CN106344004A - Electrocardiosignal feature point detecting method and device - Google Patents
Electrocardiosignal feature point detecting method and device Download PDFInfo
- Publication number
- CN106344004A CN106344004A CN201610862893.XA CN201610862893A CN106344004A CN 106344004 A CN106344004 A CN 106344004A CN 201610862893 A CN201610862893 A CN 201610862893A CN 106344004 A CN106344004 A CN 106344004A
- Authority
- CN
- China
- Prior art keywords
- point
- electrocardiosignal
- feature
- test
- signaling point
- 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]
-
- 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
-
- 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
-
- 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)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides an electrocardiosignal feature point detecting method and device. The electrocardiosignal feature point detecting method comprises the steps that signal point pair features of all electrocardiosignal feature points in a sample set are extracted, and the signal point pair features of all electrocardiosignal testing points in a testing set are extracted; a mode recognition algorithm is utilized to train the extracted signal point pair features in the sample set to obtain an electrocardiosignal feature classification model; the electrocardiosignal feature classification model is utilized to classify the signal point pair features of all the electrocardiosignal testing points so as to obtain classification results of the signal point pair features of all the electrocardiosignal testing points, and the classification results serve as feature point detecting results of the electrocardiosignal testing points. The electrocardiosignal feature point detecting method can detect electrocardiosignal feature points in real time and is simple to achieve and higher in detecting sensitivity and accuracy rate.
Description
Technical field
The present invention relates to ecg information processing technology field, more particularly, to a kind of electrocardiosignal feature point detecting method and dress
Put.
Background technology
Electrocardiosignal (electrocardiogram, abbreviation ecg) reflects the electrical activity process of cardiac excitation, and it is to the heart
Dirty basic function and its pathological study aspect, have important reference value.
At present, characteristic point (p crest value and its border, qrs ripple, the t crest value and its border) detection of general electrocardiosignal
Method can be divided into: one, carries out feature point detection using substrate method of deploying；2nd, use sef-adapting filter (adaptive
Filter) detected；3rd, using electro-cardiologic signal waveforms model (such as Gauss model), ecg signal is fitted, according to plan
Close the position that result draws p ripple, t ripple and qrs ripple.
Carry out feature point detection using substrate method of deploying, the mode that substrate is launched includes discrete Fourier transform, discrete
Cosine transform and wavelet transformation etc., the method for most common of which is to use wavelet transformation.The basic ideas of this method are p
Ripple, qrs ripple and t ripple often only can occur in special frequency band, thus for these wave characters detection can be limited to little
Detected above several decomposition level after wave conversion.By design threshold and decision logic, can detect that ecg believes first
The most obvious qrs ripple of feature in number.Secondly, according to the qrs ripple position detecting it may be determined that corresponding p ripple and t ripple
Region of search, detects to p ripple and t ripple setting threshold value respectively in corresponding region of search, may finally obtain each ecg
The testing result of characteristic point.Using the problem that this kind of wavelet method carries out ecg feature point detection it is, the knot of ecg feature point detection
Often the setting for detection threshold value is more sensitive for fruit, and the setting of each detection threshold value needs to refer to the ecg waveform of reality,
When same group of detection threshold value is detected on being transplanted to other data bases, often will be according to the ecg waveform feelings in new database
Condition, modification threshold value and decision logic, very inconvenient.
Detected using sef-adapting filter, sef-adapting filter can remove baseline drift in ecg signal, 60hz
Power supply noise interference, muscle noise and motion artifacts.But adaptive filter algorithm needs one and input ecg signal are same
The reference signal of step, this condition is often difficult to meet in real world applications.
Using electro-cardiologic signal waveforms model, ecg signal is fitted, p ripple, t ripple and qrs are drawn according to fitting result
The position of ripple.This kind of method needs first each waveform shape in ecg waveform to be modeled, by the different parameters of model Lai
The change of reaction ecg wave form correspondingly-shaped.By adjusting model parameter, minimize the mistake between input ecg signal and model
Difference, obtains final fitting result, thus drawing the position of each key point of electrocardiosignal.The problem of this method is, if
The model of definition is excessively simple, and autgmentability will be had a greatly reduced quality it is impossible to represent diversified electro-cardiologic signal waveforms；If definition mould
Type is more complicated, and will increase the amount of calculation of model fitting process it is difficult to ensure the real-time of algorithm in some instances it may even be possible to lead to matching
Algorithm cannot be restrained.
In consideration of it, how to provide a kind of realizing simple, detection sensitivity and the higher electrocardiosignal characteristic point inspection of accuracy rate
Surveying method and device becomes the current technical issues that need to address.
Content of the invention
For solving above-mentioned technical problem, the present invention provides a kind of electrocardiosignal feature point detecting method and device, can
Electrocardiosignal characteristic point is carried out with real-time detection, realizes simple, detection sensitivity and accuracy rate is higher.
In a first aspect, the present invention provides a kind of electrocardiosignal feature point detecting method, comprising:
The signaling point extracting all electrocardio sampled points in sample set is to feature, and extracts all electrocardiosignaies in test set
The signaling point of test point is to feature；
Land use models recognizer, is trained to feature to the signaling point extracting in sample set, obtains electrocardiosignal
Tagsort model；
Using described electrocardiosignal tagsort model, to the signaling point of electrocardiosignal test points all in test set to spy
Levy and classified, obtain the signaling point of all electrocardiosignal test points classification results to feature；
Using described classification results as electrocardiosignal test points all in test set feature point detection result.
Alternatively, described sample set, comprising: in electrocardiosignal sample choose band markd electrocardio sampled point and
The non-characteristic point electrocardio sampled point chosen in electrocardiosignal sample；
Described identical with the quantity of described non-characteristic point electrocardio sampled point with markd electrocardio sampled point；
Correspondingly, the described signaling point extracting all electrocardio sampled points in sample set is to feature, comprising:
In extraction sample set, the signaling point with markd electrocardio sampled point is to feature；
The signaling point extracting non-characteristic point electrocardio sampled point in sample set is to feature；
Correspondingly, described Land use models recognizer, is trained to feature to the signaling point extracting in sample set, obtains
To electrocardiosignal tagsort model, comprising:
Using the signaling point with markd electrocardio sampled point in the sample set of extraction to feature as training positive example；
In the sample set that will extract, the signaling point of non-characteristic point electrocardio sampled point bears example to feature as training；
Land use models recognizer, is trained to feature to the signaling point in described training positive example and the negative example of training, obtains
To electrocardiosignal tagsort model.
Alternatively, described algorithm for pattern recognition, comprising: random forests algorithm.
Alternatively, described extract sample set in all electrocardio sampled points signaling point to feature, and extract test set in
The signaling point of all electrocardiosignal test points is to feature, comprising:
Using signaling point, the signaling point of all electrocardio sampled points in sample set is extracted to feature to feature extraction algorithm, and
Using described signaling point, the signaling point of all electrocardiosignal test points in test set is extracted to feature to feature extraction algorithm；
Wherein, described signaling point is to feature extraction algorithm, comprising: extract signaling point pair in the time-domain signal of electrocardiosignal
Feature or in the base expansion coefficient of electrocardiosignal extract signaling point to feature；
The base expansion coefficient of described electrocardiosignal, comprising: the wavelet transform dwt coefficient of electrocardiosignal or electrocardio
The empirical mode decomposition emd coefficient of signal.
Alternatively, extract signaling point in the wavelet transform dwt coefficient of electrocardiosignal to feature, comprising:
By electrocardio sampled point/test point in the position in electro-cardiologic signal waveforms centered on, setting one preset length window
Mouthful, and intercept the electrocardiosignal in described window；
Using maximum-minima, the electrocardiosignal intercepting is normalized；
Using wavelet transform dwt, extract the different decomposition level of the wavelet transformation of electrocardiosignal after normalization, and
Random selection predetermined number point pair on each wavelet decomposition level coefficient；
Calculate each point to pair (x1, x2) two sampling point position x1And x2Absolute amplitude difference and this point right
pair(x1, x2) two sampling point position x1And x2Amplitude difference symbol；
Using result of calculation as described electrocardio sampled point/test point signaling point to feature.
Alternatively, described each point that calculates is to pair (x1, x2) two sampling point position x1And x2Absolute amplitude poor
Value and this point are to pair (x1, x2) two sampling point position x1And x2Amplitude difference symbol, comprising:
By the first formula, calculate each point to pair (x1, x2) two sampling point position x1And x2Absolute amplitude
Difference and this point are to pair (x1, x2) two sampling point position x1And x2Amplitude difference symbol；
Wherein, described first formula is:
Wherein, sig (x1) it is electrocardiosignal in sampling point position x1The amplitude at place, sig (x2) it is electrocardiosignal in sampled point
Position x2The amplitude at place, sign [sig (x1)-sig(x2)] it is point to pair (x1, x2) two sampling point position x1And x2Width
The symbol of value difference value, makes sig (x1)-sig(x2)=m,
Alternatively, described using described electrocardiosignal tagsort model, to electrocardiosignal tests all in test set
The signaling point of point is classified to feature, obtain the signaling point of all electrocardiosignal test points to the classification results of feature after,
Methods described also includes:
Using post-processing algorithm, described classification results are removed with false-alarm output；
Correspondingly, described using described classification results as electrocardiosignal test points all in test set feature point detection knot
Really, comprising:
The feature point detection as electrocardiosignal test points all in test set for the result obtaining after false-alarm output will be removed
Result.
Alternatively, described classification results are removed false-alarm output by described utilization post-processing algorithm, comprising:
Difference for the time in classification results is polymerized to one group less than the cohort labelling of predetermined threshold value, takes the time domain average of this group
Output result as this class labelling；Meanwhile, it is used each labelling appearance order of electrocardiosignal set in advance to believe as priori
Breath, is removed to the incorrect output of labelling appearance order in classification results.
Second aspect, the present invention provides a kind of electrocardiosignal feature point detection device, comprising:
Extraction module, for extracting the signaling point of all electrocardio sampled points in sample set to feature, and extracts test set
In all electrocardiosignal test points signaling point to feature；
Training module, for Land use models recognizer, is trained to feature to the signaling point extracting in sample set,
Obtain electrocardiosignal tagsort model；
Sort module, for using described electrocardiosignal tagsort model, to electrocardiosignal tests all in test set
The signaling point of point is classified to feature, obtains the signaling point of all electrocardiosignal test points classification results to feature；
Result acquisition module, for using described classification results as electrocardiosignal test points all in test set characteristic point
Testing result.
Alternatively, described device also includes:
Remove module, for utilizing post-processing algorithm, described classification results are removed with false-alarm output；
Correspondingly, described result acquisition module, specifically for
The feature point detection as electrocardiosignal test points all in test set for the result obtaining after false-alarm output will be removed
Result.
As shown from the above technical solution, the electrocardiosignal feature point detecting method of the present invention and device, by extracting sample
The signaling point concentrating all electrocardio sampled points is to feature, and the signaling point pair extracting all electrocardiosignal test points in test set
Feature；Land use models recognizer is trained to feature to the signaling point extracting in sample set, obtains electrocardiosignal feature
Disaggregated model；Using electrocardiosignal tagsort model, the signaling point of electrocardiosignal test points all in test set is entered to feature
Row classification, obtains the signaling point of all electrocardiosignal test points classification results to feature, and using this classification results as test
Concentrate the feature point detection result of all electrocardiosignal test points.Thus, the present invention can carry out reality to electrocardiosignal characteristic point
When detection, realize simple, detection sensitivity and accuracy rate be higher.This method can be applied and singly lead and multi-lead signal
In detection, provide and realize detection scheme that is simple, extending on multiple test sets, real-time testing result output is provided.
Brief description
The schematic flow sheet of the electrocardiosignal feature point detecting method that Fig. 1 provides for one embodiment of the invention；
Fig. 2 is the extraction schematic diagram to feature for the signaling point in the dwt coefficient of electrocardiosignal provided in an embodiment of the present invention；
Fig. 3 is a kind of schematic diagram of the testing result output false-alarm in classification results output in FIG；
The structural representation of the electrocardiosignal feature point detection device that Fig. 4 provides for one embodiment of the invention.
Specific embodiment
Purpose, technical scheme and advantage for making the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is carried out with clear, complete description it is clear that described embodiment only
It is only a part of embodiment of the present invention, rather than whole embodiments.Based on embodiments of the invention, ordinary skill people
The every other embodiment that member is obtained under the premise of not making creative work, broadly falls into the scope of protection of the invention.
Fig. 1 shows the schematic flow sheet of the electrocardiosignal feature point detecting method that one embodiment of the invention provides, such as Fig. 1
Shown, the electrocardiosignal feature point detecting method of the present embodiment is as described below.
101st, extract the signaling point of all electrocardio sampled points in sample set to feature, and extract all electrocardios in test set
The signaling point of signal testing point is to feature.
In a particular application, described sample set, it may include: the markd electrocardio of band chosen in electrocardiosignal sample is adopted
Sampling point and the non-characteristic point electrocardio sampled point chosen in electrocardiosignal sample；
Described identical with the quantity of described non-characteristic point electrocardio sampled point with markd electrocardio sampled point；
Correspondingly, " signaling point extracting all electrocardio sampled points in sample set is to feature " in described step 101, permissible
Including:
In extraction sample set, the signaling point with markd electrocardio sampled point is to feature；
The signaling point extracting non-characteristic point electrocardio sampled point in sample set is to feature.
It should be noted that, before described step 101, can be in advance to the electrocardiosignal characteristic point in electrocardiosignal sample
Position (p ripple, the boundary point of qrs ripple and t ripple and peak value) is marked.
In a particular application, in described step 101, it is possible to use signaling point extracts in sample set to feature extraction algorithm
The signaling point of all electrocardio sampled points is to feature, and using described signaling point, feature extraction algorithm is extracted all in test set
The signaling point of electrocardiosignal test point is to feature；
Wherein, described signaling point, to feature extraction algorithm, may include that extraction signal in the time-domain signal of electrocardiosignal
Point extracts signaling point to feature etc. to feature or in the base expansion coefficient of electrocardiosignal；
The base expansion coefficient of described electrocardiosignal, may include that electrocardiosignal wavelet transform dwt coefficient or
The empirical mode decomposition emd coefficient of electrocardiosignal, the present embodiment and be not limited thereof or electrocardiosignal other
Base expansion coefficient.
For example, extract signaling point in the dwt coefficient of electrocardiosignal to feature, may include that
By electrocardio sampled point/test point in the position in electro-cardiologic signal waveforms centered on, setting one preset length window
Mouthful, and intercept the electrocardiosignal in described window, refer to Fig. 2 a；
Using maximum-minima, the electrocardiosignal intercepting is normalized, increases the robustness of the feature extracted；
Using wavelet transform dwt, the different decomposition level extracting the wavelet transformation of electrocardiosignal after normalization (can be joined
Examine Fig. 2 b- Fig. 2 f), and random selection predetermined number point pair on each wavelet decomposition level coefficient；
By the first formula, calculate each point to pair (x1, x2) two sampling point position x1And x2Absolute amplitude
Difference and this point are to pair (x1, x2) two sampling point position x1And x2Amplitude difference symbol；
Using result of calculation as described electrocardio sampled point/test point signaling point to feature；
Wherein, described first formula is:
Wherein, sig (x1) it is electrocardiosignal in sampling point position x1The amplitude at place, sig (x2) it is electrocardiosignal in sampled point
Position x2The amplitude at place, sign [sig (x1)-sig(x2)] it is point to pair (x1, x2) two sampling point position x1And x2Width
The symbol of value difference value, makes sig (x1)-sig(x2)=m,
102nd, Land use models recognizer, is trained to feature to the signaling point extracting in sample set, obtains electrocardio
Signal characteristic disaggregated model.
In a particular application, described algorithm for pattern recognition, may include that random forests algorithm etc., the present embodiment is not right
It is defined or other algorithm for pattern recognitions.
In a particular application, the band markd electrocardio sampling chosen in electrocardiosignal sample is included in described sample set
During the non-characteristic point electrocardio sampled point put and choose in electrocardiosignal sample, described step 102 can accordingly specifically include:
Using the signaling point with markd electrocardio sampled point in the sample set of extraction to feature as training positive example；
In the sample set that will extract, the signaling point of non-characteristic point electrocardio sampled point bears example to feature as training；
Land use models recognizer, is trained to feature to the signaling point in described training positive example and the negative example of training, obtains
To electrocardiosignal tagsort model.
103rd, described electrocardiosignal tagsort model, the signaling point to electrocardiosignal test points all in test set are utilized
Feature is classified, obtains the signaling point of all electrocardiosignal test points classification results to feature.
It is understood that because the markd electrocardio of band that described sample set includes choosing in electrocardiosignal sample is adopted
Sampling point and the non-characteristic point electrocardio sampled point chosen in electrocardiosignal sample, so utilize described electrocardiosignal tagsort mould
Type, when the signaling point of electrocardiosignal test points all in test set is classified to feature, described electrocardiosignal tagsort
Model can be marked to electrocardiosignal test points all in test set, obtains wherein characteristic point (p crest value and its border, qrs
Ripple, t crest value and its border).
104th, using described classification results as electrocardiosignal test points all in test set feature point detection result.
The electrocardiosignal feature point detecting method of the present embodiment, by extracting the signal of all electrocardio sampled points in sample set
Point is to feature, and extracts the signaling point of all electrocardiosignal test points in test set to feature；Land use models recognizer pair
The signaling point extracting in sample set is trained to feature, obtains electrocardiosignal tagsort model；Special using electrocardiosignal
Levy disaggregated model the signaling point of electrocardiosignal test points all in test set is classified to feature, obtain all electrocardiosignaies
The classification results to feature for the signaling point of test point, and using this classification results as electrocardiosignal test points all in test set
Feature point detection result.Thus, the present invention can carry out real-time detection to electrocardiosignal characteristic point, realizes simple, detection sensitivity
Degree is higher with accuracy rate.This method can apply singly lead and the detection of multi-lead signal in, provide realization simple, can
Expand to the detection scheme on multiple test sets, real-time testing result output is provided.
The present embodiment methods described has very high robustness, and model parameter therein is fewer, and detects performance pair
Parameter value variation is simultaneously insensitive, can greatly mitigate the workload during algorithm is realized, for the new test data adding, this method energy
Enough provide the test result with higher credibility it is no longer necessary to professional modifies to control parameter.
The present embodiment methods described has real-time, can apply to, in heart real time monitoring device, timely provide the heart
The annotation results of electrical feature point, and according to characteristic point annotation results, anomalous ecg is partly recorded in time and sends alarm.
The present embodiment methods described can feed back to method with self improvement according to the mistake mark in output result
Flow process, carries out Feedback error learning, with the increase of amount of test data, can significantly improve Detection accuracy.
The present embodiment methods described can apply singly lead or multi-lead data on, some can only offer is singly led
The application scenarios of connection electrocardiogram (ECG) data, this programme still can provide higher Detection accuracy.
In the classification results output obtaining due to step 103, may occur some near correct characteristic point position empty
Alert testing result output, as shown in Figure 3.Therefore, in a particular application, after described step 103, methods described is acceptable
Including unshowned step s1 of in figure:
S1, utilize post-processing algorithm, described classification results are removed with false-alarm output；
Correspondingly, described step 104 can particularly as follows:
The feature point detection as electrocardiosignal test points all in test set for the result obtaining after false-alarm output will be removed
Result.
Further, described step s1 may particularly include:
Difference for the time in classification results is polymerized to one group less than the cohort labelling of predetermined threshold value, takes the time domain average of this group
Output result as this class labelling；Meanwhile, it is used each labelling appearance order of electrocardiosignal set in advance to believe as priori
Breath, is removed to the incorrect output of labelling appearance order in classification results.
It is understood that by the post processing of step s1, the spy of all electrocardiosignal test points in the test set obtaining
Levy a testing result and can reach higher detection sensitivity and accuracy rate.
Fig. 4 shows the structural representation of the electrocardiosignal feature point detection device that one embodiment of the invention provides, such as Fig. 4
Shown, the electrocardiosignal feature point detection device of the present embodiment, comprising: extraction module 41, training module 42, sort module 43 and
Result acquisition module 44；Wherein:
Described extraction module 41, for extracting the signaling point of all electrocardio sampled points in sample set to feature, and extracts
In test set, the signaling point of all electrocardiosignal test points is to feature；
Described training module 42, for Land use models recognizer, enters to feature to the signaling point extracting in sample set
Row training, obtains electrocardiosignal tagsort model；
Described sort module 43, for using described electrocardiosignal tagsort model, to electrocardio letters all in test set
The signaling point of number test point is classified to feature, and the signaling point obtaining all electrocardiosignal test points is tied to the classification of feature
Really；
Described result acquisition module 44, for using described classification results as electrocardiosignal test points all in test set
Feature point detection result.
In a particular application, described sample set, may include that the markd electrocardio of band chosen in electrocardiosignal sample
Sampled point and the non-characteristic point electrocardio sampled point chosen in electrocardiosignal sample；
Described identical with the quantity of described non-characteristic point electrocardio sampled point with markd electrocardio sampled point；
Correspondingly, described extraction module 41, can be specifically for
Extract the signaling point with markd electrocardio sampled point in sample set and, to feature, extract non-feature dessert in sample set
The signaling point of electric sampled point is to feature, and extracts the signaling point of all electrocardiosignal test points in test set to feature；
Correspondingly, described training module 42, can be specifically for
Using the signaling point with markd electrocardio sampled point in the sample set of extraction to feature as training positive example；
In the sample set that will extract, the signaling point of non-characteristic point electrocardio sampled point bears example to feature as training；
Land use models recognizer, is trained to feature to the signaling point in described training positive example and the negative example of training, obtains
To electrocardiosignal tagsort model.
In a particular application, described algorithm for pattern recognition, may include that random forests algorithm etc., the present embodiment is not right
It is defined or other algorithm for pattern recognitions.
In a particular application, described extraction module 41, can be specifically for
Using signaling point, the signaling point of all electrocardio sampled points in sample set is extracted to feature to feature extraction algorithm, and
Using described signaling point, the signaling point of all electrocardiosignal test points in test set is extracted to feature to feature extraction algorithm；
Wherein, described signaling point, to feature extraction algorithm, may include that extraction signal in the time-domain signal of electrocardiosignal
Point extracts signaling point to feature etc. to feature or in the base expansion coefficient of electrocardiosignal；
The base expansion coefficient of described electrocardiosignal, may include that electrocardiosignal wavelet transform dwt coefficient or
Empirical mode decomposition emd coefficient of electrocardiosignal etc., the present embodiment and be not limited thereof or electrocardiosignal its
His base expansion coefficient.
In a particular application, can also to include in figure unshowned for described device:
Remove module, for utilizing post-processing algorithm, described classification results are removed with false-alarm output；
Correspondingly, described result acquisition module 44, can be specifically for
The feature point detection as electrocardiosignal test points all in test set for the result obtaining after false-alarm output will be removed
Result.
It should be noted that for device/system embodiment, due to itself and embodiment of the method basic simlarity, so
Describe is fairly simple, and in place of correlation, the part referring to embodiment of the method illustrates.
The electrocardiosignal feature point detection device of the present embodiment, can carry out real-time detection to electrocardiosignal characteristic point, real
Now simply, detection sensitivity and accuracy rate are higher.This method can apply singly lead and the detection of multi-lead signal in, carry
For realizing the simple, detection scheme extending on multiple test sets, provide real-time testing result output.
The electrocardiosignal feature point detection device of the present embodiment, can be used for executing embodiment of the method shown in aforementioned Fig. 1
Technical scheme, it is realized, and principle is similar with technique effect, and here is omitted.
Those skilled in the art are it should be appreciated that embodiments herein can be provided as method, system or computer program
Product.Therefore, the application can be using complete hardware embodiment, complete software embodiment or the reality combining software and hardware aspect
Apply the form of example.And, the application can be using in one or more computers wherein including computer usable program code
The upper computer program implemented of usable storage medium (including but not limited to disk memory, cd-rom, optical memory etc.) produces
The form of product.
The application is the flow process with reference to method, equipment (system) and computer program according to the embodiment of the present application
Figure and/or block diagram are describing.It should be understood that can be by each stream in computer program instructions flowchart and/or block diagram
Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor instructing general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device is to produce
A raw machine is so that produced for reality by the instruction of computer or the computing device of other programmable data processing device
The device of the function of specifying in present one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing device with spy
Determine in the computer-readable memory that mode works so that the instruction generation inclusion being stored in this computer-readable memory refers to
Make the manufacture of device, this command device realize in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The function of specifying in multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing device so that counting
On calculation machine or other programmable devices, execution series of operation steps to be to produce computer implemented process, thus in computer or
On other programmable devices, the instruction of execution is provided for realizing in one flow process of flow chart or multiple flow process and/or block diagram one
The step of the function of specifying in individual square frame or multiple square frame.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation are made a distinction with another entity or operation, and not necessarily require or imply these entities or deposit between operating
In any this actual relation or order.And, term " inclusion ", "comprising" or its any other variant are intended to
Comprising of nonexcludability, wants so that including a series of process of key elements, method, article or equipment and not only including those
Element, but also include other key elements being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element that limited by sentence "including a ..." it is not excluded that
Also there is other identical element including in the process of described key element, method, article or equipment.Term " on ", D score etc. refers to
The orientation showing or position relationship are based on orientation shown in the drawings or position relationship, are for only for ease of the description present invention and simplification
Description, rather than indicate or imply that the device of indication or element must have specific orientation, with specific azimuth configuration and behaviour
Make, be therefore not considered as limiting the invention.Unless otherwise clearly defined and limited, term " installation ", " being connected ",
" connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or is integrally connected；Can be
It is mechanically connected or electrically connect；Can be to be joined directly together it is also possible to be indirectly connected to by intermediary, can be two
The connection of element internal.For the ordinary skill in the art, above-mentioned term can be understood as the case may be at this
Concrete meaning in invention.
In the description of the present invention, illustrate a large amount of details.Although it is understood that, embodiments of the invention can
To put into practice in the case of there is no these details.In some instances, known method, structure and skill are not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly it will be appreciated that disclosing and help understand respectively to simplify the present invention
One or more of individual inventive aspect, in the description to the exemplary embodiment of the present invention above, each of the present invention is special
Levy and be sometimes grouped together in single embodiment, figure or descriptions thereof.However, should not be by the method solution of the disclosure
Release is in reflect an intention that i.e. the present invention for required protection requires than the feature being expressly recited in each claim more
Many features.More precisely, as the following claims reflect, inventive aspect is less than single reality disclosed above
Apply all features of example.Therefore, it then follows claims of specific embodiment are thus expressly incorporated in this specific embodiment,
Wherein each claim itself is as the separate embodiments of the present invention.It should be noted that in the case of not conflicting, this
Embodiment in application and the feature in embodiment can be mutually combined.The invention is not limited in any single aspect,
It is not limited to any single embodiment, be also not limited to combination in any and/or the displacement of these aspects and/or embodiment.And
And, can be used alone each aspect of the present invention and/or embodiment or with other aspects one or more and/or its enforcement
Example is used in combination.
Finally it is noted that various embodiments above, only in order to technical scheme to be described, is not intended to limit；To the greatest extent
Pipe has been described in detail to the present invention with reference to foregoing embodiments, it will be understood by those within the art that: its according to
So the technical scheme described in foregoing embodiments can be modified, or wherein some or all of technical characteristic is entered
Row equivalent；And these modifications or replacement, do not make the essence of appropriate technical solution depart from various embodiments of the present invention technology
The scope of scheme, it all should be covered in the middle of the claim of the present invention and the scope of description.
Claims (10)
1. a kind of electrocardiosignal feature point detecting method is it is characterised in that include:
The signaling point extracting all electrocardio sampled points in sample set is to feature, and extracts all electrocardiosignal tests in test set
The signaling point of point is to feature；
Land use models recognizer, is trained to feature to the signaling point extracting in sample set, obtains electrocardiosignal feature
Disaggregated model；
Using described electrocardiosignal tagsort model, the signaling point of electrocardiosignal test points all in test set is entered to feature
Row classification, obtains the signaling point of all electrocardiosignal test points classification results to feature；
Using described classification results as electrocardiosignal test points all in test set feature point detection result.
2. method according to claim 1 is it is characterised in that described sample set, comprising: choose in electrocardiosignal sample
With markd electrocardio sampled point and in electrocardiosignal sample choose non-characteristic point electrocardio sampled point；
Described identical with the quantity of described non-characteristic point electrocardio sampled point with markd electrocardio sampled point；
Correspondingly, the described signaling point extracting all electrocardio sampled points in sample set is to feature, comprising:
In extraction sample set, the signaling point with markd electrocardio sampled point is to feature；
The signaling point extracting non-characteristic point electrocardio sampled point in sample set is to feature；
Correspondingly, described Land use models recognizer, is trained to feature to the signaling point extracting in sample set, obtains the heart
Signal characteristics disaggregated model, comprising:
Using the signaling point with markd electrocardio sampled point in the sample set of extraction to feature as training positive example；
In the sample set that will extract, the signaling point of non-characteristic point electrocardio sampled point bears example to feature as training；
Land use models recognizer, is trained to feature to the signaling point in described training positive example and the negative example of training, obtains the heart
Signal characteristics disaggregated model.
3. method according to claim 1 is it is characterised in that described algorithm for pattern recognition, comprising: random forests algorithm.
4. method according to claim 1 it is characterised in that in described extraction sample set all electrocardio sampled points signal
Point is to feature, and extracts the signaling point of all electrocardiosignal test points in test set to feature, comprising:
Using signaling point, the signaling point of all electrocardio sampled points in sample set is extracted to feature to feature extraction algorithm, and utilize
Described signaling point extracts the signaling point of all electrocardiosignal test points in test set to feature to feature extraction algorithm；
Wherein, described signaling point is to feature extraction algorithm, comprising: extract signaling point in the time-domain signal of electrocardiosignal to spy
Levy or extract in the base expansion coefficient of electrocardiosignal signaling point to feature；
The base expansion coefficient of described electrocardiosignal, comprising: the wavelet transform dwt coefficient of electrocardiosignal or electrocardiosignal
Empirical mode decomposition emd coefficient.
5. method according to claim 4 is it is characterised in that carry in the wavelet transform dwt coefficient of electrocardiosignal
Take signaling point to feature, comprising:
By electrocardio sampled point/test point in the position in electro-cardiologic signal waveforms centered on, setting one preset length window, and
Intercept the electrocardiosignal in described window；
Using maximum-minima, the electrocardiosignal intercepting is normalized；
Using wavelet transform dwt, extract the different decomposition level of the wavelet transformation of electrocardiosignal after normalization, and at each
Random selection predetermined number point pair on wavelet decomposition level coefficient；
Calculate each point to pair (x1, x2) two sampling point position x1And x2Absolute amplitude difference and this point to pair
(x1, x2) two sampling point position x1And x2Amplitude difference symbol；
Using result of calculation as described electrocardio sampled point/test point signaling point to feature.
6. method according to claim 5 is it is characterised in that each point of described calculating is to pair (x1, x2) two adopt
Sampling point position x1And x2Absolute amplitude difference and this point to pair (x1, x2) two sampling point position x1And x2Amplitude difference
Symbol, comprising:
By the first formula, calculate each point to pair (x1, x2) two sampling point position x1And x2Absolute amplitude difference
With this point to pair (x1, x2) two sampling point position x1And x2Amplitude difference symbol；
Wherein, described first formula is:
Wherein, sig (x1) it is electrocardiosignal in sampling point position x1The amplitude at place, sig (x2) it is electrocardiosignal in sampling point position
x2The amplitude at place, sign [sig (x1)-sig(x2)] it is point to pair (x1, x2) two sampling point position x1And x2Difference in magnitude
The symbol of value, makes sig (x1)-sig(x2)=m,
7. the method according to any one of claim 1-6 is it is characterised in that described using described electrocardiosignal feature
Disaggregated model, classifies to feature to the signaling point of electrocardiosignal test points all in test set, obtains all electrocardiosignaies
After the signaling point of test point is to the classification results of feature, methods described also includes:
Using post-processing algorithm, described classification results are removed with false-alarm output；
Correspondingly, described using described classification results as electrocardiosignal test points all in test set feature point detection result,
Including:
The feature point detection result as electrocardiosignal test points all in test set for the result obtaining after false-alarm output will be removed.
8. method according to claim 7, it is characterised in that described utilization post-processing algorithm, is gone to described classification results
Except false-alarm output, comprising:
Difference for the time in classification results is polymerized to one group less than the cohort labelling of predetermined threshold value, takes the time domain average conduct of this group
The output result of this class labelling；Meanwhile, set in advance electrocardiosignal each labelling appearance order is used as prior information, right
In classification results, the incorrect output of labelling appearance order is removed.
9. a kind of electrocardiosignal feature point detection device is it is characterised in that include:
Extraction module, for extracting the signaling point of all electrocardio sampled points in sample set to feature, and extracts institute in test set
The signaling point having electrocardiosignal test point is to feature；
Training module, for Land use models recognizer, is trained to feature to the signaling point extracting in sample set, obtains
Electrocardiosignal tagsort model；
Sort module, for using described electrocardiosignal tagsort model, to electrocardiosignal test points all in test set
Signaling point is classified to feature, obtains the signaling point of all electrocardiosignal test points classification results to feature；
Result acquisition module, for using described classification results as electrocardiosignal test points all in test set feature point detection
Result.
10. device according to claim 9 is it is characterised in that described device also includes:
Remove module, for utilizing post-processing algorithm, described classification results are removed with false-alarm output；
Correspondingly, described result acquisition module, specifically for
The feature point detection result as electrocardiosignal test points all in test set for the result obtaining after false-alarm output will be removed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610862893.XA CN106344004A (en) | 2016-09-28 | 2016-09-28 | Electrocardiosignal feature point detecting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610862893.XA CN106344004A (en) | 2016-09-28 | 2016-09-28 | Electrocardiosignal feature point detecting method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106344004A true CN106344004A (en) | 2017-01-25 |
Family
ID=57865674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610862893.XA Pending CN106344004A (en) | 2016-09-28 | 2016-09-28 | Electrocardiosignal feature point detecting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106344004A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107184203A (en) * | 2017-07-03 | 2017-09-22 | 重庆大学 | Electrocardiosignal Feature point recognition method based on adaptive set empirical mode decomposition |
| CN107239684A (en) * | 2017-05-22 | 2017-10-10 | 吉林大学 | A kind of feature learning method and system for ECG identifications |
| CN107516075A (en) * | 2017-08-03 | 2017-12-26 | 安徽华米信息科技有限公司 | Detection method, device and the electronic equipment of electrocardiosignal |
| CN107714029A (en) * | 2017-11-20 | 2018-02-23 | 北京工业大学 | A kind of ECG Telemonitor System |
| CN109009047A (en) * | 2018-05-24 | 2018-12-18 | 东软集团股份有限公司 | A kind of arrhythmia detection method, device and equipment |
| CN109544479A (en) * | 2018-11-27 | 2019-03-29 | 中国科学院深圳先进技术研究院 | A kind of Enhancement Method and relevant device of time-frequency image |
| CN111067511A (en) * | 2019-11-21 | 2020-04-28 | 东软集团股份有限公司 | Method, device and equipment for determining key points in electrocardiogram data |
| CN113180689A (en) * | 2021-04-08 | 2021-07-30 | 上海数创医疗科技有限公司 | P wave crest and initial position extraction method based on Gaussian function fitting |
| CN113647959A (en) * | 2021-07-27 | 2021-11-16 | 东软集团股份有限公司 | Method, device and equipment for identifying waveform of electrocardiographic waveform signal |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101782895A (en) * | 2009-01-12 | 2010-07-21 | 财团法人工业技术研究院 | Method and device thereof for performing hierarchical empirical mode decomposition on signal |
| CN101919695A (en) * | 2010-08-06 | 2010-12-22 | 李楚雅 | Electrocardiosignal QRS complex detection method based on wavelet transform |
| CN102274020A (en) * | 2011-06-30 | 2011-12-14 | 东北大学 | Low-power consumption portable electrocardiograph monitor and control method thereof |
| CN103560795A (en) * | 2013-10-29 | 2014-02-05 | 东软熙康健康科技有限公司 | Compression method, transmission method, reconstruction method and device for electrocardiograph signals |
| US20140235977A1 (en) * | 2013-02-20 | 2014-08-21 | Perminova Inc. | Necklace-shaped physiological monitor |
| CN104182625A (en) * | 2014-08-15 | 2014-12-03 | 重庆邮电大学 | Electrocardiosignal denoising method based on morphology and EMD (empirical mode decomposition) wavelet threshold value |
| CN104398252A (en) * | 2014-11-05 | 2015-03-11 | 深圳先进技术研究院 | Electrocardiogram signal processing method and device |
| CN104783787A (en) * | 2015-04-24 | 2015-07-22 | 太原理工大学 | J-wave detecting method based on neural network |
| CN105054926A (en) * | 2015-04-13 | 2015-11-18 | 深圳市飞马与星月科技研究有限公司 | Electrocardiosignal feature information extraction method and device |
| CN105266801A (en) * | 2015-09-10 | 2016-01-27 | 太原理工大学 | J wave detection and classification method based on probabilistic neural network (PNN) |
| CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
-
2016
- 2016-09-28 CN CN201610862893.XA patent/CN106344004A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101782895A (en) * | 2009-01-12 | 2010-07-21 | 财团法人工业技术研究院 | Method and device thereof for performing hierarchical empirical mode decomposition on signal |
| CN101919695A (en) * | 2010-08-06 | 2010-12-22 | 李楚雅 | Electrocardiosignal QRS complex detection method based on wavelet transform |
| CN102274020A (en) * | 2011-06-30 | 2011-12-14 | 东北大学 | Low-power consumption portable electrocardiograph monitor and control method thereof |
| US20140235977A1 (en) * | 2013-02-20 | 2014-08-21 | Perminova Inc. | Necklace-shaped physiological monitor |
| CN103560795A (en) * | 2013-10-29 | 2014-02-05 | 东软熙康健康科技有限公司 | Compression method, transmission method, reconstruction method and device for electrocardiograph signals |
| CN104182625A (en) * | 2014-08-15 | 2014-12-03 | 重庆邮电大学 | Electrocardiosignal denoising method based on morphology and EMD (empirical mode decomposition) wavelet threshold value |
| CN104398252A (en) * | 2014-11-05 | 2015-03-11 | 深圳先进技术研究院 | Electrocardiogram signal processing method and device |
| CN105054926A (en) * | 2015-04-13 | 2015-11-18 | 深圳市飞马与星月科技研究有限公司 | Electrocardiosignal feature information extraction method and device |
| CN104783787A (en) * | 2015-04-24 | 2015-07-22 | 太原理工大学 | J-wave detecting method based on neural network |
| CN105266801A (en) * | 2015-09-10 | 2016-01-27 | 太原理工大学 | J wave detection and classification method based on probabilistic neural network (PNN) |
| CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
Non-Patent Citations (1)
| Title |
|---|
| PENGFEI GAO ET AL: "Real Time ECG Characteristic Point Detection with Randomly Selected Signal Pair Difference (RSSPD) Feature and Random Forest Classifier", 《2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239684A (en) * | 2017-05-22 | 2017-10-10 | 吉林大学 | A kind of feature learning method and system for ECG identifications |
| CN107184203A (en) * | 2017-07-03 | 2017-09-22 | 重庆大学 | Electrocardiosignal Feature point recognition method based on adaptive set empirical mode decomposition |
| CN107516075A (en) * | 2017-08-03 | 2017-12-26 | 安徽华米信息科技有限公司 | Detection method, device and the electronic equipment of electrocardiosignal |
| WO2019024861A1 (en) * | 2017-08-03 | 2019-02-07 | 安徽华米信息科技有限公司 | Detection of electrocardiogram signal |
| US11534097B2 (en) | 2017-08-03 | 2022-12-27 | Anhui Huami Information Technology Co., Ltd. | Detection of electrocardiographic signal |
| CN107516075B (en) * | 2017-08-03 | 2020-10-09 | 安徽华米智能科技有限公司 | Electrocardiosignal detection method and device and electronic equipment |
| CN107714029A (en) * | 2017-11-20 | 2018-02-23 | 北京工业大学 | A kind of ECG Telemonitor System |
| CN109009047B (en) * | 2018-05-24 | 2021-10-26 | 东软集团股份有限公司 | Arrhythmia detection method, device and equipment |
| CN109009047A (en) * | 2018-05-24 | 2018-12-18 | 东软集团股份有限公司 | A kind of arrhythmia detection method, device and equipment |
| CN109544479A (en) * | 2018-11-27 | 2019-03-29 | 中国科学院深圳先进技术研究院 | A kind of Enhancement Method and relevant device of time-frequency image |
| CN111067511B (en) * | 2019-11-21 | 2022-08-16 | 东软集团股份有限公司 | Method, device and equipment for determining key points in electrocardiogram data |
| CN111067511A (en) * | 2019-11-21 | 2020-04-28 | 东软集团股份有限公司 | Method, device and equipment for determining key points in electrocardiogram data |
| CN113180689A (en) * | 2021-04-08 | 2021-07-30 | 上海数创医疗科技有限公司 | P wave crest and initial position extraction method based on Gaussian function fitting |
| CN113647959A (en) * | 2021-07-27 | 2021-11-16 | 东软集团股份有限公司 | Method, device and equipment for identifying waveform of electrocardiographic waveform signal |
| CN113647959B (en) * | 2021-07-27 | 2024-01-12 | 东软集团股份有限公司 | Waveform identification method, device and equipment for electrocardiographic waveform signals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106344004A (en) | Electrocardiosignal feature point detecting method and device | |
| CN108030494B (en) | Electrocardiosignal error flag training sample recognition methods based on cross validation | |
| WO2022183698A1 (en) | Artificial intelligence fault identification system and method based on power transmission line transient waveform | |
| Perunicic et al. | Power quality disturbance detection and classification using wavelets and artificial neural networks | |
| CN103268497B (en) | A kind of human face posture detection method and the application in recognition of face | |
| US20170143226A1 (en) | Action Recognition Method and Device Based on Surface Electromyography Signal | |
| CN103743980A (en) | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) | |
| CN105841961A (en) | Bearing fault diagnosis method based on Morlet wavelet transformation and convolutional neural network | |
| CN103810393B (en) | A kind of ecg wave form characteristic point positioning method based on electrocardial vector | |
| CN105117708A (en) | Facial expression recognition method and apparatus | |
| CN105354866A (en) | Polygon contour similarity detection method | |
| CN104517097A (en) | Kinect-based moving human body posture recognition method | |
| CN109359693A (en) | A kind of Power Quality Disturbance Classification Method | |
| CN107679453A (en) | Weather radar electromagnetic interference echo recognition methods based on SVMs | |
| CN109323754A (en) | A kind of train wheel polygon fault diagnosis detection method | |
| CN105844221A (en) | Human face expression identification method based on Vadaboost screening characteristic block | |
| CN103440471B (en) | The Human bodys' response method represented based on low-rank | |
| CN101738998B (en) | System and method for monitoring industrial process based on local discriminatory analysis | |
| CN103646255A (en) | Face detection method based on Gabor characteristics and extreme learning machine | |
| CN109065046A (en) | Method, apparatus, electronic equipment and the computer readable storage medium that voice wakes up | |
| CN101853388B (en) | Unchanged view angle behavior identification method based on geometric invariable | |
| CN104103033A (en) | Image real-time processing method | |
| CN104182621A (en) | DBN based ADHD discriminatory analysis method | |
| CN109817339A (en) | Patient's group technology and device based on big data | |
| CN105572501A (en) | Power quality disturbance identification method based on SST conversion and LS-SVM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170125 |
|
| RJ01 | Rejection of invention patent application after publication |