CN110236530A - A kind of electrocardiosignal QRS wave group localization method, device and computer storage medium - Google Patents
A kind of electrocardiosignal QRS wave group localization method, device and computer storage medium Download PDFInfo
- Publication number
- CN110236530A CN110236530A CN201910537562.2A CN201910537562A CN110236530A CN 110236530 A CN110236530 A CN 110236530A CN 201910537562 A CN201910537562 A CN 201910537562A CN 110236530 A CN110236530 A CN 110236530A
- Authority
- CN
- China
- Prior art keywords
- data
- electrocardiosignal
- label value
- data segment
- localization method
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/366—Detecting abnormal QRS complex, e.g. widening
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Cardiology (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention relates to ECG's data compression technical field, a kind of electrocardiosignal QRS wave group localization method, device and computer storage medium are disclosed.Wherein, method is the following steps are included: acquire a plurality of electrocardiosignal building sample data set；Each sample data is demarcated, and the sample data demarcated is cut into multiple data segments；For the data segment addition embody its whether include QRS complex training label value；The data segment added with training label value is trained by neural network, obtains Tag Estimation model；The QRS complex positioning of case data is carried out according to the Tag Estimation model.The present invention has to abnormal electrocardiogram signal framing technical effect with high accuracy.
Description
Technical field
The present invention relates to ECG's data compression technical fields, and in particular to a kind of electrocardiosignal QRS wave group localization method, dress
It sets and computer storage medium.
Background technique
In cardiac diagnosis, the positioning of QRS complex is had very important effect.Currently, traditional QRS complex location algorithm
Higher positioning is able to carry out for normal ecg wave form, susceptibility and precision can reach requirement but for cardiac'ss
The QRS complex of the unusual waveforms such as special waveform identifies that effect is very unsatisfactory.
Summary of the invention
It is an object of the invention to overcome above-mentioned technical deficiency, a kind of electrocardiosignal QRS wave group localization method, device are provided
And computer storage medium, solve the low technical problem of the QRS complex accuracy of identification for unusual waveforms in the prior art.
To reach above-mentioned technical purpose, technical solution of the present invention provides a kind of electrocardiosignal QRS wave group localization method, packet
Include following steps:
Acquire a plurality of electrocardiosignal building sample data set；
Each sample data is demarcated, and the sample data demarcated is cut into multiple data segments；
For the data segment addition embody its whether include QRS complex training label value；
The data segment added with training label value is trained by neural network, obtains Tag Estimation model；
The QRS complex positioning of case data is carried out according to the Tag Estimation model.
The present invention also provides a kind of electrocardiosignal QRS wave group positioning device, including processor and memory, the storages
It is stored with computer program on device, when the computer program is executed by the processor, realizes the electrocardiosignal QRS wave group
Localization method.
The present invention also provides a kind of computer storage mediums, are stored thereon with computer program, the computer program quilt
When processor executes, the electrocardiosignal QRS wave group localization method is realized.
Compared with prior art, it the beneficial effect comprise that the present invention cuts sample data, is cut
For multiple data segments, training label value is added for each data segment, to embody whether data segment wraps by training label value
Data segment is trained containing QRS complex, then by neural network, obtains Tag Estimation model, realizes the QRS wave of case data
Group's positioning.The present invention is cut by sample data the positioning of QRS complex being converted to whether data segment includes sentencing for QRS complex
It is disconnected, and then neural network Tag Estimation model is utilized, realize whether sample data section includes QRS complex by Tag Estimation
Accurate judgement, realize the accurate positionin of QRS complex.
Detailed description of the invention
Fig. 1 is the flow chart of one embodiment of electrocardiosignal QRS wave group localization method provided by the invention；
Fig. 2 is the comparison diagram of traditional QRS complex detection algorithm Detection Point and reference point；
Fig. 3 is the calibration schematic diagram of calibration one embodiment of sample data provided by the invention；
Fig. 4 is the prediction result of one embodiment of prediction label value obtained using Tag Estimation model provided by the invention
Figure；
Fig. 5 is the filter result figure in Fig. 4 after prediction label value filtering.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Embodiment 1
As shown in Figure 1, the embodiment of the present invention 1 provides electrocardiosignal QRS wave group localization method, comprising the following steps:
S1, a plurality of electrocardiosignal of acquisition construct sample data set；
S2, calibration each sample data, and the sample data demarcated is cut into multiple sample data sections；
S3, for the sample data section addition embody its whether include QRS complex training label value；
S4, the sample data section added with training label value is trained by neural network, obtains Tag Estimation mould
Type；
S5, the QRS complex that case data are carried out according to the Tag Estimation model position.
Currently, traditional QRS location algorithm is low to accuracy of identification such as special waveform, the unusual waveforms of cardiac.Tool
Body, the positioning knot using traditional QRS location algorithm to the progress QRS complex positioning of three sections of different data is shown in Fig. 2
Fruit figure.The data C that the data A and number that number is data00148 are data00480 is normal electrocardiosignal, and number is
The data B of data00004 is abnormal electrocardiogram signal.Upper row's point is R wave wave crest reference point in the positioning result of three segment datas
Detectted QRS Location, lower row's point are the R wave wave crest test point detected using traditional QRS location algorithm
Referrence QRS Location.From figure 2, it is seen that traditional QRS location algorithm when positioning to abnormal electrocardiogram, leaks
The case where inspection and false retrieval, clearly data B fallout ratio reached 87.5%.
In response to this problem, depth learning technology is applied in the QRS complex positioning of electrocardiosignal for the embodiment of the present invention.Tool
Body, after being demarcated to sample data, it is cut, is converted the positioning of QRS complex by sample data cutting
For sample data section whether include QRS complex judgement.Training label value is added for each sample data section, to pass through instruction
Practice label value and embody whether sample data section includes QRS complex, sample data section is trained in conjunction with neural network, is obtained
Tag Estimation model is positioned by the QRS complex of Tag Estimation model realization case data.
Preferably, the sample data demarcated is cut into multiple sample data sections, specifically:
The sample data demarcated is cut to set step-length and be sized the sizes such as at equal intervals, obtains multiple samples
Notebook data section.
It is cut to sample data has been demarcated, it is root that the size that this preferred embodiment chooses data cutting window, which is 0.25s,
It is determined according to the range in human ecg signal period, the heart rate of human ecg signal is also single between 30--300bpm
The length of a cardiac electrical cycle is 0.2s--2s, between general QRS complex width 0.12-0.2s, selects the size of data cutting window
The width less times greater than QRS complex is needed, is found through experiments that the size of selection data cutting window in 0.25s or so, is tested
Effect is optimal.Specifically, data sampling frequency is 500HZ in the present embodiment, cutting size is 0.25s, i.e., cutting size is 125
A unit length.Step-length to describe cutting size and is hereinafter cut with unit length number, selecting cutting step-length is 5
It is a.The length number of whole section of sample data signal is 5000, then the sample data section after cutting is respectively as follows: signal
[1,2 ..., 125], signal [6,7 ..., 130], signal [4876,4877 ..., 5000], that is, complete sample
The cutting of data.
Preferably, the sample data is demarcated, specifically:
Demarcate the R crest location of the sample data.
This preferred embodiment passes through the method manually demarcated, as shown in figure 3, circle calibration position is R crest location, circle
The adjacent triangle in both sides be the QRS complex comprising the R wave crest start-stop point.When the R crest location and actual R wave of calibration
The distance of peak position is no more than the size of QRS complex, can determine that the R crest location demarcated in the present embodiment exists to demarcate effectively
Before and after practical R crest location within the scope of 37.5ms, can it regard as effectively.
Preferably, for the sample data section addition embody its whether include QRS complex training label value, specifically:
Centered on the R crest location nearest apart from the sample data section, it is cut into the sample data and institute
State the reference field of sample data section same size；
Calculate the IOU value of the sample data Duan Yuqi reference field；
It is that the sample data section adds training label value according to the IOU value.
This preferred embodiment introduces IOU, the i.e. concept of Intersection over Union, and IOU is that a kind of measure exists
Specific data concentrates a standard of detection respective objects accuracy.The present invention determines the sample data after cutting by IOU
Duan Zhong, which sample data section is positive sample, that is, includes QRS complex section, which sample data section is negative sample, that is, is not included
QRS complex section is conducive to subsequent training.In order to guarantee data validity.After being cut to whole sample data, after cutting
Sample data section calculate and the IOU value of its reference field.Wherein: the size of reference field is identical as sample data section, in reference field
Point is located at the nearest R crest location of calibration distance sample data segment, and head and the tail are respectively forward and to be translated in based on midpoint
" window size subtracts 1 divided by 2 " a point translates 125/2-1=62 point in the present embodiment.
Preferably, training label value is added to the sample data section according to the IOU value, specifically:
When the IOU value is less than the first given threshold, add for the sample data section without QRS wave label value；
When the IOU value is greater than the second given threshold, QRS wave label value is added with for the sample data section；
When the IOU value is greater than first given threshold and is less than second given threshold, add without label
Add.
In this preferred embodiment, the first given threshold takes 0.3, and the second given threshold takes 0.7, and no QRS wave label value takes 0,
There is QRS wave label value to take 1.When IOU value [0.3,0.7] ∈, this sample data section is given up, not as training sample, because
This addition without label；As IOU < 0.3, demarcating this sample data section corresponding label is 0, illustrates this sample number
According to Duan Zhongwu QRS complex；As IOU > 0.7, demarcating this sample data section corresponding label is 1, illustrates this sample data section
In contain a QRS complex.
Preferably, the neural network is ResNet neural network.
After obtaining sample data section and corresponding training label value, this preferred embodiment is neural by 32 layers of ResNet
Network is trained.ResNet neural network has one-dimensional convolutional coding structure, two-dimensional convolution structure and multidimensional convolution structure, this implementation
The ResNet neural network of example application is one-dimensional convolutional coding structure.
Preferably, it is positioned according to the QRS complex that the Tag Estimation model carries out case data, specifically:
The case data are cut into multiple case data segments, each case data segment is inputted into the Tag Estimation
Model obtains the prediction label value of each case data segment；
By the prediction label value compared with the trained label value, judge whether corresponding case data segment includes QRS wave
Group, obtains the case data segment comprising QRS complex.
After obtaining Tag Estimation model, the prediction label value of case data segment can be obtained, according to prediction label value
Judge whether corresponding case data segment includes QRS complex, to realize the positioning of QRS complex.
Specifically, this preferred embodiment, the case data cutting that can be 0001 by data number is 976 case data
Section, the cutting of case data need to meet IOU standard when Tag Estimation model foundation.976 case data segments are inputted respectively
The prediction of label value is carried out into trained Tag Estimation model, obtained prediction result is as shown in Figure 4.Compare prediction label
Value and training label value, training label value include representing to have QRS wave label value comprising QRS complex, further include representing not including
QRS complex without QRS wave label value, if prediction label value is closer to there is QRS wave label value to indicate this case data segment
In contain QRS complex, if prediction label value indicates not containing in this case data segment closer to no QRS wave label value
QRS complex.
Specifically, comparison prediction label value and training label value can be used filtering processing and realize, to the prediction of result in Fig. 4
Figure is filtered, this preferred embodiment is extreme value filtering processing: having taken QRS wave label value and no QRS wave label value
Average value, i.e., 0.5, when the prediction label value of case data segment be more than or equal to 0.5 when, enable the prediction label value be assigned a value of 1；When
When the prediction label value of case data segment is less than 0.5, the prediction label value is enabled to be assigned a value of 0；Filter result figure is as shown in Figure 5:
Preferably, electrocardiosignal QRS wave group localization method further include:
Take the midpoint of the case data segment comprising QRS complex；
The middle position is scaled to the location information of the case data, obtains the R wave crest position of the case data
It sets.
By being filtered to the prediction result in Fig. 4, filter result shown in Fig. 5 is obtained, it is all continuous pre- from Fig. 5
Surveying label value is to have in the sample data section of QRS wave label value, takes its midpoint, as position corresponding to case data R wave crest
It sets, i.e. position shown in vertical line in Fig. 5.At the QRS wave for the case data for converting back original by the midpoint being marked in Fig. 5,
It can be seen that in Fig. 5, x-axis data point number is 976, this is because original data volume is 5000, window size is 125, and window is mobile
Step-length be 5 caused by, (5000-125)/5+1=976.
Embodiment 2
The embodiment of the present invention 2 provides electrocardiosignal QRS wave group positioning device, including processor and memory, institute
It states and is stored with computer program on memory, when the computer program is executed by the processor, realize that any of the above is implemented
The electrocardiosignal QRS wave group localization method that example provides.
Electrocardiosignal QRS wave group positioning device provided in an embodiment of the present invention, for realizing the positioning of electrocardiosignal QRS wave group
Method, therefore, the technical effect that above-mentioned electrocardiosignal QRS wave group localization method has, electrocardiosignal QRS wave group positioning device
It is likewise supplied with, details are not described herein.
Embodiment 3
The embodiment of the present invention 3 provides computer storage medium, is stored thereon with computer program, the computer journey
When sequence is executed by processor, the electrocardiosignal QRS wave group localization method that any of the above embodiment provides is realized.
Computer storage medium provided in an embodiment of the present invention, for realizing electrocardiosignal QRS wave group localization method, because
This, the technical effect that above-mentioned electrocardiosignal QRS wave group localization method has, computer storage medium is likewise supplied with, herein not
It repeats again.
The above described specific embodiments of the present invention are not intended to limit the scope of the present invention..Any basis
Any other various changes and modifications that technical concept of the invention is made should be included in the guarantor of the claims in the present invention
It protects in range.
Claims (10)
1. a kind of electrocardiosignal QRS wave group localization method, which comprises the following steps:
Acquire a plurality of electrocardiosignal building sample data set；
Each sample data is demarcated, and the sample data demarcated is cut into multiple data segments；
For the data segment addition embody its whether include QRS complex training label value；
The data segment added with training label value is trained by neural network, obtains Tag Estimation model；
The QRS complex positioning of case data is carried out according to the Tag Estimation model.
2. electrocardiosignal QRS wave group localization method according to claim 1, which is characterized in that the sample number that will have been demarcated
According to being cut into multiple data segments, specifically:
The sample data demarcated is cut to set step-length and be sized the sizes such as at equal intervals, obtains multiple data
Section.
3. electrocardiosignal QRS wave group localization method according to claim 1, which is characterized in that the sample data is demarcated,
Specifically:
Demarcate the R crest location of the sample data.
4. electrocardiosignal QRS wave group localization method according to claim 3, which is characterized in that added for the data segment
Embody its whether include QRS complex training label value, specifically:
Centered on the R crest location nearest apart from the data segment, it is cut into the sample data and the data segment
The reference field of same size；
Calculate the IOU value of the data segment Yu its reference field；
It is that the data segment adds training label value according to the IOU value.
5. electrocardiosignal QRS wave group localization method according to claim 4, which is characterized in that according to the IOU value to institute
It states data segment and adds training label value, specifically:
When the IOU value is less than the first given threshold, add for the data segment without QRS wave label value；
When the IOU value is greater than the second given threshold, QRS wave label value is added with for the data segment；
When the IOU value is greater than first given threshold and is less than second given threshold, added without label.
6. electrocardiosignal QRS wave group localization method according to claim 1, which is characterized in that the neural network is
ResNet neural network.
7. electrocardiosignal QRS wave group localization method according to claim 1, which is characterized in that according to the Tag Estimation
Model carries out the QRS complex positioning of case data, specifically:
The case data are cut into multiple case data segments, each case data segment is inputted into the Tag Estimation mould
Type obtains the prediction label value of each case data segment；
By the prediction label value compared with the trained label value, judge whether corresponding case data segment includes QRS complex, is obtained
To the case data segment comprising QRS complex.
8. electrocardiosignal QRS wave group localization method according to claim 7, which is characterized in that further include:
Take the midpoint of the case data segment comprising QRS complex；
The middle position is scaled to the location information of the case data, obtains the R crest location of the case data.
9. a kind of electrocardiosignal QRS wave group positioning device, which is characterized in that including processor and memory, the memory
On be stored with computer program, when the computer program is executed by the processor, realize as described in claim 1-8 is any
Electrocardiosignal QRS wave group localization method.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is located
When managing device execution, electrocardiosignal QRS wave group localization method a method as claimed in any one of claims 1-8 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910537562.2A CN110236530A (en) | 2019-06-20 | 2019-06-20 | A kind of electrocardiosignal QRS wave group localization method, device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910537562.2A CN110236530A (en) | 2019-06-20 | 2019-06-20 | A kind of electrocardiosignal QRS wave group localization method, device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110236530A true CN110236530A (en) | 2019-09-17 |
Family
ID=67888560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910537562.2A Pending CN110236530A (en) | 2019-06-20 | 2019-06-20 | A kind of electrocardiosignal QRS wave group localization method, device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110236530A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110693486A (en) * | 2019-09-27 | 2020-01-17 | 武汉中旗生物医疗电子有限公司 | Electrocardiogram abnormity labeling method and device |
| CN111110228A (en) * | 2020-01-17 | 2020-05-08 | 武汉中旗生物医疗电子有限公司 | Electrocardiosignal R wave detection method and device |
| CN111214225A (en) * | 2019-12-24 | 2020-06-02 | 北京超思电子技术有限责任公司 | Room excitement identification method and device, electronic equipment and readable storage medium |
| CN112107310A (en) * | 2020-09-30 | 2020-12-22 | 西安理工大学 | ECG identity recognition method based on IWT and AGA-BP models |
| CN113080996A (en) * | 2021-04-08 | 2021-07-09 | 大同千烯科技有限公司 | Electrocardiogram analysis method and device based on target detection |
| CN114159070A (en) * | 2021-12-20 | 2022-03-11 | 武汉大学 | Real-time cardiac arrest risk prediction method and system of convolutional neural network |
| CN115770048A (en) * | 2021-09-08 | 2023-03-10 | 上海联影医疗科技股份有限公司 | Electrocardiosignal processing method and device, computer equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106073755A (en) * | 2016-05-27 | 2016-11-09 | 成都信汇聚源科技有限公司 | The implementation method that in a kind of miniature holter devices, atrial fibrillation identifies automatically |
| CN106897714A (en) * | 2017-03-23 | 2017-06-27 | 北京大学深圳研究生院 | A kind of video actions detection method based on convolutional neural networks |
| CN107123123A (en) * | 2017-05-02 | 2017-09-01 | 电子科技大学 | Image segmentation quality evaluating method based on convolutional neural networks |
| CN107145833A (en) * | 2017-04-11 | 2017-09-08 | 腾讯科技（上海）有限公司 | The determination method and apparatus of human face region |
| CN107495959A (en) * | 2017-07-27 | 2017-12-22 | 大连大学 | A kind of electrocardiosignal sorting technique based on one-dimensional convolutional neural networks |
| CN107609464A (en) * | 2017-07-24 | 2018-01-19 | 南京邮电大学 | A kind of real-time high-precision human face quick detection method |
| CN108056773A (en) * | 2017-12-11 | 2018-05-22 | 重庆邮电大学 | Based on the algorithms of QRS complexes detection in electrocardiogram signal for improving variation mode decomposition |
| CN109063552A (en) * | 2018-06-22 | 2018-12-21 | 深圳大学 | A kind of multi-lead electrocardiosignal classification method and system |
| CN109190442A (en) * | 2018-06-26 | 2019-01-11 | 杭州雄迈集成电路技术有限公司 | A kind of fast face detecting method based on depth cascade convolutional neural networks |
| CN109271876A (en) * | 2018-08-24 | 2019-01-25 | 南京理工大学 | Video actions detection method based on temporal evolution modeling and multi-instance learning |
-
2019
- 2019-06-20 CN CN201910537562.2A patent/CN110236530A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106073755A (en) * | 2016-05-27 | 2016-11-09 | 成都信汇聚源科技有限公司 | The implementation method that in a kind of miniature holter devices, atrial fibrillation identifies automatically |
| CN106897714A (en) * | 2017-03-23 | 2017-06-27 | 北京大学深圳研究生院 | A kind of video actions detection method based on convolutional neural networks |
| CN107145833A (en) * | 2017-04-11 | 2017-09-08 | 腾讯科技（上海）有限公司 | The determination method and apparatus of human face region |
| CN107123123A (en) * | 2017-05-02 | 2017-09-01 | 电子科技大学 | Image segmentation quality evaluating method based on convolutional neural networks |
| CN107609464A (en) * | 2017-07-24 | 2018-01-19 | 南京邮电大学 | A kind of real-time high-precision human face quick detection method |
| CN107495959A (en) * | 2017-07-27 | 2017-12-22 | 大连大学 | A kind of electrocardiosignal sorting technique based on one-dimensional convolutional neural networks |
| CN108056773A (en) * | 2017-12-11 | 2018-05-22 | 重庆邮电大学 | Based on the algorithms of QRS complexes detection in electrocardiogram signal for improving variation mode decomposition |
| CN109063552A (en) * | 2018-06-22 | 2018-12-21 | 深圳大学 | A kind of multi-lead electrocardiosignal classification method and system |
| CN109190442A (en) * | 2018-06-26 | 2019-01-11 | 杭州雄迈集成电路技术有限公司 | A kind of fast face detecting method based on depth cascade convolutional neural networks |
| CN109271876A (en) * | 2018-08-24 | 2019-01-25 | 南京理工大学 | Video actions detection method based on temporal evolution modeling and multi-instance learning |
Non-Patent Citations (1)
| Title |
|---|
| XINGJUN WANG: "QRS Detection in ECG Signal Based on Residual Network", 《2019 IEEE 11TH INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110693486A (en) * | 2019-09-27 | 2020-01-17 | 武汉中旗生物医疗电子有限公司 | Electrocardiogram abnormity labeling method and device |
| CN111214225A (en) * | 2019-12-24 | 2020-06-02 | 北京超思电子技术有限责任公司 | Room excitement identification method and device, electronic equipment and readable storage medium |
| CN111214225B (en) * | 2019-12-24 | 2022-12-06 | 北京超思电子技术有限责任公司 | Room excitement identification method and device, electronic equipment and readable storage medium |
| CN111110228A (en) * | 2020-01-17 | 2020-05-08 | 武汉中旗生物医疗电子有限公司 | Electrocardiosignal R wave detection method and device |
| CN112107310A (en) * | 2020-09-30 | 2020-12-22 | 西安理工大学 | ECG identity recognition method based on IWT and AGA-BP models |
| CN113080996A (en) * | 2021-04-08 | 2021-07-09 | 大同千烯科技有限公司 | Electrocardiogram analysis method and device based on target detection |
| CN115770048A (en) * | 2021-09-08 | 2023-03-10 | 上海联影医疗科技股份有限公司 | Electrocardiosignal processing method and device, computer equipment and storage medium |
| CN114159070A (en) * | 2021-12-20 | 2022-03-11 | 武汉大学 | Real-time cardiac arrest risk prediction method and system of convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110236530A (en) | A kind of electrocardiosignal QRS wave group localization method, device and computer storage medium | |
| US10980429B2 (en) | Method and system for cuffless blood pressure estimation using photoplethysmogram features and pulse transit time | |
| CN109308695A (en) | Based on the cancer cell identification method for improving U-net convolutional neural networks model | |
| CN104382618B (en) | The denoising method and Fetal Heart Rate detector detected based on Fetal Heart Rate | |
| WO2019100827A1 (en) | Method and apparatus for extracting blood pressure data from pulse wave signal | |
| CN109584283A (en) | A kind of Medical Image Registration Algorithm based on convolutional neural networks | |
| CN104271038B (en) | A kind of method and apparatus that myocardial damage is assessed based on current density change | |
| CN113855038B (en) | Electrocardiosignal critical value prediction method and device based on multi-model integration | |
| CN109009084A (en) | QRS wave group calibration method, device, equipment and medium for multi-lead electrocardiosignal | |
| CN109191442A (en) | Ultrasound image assessment and screening technique and device | |
| CN116172517A (en) | Seizure interval epileptiform discharge detection method and device based on double-view feature fusion framework | |
| Liu et al. | Using the VQ-VAE to improve the recognition of abnormalities in short-duration 12-lead electrocardiogram records | |
| CN115153581A (en) | Electrocardiosignal characteristic waveform detection method and device and storage medium | |
| CN111053552B (en) | QRS wave detection method based on deep learning | |
| CN109875550A (en) | A kind of sequences of ventricular depolarization critical point detection method | |
| CN111248881B (en) | Method and device for predicting blood pressure | |
| CN111214225B (en) | Room excitement identification method and device, electronic equipment and readable storage medium | |
| CN114469176A (en) | Detection method and related device for fetal heart ultrasonic image | |
| CN105517018B (en) | A kind of method and device obtaining location information | |
| CN105138823B (en) | A kind of physiological signal quality determining method based on auto-correlation function | |
| CN114176602A (en) | Method for simultaneously positioning positions of electrocardio P wave, QRS wave and T wave based on deep learning multi-target detection | |
| Wang et al. | A pooling convolution model for multi-classification of ECG and PCG signals | |
| CN108652604A (en) | It is a kind of based on electrocardiosignal without air bag blood pressure detecting method and system | |
| CN102551687A (en) | Extraction method of pulse signal feature points based on second-generation wavelets | |
| CN104983415A (en) | Heart beat recognition method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190917 |
|
| RJ01 | Rejection of invention patent application after publication |