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

Fetal heart sound denoising method

A fetal heart sound and fetal sound technology, applied in the field of signal processing, can solve the problems of low energy of fetal heart sound and difficulty in extracting fetal heart sound

Inactive Publication Date: 2016-01-13
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the energy of fetal heart sounds is low and the spectrum range is wide (20-150Hz), which makes it difficult to extract fetal heart sounds

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
  • Fetal heart sound denoising method
  • Fetal heart sound denoising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Such as Figure 1 ~ Figure 2 As shown, a method for fetal heart sound denoising, the method steps are as follows:

[0026] A. Segment the fetal heart sound signal X: the fetal heart sound signal X is obtained by collecting a fetal heart sound cycle of the fetal heart sound, and the maximum number of points of a fetal sound cycle is calculated according to the sampling frequency to be A, and the total number of fetal heart sound signal X Length L; Calculate the minimum segment number N of the fetal heart sound signal X according to the formula N=L / A, and carry out segmentation at the maximum point value of the fetal heart sound signal X:

[0027] B. Determine the reference fetal sound signal S: the steps are as follows:

[0028] b1, calculate the signal-to-noise ratio of each segment of the fetal heart sound signal X in step A, select the maximum value and the minimum value in the signal-to-noise ratio in all segments, and obtain the average value of the maximum value a...

Embodiment 2

[0038] Such as Figure 1 ~ Figure 2 As shown, a method for fetal heart sound denoising, the method steps are as follows:

[0039] A. According to the sampling frequency, the maximum number of points for calculating a fetal sound cycle is s_max, and the minimum number of segments is calculated according to the total length Length and s_max of the fetal sound signal X: Num=Length / s_max.;

[0040] The specific implementation steps of step A are as follows:

[0041] A1. The maximum number of points for calculating a fetal sound cycle according to the sampling frequency is s_max;

[0042] A2. Calculate the minimum segment number according to the total length Length and s_max of the fetal sound signal X: Num=Length / s_max.

[0043] B. Calculate the signal-to-noise ratio of each segment, if the signal-to-noise ratio of three consecutive segments is greater than the threshold TH, then save these three segments as the reference fetal sound signal S. The selection method of the thresh...

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 fetal heart sound denoising method. The fetal heart sound denoising method includes segmenting a collected fetal heart sound signal, selecting a collected segment with good quality as reference, performing empirical mode decomposition to decompose the signal into a plurality of IMF components, performing discrete wavelet transform on the prior two IMF components, and performing ICA (independent component analysis) estimation on the transformed signal to obtain two independent wavelets; combining the two independent wavelets with each segment of the fetal heart sound signal, separating the mixed signal according to an ICA method, extracting a signal with small noise, and naming the signal as a pure signal; further analyzing the extracted pure fetal heart sound signal to obtain the denoised fetal heart sound signal. By the fetal heart sound denoising method, accurate, quick and high-quality fetal heart sound signals can be provided for fetal detecting and monitoring in pregnancy period.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a method for denoising fetal heart sounds. Background technique [0002] Fetal detection during pregnancy is an important process of maternal and child health care. Long-term and effective monitoring of fetal detection can help obstetricians determine the health of the fetus, diagnose and treat as early as possible. [0003] Current techniques for detecting fetal health rely largely on ultrasound images, but such techniques cannot provide long-term predictions of fetal disease. The extraction of fetal heart sounds can be achieved by placing a sensitive transducer in the mother's abdomen, but the sound energy we can hear is very low due to the sound wave damping of the amniotic fluid and maternal tissue in the mother's body. Therefore, the signal is often interfered by noise from the parent body, the external environment and the sensor itself. In addition, the energy o...

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): A61B5/024
Inventor 梁庆真刘传银
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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