capture the dependency among the ...
متن کاملBayesian Learning Algorithm for Compressive Sensing of Non-Sparse (EEG) Signals
Compressive Sensing (CS) is an emerging compression technique that takes advantage of a signal’s sparsity to sample and compress this signal at the same time. Its many advantages as well as its satisfactory compression ratios (CR) makes it a very desirable technique in telemonitoring where the bandwidth available is very small and needs to be efficiently used. In the case of electroencephalogra...
متن کاملBayesian Multi-Task Compressive Sensing with Dirichlet Process Priors
Compressive sensing (CS) is an emerging field that, under appropriate conditions, can significantly reduce the number of measurements required for a given signal. Specifically, if the m-dimensional signal u is sparse in an orthonormal basis represented by the m × m matrix Ψ, then one may infer u based on n m projection measurements. If u = Ψθ, where θ are the sparse coefficients in basis Ψ, the...
متن کاملBayesian compressive sensing for cluster structured sparse signals
In traditional framework of Compressive Sensing (CS), only sparse prior on the property of signals in time or frequency domain is adopted to guarantee the exact inverse recovery. Other than sparse prior, structures on the sparse pattern of the signal have also been used as an additional prior, called modelbased compressive sensing, such as clustered structure and tree structure on wavelet coeff...
متن کامل