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

Adaptive filtering method based on non-contact sensor

An adaptive filtering and non-contact technology, applied in the field of intelligent medical treatment, can solve the problems of weak BCG signal, individual differences in signals and environmental noise differences, signal drowning, etc.

Pending Publication Date: 2020-10-30
YANGTZE DELTA REGION INST OF TSINGHUA UNIV ZHEJIANG
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the BCG signal collected above is relatively weak and is extremely susceptible to noise interference
If the collected signal is not filtered, the real signal will be overwhelmed by noise
Moreover, the traditional filtering method will select a fixed filtering frequency segment, and then pass the signal through the corresponding filter to filter out part of the noise signal, but does not consider the individual differences of the signal and the difference of the environmental noise, and the filtering effect is not good.

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
  • Adaptive filtering method based on non-contact sensor
  • Adaptive filtering method based on non-contact sensor
  • Adaptive filtering method based on non-contact sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Example one: such as figure 1 As shown, which is only one of the embodiments of the present invention, a non-contact sensor-based adaptive filtering method includes the following steps:

[0038] An adaptive filtering method based on non-contact sensors includes the following steps:

[0039] S1: Obtain the original signal of mixed noise;

[0040] The original signal of the mixed noise is obtained through the non-contact sensor installed on the bed, and the sampling frequency is 500HZ.

[0041] After step S1 is executed, the original signal is processed in segments, and the length of each segment is 20 seconds.

[0042] S2: Initialize the particle swarm parameters;

[0043] When step S2 is performed, the particle swarm parameters include the number of populations and the number of iteration steps, and the range of each particle is initialized randomly, that is, the filter range.

[0044] S3: Perform band-pass filtering according to different filtering ranges of each particle;

[0045]...

Embodiment 2

[0056] Embodiment two: such as figure 2 As shown, it is only one of the embodiments of the present invention, a non-contact sensor-based adaptive filtering method. When step S2 is performed, the particle swarm parameters include the number of populations and the number of iteration steps, where the number of populations is n Not more than 5, and the number of iteration steps m is not more than 5.

[0057] In addition, when step S6 is performed, when the particle population does not meet the maximum iteration range or the optimal fitness value, return to step S3, perform particle signal calculation again iteratively, calculate the number of re-iterations, and determine whether the number of re-iterations is not greater than 5, If yes, continue to return to step S3 for iteration; otherwise, stop iteration.

[0058] It should be noted that to calculate the number of re-iterations, the value of the number of iteration steps m of the last iteration plus one, that is, the value of the n...

Embodiment 3

[0060] Embodiment three: such as image 3 As shown, it is only one of the embodiments of the present invention. A non-contact sensor-based adaptive filtering method. The specific algorithm process in the particle swarm algorithm is as follows:

[0061] First, obtain the original signal of the mixed noise and process it in segments. The length of each signal segment is 20 seconds, denoted as F(t);

[0062] Second, initialize the particle swarm parameters;

[0063] Third, perform band-pass filtering according to the different filtering ranges of each particle. After filtering, the signal is Fn(t), where n = 1, 2...5, representing different particles;

[0064] Fourth, calculate the Hilbert yellow transform H(t) of F(t);

[0065] Fifth, calculate the envelope E(t) of the signal;

[0066] Sixth, perform Fourier transform on the calculated envelope signal to obtain the frequency spectrum signal f(w);

[0067] Seventh, normalize the frequency spectrum to fnorm(w);

[0068] Eighth, calculate the p...

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 provides an adaptive filtering method based on a non-contact sensor, and relates to the technical field of intelligent medical treatment. The method comprises the steps of S1, obtaininga mixed noise original signal; s2, initializing particle swarm parameters; s3, performing band-pass filtering according to different filtering ranges of the particles; s4, calculating an original signal envelope line, and obtaining a frequency spectrum signal; s5, obtaining a particle fitness function, updating the speed and position of the particles, and updating the particle population; s6, judging whether the particle swarm meets a maximum iteration range or an optimal fitness value or not, if so, stopping iteration, and executing S7; otherwise, returning to S3; and S7, acquiring a cardiogram signal. The self-adaptive filtering method based on the non-contact sensor can adapt to the influence caused by individual difference of signals and difference of environmental noise, the optimal filtering range is automatically found through the particle swarm algorithm according to the characteristics of the signals, then filtering is carried out in combination with a corresponding filter, and the filtering effect is good.

Description

Technical field [0001] The present invention relates to the field of intelligent medical technology, [0002] In particular, the present invention relates to an adaptive filtering method based on a non-contact sensor. Background technique [0003] In recent years, with the improvement of technology and economy, people are paying more and more attention to their own health problems. Changes in the heartbeat rhythm beyond the normal range usually indicate the occurrence of certain diseases, such as sudden cardiac death, asphyxia, and arrhythmia. Therefore, heart rate monitoring in daily life is of great significance for the early detection and treatment of people's own diseases. [0004] Cardiac shock signal (BCG) is a physiological signal that can reflect the activity of the human heart. It can use non-contact sensors to continuously collect BCG signals when the human body is insensitive. For example, the Chinese patent invention patent CN109431482A relates to a non-contact type ma...

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): G06K9/00G06N3/00A61B5/024
CPCG06N3/006A61B5/024G06F2218/04G06F2218/08
Inventor 李红文杨向东韩秀萍王家冬曹凯敏朱震宇陈鑫
Owner YANGTZE DELTA REGION INST OF TSINGHUA UNIV ZHEJIANG