Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Underwater target signal feature extraction method based on probabilistic latent semantic analysis

A technology for underwater target and semantic analysis, applied in signal pattern recognition, instrument, character and pattern recognition, etc., can solve the problem of low time-frequency resolution, large impact on accuracy, lack of self-adaptive ability, etc. question

Active Publication Date: 2021-01-05
OCEAN UNIV OF CHINA
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 1) The traditional method extracts features in a single direction in the time domain or frequency domain. For an acoustic signal, time and frequency can both reflect the characteristics of the acoustic signal. The traditional method fails to combine the two for research, and the impact of noise on the accuracy Greater impact
[0007] 2) For wavelet analysis, although it can provide localized information in the time domain and frequency domain of the sound signal at the same time, its time-frequency resolution is not high and it does not have adaptive capabilities

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
  • Underwater target signal feature extraction method based on probabilistic latent semantic analysis
  • Underwater target signal feature extraction method based on probabilistic latent semantic analysis
  • Underwater target signal feature extraction method based on probabilistic latent semantic analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0068] The present invention provides a method for extracting underwater target signal features based on probabilistic latent semantic analysis, such as figure 1 As shown, it specifically includes the following steps:

[0069] Step 1: Process the underwater target signal mixed with noise to obtain the noise-reduced spectrogram

[0070] The collected signal includes sound source signal and noise signal, expressed as:

[0071]

[0072] Among them, P(f,t) represents the mixed signal at time t and frequency f, S and N represent sound source and noise respectively, P(z s ) and P(z n ) respectively represent the possibility distribution of the latent variable z in the sound source signal and the noise signal, P(f|z s ) and P(t|z s ) represent the frequency possibility dist...

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 an underwater target signal feature extraction method based on probability latent semantic analysis, and the method comprises the following steps: processing an underwater target signal mixed with noise to obtain a noise reduction spectrogram, and carrying out the spectrum reliability weight calculation through an original spectrogram v and the noise reduction spectrogram;obtaining a noise reduction spectrogram Sn of the nth frequency band after weighting; carrying out short-time Fourier transform on Sn to obtain a signal pair, filtering the signal pair by using a frequency spectrum triangular filter, carrying out matrix decomposition on the whole frequency spectrum pair after filtering, and extracting first L feature vectors with the highest contribution rate to form an acoustics subspace; performing normalization calculation on the extracted first L feature vectors, and connecting the normalized L feature vectors to construct an acoustic feature vector. According to the method disclosed by the invention, the characteristics of the sound signal are reflected by combining time and frequency, and the noise pollution can be reduced, so that the sound signal can be more effectively represented.

Description

technical field [0001] The invention relates to a method for extracting underwater target signal features based on probabilistic latent semantic analysis. Background technique [0002] The development and utilization of marine resources is an important way to achieve sustainable development, and underwater target recognition can better carry out ocean exploration and marine life protection. Underwater target recognition technology is divided into active recognition and passive recognition. The former uses sonar to emit pulse signals and judge the target according to the characteristics of the received echo signal. The advantage is that the echo signal contains a large amount of information that reflects the essential characteristics of the target. , but the disadvantage is that it is easy to expose. Passive target recognition can be classified and judged by receiving underwater target radiation noise characteristics through passive sonar. [0003] Target feature extraction...

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): G06K9/00
CPCG06F2218/06G06F2218/10
Inventor 殷波魏志强贾东宁
Owner OCEAN UNIV OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com