Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Depth generative adversarial method for underwater acoustic signal denoising

An underwater acoustic signal and depth technology, which is applied in the recognition of patterns in signals, neural learning methods, biological neural network models, etc. The effect of fitting the problem

Active Publication Date: 2021-01-12
NORTHWESTERN POLYTECHNICAL UNIV
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the small sample training problem unique to underwater acoustic signals, this paper proposes a deep generative confrontation method for underwater acoustic signal denoising technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Depth generative adversarial method for underwater acoustic signal denoising
  • Depth generative adversarial method for underwater acoustic signal denoising
  • Depth generative adversarial method for underwater acoustic signal denoising

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In step 1, the samples are first divided into frames and processed in batches.

[0038] Step 2 Then send the processed data into the generative model for model training. The generative model is a semi-supervised model, so there is a difference between the trained data and the clean data

[0039] Step 3. Add the data generated by the generator to the noisy data, and send it to the discriminant model together with the original clean and noisy data for discrimination. At the beginning, the discriminator can discriminate well. The data generated by the model is a fake sample, and the output is 0. Originally, the clean and noisy data is a real sample and the output is 1. According to the result of the discriminator, the generator starts to simulate its own generated data, so that the data is as close as possible to the real data, so that until the discriminator has no way to distinguish, the generator will generate The data is sent to the discriminator again, and the discrim...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a depth generative adversarial method for underwater acoustic signal denoising, and belongs to the technical field of underwater acoustic signal denoising. The method comprisesthe following steps: firstly, carrying out sampling and feature extraction on an original underwater acoustic signal, then sending the extracted signal into a Gaussian restricted Boltzmann machine, and carrying out semi-supervised pre-training on a probability generation model; and finally, constructing a deep generative adversarial model, sending data generated in the probability generation model and a real label data stream into a Bernoulli restricted Boltzmann machine adversarial model, and performing supervised training. According to the method, a generative adversarial model is introduced into a restricted Boltzmann probability model according to the feature extraction characteristics of underwater acoustic signals, so that the problems of strong dependence and over-fitting of a restricted Boltzmann machine in the training process caused by complex signals carried by underwater sound are effectively eliminated, and the self-applicability of the training model is higher.

Description

technical field [0001] The invention belongs to the technical field of noise reduction of underwater acoustic signals, and can effectively reproduce original useful signals from underwater acoustic signals with a large signal-to-noise ratio. Background technique [0002] In the existing underwater acoustic signal denoising, there are traditional denoising methods, time-domain-based modal decomposition methods and frequency-domain-based overall modal decomposition methods. It is necessary to set some empirical parameters in advance, so that the denoising process depends on experience value, the classical mode decomposition method can complete the denoising process without setting the function in advance, but it is easy to produce mode mixing and boundary effects in the decomposition process. In order to overcome boundary mixing, the underwater acoustic signal denoising method based on CEEMDAN, refined compound multiscale dispersion entropy and wavelet threshold denoising has ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F2218/04G06F2218/08G06F18/214
Inventor 曾向阳薛灵芝
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products