Unlock instant, AI-driven research and patent intelligence for your innovation.

Snoring Feature Extraction and Detection Method and Device Based on Complex Derivative Processing

A complex number and step derivative technology, applied in the field of signal processing and sound detection, can solve the problems of increased hardware cost, low cost, complex recognition rate of snoring recognition algorithm, etc., and achieve the effect of improving accuracy and reducing complexity

Active Publication Date: 2022-05-17
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the snoring sound features obtained by using the existing snoring sound processing method are not significantly different from other sound signals, the snoring sound recognition algorithm becomes complicated, the recognition rate is not high, and the hardware cost increases, so it cannot be widely used in civilian products.

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
  • Snoring Feature Extraction and Detection Method and Device Based on Complex Derivative Processing
  • Snoring Feature Extraction and Detection Method and Device Based on Complex Derivative Processing
  • Snoring Feature Extraction and Detection Method and Device Based on Complex Derivative Processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] In this embodiment, feature extraction and snoring detection are performed by using the feature that the projection of the complex derivative of the snoring signal on the plane where the time axis and the real axis are located is significantly different in amplitude from other sounds.

[0054] see figure 2 , 3 , (c) in 4, on the projection of the snoring sound, mobile phone music sound and percussion sound on the plane where the time axis and the real axis are located, the thickness of the graphics is different, that is, the amplitude is different. Then, the amplitude in this embodiment refers to the distance of the complex order derivative of the audio signal from the time axis in the projection of the time axis and the plane where the real axis is located, that is, the absolute value of the real part amplitude of the complex order derivative. In order to measure the size of the data, the average value of the absolute value of the real part amplitude of the complex d...

Embodiment 2

[0087] In this embodiment, feature extraction and snoring detection are performed by utilizing the feature that the projection of the complex derivative of the snoring signal on the complex plane is significantly different from other sounds in amplitude. see figure 2 , 3 , (d) in 4, the snoring sound, mobile phone music sound and percussion sound are projected on the complex plane, the size of the graph is different, and the size of the circle can be measured by the radius of the circle. The circular radius can be calculated by using the signal amplitude. For the complex plane, the signal amplitude can be regarded as the distance between a point on the complex plane and the origin of the complex plane. Then, in this embodiment, the average value of the distance between the point formed by the real part and the imaginary part of the audio signal processed by the complex order derivative on the complex plane and the origin of the complex plane can be calculated as the snore d...

Embodiment 3

[0095] The present invention also provides a snoring sound feature extraction method based on complex derivative processing, comprising the following steps:

[0096] Step A, obtaining the complex order derivative of the audio signal; the step A includes:

[0097] a1. Perform fast Fourier transform on the audio signal x(t), obtain the complex form of x(t) and express it as a sequence: {X k},k=0,1,...,(N-1), k represents the kth element in the sequence, and N is the total number of elements in the sequence;

[0098] a2. Obtain the complex number sequence {X k},k=0,1,...,(N-1) the derivative X of each element (α+βi)k :

[0099] x (α+βi)k =(iω k ) α+βi x k ;

[0100] in, ω k for X k The angular frequency extracted in ; the selection range of the real part of the derivative order is 0<α<3, and the selection range of the imaginary part of the derivative order is 8<β<11;

[0101] a3, pair sequence {X (α+βi)k},k=0,1,...,(N-1) do inverse fast Fourier transform to obtain t...

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 snoring sound feature extraction and detection method based on complex derivative processing, step A, obtaining the complex derivative of the audio signal to be detected; step B, using the complex derivative of the snoring signal on the plane where the time axis and the real axis are located Or the projection of the complex plane is significantly different from other sounds in amplitude, extracting the snoring identification feature value from the complex order derivative of the audio signal to be detected; Step C, judging whether the snoring identification feature value is within the set threshold range; If yes, it is judged to be a snoring sound, otherwise it is not a snoring sound. The present invention also provides a device for extracting and detecting snoring sound features based on complex number order derivative processing, and a snoring sound feature extraction method based on complex number order derivative processing. The snoring feature extracted by the invention is obviously different from other sound features, which improves the accuracy of snoring detection and reduces the complexity of the algorithm.

Description

technical field [0001] The invention relates to the fields of signal processing and sound detection, in particular to a snoring sound feature extraction method based on complex derivative processing, a detection method and a device thereof. Background technique [0002] In daily life, snoring is a very common phenomenon. According to incomplete statistics from relevant organizations, approximately 20% to 40% of the population suffers from snoring symptoms. People who snore heavily will suffer from obstructive sleep apnea syndrome, which has a high prevalence rate and seriously affects human health. For this reason, researchers have proposed many anti-snoring or alleviating snoring devices, and recognizing the sound of snoring is a prerequisite for various anti-snoring or alleviating snoring devices. [0003] In the existing snore recognition method, it can be mainly summarized as the following two steps. First, the snoring signal is processed to obtain the characteristics ...

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 Patents(China)
IPC IPC(8): G10L25/51G10L25/66
CPCG10L25/51G10L25/66
Inventor 赵江波王晓东李杰周勇钟惠波
Owner BEIJING INSTITUTE OF TECHNOLOGYGY