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

Wide-nosed dolphin click signal detection method based on Gaussian mixture model

A Gaussian mixture model and signal detection technology, applied in measuring devices, character and pattern recognition, measuring ultrasonic/sonic/infrasonic waves, etc., to achieve simple results

Active Publication Date: 2018-10-09
西安巨通电梯有限公司
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are hundreds of methods for selecting the binarization threshold so far, there is still no general method that can achieve the most ideal effect for a variety of images.

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
  • Wide-nosed dolphin click signal detection method based on Gaussian mixture model
  • Wide-nosed dolphin click signal detection method based on Gaussian mixture model
  • Wide-nosed dolphin click signal detection method based on Gaussian mixture model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0123] The following uses the sound signal collected by a sound sensor as an example to illustrate the implementation process of a method for detecting click signals of bottlenose dolphins based on Gaussian mixture model clustering.

[0124] Step 1.1, collect the sound signal in the ocean by the sound sensor, and use the audioread function of MATLAB to read the sound signal in the ocean;

[0125] The sound signal in the ocean exists in the form of a matrix in MATLAB. The number of rows of the matrix represents the number of sampling points when the sound signal in the ocean is read, and the number of columns is the number of audio channels of the sound signal;

[0126] Step 1.2, adding a sliding Hanning window to the sound signal read into the ocean to truncate the signal to obtain a truncated signal;

[0127] Add a Hanning window to the sound signal read into the ocean, the time domain expression of the signal after windowing = the time domain expression of the original signa...

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 wide-nosed dolphin click signal detection method based on a Gaussian mixture model. Windowing Fourier transform is used to carry out time-frequency analysis on collected ocean signals to acquire an initial signal time-frequency map of the ocean sound signals, so that the implementation of subsequent steps is simple and fast. The soft clustering method of the Gaussian mixture model is used to carry out second clustering on the ocean sound signals, which improves the detection flexibility. The method has the advantages of high detection result accuracy and good integrity, and can be analogously used to detect sound signals of various dolphins.

Description

technical field [0001] The invention belongs to the technical field of sound signal processing, and in particular relates to a method for detecting a click signal of a bottlenose dolphin based on a Gaussian mixture model. Background technique [0002] Time-frequency analysis technology is one of the research contents of digital signal processing. It is often used in signal processing, fault diagnosis, feature extraction and other fields. It can clearly describe the relationship between signal frequency and time variation. The basic idea of ​​short-time Fourier transform is to add a sliding time window (truncated) to the signal, and perform Fourier transform on the signal in the window to obtain the frequency domain data of the signal. The essence of windowing is to use a so-called window function to multiply the original time-domain signal, so that the multiplied signal seems to better meet the periodicity requirements of Fourier transform. [0003] Clustering is a part of ...

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
IPC IPC(8): G01H17/00G06K9/62G06K9/38
CPCG01H17/00G06V10/28G06F18/2321
Inventor 金海燕张萌肖照林李秀秀
Owner 西安巨通电梯有限公司
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

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