Kernel signal extraction method based on dictionary training and orthogonal matching pursuit

Abstract

The invention discloses a kernel signal extraction method based on dictionary training and orthogonal matching pursuit, and the method comprises the steps: 1, carrying out the training of an initial dictionary D through employing a sparse K-SVD algorithm and a training sample set y, and obtaining an over-complete dictionary; 2, performing sparse representation on the original nuclear pulse signalY by using an orthogonal matching pursuit algorithm to obtain a sparse coding coefficient; and 3, reconstructing a nuclear pulse signal by using dictionary atoms and sparse coding coefficients obtained by sparse decomposition. According to the method, the K-SVD dictionary learning algorithm is utilized to train the initial over-complete dictionary into the over-complete dictionary of the kernel signal with complete features, and the orthogonal matching pursuit algorithm is utilized to reconstruct the over-complete dictionary, so that the purpose of weak kernel signal extraction is achieved, and the method is accurate and efficient.

Description

technical field [0001] The invention belongs to the technical field of signal processing, in particular to a nuclear signal extraction method based on dictionary training and orthogonal matching pursuit. Background technique [0002] With the rapid development of science and technology, the collection, acquisition, processing and analysis methods of nuclear signals are constantly innovating and developing, especially the application of digital technology has greatly improved the collection and processing methods of nuclear physics data. Compared with traditional nuclear electronics The system can process and analyze nuclear signal features more efficiently. In order to improve the signal-to-noise ratio of the nuclear signal output by the reactor nuclear measurement system and weaken the interference noise of the environment and system electronics, certain signal processing methods can be adopted to extract the target signal from the aliased signal. [0003] In recent years,...

AI Technical Summary

Problems solved by technology

[0004] In summary, the existing algorithms still lack an effective solution for how to efficiently extract the weak nuclear pulse signal submerged by noise

Images