Answers are grounded in this paper and cite their sources.
The detection of weak transient signal buried in non-Gaussian noise is investigated. Non-Gaussian noise is modeled by Gaussian mixture distribution. 3-level quantizer is used as a nondynamic stochastic resonance method to enhance SNR of weak signal. NL-length samples of signal are arranged into a matrix. Every column of the matrix is calculated into M-level decomposition. Based on the squared value of the detail and approximation coefficients, a novel Power-Law detector in wavelet domain is established. Numerical experiments and comparison show that, on the same SNR and false alarm rate, proposed method could provide higher detection probability.
No takes yet. Share an insight, caveat, or question.
Zhijian Yang (2014) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: