CN113205022A - Respiratory anomaly monitoring method and system based on wavelet analysis - Google Patents
Respiratory anomaly monitoring method and system based on wavelet analysis Download PDFInfo
- Publication number
- CN113205022A CN113205022A CN202110442290.5A CN202110442290A CN113205022A CN 113205022 A CN113205022 A CN 113205022A CN 202110442290 A CN202110442290 A CN 202110442290A CN 113205022 A CN113205022 A CN 113205022A
- Authority
- CN
- China
- Prior art keywords
- respiratory
- signal
- humidity
- waveform signal
- wavelet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000241 respiratory effect Effects 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000012544 monitoring process Methods 0.000 title claims abstract description 74
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 41
- 230000009467 reduction Effects 0.000 claims abstract description 29
- 230000003044 adaptive effect Effects 0.000 claims abstract description 25
- 238000007637 random forest analysis Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims abstract description 7
- 238000003066 decision tree Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 7
- 238000013138 pruning Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 5
- 230000010355 oscillation Effects 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 23
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 208000024584 respiratory abnormality Diseases 0.000 description 3
- 208000008784 apnea Diseases 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 229920000642 polymer Polymers 0.000 description 2
- 201000002859 sleep apnea Diseases 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010006334 Breathing abnormalities Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000002209 hydrophobic effect Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- -1 vinyl hexyl imidazole bromide Chemical compound 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0809—Detecting, measuring or recording devices for evaluating the respiratory organs by impedance pneumography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/082—Evaluation by breath analysis, e.g. determination of the chemical composition of exhaled breath
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4818—Sleep apnoea
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/52—Scale-space analysis, e.g. wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention relates to the technical field of respiratory monitoring, and discloses a respiratory anomaly monitoring method based on wavelet analysis, which comprises the following steps: designing a humidity sensor, and monitoring a respiratory waveform signal of a user by using the humidity sensor; fitting the respiratory waveform signal by using a fitting method based on an interpolation function to determine a frequency band boundary of the respiratory waveform signal; designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal; performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal; and carrying out respiratory anomaly identification monitoring on the denoised respiratory signals by using a random forest model. The invention also provides a respiratory anomaly monitoring system based on wavelet analysis. The invention realizes the abnormal monitoring of the respiration.
Description
Technical Field
The invention relates to the technical field of respiratory monitoring, in particular to a respiratory anomaly monitoring method and system based on wavelet analysis.
Background
With the continuous progress of science and technology, people pay more and more attention to their own health, and how to monitor the health status more conveniently becomes the problem to be solved urgently.
The respiratory monitoring method is a common method for preventing sudden onset of the apnea syndrome, and when the patient suffering from the sleep apnea syndrome has apnea during sleep, the respiratory monitoring system can find the condition at the first time and send an alarm, so that valuable time is gained for the treatment of sudden apnea.
The conventional respiration monitoring method is to monitor respiration by using a pressure sensor, and the principle of the method is that when a subject exhales air, the pressure monitored by the sensor increases, so that the respiration of the patient is monitored, but the patient must wear a heavy and inflexible mask and an uncomfortable nasal cannula, which may adversely affect the respiration of the patient.
In view of this, how to implement simpler and more convenient respiratory anomaly monitoring becomes a problem to be urgently solved by those skilled in the art.
Disclosure of Invention
The invention provides a respiratory anomaly monitoring method based on wavelet analysis, which monitors a respiratory waveform signal of a user by using a humidity sensor, determines a frequency band boundary of the respiratory waveform signal by using a fitting method based on an interpolation function, designs a wavelet filter based on the determined frequency band boundary, performs adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter, performs noise reduction processing on the decomposed signal by using a wavelet threshold function, and performs respiratory anomaly identification on the respiratory signal subjected to noise reduction by using a random forest model.
In order to achieve the above object, the present invention provides a respiratory anomaly monitoring method based on wavelet analysis, which includes:
designing a humidity sensor, and monitoring a respiratory waveform signal of a user by using the humidity sensor;
fitting the respiratory waveform signal by using a fitting method based on an interpolation function to determine a frequency band boundary of the respiratory waveform signal;
designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal;
performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal;
and carrying out respiratory anomaly identification monitoring on the denoised respiratory signals by using a random forest model.
Optionally, the monitoring the respiration waveform signal of the user by using the humidity sensor includes:
in a specific embodiment of the invention, the preparation method comprises the steps of taking sulfydryl-containing silsesquioxane as a hydrophobic matrix material, taking vinyl hexyl imidazole bromide as a humidity sensing group, and preparing the resistance type high polymer humidity sensitive element by utilizing a one-step method in-situ alkene-sulfydryl click chemistry;
the process of calculating the real-time respiration waveform signal of the user according to the impedance change of the humidity sensor in different environments comprises the following steps:
1) reading the oscillation frequency of the humidity sensitive element under different humidity environments; wherein the output signal of the humidity sensitive element is a square wave signal;
2) at the same constant temperature t0Then, the frequency compensation processing is carried out on the frequency of the humidity sensitive element by using a frequency compensation formula, wherein the frequency compensation formula is as follows:
f′＝f+(t-t0)*1.5
wherein:
t0is the current ambient temperature;
t is a standard temperature, which is set to 20 ℃;
f is the read humidity sensor frequency;
f' is the compensated humidity sensitive element frequency;
3) taking the frequencies with different relative humidity values of 11% RH, 51% RH, 72% RH and 85% RH as standard points, and drawing a change curve of the humidity sensitive element frequency along with the humidity according to the standard points;
4) when the output frequency of unknown humidity is measured, calculating by utilizing a piecewise linear interpolation method to obtain a humidity value exhaled by the user; the formula of the piecewise linear interpolation method is as follows:
wherein:
x is an unknown humidity value to be measured;
y is the monitored humidity sensitive element frequency;
(a0，b0) And (a)1，b1) The standard point of the frequency interval where the unknown humidity value is located is obtained;
and taking the waveform of the humidity change of the user as a real-time respiration waveform of the user, and taking the humidity waveform signal of the user as a real-time respiration waveform signal of the user.
Optionally, the fitting the respiratory waveform signal by using a fitting method based on an interpolation function includes:
1) carrying out discrete Fourier transform processing on the respiration waveform signal to obtain X (k);
2) performing discrete space expression processing on X (k) by using a discrete scale space formula, wherein the discrete scale space formula is as follows:
L(k，δ)＝g(k,δ)X(k)
wherein:
g (k, delta) is a discrete Gaussian kernel and can be subjected to iterative convolution;
delta is a proportionality coefficient;
obtaining a plurality of different scales L (k, delta) by continuously carrying out iterative convolution processing on the discrete Gaussian kernel;
3) x (k) generating space curves with different scales at a local minimum value i of an x axis, wherein if the length of the space curve corresponding to the local minimum value i is less than a threshold value, an x axis coordinate corresponding to the local minimum value i is a signal boundary w of the respiration waveform signali(ii) a In one embodiment of the invention, the invention utilizes the Otsu algorithm to determine a spatial curve length threshold;
4) dividing X (k) into M segments according to the determined M signal boundaries, wherein the corresponding signal boundary is w ═ w { (w) }0,…,wM-1In which w0＝0，wM-1The monitored humidity sensitive element frequency;
5) search for the maximum X of the amplitude spectrum X (k) within each segment ii，maxObtaining M discrete amplitudes Q { (X)1，max，x1)，…，(XM，max,xM) In which xiDenotes X within the ith segmenti,maxThe abscissa of (a); fitting Q by using a quadratic spline interpolation method to obtain a curve Y (k);
6) dividing x (k) into N frequency bands by using frequencies corresponding to minimum points of curve y (k), wherein the boundaries of the intervals corresponding to the frequency bands are w '= { w'0，…，w′N-1And f, the frequency band boundary of the respiration waveform signal is obtained.
Optionally, the performing, by using a wavelet filter, an adaptive decomposition process on the respiration waveform signal includes:
the wavelet filter is as follows:
wherein:
β(x)＝x4(35-84x+70x2-20x3)；
εicontrol parameters of the ith frequency band;
the respiratory waveform signal x (t) is subjected to adaptive decomposition by using a wavelet filter, and the decomposition result is as follows:
wherein:
xi(t) a respiratory waveform signal representing the ith frequency band;
in a specific embodiment of the present invention, the adaptive decomposition signal obtained by the final decomposition is { x'1(t)，…，x′i(t)，…，x′N(t), where N is the number of divided bins.
Optionally, the performing noise reduction processing on the adaptive decomposition signal by using a wavelet threshold function includes:
the wavelet threshold function is:
wherein:
λ is the critical threshold.
Optionally, the performing, by using a random forest model, respiratory recognition monitoring on the noise-reduced respiratory signal includes:
acquiring N normal respiration signals and N abnormal respiration signals, and taking the signals as a training set; performing M rounds of self-help sampling (repeated independent sampling with replacement) on the training sets to obtain M training sets containing N training samples, and training M decision trees without pruning based on the training sets;
for each decision tree, pruning the decision tree by adopting a kini coefficient index;
and determining an optimal decision tree by adopting a voting mode, inputting the noise-reduced respiratory signal into the optimal decision tree, and finally obtaining the output result of the decision tree as a normal respiratory signal/an abnormal respiratory signal.
In addition, to achieve the above object, the present invention further provides a respiratory anomaly monitoring system based on wavelet analysis, the system comprising:
the breathing signal acquisition device is used for monitoring a breathing waveform signal of a user by using the humidity sensor;
the data processor is used for fitting the respiratory waveform signal by using a fitting method based on an interpolation function and determining a frequency band boundary of the respiratory waveform signal; designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal; performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal;
and the breathing abnormity monitoring device is used for identifying and monitoring the breathing abnormity of the noise-reduced breathing signal by utilizing the random forest model.
In addition, to achieve the above object, the present invention also provides a computer readable storage medium, which stores thereon breathing anomaly monitoring program instructions, which are executable by one or more processors to implement the steps of the implementation method of breathing anomaly monitoring based on wavelet analysis as described above.
Compared with the prior art, the invention provides a respiratory anomaly monitoring method based on wavelet analysis, and the method has the following advantages:
firstly, designing a humidity sensor by using a resistance type high-molecular humidity sensitive element, and calculating to obtain a real-time respiration waveform signal of a user according to impedance changes of the humidity sensor in different environments; the process of calculating the real-time respiration waveform signal of the user according to the impedance change of the humidity sensor in different environments comprises the following steps: reading the oscillation frequency of the humidity sensitive element under different humidity environments; wherein the output signal of the humidity sensitive element is a square waveA signal; meanwhile, because the humidity sensing degree of the resistance type polymer humidity sensitive element changes along with the change of the temperature, temperature compensation is added, namely, the temperature is compensated at the same constant temperature t0Then, the frequency compensation processing is carried out on the frequency of the humidity sensitive element by using a frequency compensation formula, wherein the frequency compensation formula is as follows:
f′＝f+(t-t0)*1.5
wherein: t is t0Is the current ambient temperature; t is a standard temperature, which is set to 20 ℃; f is the read humidity sensor frequency; f' is the compensated humidity sensitive element frequency; taking the frequencies with different relative humidity values of 11% RH, 51% RH, 72% RH and 85% RH as standard points, and drawing a change curve of the humidity sensitive element frequency along with the humidity according to the standard points; when the output frequency of unknown humidity is measured, calculating by utilizing a piecewise linear interpolation method to obtain a humidity value exhaled by the user; the formula of the piecewise linear interpolation method is as follows:
wherein: x is an unknown humidity value to be measured; y is the monitored humidity sensitive element frequency; (a)0,b0) And (a)1,b1) The standard point of the frequency interval where the unknown humidity value is located is obtained; the waveform of the humidity change of the user is used as the real-time respiration waveform of the user, so that the real-time respiration waveform signal of the user is effectively represented.
Meanwhile, fitting is carried out on the respiratory waveform signal by using a fitting method based on an interpolation function, and the frequency band boundary of the respiratory waveform signal is determined. Firstly, carrying out discrete Fourier transform processing on a respiration waveform signal to obtain X (k); and performing discrete space expression processing on X (k) by using a discrete scale space formula, wherein the discrete scale space formula is as follows:
L(k,δ)＝g(k,δ)X(k)
wherein: g (k, delta) is a discrete Gaussian kernel and can be subjected to iterative convolution; delta is a proportionality coefficient; obtaining a plurality of different scales L (k, delta) by continuously carrying out iterative convolution processing on the discrete Gaussian kernel; generating space curves with different scales by using a local minimum value i of X (k) on an x axis, wherein if the length of the space curve corresponding to the local minimum value i is less than a threshold value, an x axis coordinate corresponding to the local minimum value i is a signal boundary w of the respiration waveform signali(ii) a Dividing X (k) into M segments according to the determined M signal boundaries, wherein the corresponding signal boundary is w ═ w { (w) }0，…，wM-1In which w0＝0，wM-1The monitored humidity sensitive element frequency; search for the maximum X of the amplitude spectrum X (k) within each segment ii,maxObtaining M discrete amplitudes Q { (X)1,max，x1)，…，(XM，max，xM) In which xiDenotes X within the ith segmenti,maxThe abscissa of (a); fitting Q by using a quadratic spline interpolation method to obtain a curve Y (k); dividing x (k) into N frequency bands by using frequencies corresponding to minimum points of curve y (k), wherein the boundaries of the intervals corresponding to the frequency bands are w '= { w'0,…,w′N-1And f, the frequency band boundary of the respiration waveform signal is obtained. Compared with the traditional algorithm in which the kurtosis index is greatly interfered by noise, the method utilizes a scale expression method based on a discrete scale space to determine the heuristic band boundary, and performs adaptive signal decomposition according to the determined band boundary, and finally utilizes a wavelet threshold function to perform noise reduction processing on the adaptive decomposition signal, wherein the wavelet threshold function is as follows:
wherein:
the noise reduction signal is obtained after noise reduction processing; lambda is a critical threshold; compared with the problem that the discontinuity is generated at the partial point of the traditional wavelet threshold function, which may cause the uninterrupted oscillation of the reconstructed signal, the method and the device have the advantages thatThe proposed wavelet threshold function is continuous from place to place, as
The increase in the number of the first and second,
the number of the grooves is reduced, and the,
and
the deviation between the signals is small, so that the deviation between the signals after wavelet reconstruction and the real wavelet coefficients is reduced, and the smaller deviation between the de-noised signals and the original signals is ensured.
Drawings
Fig. 1 is a schematic flowchart of a respiratory anomaly monitoring method based on wavelet analysis according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a respiratory anomaly monitoring system based on wavelet analysis according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Monitoring a respiratory waveform signal of a user by using a humidity sensor, determining a frequency band boundary of the respiratory waveform signal by using a fitting method based on an interpolation function, designing a wavelet filter based on the determined frequency band boundary, performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter, performing noise reduction processing on the decomposed signal by using a wavelet threshold function, and performing respiratory anomaly identification on the respiratory signal subjected to noise reduction by using a random forest model. Fig. 1 is a schematic view of a respiratory anomaly monitoring method based on wavelet analysis according to an embodiment of the present invention.
In the embodiment, the respiratory anomaly monitoring method based on wavelet analysis comprises the following steps:
and S1, designing a humidity sensor, and monitoring the respiratory waveform signal of the user by using the humidity sensor.
Firstly, designing a humidity sensor by using a resistance type high-molecular humidity sensitive element, and calculating to obtain a real-time respiration waveform signal of a user according to impedance changes of the humidity sensor in different environments;
the process of calculating the real-time respiration waveform signal of the user according to the impedance change of the humidity sensor in different environments comprises the following steps:
1) reading the oscillation frequency of the humidity sensitive element under different humidity environments; wherein the output signal of the humidity sensitive element is a square wave signal;
2) at the same constant temperature t0Then, the frequency compensation processing is carried out on the frequency of the humidity sensitive element by using a frequency compensation formula, wherein the frequency compensation formula is as follows:
f′＝f+(t-t0)*1.5
wherein:
t0is the current ambient temperature;
t is a standard temperature, which is set to 20 ℃;
f is the read humidity sensor frequency;
f' is the compensated humidity sensitive element frequency;
3) taking the frequencies with different relative humidity values of 11% RH, 51% RH, 72% RH and 85% RH as standard points, and drawing a change curve of the humidity sensitive element frequency along with the humidity according to the standard points;
4) when the output frequency of unknown humidity is measured, calculating by utilizing a piecewise linear interpolation method to obtain a humidity value exhaled by the user; the formula of the piecewise linear interpolation method is as follows:
wherein:
x is an unknown humidity value to be measured;
y is the monitored humidity sensitive element frequency;
(a0，b0) And (a)1，b1) The standard point of the frequency interval where the unknown humidity value is located is obtained;
and taking the waveform of the humidity change of the user as a real-time respiration waveform of the user, and taking the humidity waveform signal of the user as a real-time respiration waveform signal of the user.
And S2, fitting the respiratory waveform signal by using a fitting method based on an interpolation function, and determining the frequency band boundary of the respiratory waveform signal.
Furthermore, the invention uses a fitting method based on an interpolation function to fit the respiratory waveform signal, and the fitting process comprises the following steps:
1) carrying out discrete Fourier transform processing on the respiration waveform signal to obtain X (k);
2) performing discrete space expression processing on X (k) by using a discrete scale space formula, wherein the discrete scale space formula is as follows:
L(k，δ)＝g(k,δ)X(k)
wherein:
g (k, delta) is a discrete Gaussian kernel and can be subjected to iterative convolution;
delta is a proportionality coefficient;
obtaining a plurality of different scales L (k, delta) by continuously carrying out iterative convolution processing on the discrete Gaussian kernel;
3) x (k) generating space curves with different scales at a local minimum value i of an x axis, wherein if the length of the space curve corresponding to the local minimum value i is less than a threshold value, an x axis coordinate corresponding to the local minimum value i is a signal boundary w of the respiration waveform signali(ii) a In a specific embodiment of the inventionIn the method, an Otsu algorithm is utilized to determine a space curve length threshold;
4) dividing X (k) into M segments according to the determined M signal boundaries, wherein the corresponding signal boundary is w ═ w { (w) }0,…，wM-1In which w0＝0，wM-1The monitored humidity sensitive element frequency;
5) search for the maximum X of the amplitude spectrum X (k) within each segment ii,maxObtaining M discrete amplitudes Q { (X)1,max,x1)，…，(XM，max，xM) In which xiDenotes X within the ith segmenti，maxThe abscissa of (a); fitting Q by using a quadratic spline interpolation method to obtain a curve Y (k);
6) dividing x (k) into N frequency bands by using frequencies corresponding to minimum points of curve y (k), wherein the boundaries of the intervals corresponding to the frequency bands are w '= { w'0，…,w′N-1And f, the frequency band boundary of the respiration waveform signal is obtained.
And S3, designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal.
Further, the present invention designs a wavelet filter according to the determined band boundary, the wavelet filter being:
wherein:
β(x)＝x4(35-84x+70x2-20x3)；
εicontrol parameters of the ith frequency band;
further, the invention uses wavelet filter to make self-adaptive decomposition on the respiration waveform signal x (t), the decomposition result is as follows:
wherein:
xi(t) a respiratory waveform signal representing the ith frequency band;
in a specific embodiment of the present invention, the adaptive decomposition signal obtained by the final decomposition is { x'1(t),…,x′i(t)，…，x′N(t), where N is the number of divided bins.
And S4, performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal.
Further, the invention utilizes wavelet threshold function to perform noise reduction processing on the self-adaptive decomposition signal, and the wavelet threshold function is as follows:
wherein:
λ is the critical threshold.
And S5, recognizing and monitoring the breathing abnormity of the noise-reduced breathing signal by using a random forest model.
Furthermore, the invention utilizes a random forest model to identify and monitor the breathing abnormity of the denoised breathing signal, and the flow of identifying and monitoring the breathing abnormity is as follows:
acquiring N normal respiration signals and N abnormal respiration signals, and taking the signals as a training set; performing M rounds of self-help sampling (repeated independent sampling with replacement) on the training sets to obtain M training sets containing N training samples, and training M decision trees without pruning based on the training sets;
for each decision tree, pruning the decision tree by adopting a kini coefficient index;
and determining an optimal decision tree by adopting a voting mode, inputting the noise-reduced respiratory signal into the optimal decision tree, and finally obtaining the output result of the decision tree as a normal respiratory signal/an abnormal respiratory signal.
The following describes embodiments of the present invention through an algorithmic experiment and tests of the inventive treatment method. The hardware test environment of the algorithm of the invention is as follows: inter (R) core (TM) i7-6700K CPU with software Matlab2018 a; the comparison method is a respiratory anomaly monitoring method based on SVM and a respiratory anomaly monitoring method based on RNN.
In the algorithm experiment of the invention, the data set is 10G of respiratory signal data. According to the experiment, the respiratory signal data are input into the algorithm model, the accuracy rate of respiratory monitoring is used as an evaluation index of algorithm feasibility, and the higher the accuracy rate of respiratory monitoring is, the higher the effectiveness and the feasibility of the algorithm are.
According to the experimental result, the respiratory anomaly monitoring accuracy rate of the respiratory anomaly monitoring method based on the SVM is 83.1%, the respiratory anomaly monitoring accuracy rate of the respiratory anomaly monitoring method based on the RNN is 79.34%, the respiratory anomaly monitoring accuracy rate of the method is 86.73%, and compared with a comparison algorithm, the respiratory anomaly monitoring method based on the wavelet analysis can achieve higher respiratory anomaly monitoring accuracy rate.
The invention also provides a respiratory anomaly monitoring system based on wavelet analysis. Fig. 2 is a schematic diagram illustrating an internal structure of a respiratory anomaly monitoring system based on wavelet analysis according to an embodiment of the present invention.
In the present embodiment, the respiratory anomaly monitoring system 1 based on wavelet analysis at least includes a respiratory signal acquisition device 11, a data processor 12, a respiratory anomaly monitoring device 13, a communication bus 14, and a network interface 15.
The respiratory signal acquiring device 11 may be a PC (Personal Computer), a terminal device such as a smart phone, a tablet Computer, and a mobile Computer, or may be a server.
The data processor 12 includes at least one type of readable storage medium including flash memory, hard disks, multi-media cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, and the like. The data processor 12 may in some embodiments be an internal storage unit of the wavelet analysis based breathing anomaly monitoring system 1, for example a hard disk of the wavelet analysis based breathing anomaly monitoring system 1. The data processor 12 may also be an external storage device of the respiratory anomaly monitoring system 1 based on wavelet analysis in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the respiratory anomaly monitoring system 1 based on wavelet analysis. Further, the data processor 12 may also include both an internal memory unit and an external memory device of the respiratory abnormality monitoring system 1 based on wavelet analysis. The data processor 12 can be used not only to store application software installed in the respiratory abnormality monitoring system 1 based on wavelet analysis and various kinds of data, but also to temporarily store data that has been output or is to be output.
The respiratory anomaly monitoring device 13 may be, in some embodiments, a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip for running program code stored in the data processor 12 or Processing data, such as respiratory anomaly monitoring program instructions.
The communication bus 14 is used to enable connection communication between these components.
The network interface 15 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the system 1 and other electronic devices.
Optionally, the system 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the wavelet analysis based breathing abnormality monitoring system 1 and for displaying a visual user interface.
While fig. 2 only shows the respiratory anomaly monitoring system 1 with the components 11-15 and based on wavelet analysis, it will be understood by those skilled in the art that the configuration shown in fig. 1 does not constitute a limitation of the respiratory anomaly monitoring system 1 based on wavelet analysis, and may include fewer or more components than shown, or some components in combination, or a different arrangement of components.
In the embodiment of the apparatus 1 shown in fig. 2, the data processor 12 stores program instructions for monitoring respiratory abnormalities; the steps of the respiratory anomaly monitoring device 13 executing the respiratory anomaly monitoring program instructions stored in the data processor 12 are the same as the implementation method of the respiratory anomaly monitoring method based on wavelet analysis, and are not described here.
Furthermore, an embodiment of the present invention also provides a computer-readable storage medium having stored thereon respiratory anomaly monitoring program instructions executable by one or more processors to implement the following operations:
designing a humidity sensor, and monitoring a respiratory waveform signal of a user by using the humidity sensor;
fitting the respiratory waveform signal by using a fitting method based on an interpolation function to determine a frequency band boundary of the respiratory waveform signal;
designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal;
performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal;
and carrying out respiratory anomaly identification monitoring on the denoised respiratory signals by using a random forest model.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A respiratory anomaly monitoring method based on wavelet analysis, the method comprising:
designing a humidity sensor, and monitoring a respiratory waveform signal of a user by using the humidity sensor;
fitting the respiratory waveform signal by using a fitting method based on an interpolation function to determine a frequency band boundary of the respiratory waveform signal;
designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal;
performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal;
and carrying out respiratory anomaly identification monitoring on the denoised respiratory signals by using a random forest model.
2. The respiratory anomaly monitoring method based on wavelet analysis as claimed in claim 1, wherein said monitoring the respiratory waveform signal of the user with a humidity sensor comprises:
1) reading the oscillation frequency of the humidity sensitive element under different humidity environments; wherein the output signal of the humidity sensitive element is a square wave signal;
2) at the same constant temperature t0Then, the frequency compensation processing is carried out on the frequency of the humidity sensitive element by using a frequency compensation formula, wherein the frequency compensation formula is as follows:
f′＝f+(t-t0)*1.5
wherein:
t0is the current ambient temperature;
t is a standard temperature, which is set to 20 ℃;
f is the read humidity sensor frequency;
f' is the compensated humidity sensitive element frequency;
3) taking the frequencies with different relative humidity values of 11% RH, 51% RH, 72% RH and 85% RH as standard points, and drawing a change curve of the humidity sensitive element frequency along with the humidity according to the standard points;
4) when the output frequency of unknown humidity is measured, calculating by utilizing a piecewise linear interpolation method to obtain a humidity value exhaled by the user; the formula of the piecewise linear interpolation method is as follows:
wherein:
x is an unknown humidity value to be measured;
y is the monitored humidity sensitive element frequency;
(a0，b0) And (a)1，b1) The standard point of the frequency interval where the unknown humidity value is located is obtained;
and taking the waveform of the humidity change of the user as a real-time respiration waveform of the user, and taking the humidity waveform signal of the user as a real-time respiration waveform signal of the user.
3. The respiratory anomaly monitoring method based on wavelet analysis as claimed in claim 2, wherein said fitting respiratory waveform signal by using fitting method based on interpolation function comprises:
1) carrying out discrete Fourier transform processing on the respiration waveform signal to obtain X (k);
2) performing discrete space expression processing on X (k) by using a discrete scale space formula, wherein the discrete scale space formula is as follows:
L(k，δ)＝g(k，δ)X(k)
wherein:
g (k, δ) is a discrete gaussian kernel;
delta is a proportionality coefficient;
obtaining a plurality of different scales L (k, delta) by continuously carrying out iterative convolution processing on the discrete Gaussian kernel;
3) x (k) generating space curves with different scales at a local minimum value i of an x axis, wherein if the length of the space curve corresponding to the local minimum value i is less than a threshold value, an x axis coordinate corresponding to the local minimum value i is a signal boundary w of the respiration waveform signali；
4) Dividing X (k) into M segments according to the determined M signal boundaries, wherein the corresponding signal boundary is w ═ w { (w) }0，…,wM-1In which w0＝0，wM-1The monitored humidity sensitive element frequency;
5) search for the maximum X of the amplitude spectrum X (k) within each segment ii，maxObtaining M discrete amplitudes Q { (X)1，max,x1)，…，(XM，max，xM) In which xiDenotes X within the ith segmenti，maxThe abscissa of (a); fitting Q by using a quadratic spline interpolation method to obtain a curve Y (k);
6) dividing x (k) into N frequency bands by using frequencies corresponding to minimum points of curve y (k), wherein the boundaries of the intervals corresponding to the frequency bands are w '= { w'0，…，w′N-1And f, the frequency band boundary of the respiration waveform signal is obtained.
4. The respiratory anomaly monitoring method based on wavelet analysis as claimed in claim 3, wherein said adaptive decomposition processing of respiratory waveform signal by using wavelet filter includes:
the wavelet filter is as follows:
wherein:
β(x)＝x4(35-84x+70x2-20x3)；
εicontrol parameters of the ith frequency band;
the respiratory waveform signal x (t) is subjected to adaptive decomposition by using a wavelet filter, and the decomposition result is as follows:
wherein:
xi(t) a respiratory waveform signal representing the ith frequency band;
the self-adaptive decomposition signal obtained by decomposition is { x'1(t)，…，x′i(t)，…，x′N(t), where N is the number of divided bins.
5. The respiratory anomaly monitoring method based on wavelet analysis as claimed in claim 4, wherein said denoising the adaptively decomposed signal using wavelet threshold function comprises:
the wavelet threshold function is:
wherein:
λ is the critical threshold.
6. The respiratory anomaly monitoring method based on wavelet analysis as claimed in claim 5, wherein said performing respiratory recognition monitoring on denoised respiratory signals by using random forest model comprises:
acquiring N normal respiration signals and N abnormal respiration signals, and taking the signals as a training set; performing M rounds of self-help sampling (repeated independent sampling with replacement) on the training sets to obtain M training sets containing N training samples, and training M decision trees without pruning based on the training sets;
for each decision tree, pruning the decision tree by adopting a kini coefficient index;
and determining an optimal decision tree by adopting a voting mode, inputting the noise-reduced respiratory signal into the optimal decision tree, and finally obtaining the output result of the decision tree as a normal respiratory signal/an abnormal respiratory signal.
7. A respiratory anomaly monitoring system based on wavelet analysis, the system comprising:
the breathing signal acquisition device is used for monitoring a breathing waveform signal of a user by using the humidity sensor;
the data processor is used for fitting the respiratory waveform signal by using a fitting method based on an interpolation function and determining a frequency band boundary of the respiratory waveform signal; designing a wavelet filter according to the determined band boundary, and performing adaptive decomposition processing on the respiratory waveform signal by using the wavelet filter to obtain an adaptive decomposition signal; performing noise reduction processing on the self-adaptive decomposition signal by using a wavelet threshold function to obtain a noise reduction signal;
and the breathing abnormity monitoring device is used for identifying and monitoring the breathing abnormity of the noise-reduced breathing signal by utilizing the random forest model.
8. A computer readable storage medium having stored thereon breathing anomaly monitoring program instructions executable by one or more processors to implement the steps of a method for implementing wavelet analysis based breathing anomaly monitoring as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110442290.5A CN113205022B (en) | 2021-04-23 | 2021-04-23 | Respiratory anomaly monitoring method and system based on wavelet analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110442290.5A CN113205022B (en) | 2021-04-23 | 2021-04-23 | Respiratory anomaly monitoring method and system based on wavelet analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113205022A true CN113205022A (en) | 2021-08-03 |
| CN113205022B CN113205022B (en) | 2022-10-11 |
Family
ID=77028147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110442290.5A Active CN113205022B (en) | 2021-04-23 | 2021-04-23 | Respiratory anomaly monitoring method and system based on wavelet analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205022B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884758A (en) * | 2021-09-29 | 2022-01-04 | 广东电网有限责任公司 | Direct current electric energy metering method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101496716A (en) * | 2009-02-26 | 2009-08-05 | 周洪建 | Measurement method for detecting sleep apnoea with ECG signal |
| US20150190088A1 (en) * | 2014-01-07 | 2015-07-09 | Covidien Lp | Apnea analysis system and method |
| CN108186018A (en) * | 2017-11-23 | 2018-06-22 | 苏州朗开信通信息技术有限公司 | A kind of breath data processing method and processing device |
| CN109691999A (en) * | 2019-01-21 | 2019-04-30 | 深圳瀚维智能医疗科技有限公司 | Respiratory rate detection method, device, storage medium and computer equipment |
| WO2019132740A1 (en) * | 2017-12-29 | 2019-07-04 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Московский государственный университет имени М.В. Ломоносова" | Method of processing vector signals for pattern recognition on the basis of wavelet analysis |
| CN111968651A (en) * | 2020-08-25 | 2020-11-20 | 汪金玲 | WT (WT) -based voiceprint recognition method and system |
| CN112089413A (en) * | 2020-09-08 | 2020-12-18 | 长春理工大学 | Blocking type sleep apnea syndrome screening system |
| CN112245741A (en) * | 2020-11-06 | 2021-01-22 | 湖南万脉医疗科技有限公司 | Breathing machine adjusting method based on respiratory sleep event |
-
2021
- 2021-04-23 CN CN202110442290.5A patent/CN113205022B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101496716A (en) * | 2009-02-26 | 2009-08-05 | 周洪建 | Measurement method for detecting sleep apnoea with ECG signal |
| US20150190088A1 (en) * | 2014-01-07 | 2015-07-09 | Covidien Lp | Apnea analysis system and method |
| CN108186018A (en) * | 2017-11-23 | 2018-06-22 | 苏州朗开信通信息技术有限公司 | A kind of breath data processing method and processing device |
| WO2019132740A1 (en) * | 2017-12-29 | 2019-07-04 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Московский государственный университет имени М.В. Ломоносова" | Method of processing vector signals for pattern recognition on the basis of wavelet analysis |
| CN109691999A (en) * | 2019-01-21 | 2019-04-30 | 深圳瀚维智能医疗科技有限公司 | Respiratory rate detection method, device, storage medium and computer equipment |
| CN111968651A (en) * | 2020-08-25 | 2020-11-20 | 汪金玲 | WT (WT) -based voiceprint recognition method and system |
| CN112089413A (en) * | 2020-09-08 | 2020-12-18 | 长春理工大学 | Blocking type sleep apnea syndrome screening system |
| CN112245741A (en) * | 2020-11-06 | 2021-01-22 | 湖南万脉医疗科技有限公司 | Breathing machine adjusting method based on respiratory sleep event |
Non-Patent Citations (4)
| Title |
|---|
| BURÇIN CAMCI 等: "Abnormal respiratory event detection in sleep: A prescreening system with smart wearables", 《ELSEVIER》 * |
| 朱丹 等: "小波分解结合自适应神经模糊推理系统的呼吸预测研究", 《天津医科大学学报》 * |
| 杜臻 等: "一种基于小波分析的网络流量异常检测方法", 《计算机科学》 * |
| 黄青平 等: "基于小波分解与随机森林的短期负荷预测", 《电力信息与通信技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884758A (en) * | 2021-09-29 | 2022-01-04 | 广东电网有限责任公司 | Direct current electric energy metering method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113205022B (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105636515B (en) | Computer program for assessing inattentive EEG automatically and assessment equipment | |
| EP1954184B1 (en) | Residual-based monitoring of human health | |
| US10504036B2 (en) | Optimizing performance of event detection by sensor data analytics | |
| US20200201971A1 (en) | System and method for identifying user | |
| US20160029931A1 (en) | Method and system for processing and analyzing analyte sensor signals | |
| US11839480B2 (en) | Computer implemented method for analyzing electroencephalogram signals | |
| US20110029250A1 (en) | Non-Parametric Modeling Apparatus and Method for Classification, Especially of Activity State | |
| Zhou et al. | Optimizing autoencoders for learning deep representations from health data | |
| US20170220752A1 (en) | Systems and methods for probabilistic pulse rate estimation from photoplethysmographic measurements in the presence of nonstationary and nontrivial signal and noise spectra | |
| CN113205022B (en) | Respiratory anomaly monitoring method and system based on wavelet analysis | |
| Wang et al. | Image denoising based on improved wavelet threshold function for wireless camera networks and transmissions | |
| Liu et al. | ECG noise cancellation based on grey spectral noise estimation | |
| Afghah et al. | Game theoretic approach for systematic feature selection; application in false alarm detection in intensive care units | |
| WO2015011923A1 (en) | Biometric sound testing device and biometric sound testing method | |
| Rahul et al. | Short duration Vectorcardiogram based inferior myocardial infarction detection: class and subject-oriented approach | |
| Espinosa et al. | Effects of tau and sampling frequency on the regularity analysis of ecg and eeg signals using apen and sampen entropy estimators | |
| Shi et al. | Automated detection of sudden cardiac death by discrete wavelet transform of electrocardiogram signal | |
| He et al. | Multifractal analysis on age-based discrimination in X-ray images for sensing the severity of COVID-19 disease | |
| US9467182B2 (en) | Signal decomposition method and electronic apparatus using the same | |
| CN114176567B (en) | Computer-readable storage medium and terminal | |
| CN115349824A (en) | Health early warning method and device, computer equipment and storage medium | |
| Erkuş et al. | A new collective anomaly detection approach using pitch frequency and dissimilarity: Pitchy anomaly detection (PAD) | |
| Schmierer et al. | A novel empirical wavelet SODP and spectral entropy based index for assessing the depth of anaesthesia | |
| Zhang et al. | Refined composite multiscale fuzzy entropy based fault diagnosis of diesel engine | |
| Progonov et al. | Heartbeat-based authentication on smartwatches in various usage contexts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A respiratory anomaly monitoring method and system based on wavelet analysis Effective date of registration: 20231205 Granted publication date: 20221011 Pledgee: China Construction Bank Corporation Shaoyang Jianshe Road Sub-branch Pledgor: HUNAN VENT MEDICAL TECHNOLOGY Co.,Ltd. Registration number: Y2023980069588 |