CN108830255A - A kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal - Google Patents
A kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal Download PDFInfo
- Publication number
- CN108830255A CN108830255A CN201810694298.9A CN201810694298A CN108830255A CN 108830255 A CN108830255 A CN 108830255A CN 201810694298 A CN201810694298 A CN 201810694298A CN 108830255 A CN108830255 A CN 108830255A
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- wavelet
- peak
- point
- value
- 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.)
- Pending
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention discloses a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal, and step 1) obtains electrocardiosignal；Step 2) carries out Scale Decomposition with wavelet transformation to electrocardiosignal；Step 3) is denoised using soft-threshold algorithm；Electrocardiosignal is reconstructed in step 4)；Step 5) obtains all target tested points according to adaptive thresholding algorithm；Step 6) uses wave crest inspection policies, obtains the peak position R；Step 7) carries out missing inspection inquiry；Step 8) carries out erroneous detection inquiry, and algorithm terminates.The present invention carries out Scale Decomposition to electrocardiosignal using wavelet transformation, is denoised using Weighted Threshold algorithm, then extracts the peak R according to the methods of wave crest inspection policies, and method extracts the peak R according to the present invention, has satisfactory effect.
Description
Technical field
The present invention relates to a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal, belong to intelligent medical technical field.
Background technique
Electrocardiogram (Electrocardiogram, ECG) is a kind of electricity for being generated cardiac pacing by electrocardiogram acquisition equipment
The signal graph that position variation is recorded using the time as function, is the important evidence whether clinical diagnosis heart lesion occurs；Therefore, right
The analysis of electrocardiosignal is of great significance with identification, is the emphasis of research.
The human body electrocardio waveform diagram of normal health contains the most important feature of electrocardio by P wave, QRS complex and T wave component
Information.Each feature sub-waveform or interphase have its specific electrophysiology meaning in one complete cardiac electrical cycle waveform.Such as P wave
Potential change when due to Atrial depolarization before atrial contraction；QRS complex is due to the sequences of ventricular depolarization before ventricular contraction
When potential change；Potential change when T wave is ventricular bipolar.
Since electrocardiogram has many advantages, such as noninvasive, safe and simple, great convenience is provided for the diagnosis of clinical heart disease.
Traditional diagnostic method is patient to hospital, and doctor carries out ECG examination to it, and then provides diagnostic result, task it is heavy and
Doctor is needed to have clinical experience abundant and professional knowledge.And rare medical resource, it is difficult to meet substantial amounts PATIENT POPULATION
Requirement.
In order to improve medical efficiency, convenience and agility, there is automatically analyzing diagnosis ECG Technique, auxiliary doctor into
Row diagnosis, and handling and accurately identifying to electrocardiosignal, are the bases of automated diagnostic.
Automated diagnostic to electrocardiosignal is work that is very significant and having any problem again, and process mainly has signal
Pretreatment, feature extraction and diagnosis.The pretreatment of electrocardiosignal is the basis of ecg analysis, is the premise of follow-up work.Closely
A little years, Denoising Algorithm of ECG Signals mainly have the side such as traditional digital filtering method, improved sef-adapting filter, wavelet transformation
Method；The basic thought of these algorithms is converted a signal into frequency domain, is identified in primary frequency range to signal, is inhibited
Noise.
Feature extraction refers to extracting various parameters, provides foundation for diagnosis；QRS wave, P wave, T wave, waveform rise
Initial point and terminal etc. accurately identify be parameter extraction guarantee.Recognition detection method mainly have filtering and difference threshold algorithm,
Neural network, slope-threshold arithmetic, wavelet transformation etc..In ECG, R wave is most apparent feature, after the position for determining R wave,
The position of other waveforms can be found as benchmark, therefore, R wave is the key that ECG detection.
Summary of the invention
The object of the invention is that providing a kind of peak R based on Wavelet Denoising Method electrocardiosignal to solve the above-mentioned problems
Recognition methods extracts the methods of strategy by using wavelet transformation, threshold method and the peak R, comes the peak automatic identification R, to realize certainly
Dynamicization diagnosis, the waste alleviated medical resource in short supply, reduce medical resource improve medical efficiency offer basis.
The present invention is achieved through the following technical solutions above-mentioned purpose：A kind of peak R knowledge based on Wavelet Denoising Method electrocardiosignal
Other method, includes the following steps：
Step 1) obtains electrocardiosignal；
Step 2) carries out Scale Decomposition with wavelet transformation to electrocardiosignal；
Step 3) is denoised using soft-threshold algorithm；
Electrocardiosignal is reconstructed in step 4)；
Step 5) obtains all target tested points according to adaptive thresholding algorithm；
Step 6) uses wave crest inspection policies, obtains the peak position R；
Step 7) carries out missing inspection inquiry；
Step 8) carries out erroneous detection inquiry, and algorithm terminates.
The step 2) carries out Scale Decomposition with wavelet transformation to electrocardiosignal：
A. continuous wavelet transform
If Ψ (t) ∈ L2(R), Fourier transform is Ψ (ω), if met
Then Ψ (t) is morther wavelet, and morther wavelet is the starting point of wavelet transformation, is known as by the small echo that flexible and translation obtains
Wavelet basis function Ψa,τ(t), i.e.,
Wherein, a is scale factor, and τ is shift factor,It is to keep energy after function stretcher strain constant；L2
(R) refer to that R is the function space that quadractically integrable function is constituted；
Function inner product is
It is defined as the continuous wavelet transform (Continuous wavelet transform, CWT) of f (t), WTf(a, τ) is
Transformation coefficient；Its frequency domain of equal value is defined as
B. wavelet transform
Wavelet transform (Discrete wavelet transform, DWT) essence is that discretization is carried out to a and τ, one
Planting classical discrete way isa0,τ0∈ C > 0, m, k ∈ Z, bring into
In actual use, a is usually set0=2, τ0=1；
C. multiresolution analysis
Multiresolution analysis is also referred to as multiscale analysis, be by signal decomposition be different scale space and wavelet space in portion
Point；Realize function space L2(R) multiresolution analysis of small echo in, needs to construct the closed subspace for meeting following condition
{Vj}j∈Z, i.e.,
(1) Uniform Monotonicity：
(2) progressive completeness：∩j∈ZVj=φ ∪j∈ZVj=L2(R)
(3) two into flexible systematicness：
(4) translation invariance：
(5) orthogonal basis existence：There are φ (t) ∈ V0, so that { φ (t-n) }n∈ZAs V0Orthogonal basis, i.e.,And < φ (t-n), φ (t-m) >=δ (n-m), commonly referred to as VjFor the scale space of scale j, φ (t)
The referred to as scaling function of multiresolution analysis.
The step 2) is denoised using soft-threshold algorithm, including：
8 layers of wavelet decomposition, denoising are carried out to electrocardiogram (ECG) data using DB4 small echo：
1st layer is set 0 with layer 7 detail coefficients and the 8th layer of approximation coefficient, directly removal radio-frequency component and baseline drift；
3rd layer to the 6th layer uses soft-threshold algorithm；Retain the characteristic component in electrocardiosignal to the greatest extent, reduces letter
Number reconstruct when distortion.
Step 5) obtains all target tested points according to adaptive thresholding algorithm, including：
After electrocardiosignal after being reconstructed, the positive negative threshold value of signal is sought according to this；In view of the difference between individual,
The data of sample frequency interception 10s are first depending on, by 10 sections of data etc. point, maximizing and minimum value are distinguished in each section,
Take 0.7 times of its mean value initial threshold as lookup R crest value；It is respectively labeled as max_th, min_th；
In order to improve detection accuracy, using a kind of more new strategy for adaptively R-wave amplitude being followed to change, respectively with 0.3 with
0.7 weight distribution obtains next threshold value to present threshold value and the extreme point found, with this；By taking positive peak as an example, update public
Formula is：
In max_th=0.3 × max_th+0.7 × 0.7max_c formula, max_c is the current extreme value point amplitude found, is led to
This method is crossed to make threshold value adapt to the mutation of signal.
Step 6) uses wave crest inspection policies, obtains the peak position R comprising following procedure：
S1~s6 is data point, takes three points first, calculates the distance between two adjacent data points, is denoted as temp1 respectively,
Temp2, if (temp1 < RR_thr) && (temp2 < RR_thr) is set up, and illustrates s1, s2, s3 be in the same packet,
As shown in r1 packet；
When getting s4, when s5, s6, s5, the distance between s6 is larger, is unsatisfactory for Rule of judgment to get s6 and s1~s5 not
In the same packet, which terminates, and so on；
The distance between two o'clock is 1 in the same packet under normal circumstances, and normal person RR interphase is generally not less than 200ms,
Parameter RR_thr is set as 30, and in s1~s5, the maximum of points found is exactly R crest value point.
Step 7) carries out missing inspection inquiry, and process is as follows：
The sequence information searched using adaptive threshold, calculate two data between interval, judge interval whether be more than
1.8 times of its equispaced；Equispaced is the average value at 10 intervals RR.
The inquiry of step 8) error is whether the interval detected between two data meets erroneous detection condition, if it is satisfied, then deleting
This point；By taking positive value as an example, in two steps：
(1) distance of point-to-point transmission is calculated
Dis=max_index (i+1)-max_index (i)
(2) judge whether to meet erroneous detection condition
Erroneous detection condition is dis < median (RR), and satisfaction then deletes i+1 point.
Compared with prior art, the present invention carries out Scale Decomposition to electrocardiosignal using wavelet transformation, uses Weighted Threshold
Algorithm is denoised, then extracts the peak R according to the methods of wave crest inspection policies, to realize automated diagnostic, alleviating medical treatment in short supply
Resource, the waste for reducing medical resource improve medical efficiency offer basis.
Detailed description of the invention
Fig. 1 is specific method flow chart of the present invention；
Fig. 2 is particle swarm algorithm of the present invention and other algorithm performance comparison diagrams；
Fig. 3 is inventive algorithm figure compared with the performance of filter that other methods design；
Fig. 4 is R wave crest inspection policies schematic diagram of the present invention；
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Fig. 1, a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal, which is characterized in that including following
Step：
Step 1) obtains electrocardiosignal；
Step 2) carries out Scale Decomposition with wavelet transformation to electrocardiosignal；It includes：
Including：
A. continuous wavelet transform
If Ψ (t) ∈ L2(R), Fourier transform is Ψ (ω), if met
Then Ψ (t) is morther wavelet, and morther wavelet is the starting point of wavelet transformation, is known as by the small echo that flexible and translation obtains
Wavelet basis function Ψa,τ(t), i.e.,
Wherein, a is scale factor, and τ is shift factor,It is to keep energy after function stretcher strain constant.L2
(R) refer to that R is the function space that quadractically integrable function is constituted；
Function inner product is
It is defined as the continuous wavelet transform (Continuous wavelet transform, CWT) of f (t), WTf(a, τ) is
Transformation coefficient；Its frequency domain of equal value is defined as
B. wavelet transform
Wavelet transform (Discrete wavelet transform, DWT) essence is that discretization is carried out to a and τ, one
Planting classical discrete way isa0,τ0∈ C > 0, m, k ∈ Z, bring into
In actual use, a is usually set0=2, τ0=1；
C. multiresolution analysis
Multiresolution analysis is also referred to as multiscale analysis, be by signal decomposition be different scale space and wavelet space in portion
Point；Realize function space L2(R) multiresolution analysis of small echo in, needs to construct the closed subspace for meeting following condition
{Vj}j∈Z, i.e.,
(1) Uniform Monotonicity：
(2) progressive completeness：∩j∈ZVj=φ ∪j∈ZVj=L2(R)
(3) two into flexible systematicness：
(4) translation invariance：
(5) orthogonal basis existence：There are φ (t) ∈ V0, so that { φ (t-n) }n∈ZAs V0Orthogonal basis, i.e.,And < φ (t-n), φ (t-m)>=δ (n-m), commonly referred to as VjFor the scale space of scale j, φ (t)
The referred to as scaling function of multiresolution analysis.
Step 3) is denoised using soft-threshold algorithm；
The frequency range of electrocardiosignal is 0.05~100Hz, and 90% energy concentrates on 0.25~40Hz.It is specific next
It says, QRS wave group frequency is in 3~40Hz, and P, T wave frequency rate are in 0.7~10Hz；
8 layers of wavelet decomposition, denoising are carried out to electrocardiogram (ECG) data using DB4 small echo：
1st layer is set 0 with layer 7 detail coefficients and the 8th layer of approximation coefficient, directly removal radio-frequency component and baseline drift；
3rd layer to the 6th layer uses soft-threshold algorithm；Retain the characteristic component in electrocardiosignal to the greatest extent, reduces letter
Number reconstruct when distortion.
Electrocardiosignal is reconstructed in step 4)；
Step 5) obtains all target tested points according to adaptive thresholding algorithm；
After electrocardiosignal after being reconstructed, the positive negative threshold value of signal is sought according to this；In view of the difference between individual,
The data of sample frequency interception 10s are first depending on, by 10 sections of data etc. point, maximizing and minimum value are distinguished in each section,
Take 0.7 times of its mean value initial threshold as lookup R crest value；It is respectively labeled as max_th, min_th；
In order to improve detection accuracy, using a kind of more new strategy for adaptively R-wave amplitude being followed to change, respectively with 0.3 with
0.7 weight distribution obtains next threshold value to present threshold value and the extreme point found, with this；By taking positive peak as an example, update public
Formula is：
In max_th=0.3 × max_th+0.7 × 0.7max_c formula, max_c is the current extreme value point amplitude found, is led to
This method is crossed to make threshold value adapt to the mutation of signal.
Step 6) uses wave crest inspection policies, obtains the peak position R；
As shown in Figure 4：It includes following procedure：
S1~s6 is data point, takes three points first, calculates the distance between two adjacent data points, is denoted as temp1 respectively,
Temp2, if (temp1 < RR_thr) && (temp2 < RR_thr) is set up, and illustrates s1, s2, s3 be in the same packet,
As shown in r1 packet；
When getting s4, when s5, s6, s5, the distance between s6 is larger, is unsatisfactory for Rule of judgment to get s6 and s1~s5 not
In the same packet, which terminates, and so on；
The distance between two o'clock is 1 in the same packet under normal circumstances, and normal person RR interphase is generally not less than 200ms,
Parameter RR_thr is set as 30, and in s1~s5, the maximum of points found is exactly R crest value point.
Step 7) carries out missing inspection inquiry；
Missing inspection inquiry is carried out to the peak R, can use the sequence information that adaptive threshold searches, is calculated between two data
Interval judges whether interval is more than 1.8 times of its equispaced；Equispaced is the average value at 10 intervals RR.Initial value is flat
The setting being spaced is according in adaptive threshold renewal process, and distance is flat between the adjacent maxima or minimum value of acquisition
Mean value；To improve accuracy, adaptability, need often to update equispaced；If it does, then carrying out missing inspection, leakage in the region
Inspection threshold value is set as 0.3 times of initial threshold, and step is constant later.
Step 8) carries out erroneous detection inquiry, and algorithm terminates：
Similar with missing inspection, error inquiry is whether the interval detected between two data meets erroneous detection condition, if it is satisfied, then
Delete the point.By taking positive value as an example, in two steps：
(1) distance of point-to-point transmission is calculated
Dis=max_index (i+1)-max_index (i)
(2) judge whether to meet erroneous detection condition
Erroneous detection condition is dis < median (RR), and satisfaction then deletes i+1 point.
Using the electrocardiogram (ECG) data in MIT-BIH database, to make schematically analysis with the data of this database convenient for narration
It introduces.
Fig. 2 is to carry out 8 Scale Decomposition figures to electrocardiosignal with DB4 small echo.It is decomposed by 8 multi-scale wavelets, it can will be useful
Signal component be distinguished with noise, then with not having noisy signal component reconstruction signal, can achieve the purpose of denoising.
Fig. 3 is the effect display figure that method extracts the peak R according to the present invention.It can be seen from the figure that method according to the present invention
The peak R in ecg wave form can be recognized accurately, demonstrate the feasibility, validity of the method for the present invention.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (7)
1. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal, which is characterized in that include the following steps：
Step 1) obtains electrocardiosignal；
Step 2) carries out Scale Decomposition with wavelet transformation to electrocardiosignal；
Step 3) is denoised using soft-threshold algorithm；
Electrocardiosignal is reconstructed in step 4)；
Step 5) obtains all target tested points according to adaptive thresholding algorithm；
Step 6) uses wave crest inspection policies, obtains the peak position R；
Step 7) carries out missing inspection inquiry；
Step 8) carries out erroneous detection inquiry, and algorithm terminates.
2. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal according to claim 1, it is characterised in that：Institute
It states step 2) Scale Decomposition is carried out with wavelet transformation to electrocardiosignal and include：
A. continuous wavelet transform
If Ψ (t) ∈ L2(R), Fourier transform is Ψ (ω), if met
Then Ψ (t) is morther wavelet, and morther wavelet is the starting point of wavelet transformation, is known as small echo by the small echo that flexible and translation obtains
Basic function Ψa,τ(t), i.e.,
Wherein, a is scale factor, and τ is shift factor,It is to keep energy after function stretcher strain constant；L2(R) refer to R
It is the function space that quadractically integrable function is constituted；
Function inner product is
It is defined as the continuous wavelet transform (Continuous wavelet transform, CWT) of f (t), WTf(a, τ) is transformation
Coefficient；Its frequency domain of equal value is defined as
B. wavelet transform
Wavelet transform (Discrete wavelet transform, DWT) essence is to carry out discretization, Yi Zhongjing to a and τ
The discrete way of allusion quotation isIt brings into
In actual use, a is usually set0=2, τ0=1；
C. multiresolution analysis
Multiresolution analysis is also referred to as multiscale analysis, be by signal decomposition be different scale space and wavelet space in part；
Realize function space L2(R) multiresolution analysis of small echo in needs to construct the closed subspace { V for meeting following conditionj}j∈Z, i.e.,
(1) Uniform Monotonicity：
(2) progressive completeness：∩j∈ZVj=φ ∪j∈ZVj=L2(R)
(3) two into flexible systematicness：
(4) translation invariance：
(5) orthogonal basis existence：There are φ (t) ∈ V0, so that { φ (t-n) }n∈ZAs V0Orthogonal basis, i.e.,And<φ(t-n),φ(t-m)>=δ (n-m), commonly referred to as VjFor the scale space of scale j, φ (t) claims
For the scaling function of multiresolution analysis.
3. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal according to claim 1, it is characterised in that：Institute
Step 2) is stated to denoise using soft-threshold algorithm, including：
8 layers of wavelet decomposition, denoising are carried out to electrocardiogram (ECG) data using DB4 small echo：
1st layer is set 0 with layer 7 detail coefficients and the 8th layer of approximation coefficient, directly removal radio-frequency component and baseline drift；
3rd layer to the 6th layer uses soft-threshold algorithm；Retain the characteristic component in electrocardiosignal to the greatest extent, reduces signal weight
Distortion when structure.
4. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal according to claim 1, it is characterised in that：Step
It is rapid to obtain all target tested points 5) according to adaptive thresholding algorithm, including：
After electrocardiosignal after being reconstructed, the positive negative threshold value of signal is sought according to this；In view of the difference between individual, first
According to the data of sample frequency interception 10s, by 10 sections of data etc. point, maximizing and minimum value are distinguished in each section, takes it
0.7 times of mean value is as the initial threshold for searching R crest value；It is respectively labeled as max_th, min_th；
In order to improve detection accuracy, using a kind of more new strategy for adaptively R-wave amplitude being followed to change, respectively with 0.3 and 0.7
Weight distribution obtains next threshold value to present threshold value and the extreme point found, with this；By taking positive peak as an example, more new formula is：
In max_th=0.3 × max_th+0.7 × 0.7max_c formula, max_c is the current extreme value point amplitude found, passes through this
Kind of method makes the threshold value adapt to the mutation of signal.
5. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal according to claim 1, it is characterised in that：Step
It is rapid 6) to use wave crest inspection policies, obtain the peak position R comprising following procedure：
S1~s6 is data point, takes three points first, calculates the distance between two adjacent data points, is denoted as temp1 respectively,
Temp2, if (temp1 < RR_thr) && (temp2 < RR_thr) is set up, and illustrates s1, s2, s3 be in the same packet,
As shown in r1 packet；
When getting s4, when s5, s6, s5, the distance between s6 is larger, is unsatisfactory for Rule of judgment to get s6 and s1~s5 not same
In one packet, which terminates, and so on；
The distance between two o'clock is 1 in the same packet under normal circumstances, and normal person RR interphase is generally not less than 200ms, parameter
RR_thr is set as 30, and in s1~s5, the maximum of points found is exactly R crest value point.
6. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal according to claim 1, it is characterised in that：Step
Rapid 7) to carry out missing inspection inquiry, process is as follows：
The sequence information searched using adaptive threshold calculates the interval between two data, judges whether interval is flat more than it
1.8 times be spaced；Equispaced is the average value at 10 intervals RR.
7. a kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal according to claim 1, it is characterised in that：Step
Rapid 8) error inquiry is whether the interval detected between two data meets erroneous detection condition, if it is satisfied, then deleting the point；With positive value
For, in two steps：
(1) distance of point-to-point transmission is calculated
Dis=max_index (i+1)-max_index (i)
(2) judge whether to meet erroneous detection condition
Erroneous detection condition is dis < median (RR), and satisfaction then deletes i+1 point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810694298.9A CN108830255A (en) | 2018-06-29 | 2018-06-29 | A kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810694298.9A CN108830255A (en) | 2018-06-29 | 2018-06-29 | A kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108830255A true CN108830255A (en) | 2018-11-16 |
Family
ID=64134033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810694298.9A Pending CN108830255A (en) | 2018-06-29 | 2018-06-29 | A kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108830255A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109875548A (en) * | 2019-03-24 | 2019-06-14 | 浙江好络维医疗技术有限公司 | A kind of Characteristics of electrocardiogram waveform clustering method based on multi-lead comprehensive analysis |
| CN110101383A (en) * | 2019-04-19 | 2019-08-09 | 长沙理工大学 | A kind of Denoising Algorithm of ECG Signals based on wavelet energy |
| CN111956209A (en) * | 2020-08-27 | 2020-11-20 | 重庆邮电大学 | Electrocardiosignal R wave identification method based on EWT and structural feature extraction |
| CN113647925A (en) * | 2021-07-05 | 2021-11-16 | 新绎健康科技有限公司 | Heart rate determination method and device based on heart attack signal |
| CN113951891A (en) * | 2021-11-11 | 2022-01-21 | 西安博远恒达电气科技有限公司 | ECG (electrocardiogram) identity recognition method based on space-time combination feature vector |
| CN114271830A (en) * | 2021-12-15 | 2022-04-05 | 山东领能电子科技有限公司 | Electrocardiosignal detection method and system |
| CN114428458A (en) * | 2022-01-18 | 2022-05-03 | 哈尔滨理工大学 | Space distribution process increment modeling method based on space-time data flow |
| CN115886834A (en) * | 2022-11-11 | 2023-04-04 | 研祥智慧物联科技有限公司 | ECG data peak detection method and device and computer equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102247143A (en) * | 2011-06-03 | 2011-11-23 | 吉林大学珠海学院 | Integratable fast algorithm for denoising electrocardiosignal and identifying QRS waves |
| CN102626310A (en) * | 2012-04-23 | 2012-08-08 | 天津工业大学 | Electrocardiogram signal feature detection algorithm based on wavelet transformation lifting and approximate envelope improving |
| CN104161510A (en) * | 2014-08-27 | 2014-11-26 | 电子科技大学 | Multistage lead electrocardiograph signal QRS waveform identification method |
-
2018
- 2018-06-29 CN CN201810694298.9A patent/CN108830255A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102247143A (en) * | 2011-06-03 | 2011-11-23 | 吉林大学珠海学院 | Integratable fast algorithm for denoising electrocardiosignal and identifying QRS waves |
| CN102626310A (en) * | 2012-04-23 | 2012-08-08 | 天津工业大学 | Electrocardiogram signal feature detection algorithm based on wavelet transformation lifting and approximate envelope improving |
| CN104161510A (en) * | 2014-08-27 | 2014-11-26 | 电子科技大学 | Multistage lead electrocardiograph signal QRS waveform identification method |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109875548A (en) * | 2019-03-24 | 2019-06-14 | 浙江好络维医疗技术有限公司 | A kind of Characteristics of electrocardiogram waveform clustering method based on multi-lead comprehensive analysis |
| CN109875548B (en) * | 2019-03-24 | 2022-04-19 | 浙江好络维医疗技术有限公司 | Electrocardiogram characteristic waveform clustering method based on multi-lead comprehensive analysis |
| CN110101383A (en) * | 2019-04-19 | 2019-08-09 | 长沙理工大学 | A kind of Denoising Algorithm of ECG Signals based on wavelet energy |
| CN111956209A (en) * | 2020-08-27 | 2020-11-20 | 重庆邮电大学 | Electrocardiosignal R wave identification method based on EWT and structural feature extraction |
| CN111956209B (en) * | 2020-08-27 | 2022-06-03 | 重庆邮电大学 | Electrocardiosignal R wave identification method based on EWT and structural feature extraction |
| CN113647925A (en) * | 2021-07-05 | 2021-11-16 | 新绎健康科技有限公司 | Heart rate determination method and device based on heart attack signal |
| CN113951891A (en) * | 2021-11-11 | 2022-01-21 | 西安博远恒达电气科技有限公司 | ECG (electrocardiogram) identity recognition method based on space-time combination feature vector |
| CN114271830A (en) * | 2021-12-15 | 2022-04-05 | 山东领能电子科技有限公司 | Electrocardiosignal detection method and system |
| CN114428458A (en) * | 2022-01-18 | 2022-05-03 | 哈尔滨理工大学 | Space distribution process increment modeling method based on space-time data flow |
| CN114428458B (en) * | 2022-01-18 | 2022-09-02 | 哈尔滨理工大学 | Space distribution process increment modeling method based on space-time data flow |
| CN115886834A (en) * | 2022-11-11 | 2023-04-04 | 研祥智慧物联科技有限公司 | ECG data peak detection method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108830255A (en) | A kind of peak R recognition methods based on Wavelet Denoising Method electrocardiosignal | |
| Gothwal et al. | Cardiac arrhythmias detection in an ECG beat signal using fast fourier transform and artificial neural network | |
| Sayadi et al. | A model-based Bayesian framework for ECG beat segmentation | |
| Adam et al. | Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals | |
| Sasikala et al. | Extraction of P wave and T wave in Electrocardiogram using Wavelet Transform | |
| CN113749664A (en) | Reducing intracardiac electrocardiogram noise using an autoencoder and refining intracardiac and body surface electrocardiograms using a deep learning training loss function | |
| Liu et al. | Automatic identification of abnormalities in 12-lead ECGs using expert features and convolutional neural networks | |
| CN110226919B (en) | Electrocardiosignal type detection method and device, computer equipment and storage medium | |
| Manriquez et al. | An algorithm for QRS onset and offset detection in single lead electrocardiogram records | |
| Kelwade et al. | Radial basis function neural network for prediction of cardiac arrhythmias based on heart rate time series | |
| CN114052744B (en) | Electrocardiosignal classification method based on impulse neural network | |
| CN110367936B (en) | Electrocardiosignal detection method and device | |
| CN115486855B (en) | Electrocardiogram and heart beat classification method based on QRS complex indefinite cycle superposition | |
| Malek et al. | Automated detection of premature ventricular contraction in ECG signals using enhanced template matching algorithm | |
| CN110192853A (en) | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart | |
| CN109893118A (en) | A kind of electrocardiosignal classification diagnosis method based on deep learning | |
| CN113499079A (en) | Atrial fibrillation detection method in electrocardiogram | |
| Prasad et al. | Heart rate detection using Hilbert transform | |
| CN105877739A (en) | Clinical examination method of electrocardio intelligent analyzing system | |
| Patel et al. | Machine learning for biomedical signal processing | |
| Sahoo et al. | Classification of heart rhythm disorders using instructive features and artificial neural networks | |
| Mahamat et al. | Wolff-Parkinson-White (WPW) syndrome: the detection of delta wave in an electrocardiogram (ECG) | |
| Murthy et al. | ECG signal denoising and ischemic event feature extraction using Daubechies wavelets | |
| CN108836316B (en) | Electrocardiosignal R wave extraction method based on BP neural network | |
| Manlong et al. | ST segment analysis for early detection of myocardial infarction |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181116 |