CN108784681B - Electrocardio characteristic identification method - Google Patents
Electrocardio characteristic identification method Download PDFInfo
- Publication number
- CN108784681B CN108784681B CN201810319626.7A CN201810319626A CN108784681B CN 108784681 B CN108784681 B CN 108784681B CN 201810319626 A CN201810319626 A CN 201810319626A CN 108784681 B CN108784681 B CN 108784681B
- Authority
- CN
- China
- Prior art keywords
- characteristic
- wave
- electrocardiogram
- electrocardio
- time
- 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.)
- Active
Links
Images
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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
Abstract
The invention relates to an electrocardio characteristic identification method, which comprises a registration stage, an identification stage and an update stage, wherein the registration stage registers the electrocardio characteristic vector and period of a user, the identification stage judges whether the electrocardiogram is matched with the registered electrocardio characteristic vector or not based on the electrocardiogram of the user acquired by an electrocardio acquisition instrument, and the update stage updates the electrocardio characteristic vector. The method improves the accuracy of the electrocardio-feature recognition.
Description
[ technical field ] A method for producing a semiconductor device
The invention belongs to the field of biological identification, and particularly relates to an electrocardio characteristic identification method.
[ background of the invention ]
Biometric identification techniques are now rapidly developed, and existing biometric identification is usually the identification of biometric features such as a user's fingerprint, face shape, iris, and the like. These biometrics have their own advantages and their own disadvantages, such as false recognition or rejection of a person with a finger injured or blurred, difficulty in obtaining a signal for iris recognition, and influence from contact lenses.
In recent years, a new biometric identification method by means of electrocardiographic features has appeared, for example, electrocardiographic features, i.e., Electrocardiogram (ECG) features, of a user are acquired by a portable electrocardiograph. The electrocardio characteristics are difficult to forge and not easy to be damaged by external factors, and the electrocardio characteristics have higher safety. The existing identification methods for the electrocardio characteristics comprise two categories of identification based on characteristic points and identification based on waveforms, and the two identification methods have advantages and disadvantages respectively, but the identification accuracy rate of the two identification methods is reduced to a certain extent under certain environmental conditions.
[ summary of the invention ]
In order to solve the problems, the invention provides a novel electrocardio characteristic identification method.
The technical scheme adopted by the invention is as follows:
an identification method of electrocardio characteristics comprises a registration stage and an identification stage,
the registration phase comprises:
collecting a plurality of electrocardiogram waves of a user, respectively extracting characteristic values of each wave, wherein the characteristic values comprise at least two peak characteristics and at least two time characteristics, calculating the average of the same characteristic values of each wave, forming an electrocardiogram characteristic vector F of the user by each obtained average characteristic value, simultaneously calculating the average cycle time R of the electrocardiogram waves, and registering the F and the R in a database of an identification server;
the identification phase comprises:
(1) an electrocardiogram acquisition instrument acquires an electrocardiogram of a user to obtain electrocardiogram waves of k periods;
(2) the identification server respectively extracts the characteristic vectors from the electrocardiograph waves of the k periods to obtain k characteristic vectors F1，F2，……，FkWhile obtaining a corresponding time R per cycle1，R2，……，Rk；
(3) For any one Fi(i is more than or equal to 1 and less than or equal to k), the recognition server calculates FiThe difference value C of the electrocardio characteristic vector F registered by the useri；
(4) And the identification server calculates the average value C of the k difference values, and if the average value C is smaller than a predefined threshold value, the acquired electrocardiogram wave is considered to be matched with the registered electrocardiogram feature vector F.
Furthermore, the electrocardio characteristic vectors F and the k characteristic vectors have the same composition structure and are composed of m time characteristic values (m is more than or equal to 2) and n peak characteristic values (n is more than or equal to 2), namely
F＝{T1，T2，……，Tm，V1，V2，……，Vn}
Wherein the characteristic value T1，T2，……，TmIs m time characteristic values, V2，……，VnIs n peak eigenvalues;
Fi＝{Ti1，Ti2，……，Tim，Vi1，Vi2，……，Vin}
Ti1，Ti2，……，Timis m time characteristic values, Vi1，Vi2，……，VinIs the n peak eigenvalues.
Further, the difference value CiCalculated by the following formula:
further, an update phase is included, the update phase including: the identification server selects a median from the k difference values to obtain a feature vector F corresponding to the medianaCalculating a new ECG eigenvector FnewSaid FnewIs F and FaThe average value of the corresponding characteristic components; subjecting said F tonewAnd replacing the electrocardio characteristic vector F stored in the database.
Further, the peak features include at least two of the following features: p wave peak point, Q wave peak point, R wave peak point, S wave peak point and T wave peak point.
Further, the temporal features include at least two of the following features: the time of the start of the P-wave, the duration of the P-wave, the time width of the QS, the time width of the ST, and the duration of the T-wave.
The invention has the beneficial effects that: the accuracy of the electrocardio characteristic identification is improved.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, and are not to be considered limiting of the invention, in which:
fig. 1 is an exemplary application scenario of the method of the present invention.
[ detailed description ] embodiments
The present invention will now be described in detail with reference to the drawings and specific embodiments, wherein the exemplary embodiments and descriptions are provided only for the purpose of illustrating the present invention and are not to be construed as limiting the present invention.
Referring to fig. 1, an exemplary application scenario of the method of the present invention is shown, in which an electrocardiograph acquisition instrument acquires an electrocardiogram of a user, sends the electrocardiogram data to an identification server, and the identification server extracts corresponding electrocardiographic features from the electrocardiogram data, compares the electrocardiographic features with electrocardiographic features of the user pre-stored in a database, and if the comparison is passed, confirms the identity of the user.
In order to perform electrocardiographic recognition, first, electrocardiographic features in electrocardiographic data need to be defined. An electrocardiogram generally comprises a plurality of periodically repeating electrocardiographic waveforms, each generally consisting of a P-wave, a QRS complex, and a T-wave, which contain various unique physiologically meaningful information.
For an electrocardiographic wave, corresponding characteristic values can be extracted from the electrocardiographic wave, and the characteristic values can be divided into two types: the first type is peak characteristics, including a P wave peak point, a Q wave peak point, an R wave peak point, an S wave peak point and a T wave peak point; the second category is temporal features such as the time of the start of the P-wave, the duration of the P-wave, the temporal width of the QS, the temporal width of the ST, the duration of the T-wave, etc. within one cardiac cycle. It should be noted that not every peak feature and temporal feature need to be extracted, and there are many ways for extracting features of an electrocardiogram in the art, but these ways are usually based on the above peak features or temporal features.
Based on the above definition, before the electrocardiographic feature recognition, the electrocardiographic feature vector F of the user is registered in the database of the recognition server. In the registration stage, only a large number of electrocardiographic waves of the user need to be collected, the characteristic value of each wave is respectively extracted, then the average of the same characteristic values of each wave is calculated, and the obtained average characteristic values form the electrocardiographic characteristic vector F of the user. Supposing that the adopted electrocardio characteristic vector comprises m time characteristic values T1，T2，……，Tm(m.gtoreq.2), and n peak characteristic values V1，V2，……，Vn(n is more than or equal to 2), the electrocardiogram feature vector F can be expressed as:
F＝{T1，T2，……，Tm，V1，V2，……，Vn}
i.e. F has m + n components in total.
Meanwhile, for each collected electrocardiogram wave, the average cycle time R is calculated and registered in the database.
Based on the above result and the registered electrocardiographic feature vector F and period R of the user, the following describes the identification process of the present invention in detail:
(1) the electrocardiogram acquisition instrument acquires the electrocardiogram of the user to obtain electrocardiogram waves of a plurality of periods.
In the user identification stage, a large number of electrocardiographic waves cannot be acquired as in the registration stage generally, but electrocardiographic waves of multiple cycles can be acquired through acquisition of predetermined identification time, the specific number of cycles is not limited, and it is assumed that electrocardiographic waves of k cycles are acquired in the step.
(2) The identification server respectively extracts the characteristic vectors of the electrocardiograph waves of the k periods obtained in the step 1 to obtain k characteristic vectors F1，F2，……，FkWhile obtaining a corresponding actual duration R of each cycle1，R2，……，Rk。
Specifically, for the first onePeriodic electrocardiographic waves of duration R1The extracted feature vector is F1And so on.
The method for extracting the feature vector from each electrocardiographic wave in step 2 is the same as the extraction method in the registration stage, and therefore the feature vector acquired in step 2 also includes m time feature values and n peak feature values. From which F can be definedi(1. ltoreq. i. ltoreq. k) is:
Fi＝{Ti1，Ti2，……，Tim，Vi1，Vi2，……，Vin}
wherein T isi1，Ti2，……，TimIs m time characteristic values which are respectively corresponding to the m time characteristic values T at the time of registration1，T2，……，TmAnd correspondingly. Vi1，Vi2，……，VinIs n peak characteristic values which are also respectively matched with the n peak characteristic values V at the time of registration1，V2，……，VnAnd correspondingly.
(3) For any one FiRecognition Server calculation FiThe difference value C of the electrocardio characteristic vector F registered by the useri。
Specifically, the difference value CiCalculated by the following formula:
the method is based on the different characteristics of the two characteristics, the calculation of the difference value is divided into two parts of time characteristic calculation and peak value characteristic calculation, and the accuracy rate of the electrocardio characteristic identification is improved.
(4) Based on step 3, the recognition server can calculate and obtain k difference values C1，C2，……，CkAnd the identification server calculates an average value C of the k difference values, and if the average value C is smaller than a predefined threshold value, the acquired electrocardiogram wave is considered to be matched with the registered electrocardiogram feature vector F, so that the user is judged to be the registered user.
By step 4, the recognition server has in fact completed the matching and recognition process of the electrocardiogram acquired from the user. However, in order to improve the accuracy of subsequent identification, the present invention further adds an updating process for the registered ecg feature vector F, which specifically includes the following steps:
the identification server selects a median from the k difference values, obtains a feature vector corresponding to the median, and sets the feature vector as Fa＝{Ta1，Ta2，……，Tam，Va1，Va2，……，Van}; recognition Server computations F and FaThe average value of the respective feature components in (1), namely:
Ti_new＝(Ti+Tai)/2；(1≤i≤m)
Vj_new＝(Vj+Vaj)/2；(1≤j≤n)
the average value is used as the characteristic component of the new electrocardio characteristic vector, namely:
Fnew＝{T1_new，T2_new，……，Tm_new，V1_new，V2_new，……，Vn_new}
subjecting said F tonewThe new electrocardio feature vector is used for replacing the electrocardio feature vector F stored in the database, thereby realizing the updating of the electrocardio feature vector.
The above description is only a preferred embodiment of the present invention, and all equivalent changes or modifications of the structure, characteristics and principles described in the present invention are included in the scope of the present invention.
Claims (3)
1. The method for identifying the electrocardio characteristics is characterized by comprising a registration stage and an identification stage, wherein the registration stage comprises the following steps:
collecting a plurality of electrocardiogram waves of a user, respectively extracting characteristic values of each wave, wherein the characteristic values comprise at least two peak characteristics and at least two time characteristics, calculating the average of the same characteristic values of each wave, forming an electrocardiogram characteristic vector F of the user by each obtained average characteristic value, simultaneously calculating the average cycle time R of the electrocardiogram waves, and registering the F and the R in a database of an identification server;
the identification phase comprises:
(1) an electrocardiogram acquisition instrument acquires an electrocardiogram of a user to obtain electrocardiogram waves of k periods;
(2) the identification server respectively extracts the characteristic vectors from the electrocardiograph waves of the k periods to obtain k characteristic vectors F1，F2，……，FkWhile obtaining a corresponding time R per cycle1，R2，……，Rk；
(3) For any one Fi(i is more than or equal to 1 and less than or equal to k), the recognition server calculates FiThe difference value C of the electrocardio characteristic vector F registered by the useri；
(4) The identification server calculates an average value C of the k difference values, and if the average value C is smaller than a predefined threshold value, the acquired electrocardiogram wave is considered to be matched with the registered electrocardiogram feature vector F;
the electrocardio characteristic vector F and the k characteristic vectors have the same composition structure and are composed of m time characteristic values (m is more than or equal to 2) and n peak characteristic values (n is more than or equal to 2), namely
F＝{T1，T2，……，Tm，V1，V2，……，Vn}
Wherein the characteristic value T1，T2，……，TmIs m time characteristic values, V2，……，VnIs n peak eigenvalues;
Fi＝{Ti1，Ti2，……，Tim，Vi1，Vi2，……，Vin}
Ti1，Ti2，……，Timis m time characteristic values, Vi1，Vi2，……，VinIs n peak eigenvalues;
the difference value CiCalculated by the following formula:
the method further comprises an update phase comprising: the identification server selects a median from the k difference values to obtain a feature vector F corresponding to the medianaCalculating a new ECG eigenvector FnewSaid FnewIs F and FaThe average value of the corresponding characteristic components; subjecting said F tonewAnd replacing the electrocardio characteristic vector F stored in the database.
2. The method of claim 1, wherein the peak characteristics comprise at least two of the following characteristics: p wave peak point, Q wave peak point, R wave peak point, S wave peak point and T wave peak point.
3. The method of claim 1, wherein the temporal characteristics include at least two of the following characteristics: the time of the start of the P-wave, the duration of the P-wave, the time width of the QS, the time width of the ST, and the duration of the T-wave.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810319626.7A CN108784681B (en) | 2018-04-11 | 2018-04-11 | Electrocardio characteristic identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810319626.7A CN108784681B (en) | 2018-04-11 | 2018-04-11 | Electrocardio characteristic identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108784681A CN108784681A (en) | 2018-11-13 |
| CN108784681B true CN108784681B (en) | 2021-03-16 |
Family
ID=64095501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810319626.7A Active CN108784681B (en) | 2018-04-11 | 2018-04-11 | Electrocardio characteristic identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108784681B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021108950A1 (en) * | 2019-12-02 | 2021-06-10 | 深圳迈瑞生物医疗电子股份有限公司 | Monitoring method, monitoring apparatus, monitoring device, and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101773394A (en) * | 2010-01-06 | 2010-07-14 | 中国航天员科研训练中心 | Identification method and identification system using identification method |
| CN102274029A (en) * | 2011-05-25 | 2011-12-14 | 中国科学院深圳先进技术研究院 | Identity recognition method and system |
| CN104063645A (en) * | 2014-07-01 | 2014-09-24 | 清华大学深圳研究生院 | Identity recognition method based on ECG dynamic self-updating samples |
| CN104573458A (en) * | 2014-12-30 | 2015-04-29 | 深圳先进技术研究院 | Identity recognition method, device and system based on electrocardiogram signals |
| CN204813858U (en) * | 2015-07-28 | 2015-12-02 | 杭州暖芯迦电子科技有限公司 | Blood pressure appearance based on pulse back wave transmission time |
-
2018
- 2018-04-11 CN CN201810319626.7A patent/CN108784681B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101773394A (en) * | 2010-01-06 | 2010-07-14 | 中国航天员科研训练中心 | Identification method and identification system using identification method |
| CN102274029A (en) * | 2011-05-25 | 2011-12-14 | 中国科学院深圳先进技术研究院 | Identity recognition method and system |
| CN104063645A (en) * | 2014-07-01 | 2014-09-24 | 清华大学深圳研究生院 | Identity recognition method based on ECG dynamic self-updating samples |
| CN104573458A (en) * | 2014-12-30 | 2015-04-29 | 深圳先进技术研究院 | Identity recognition method, device and system based on electrocardiogram signals |
| CN204813858U (en) * | 2015-07-28 | 2015-12-02 | 杭州暖芯迦电子科技有限公司 | Blood pressure appearance based on pulse back wave transmission time |
Non-Patent Citations (4)
| Title |
|---|
| 付乾坤.基于心电信号的生物识别技术研究.《中国优秀硕士学位论文全文数据库 信息科技辑》.2016,(第03期), * |
| 基于动态阈值和DTW的ECG身份识别算法;卢阳，等;《宁波工程学院学报》;20140630;第26卷(第2期);22-26 * |
| 基于心电信号的生物识别技术研究;付乾坤;《中国优秀硕士学位论文全文数据库 信息科技辑》;20160315(第03期);8,24-44 * |
| 虹膜定位及识别算法研究;李详;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150115(第01期);12-17 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108784681A (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hammad et al. | A novel two-dimensional ECG feature extraction and classification algorithm based on convolution neural network for human authentication | |
| CN108460318B (en) | Identity authentication/identification method and equipment based on electrocardiosignals | |
| Labati et al. | ECG biometric recognition: Permanence analysis of QRS signals for 24 hours continuous authentication | |
| Lim et al. | Heartrate-dependent heartwave biometric identification with thresholding-based GMM–HMM methodology | |
| Silva et al. | ECG biometrics: Principles and applications | |
| Singh | Human recognition using Fisher׳ s discriminant analysis of heartbeat interval features and ECG morphology | |
| Wu et al. | ECG biometric recognition: unlinkability, irreversibility, and security | |
| WO2018152711A1 (en) | Electrocardiographic authentication-based door control system and authentication method therefor | |
| CN109276242A (en) | The method and apparatus of electrocardiosignal type identification | |
| CN106388832B (en) | A kind of personal identification method based on the whole-heartedly dirty sequence image of ultrasound | |
| CN106874722A (en) | A kind of personal identification method and its device based on electrocardiosignal | |
| Sepahvand et al. | A novel multi-lead ECG personal recognition based on signals functional and structural dependencies using time-frequency representation and evolutionary morphological CNN | |
| KR101578167B1 (en) | self-organized real-time authentication method using ECG signal | |
| Gürkan et al. | A novel biometric authentication approach using electrocardiogram signals | |
| Braojos et al. | A methodology for embedded classification of heartbeats using random projections | |
| El Boujnouni et al. | A wavelet-based capsule neural network for ECG biometric identification | |
| Alajlan et al. | Fusion of fingerprint and heartbeat biometrics using fuzzy adaptive genetic algorithm | |
| CN108784681B (en) | Electrocardio characteristic identification method | |
| Zhang et al. | Practical human authentication method based on piecewise corrected Electrocardiogram | |
| Chen et al. | Finger ECG-based authentication for healthcare data security using artificial neural network | |
| Muhammed et al. | CNN based off-the-person ECG biometrics | |
| Tan et al. | Statistical n-best AFD-based sparse representation for ECG biometric identification | |
| Gurkan et al. | A novel human identification system based on electrocardiogram features | |
| Lourenço et al. | ECG biometrics: A template selection approach | |
| IŞIK et al. | Biometric person authentication framework using polynomial curve fitting-based ECG feature extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |