Supervised snore source identifying method

A recognition method and supervised technology, applied in the field of non-speech recognition, can solve the problems of complex multi-layer neural network structure, many training parameters, low learning feature efficiency, etc., to achieve accurate recognition results, few weight parameters, and excellent performance. Effect

Active Publication Date: 2017-06-13
NANJING UNIV OF SCI & TECH
View PDF2 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the multi-layer neural network has a complex structure, too many...

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
  • Supervised snore source identifying method
  • Supervised snore source identifying method
  • Supervised snore source identifying method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] The present embodiment has supervised snore source identification method, and the steps are as follows:

[0062] Step 1, through human auditory judgment and figure 2 After observing and confirming the time-spectrum diagram shown, the measured data is marked, wherein, figure 2 (a) is the time-domain diagram of the measured data, figure 2 (b) is the frequency domain diagram of the measured data. Count the start and end positions of the pure snore segment in the EXCEL table.

[0063] Step 2. Based on the starting point of the snoring sound recorded in the EXCEL table as the standard, Mel frequency transformation is performed in frames, and the spectrum amplitude is normalized to form a data sample, such as image 3 shown.

[0064] combine figure 1 , the snoring signal is divided into frames and Mel frequency conversion processing is as follows:

[0065] Step 2-1. Taking the recorded snoring start point as the standard, the data with a duration of 1 second after th...

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 supervised snore source identifying method. The method includes data pretreatment, training and identification; the main steps include, firstly, performing Mel frequency conversion on actual measured snore data, and acquiring a data sample; secondly, arranging a structure of a convolution neutral network, quantity of output feature drawings of a convolution layer and convolution core size, pooling size, weight vector updating studying rate, batch training sample number, and training iterations; thirdly, using a snore time frequency spectrogram of a training set as the convolution neutral network to input; performing network initialization on the arranged network structure; completing the training process through forward process, direction bias transmission, weight value updating and offset until the appointed iterations; at last, delivering the testing set to the trained network model and acquiring the identifying result. The supervised snore source identifying method can effectively identify the snore source, and is exact in identifying result and good in performance.

Description

technical field [0001] The invention belongs to the technical field of non-speech recognition, in particular to a supervised snoring sound source recognition method. Background technique [0002] Obstructive sleep apnea / hypopnea syndrome is a sleep-breathing disorder closely related to upper airway obstruction, structural airway narrowing, and lowered upper airway muscle tone. Obstructive sleep apnea syndrome alone affects approximately 15 million adults in the United States, and is common in patients with high blood pressure and other cardiovascular conditions, including coronary heart disease, stroke and atrial fibrillation. The incidence rate of obstructive sleep apnea / hypopnea syndrome is high worldwide, and the incidence rate of men is higher than that of women (the prevalence rate of adult men is 3% to 7%, and that of adult women is 2% to 5%). Obstructive sleep apnea / hypopnea syndrome is often accompanied by symptoms such as snoring, sleep structure disturbance, frequ...

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): A61B5/00G10L15/22G10L15/16G10L19/032
CPCA61B5/4818A61B5/7235A61B5/7264A61B5/7267G10L15/16G10L15/22G10L19/032
Inventor 贺冲李阳许志勇田巳睿赵兆
Owner NANJING UNIV OF SCI & TECH
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap