CN108334868A - A kind of pulse analysis method based on PPG signals and image enhancement - Google Patents
A kind of pulse analysis method based on PPG signals and image enhancement Download PDFInfo
- Publication number
- CN108334868A CN108334868A CN201810234938.8A CN201810234938A CN108334868A CN 108334868 A CN108334868 A CN 108334868A CN 201810234938 A CN201810234938 A CN 201810234938A CN 108334868 A CN108334868 A CN 108334868A
- Authority
- CN
- China
- Prior art keywords
- pulse
- signal
- pulse wave
- ppg
- image
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of pulse analysis methods being based on PPG (photoplethysmographic graphical method) signal and image enhancement, include the following steps：Acquire facial video image；Enhancing processing is carried out to video image, eliminates the influence of low illumination；The RGB channel of video detaches；It is handled using ICA algorithm；The channels G correlation analysis obtains PPG pulse wave signals；Denoising is carried out to noisy PPG pulse wave signals；Seek each characteristic point of PPG pulse wave signals；The characteristic value of pulse wave is inputted into KNN algorithms, exports pulse condition classification results；Classification results compare with standard database and judge illness.A kind of pulse analysis method based on PPG signals and image enchancing method provided by the invention, the pulse condition theory of Traditional Chinese Medicine is combined with computer technology, can either effectively realize objectify, the pulse analysis of quantification, in turn avoid influence of the low photoenvironment to pulse analysis when acquisition.
Description
Technical field
The present invention relates to image procossings and field of signal processing, are that one kind being based on PPG signals and image enhancement specifically
Pulse analysis method.
Background technology
Pulse condition is the situation and dynamic of pulse, is the Main Basiss that ancient Chinese judges conditions of human body.Current medicine for
The detection of human body pulse condition first, being put to the variation for experiencing pulse at human body radial artery by finger, that is, is passed there are mainly two types of mode
The method that system Chinese medicine is felt the pulse, second is that being changed by the beating that sensor replaces finger to perceive pulse at radial artery.The former needs specially
The Chinese medicine personnel of industry are detected, and the latter is that sensor appropriate is placed in tested position mostly, and the beating of pulse is converted to
Faint signal computer disposal is being carried out analyzing and diagnosing by electric signal, then input amplifying circuit to pulse wave.The method
Need complicated instrument and equipment and expensive, it has not been convenient to carry and family uses.It is attempted herein by analyzing common computer
The face video information of camera acquisition obtains human body pulse condition characteristic, and then realizes and detect human body using generic computer system
Health status.
The center of gravity of technical concerns is compared with the improvement for being partial to pulse signal acquisition instrument, method at present, or is directed to pulse condition
The a certain link of signal processing and analyzing carries out in-depth analysis research, lacks certain contextual, the inspection of systematic pulse condition
Analysis method is surveyed, or the factor that pulse condition detects can not influenced on some and make processing appropriate, such as illumination.Therefore for
A kind of proposition of complete, system, rigorous pulse analysis method is extremely necessary.
Invention content
In view of above-mentioned the shortcomings of the prior art, it is an object of the present invention to provide one kind being based on PPG signals and image enhancement
Pulse analysis method, eliminate the influence that detect to pulse condition of illumination factor, realize that pulse condition that is stable, objectifying diagnoses.
To achieve the goals above, the pulse analysis method proposed by the present invention based on PPG signals and image enhancement, including
Following steps：
First step：Facial video image is acquired by common computer camera；
Second step：Enhancing processing is carried out to video image by improved algorithm for image enhancement；
Third step：The RGB channel of enhanced video image is detached；
Four steps：ICA algorithm processing, and carry out correlation analysis with G channel signals and obtain PPG pulse wave signals；
5th step：Pulse Wave Signal Denoising；
6th step：Seek each characteristic point of PPG pulse wave signals；
7th step：The pulse wave characteristic value input KNN algorithms of extraction are exported into result
8th step：Pulse signal classification results are compared with standard database, judge illness.
Further, in the first step, the pulse analysis method based on PPG signals and image enhancement,
It is characterized in that：In the first step, facial video image is acquired using the camera of common computer, acquisition signal person needs quiet
Before being seated at computer, exposes forehead, stay for some time, forbid larger limb action, keep natural facial expression.
Further, in the second step, the detailed process of the Enhancement Method of the video image is as follows：
Step 1：The auto contrast that each channel of image is modified is stretched；
Step 2：The mutual conversion of color space based on HSV；
Step 3：The linear transformation that V component is segmented.
Further, in the second step, the modified auto contrast stretches formula and is：
WhereinTwo threshold values for respectively representing the pixel value of low-light (level) image, can be obtained by following formula：
In above formula：0≤tlow,thigh≤ 1, tlow+thigh≤1。
Further, in the second step, the V component piecewise linear transform in HSV space is：
The pixel value of V component is ranked up by sequence from small to large, the vector after being sorted is denoted as V'=hM×N
(x), if it is n to carry out the parameter of segment processing to V', the number of pixels of segmentation isTo each segmentation V'iSetting one
The minimum value of a pixelAnd maximum valueLinear transformation is carried out to each segmentation
Expression formula is as follows：G (x)=[g is obtained after linear transformation0(x),g1(x),
Λ gn(x)], reconstruct g (x) is M × N-dimensional matrix V "=| g (x, y) |, image is finally transformed into rgb space from HSV space and is obtained
To enhanced video image.
Further, in the four steps, the ICA algorithm extracts PPG pulse waves letter from human face image sequence
Number, Signal separator at the linear combination of the signal source of the non-Gaussian signal of statistical iteration, that is, in linear hybrid signal
Recover basic original signal
Further, in the 5th step, described is to utilize wavelet reconstruction and empirical modal to Pulse Wave Signal Denoising
Decompose the method that (EMD) is combined.After wavelet transformation is decomposed, out-of-band high-frequency signal is filtered out, height can be effectively filtered out
Frequency interferes, and in the process of processing, Sym8 wavelet functions are chosen as wavelet basis pair to signal utilizing small wave converting method
Threshold function table decomposes signal, can protrude the signal characteristic of different characteristics.Then to pulse wave signal after wavelet decomposition
Wavelet coefficient in frequency band further does the decomposition of empirical mode decomposition (EMD) method, obtains new wavelet coefficient.
Further, in the 6th step, each characteristic point for seeking PPG pulse wave signals includes the power of pulse wave
It spends, the speed that pulse wave rises, the speed that pulse wave declines, the width of a cycle pulse wave, again the dynamics of rich wave, one minute
The periodicity of interior pulse wave.
Further, in the 7th step, pulse signal is identified in classification in the KNN algorithms, is to believe PPG
Number each characteristic point as input, prediction classification is carried out to pulse signal with the KNN clustering algorithms of machine learning.
Further, it is by the prediction classification results and standard of KNN algorithms in the judgement illness in the 8th step
Database is compared, and judges the symptom representated by pulse condition.
The present invention has the following advantages that compared with existing pulse analysis method：
1, a kind of contactless pulse analysis method is proposed, it is easy to operate, it is at low cost.
2, the video image enhancing method proposed eliminates the influence to pulse analysis in the case of uneven illumination, ensure that
The stability of pulse information.
3, denoising is carried out to pulse wave signal in conjunction with small echo and EMD, further improves pulse analysis result.
3, what is proposed is identified classification it can be readily appreciated that being convenient for KNN algorithms according to PPG pulse waves characteristic point to pulse condition
It realizes.
4, the theory of traditional medicine is combined by the pulse analysis method proposed with modern computer science, can be effective
Realize pulse condition detect and diagnose that is stable, rigorous, objectifying in ground.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without having to pay creative labor, may be used also for those of ordinary skill in the art
With obtain other attached drawings according to these attached drawings：
Fig. 1 is PPG pulse wave signal characteristic patterns.
Fig. 2 is the flow chart of the method for the present invention.
Fig. 3 is proposed by the present invention to implement schematic diagram based on facial video image Enhancement Method.
Specific implementation mode
The present invention is described in further detail below in conjunction with the accompanying drawings, but implementation and protection domain of the invention is not limited to
This.
Photoplethysmographic graphical method (PPG) be it is a kind of using living tissue to light absorption detection volumetric blood change
A kind of non-invasive detection methods.As shown in Figure 1, being PPG pulse wave signal characteristic patterns, horizontal axis is the time, and the longitudinal axis is volumetric blood
Size variation.U points, the minimum point of pulse wave signal, at this time heart enter the contraction phase, a large amount of blood inject aortas, human body
Blood volume in blood vessel increases, and is the minimum point of waveform, that is, penetrates the beginning of blood.Z points are the vertex of signal, at this time intravascular blood
Cubical content reaches maximum value.W points are the Local Vertexes in signal descending branch, the aorta being turned off are encountered corresponding to the blood that backflows
Maximum ejection amount after valve reflection (some individuals inflection point unobvious do not have).V points, paradoxical expansion terminate, and blood knot is penetrated in representative
Beam.
As shown in Fig. 2, for the flow chart of the method for the present invention, facial video image is acquired by common computer camera,
Facial video image is acquired using the camera of common computer, acquisition signal person needs to sit quietly before computer, exposes forehead, stops
About one minute, forbid larger limb action, keeps natural facial expression；By improved algorithm for image enhancement to video figure
As carrying out enhancing processing, the influence for preventing low lighting issues from being tested and analyzed to pulse condition；Then by the RGB of enhanced video image
Channel separation；Then, it is handled with ICA algorithm, and handling result and G channel signals is subjected to correlation analysis and obtain PPG arteries and veins
It fights wave signal；Denoising is carried out to the PPG pulse wave signals got then in conjunction with small echo and EMD；Then seek PPG pulse wave signals
Each characteristic point；The pulse wave characteristic value input KNN algorithms of extraction are exported into result；Finally, by pulse signal classification results with
Standard database compares, and judges illness.
As shown in figure 3, video image enhancing method includes being stretched to the auto contrast that each channel of image is modified；
The mutual conversion of color space based on HSV；The linear transformation that V component is segmented.
Stretching formula to the auto contrast that each channel of video image is modified is：
WhereinTwo threshold values for respectively representing the pixel value of low-light (level) image, can be obtained by following formula：
Pixel value can be less than or equal to by formulaIt is more than or equal toValue be respectively mapped to xminWith xmax,
Other values are then mapped to xmin、xmaxBetween.
It is in the V component piecewise linear transform of HSV space：
The pixel value of V component is ranked up by sequence from small to large, the vector after being sorted is denoted as V'=hM×N
(x), if it is n to carry out the parameter of segment processing to V', the number of pixels of segmentation isTo each segmentation V'iSetting one
The minimum value of a pixelAnd maximum valueLinear transformation is carried out to each segmentation
Expression formula isG (x)=[g is obtained after linear transformation0(x),g1(x),L gn
(x)], reconstruct g (x) is M × N-dimensional matrix V "=| g (x, y) |, image is finally transformed into rgb space from HSV space and is increased
Video image after strong；
ICA algorithm is the linear combination at the signal source of the non-Gaussian signal of statistical iteration Signal separator, that is, from
Basic original signal is recovered in linear hybrid signal.It is to choose suitable threshold to be filtered pretreatment to PPG pulse wave signals
Value H and the special rule-based filtering of setting fall noise spot.In order to eliminate the influence of bigger interference, sample point is carried out at segmentation
Reason, finds out each section of maximum value, then seeks the average value of these maximum values, last set certain ratio is as threshold value；PPG
Each characteristic point of pulse wave signal, includes the dynamics of pulse wave, the speed that pulse wave rises, the speed that pulse wave declines, one
The width of period pulse wave wins the dynamics of wave, the periodicity etc. of pulse wave in one minute again.With the clustering algorithm of machine learning
Prediction classification is carried out to pulse signal；It predicts that classification results are compared with standard database, and judges the symptom representated by pulse condition.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, it is other it is any without departing from the spirit and principles of the present invention made by changes, modifications, substitutions, combinations, simplifications,
Equivalent substitute mode is should be, is included within the scope of the present invention.
Claims (10)
1. a kind of pulse analysis method based on PPG signals and image enhancement, which is characterized in that include the following steps：
First step：Facial video image is acquired by common computer camera；
Second step：Enhancing processing is carried out to video image by improved algorithm for image enhancement；
Third step：The RGB channel of enhanced video image is detached；
Four steps：ICA algorithm processing, and carry out correlation analysis with G channel signals and obtain PPG pulse wave signals；
5th step：Pulse Wave Signal Denoising；
6th step：Seek each characteristic point of PPG pulse wave signals；
7th step：The pulse wave characteristic value input KNN algorithms of extraction are exported into result
8th step：Pulse signal classification results are compared with standard database, judge illness.
2. the pulse analysis method according to claim 1 based on PPG signals and image enhancement, it is characterised in that：It is described
In first step, facial video image is acquired using the camera of common computer, acquisition signal person needs to sit quietly before computer, reveal
Go out forehead, stay for some time, forbid larger limb action, keeps natural facial expression.
3. the pulse analysis method according to claim 1 based on PPG signals and image enhancement, it is characterised in that：It is described
The detailed process of second step is as follows：
Step 1：The auto contrast that each channel of image is modified is stretched；
Step 2：The mutual conversion of color space based on HSV；
Step 3：The linear transformation that V component is segmented.
4. video image enhancing method according to claim 3, it is characterised in that：Each channel to video image into
The modified auto contrast of row stretches formula：
WhereinTwo threshold values for respectively representing the pixel value of low-light (level) image, can be obtained by following formula：
In above formula：0≤tlow,thigh≤ 1, tlow+thigh≤1。
5. video image enhancing method according to claim 3, it is characterised in that：The V component in HSV space is segmented
Linear transformation is：
The pixel value of V component is ranked up by sequence from small to large, the vector after being sorted is denoted as V'=hM×N(x), if
The parameter that segment processing is carried out to V' is n, and the number of pixels of segmentation isTo each segmentation V'iSet a pixel
Minimum valueAnd maximum valueThe expression formula of linear transformation is carried out to each segmentation
It is as follows：G (x)=[g is obtained after linear transformation0(x),g1(x),Λ gn
(x)], reconstruct g (x) is M × N-dimensional matrix V "=| g (x, y) |, image is finally transformed into rgb space from HSV space and is increased
Video image after strong.
6. a kind of pulse analysis method based on PPG signals and image enhancement according to claim 1, it is characterised in that：
In the four steps, the ICA algorithm is linear group of signal source at the non-Gaussian signal of statistical iteration Signal separator
It closes, that is, recovers basic original signal in linear hybrid signal.
7. the pulse analysis method according to claim 1 based on PPG signals and image enhancement, it is characterised in that：It is described
In 5th step, the Pulse Wave Signal Denoising is the method combined with empirical mode decomposition (EMD) using wavelet reconstruction, small
After wave conversion is decomposed, out-of-band high-frequency signal is filtered out, High-frequency Interference can be effectively filtered out, is utilizing small wave converting method
In the process of processing to signal, the selection of wavelet basis function is particularly significant, is carried out to signal using different wavelet basis functions
Decompose, the signal characteristic of different characteristics can be protruded, herein choose Sym8 wavelet functions as wavelet basis to threshold function table into
Row decomposes, and then to the wavelet coefficient after wavelet decomposition in pulse wave signal frequency band, further does empirical mode decomposition (EMD) side
The decomposition of method obtains new wavelet coefficient.
8. the pulse analysis method according to claim 1 based on PPG signals and image enhancement, it is characterised in that：It is described
In 6th step, each characteristic point of PPG pulse wave signals is sought, includes the dynamics of pulse wave, the speed that pulse wave rises, pulse wave
The speed of decline, the width of a cycle pulse wave win the dynamics of wave, the periodicity of pulse wave in one minute again.
9. a kind of pulse analysis method based on PPG signals and image enhancement according to claim 1, it is characterised in that：
In 7th step, the KNN algorithms are to carry out prediction classification to pulse signal with the clustering algorithm of machine learning.
10. a kind of pulse analysis method based on PPG signals and image enhancement according to claim 9, it is characterised in that：
It is that will predict that classification results are compared with standard database, and judge the symptom representated by pulse condition in 8th step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810234938.8A CN108334868A (en) | 2018-03-21 | 2018-03-21 | A kind of pulse analysis method based on PPG signals and image enhancement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810234938.8A CN108334868A (en) | 2018-03-21 | 2018-03-21 | A kind of pulse analysis method based on PPG signals and image enhancement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108334868A true CN108334868A (en) | 2018-07-27 |
Family
ID=62932169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810234938.8A Pending CN108334868A (en) | 2018-03-21 | 2018-03-21 | A kind of pulse analysis method based on PPG signals and image enhancement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108334868A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109363652A (en) * | 2018-09-29 | 2019-02-22 | 天津惊帆科技有限公司 | PPG signal reconfiguring method and equipment based on deep learning |
| CN109793506A (en) * | 2019-01-18 | 2019-05-24 | 合肥工业大学 | A kind of contactless radial artery Wave shape extracting method |
| CN110197172A (en) * | 2019-06-10 | 2019-09-03 | 清华大学 | One kind carrying out identity authentication method and device based on photoelectricity capacity of blood vessel information |
| CN110353646A (en) * | 2019-07-29 | 2019-10-22 | 苏州市高事达信息科技股份有限公司 | Contactless heart rate detection method |
| CN110353700A (en) * | 2019-07-29 | 2019-10-22 | 苏州市高事达信息科技股份有限公司 | Contactless method for detecting blood oxygen saturation |
| CN112949349A (en) * | 2019-12-09 | 2021-06-11 | 南宁莲现健康科技有限公司 | Method and system for displaying pulse condition waveform in real time based on face video |
| CN113488162A (en) * | 2021-07-06 | 2021-10-08 | 李颖 | Non-contact traditional Chinese medicine pulse condition detection method and device |
| CN115067935A (en) * | 2022-06-28 | 2022-09-20 | 华南师范大学 | Wink detection method and system based on photoplethysmography and storage medium |
| CN116109818A (en) * | 2023-04-11 | 2023-05-12 | 成都中医药大学 | Traditional Chinese medicine pulse condition distinguishing system, method and device based on facial video |
-
2018
- 2018-03-21 CN CN201810234938.8A patent/CN108334868A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109363652A (en) * | 2018-09-29 | 2019-02-22 | 天津惊帆科技有限公司 | PPG signal reconfiguring method and equipment based on deep learning |
| CN109363652B (en) * | 2018-09-29 | 2021-05-07 | 天津惊帆科技有限公司 | PPG signal reconstruction method and equipment based on deep learning |
| CN109793506A (en) * | 2019-01-18 | 2019-05-24 | 合肥工业大学 | A kind of contactless radial artery Wave shape extracting method |
| CN109793506B (en) * | 2019-01-18 | 2022-03-22 | 合肥工业大学 | Non-contact radial artery waveform extraction method |
| CN110197172A (en) * | 2019-06-10 | 2019-09-03 | 清华大学 | One kind carrying out identity authentication method and device based on photoelectricity capacity of blood vessel information |
| CN110353646A (en) * | 2019-07-29 | 2019-10-22 | 苏州市高事达信息科技股份有限公司 | Contactless heart rate detection method |
| CN110353700A (en) * | 2019-07-29 | 2019-10-22 | 苏州市高事达信息科技股份有限公司 | Contactless method for detecting blood oxygen saturation |
| CN112949349A (en) * | 2019-12-09 | 2021-06-11 | 南宁莲现健康科技有限公司 | Method and system for displaying pulse condition waveform in real time based on face video |
| CN112949349B (en) * | 2019-12-09 | 2022-08-05 | 南宁莲现健康科技有限公司 | Method and system for displaying pulse condition waveform in real time based on face video |
| CN113488162A (en) * | 2021-07-06 | 2021-10-08 | 李颖 | Non-contact traditional Chinese medicine pulse condition detection method and device |
| CN115067935A (en) * | 2022-06-28 | 2022-09-20 | 华南师范大学 | Wink detection method and system based on photoplethysmography and storage medium |
| CN116109818A (en) * | 2023-04-11 | 2023-05-12 | 成都中医药大学 | Traditional Chinese medicine pulse condition distinguishing system, method and device based on facial video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108334868A (en) | A kind of pulse analysis method based on PPG signals and image enhancement | |
| Oh et al. | Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats | |
| Chen et al. | Atrial fibrillation detection using a feedforward neural network | |
| CN104523266B (en) | A kind of electrocardiosignal automatic classification method | |
| Tripathy et al. | Automated detection of congestive heart failure from electrocardiogram signal using Stockwell transform and hybrid classification scheme | |
| CN104367316B (en) | Denoising of ECG Signal based on morphologic filtering Yu lifting wavelet transform | |
| CN112949349B (en) | Method and system for displaying pulse condition waveform in real time based on face video | |
| CN107736894A (en) | A kind of electrocardiosignal Emotion identification method based on deep learning | |
| CN111481192B (en) | Electrocardiosignal R wave detection method based on improved U-Net | |
| Srivastava et al. | DWT-based feature extraction from ECG signal | |
| Mandal et al. | Detection of Ventricular Arrhythmia by using Heart rate variability signal and ECG beat image | |
| CN107239684A (en) | A kind of feature learning method and system for ECG identifications | |
| CN108567418A (en) | A kind of pulse signal inferior health detection method and detecting system based on PCANet | |
| CN104809450B (en) | Wrist vena identification system based on online extreme learning machine | |
| CN113491523B (en) | Electrocardiosignal characteristic point detection method and system | |
| Huang et al. | A portable household detection system based on the combination of bidirectional LSTM and residual block for automatical arrhythmia detection | |
| Hao et al. | A quality assessment system for ppg waveform | |
| CN117908665A (en) | Control method of disabled person rehabilitation equipment based on brain-computer interface | |
| Shang et al. | Research on Classification of Scoliosis Based on Pulse Signal under Dynamic Pressure | |
| He et al. | Emotion Recognition from ECG Signals Contaminated by Motion Artifacts | |
| Kang et al. | Beat-Level Interpretation of Intra-Patient Paradigm Based on Object Detection | |
| Sarshar et al. | Automated Cardiovascular Arrhythmia Classification Based on Through Nonlinear Features and Tunable-Q Wavelet Transform (TQWT) Based Decomposition | |
| Jin et al. | A novel interpretable multilevel wavelet decomposition deep network for actual heartbeat classification | |
| Cheng et al. | Feature extraction and recognition methods based on phonocardiogram | |
| Zhao et al. | A Lightweight Convolutional Neural Network Method for Two-Dimensional PhotoPlethysmoGraphy Signals |
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: 20180727 |
|
| RJ01 | Rejection of invention patent application after publication |