CN103714281A - Identity recognition method based on electrocardiosignals - Google Patents
Identity recognition method based on electrocardiosignals Download PDFInfo
- Publication number
- CN103714281A CN103714281A CN201310686789.6A CN201310686789A CN103714281A CN 103714281 A CN103714281 A CN 103714281A CN 201310686789 A CN201310686789 A CN 201310686789A CN 103714281 A CN103714281 A CN 103714281A
- Authority
- CN
- China
- Prior art keywords
- information data
- electrocardiosignal
- euclidean distance
- training set
- vector
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/117—Identification of persons
Abstract
The invention relates to the field of biological recognition, and provides an identity recognition method based on electrocardiosignals. The method comprises the following steps: S1: acquiring ECG (electrocardio) information data; S2: preprocessing information data; S3: carrying out feature extraction on the information data processed in the step S2; S4: dividing the information data processed in the S3 into a training set and a test set; S5: obtaining a training template library by the training set; and S6: comparing the similarities of the information data of the testing set and the information data of the template library, so as to determine the owner of the ECG information data. According to the method, the electrocardiosignals can be processed to realize the identity recognition, and the reliability of the recognition is strong, the antijamming capability is strong, and the recognition accuracy is high.
Description
Technical field
The present invention relates to field of biological recognition, particularly relate to a kind of personal identification method based on electrocardiosignal.
Background technology
Along with the raising of social informatization degree, information security is more and more subject to people and payes attention to.And the identity verification mode of the forms such as original user and password is just being subject to various invasions, how to obtain the identification of safety and precise more, become the emphasis of current technical research.Biological identification technology makes this problem effectively be solved.Biological identification technology is to utilize computing machine and the intrinsic physiological property of human body to carry out the technology of discriminate individuals feature.
Identity recognizing technology based on biological characteristic is rapidly developed with advantages such as its high security, uniqueness, stability and validity, and current biological identification technology mainly contains fingerprint recognition, hand identification, iris recognition, face recognition, voice recognition, Gait Recognition, DNA identification etc.These biological characteristics have its unique advantage in some field, but also have certain limitation or defect at aspects such as accuracy rate, antifalsification and applicabilities.
Everyone heart organ form, frequency etc. are different separately, and ecg wave form is difficult for losing, and are difficult to plagiarize, and can represent uniquely my feature.Thereby electrocardio also can be applied to field of biological recognition as fingerprint, people's face etc.
At present, mainly contain the personal identification method based on resolving feature and transform characteristics.At the beginning of 21 century, Lena Biel proposes a kind of new personal identification method the earliest, adopts each a plurality of unique point of leading of 12 electrocardiosignals that lead as personal feature, after principal component analysis (PCA) is processed, carries out identification.Gahi etc. select 9 optimum features and obtain 100% recognition correct rate in 16 test samples from 24 amplitudes and interval feature.In addition, also occurred the personal identification method based on fusion feature, but because its data processing amount is larger, recognition speed is slower.
Prior art gathers the equipment operating complexity of electrocardiosignal, and data volume and noise are more, and signal-data processing difficulty is larger, distinguishes accuracy not high.Part Methods identification rate relies on the accuracy rate of waveform character point extraction, and when some ripple is small cannot measure time, its relevant proper vector cannot obtain.Prior art is not generally considered the impact that changes in heart rate is brought waveform, and directly using one or average period waveform generation transform characteristics as recognition feature, thereby affect the accuracy rate of identification.
Summary of the invention
The present invention adopts a kind of personal identification method based on electrocardiosignal, thereby makes the reliability of electrocardiosignal identification strong, and antijamming capability is strong, and recognition accuracy is high.
The present invention adopts following scheme:
A personal identification method based on electrocardiosignal, comprising:
S1: gather ecg information data;
S2: to described information data pre-service;
S3: the information data after S2 processes is carried out to feature extraction;
S4: the information data after S3 processes is divided into training set and test set;
S5: obtain training set template base by training set;
S6: test set information data and template base information data are carried out to similarity comparison, determine ecg information data owner.
Preferably, gather ecg information data, use electrocardiogram acquisition equipment to gather the data of different object different time sections.
Preferably, described information data pre-service is comprised described information data is removed to noise and baseline wander.
Preferably, use median filter and Wavelet Transformation Algorithm to remove noise and baseline wander.
The method of preferably, the information data after S2 processes being carried out to feature extraction comprises:
S501: the QRS that adopts So and Chan QRS detection algorithm to detect electrocardiosignal involves R wave-wave peak;
S502: the crest of take is found out all monocycle signal as boundary, and each monocycle signal is as a proper vector;
S503: to each proper vector normalized, carry out cubic spline interpolation processing on transverse axis on the longitudinal axis;
S504: a plurality of normalized monocycle electrocardiosignals are carried out to cluster analysis;
S505: choose signal data in maximum classification as the set of eigenvectors of this sample objects.
Preferably, described information data after S3 processes is divided into training set and test set is mean allocation.
Preferably, the described method that test set information data and template base information data are carried out to similarity comparison adopts Euclidean distance comparison algorithm, comprising: the Euclidean distance comparison algorithm of average and the Euclidean distance algorithm of matrix;
The Euclidean distance comparison algorithm of average is: establish two n+1 dimensional vectors, X=[x
0, x
1, x
2..., x
n], Y=[y
0, y
1, y
2..., y
n], their Euclidean distance is:
Utilize Euclidean distance as the similarity measurement of two characteristic curvees.In training set, have N electrocardiosignal, the k group monocycle vector that each electrocardiosignal obtains after the processing of three steps, gets the average value vector of k group monocycle vector as template
the training set data storehouse that forms altogether N vectorial template.In test set, each electrocardiosignal obtains k group monocycle vector after pre-service and feature extraction, asks respectively k group vector to training set data N vectorial template
euclidean distance, the Euclidean distance of corresponding each vectorial template.After vote in majority, select its minimum value as final value, such electrocardiosignal and training set template relatively after, obtain N value.If test set data have M electrocardiosignal, just can obtain the matrix of a M*N, the row n at the minimum value place that wherein m is capable, maximum for n template signal similarity in m electrocardiosignal in test set and training set, be ecg information data owner;
The Euclidean distance algorithm of matrix is: the Euclidean distance algorithm of matrix is on the Euclidean distance algorithm basis of average, the N of a training set electrocardiosignal is got to its k group monocycle vector data, then compare with test set k group monocycle vector, get minimum value as the distance measure of two electrocardiosignals, finally obtain the distance matrix of M*N, equally, the row n at the minimum value place that wherein m is capable, maximum for n signal similar degree in m electrocardiosignal in test set and training set, be ecg information data owner.
Compared with prior art, the present invention adopts a kind of personal identification method based on electrocardiosignal, realizes the processing of the electrocardiosignal collecting and identification, and identification certainty is strong, and antijamming capability is strong, and recognition accuracy is high.
Accompanying drawing explanation
Fig. 1 is a kind of personal identification method process flow diagram based on electrocardiosignal of the embodiment of the present invention;
Fig. 2 is the database thermal map of the embodiment of the present invention 1 indication;
Fig. 3 is the database scale-of-two thermal map of the embodiment of the present invention 1 indication;
Fig. 4 is that the sampling duration of the embodiment of the present invention 2 indications is the database scale-of-two thermal map of 5 seconds;
Fig. 5 is that the sampling duration of the embodiment of the present invention 2 indications is the database scale-of-two thermal map of 10 seconds;
Fig. 6 is that the sampling duration of the embodiment of the present invention 2 indications is the database scale-of-two thermal map of 20 seconds;
Fig. 7 is that the sampling duration of the embodiment of the present invention 2 indications is the database scale-of-two thermal map of 40 seconds.
Embodiment
Referring to shown in Fig. 1, is a kind of personal identification method process flow diagram based on electrocardiosignal of the present embodiment.
The method comprises the steps: a kind of personal identification method based on electrocardiosignal, comprising:
S1: gather ecg information data.
Gather ecg information data, use common electrocardiogram acquisition equipment to gather the data of different object different time sections.
S2: to information data pre-service.
Use median filter and Wavelet Transformation Algorithm to remove noise and baseline wander to information data.
S3: the information data after S2 processes is carried out to feature extraction.
The QRS that adopts So and Chan QRS detection algorithm to detect electrocardiosignal involves R wave-wave peak, and the crest of take is found out all monocycle signal as boundary, and each monocycle signal is as a proper vector; At the longitudinal axis (voltage axis), go up each proper vector normalization [0,1] between, on transverse axis (time shaft), carry out cubic spline interpolation processing, interpolation is spaced apart X=[0:0.01:1], a plurality of normalized monocycle electrocardiosignals are carried out to cluster analysis, choose signal data in maximum classification as the set of eigenvectors of this sample objects.
S4: the information data after S3 processes is divided into training set and test set.
Information data is equally assigned into training set and test set.
S5: obtain training set template base by training set.
S6: test set information data and template base information data are carried out to similarity comparison, determine ecg information data owner.
The method of test set information data and template base information data being carried out to similarity comparison adopts Euclidean distance comparison algorithm, comprising: the Euclidean distance comparison algorithm of average and the Euclidean distance algorithm of matrix.
The Euclidean distance comparison algorithm of average is: establish two n+1 dimensional vectors, X=[x
0, x
1, x
2..., x
n], Y=[y
0, y
1, y
2..., y
n], their Euclidean distance is:
Utilize Euclidean distance as the similarity measurement of two characteristic curvees.In training set, have N electrocardiosignal, the k group monocycle vector that each electrocardiosignal obtains after the processing of three steps, gets the average value vector of k group monocycle vector as template
the training set data storehouse that forms altogether N vectorial template.In test set, each electrocardiosignal obtains k group monocycle vector after pre-service and feature extraction, asks respectively k group vector to training set data N vectorial template
euclidean distance, the Euclidean distance of corresponding each vectorial template.After vote in majority, select its minimum value as final value, such electrocardiosignal and training set template relatively after, obtain N value.If test set data have M electrocardiosignal, just can obtain the matrix of a M*N, the row n at the minimum value place that wherein m is capable, maximum for n template signal similarity in m electrocardiosignal in test set and training set, be ecg information data owner.
The Euclidean distance algorithm of matrix is: the Euclidean distance algorithm of matrix is on the Euclidean distance algorithm basis of average, the N of a training set electrocardiosignal is got to its k group monocycle vector data, then compare with test set k group monocycle vector, get minimum value as the distance measure of two electrocardiosignals, finally obtain the distance matrix of M*N, equally, the row n at the minimum value place that wherein m is capable, maximum for n signal similar degree in m electrocardiosignal in test set and training set, be ecg information data owner.
embodiment 1:
In the present embodiment, adopt disclosed QT database as case, as table 1:
Table 1
MIT-BIH | MIT-BIH | MIT-BIH | MIT-BIH | ESC | MIT-BIH | Sudden |
Arrhyt. | ST?DB | Sup.Vent. | Long?Term | STT | NSR?DB | Death |
15 | 6 | 13 | 4 | 33 | 10 | 24 |
In QT database data acquisition totally 105 data of 7 disparate databases, wherein Healthy People data are 14,91 of other heart patient's data.Its data sampling frequency is 250HZ.
The present embodiment adopts above-mentioned a kind of personal identification method based on electrocardiosignal to carry out identification, in data after the processing of said method, its result represents as Fig. 3 as scale-of-two thermal map in Fig. 2 and database with database thermal map, and horizontal ordinate is training set, and ordinate is test set.The accuracy rate of its electrocardio identification is 92.38%.
embodiment 2:
In the present embodiment, adopt disclosed PTB database as case, as table 2:
Table 2
Diagnostic-type | Quantity |
Myocardial infarction (Myocardial infarction) | 148 |
(Cardiomyopathy/Heart failure) in |
18 |
Chamber bundle-branch block (Bundle branch block) | 15 |
Dysrhythmia (Dysrhythmia) | 14 |
Myocardial hypertrophy (Myocardial hypertrophy) | 7 |
Valvulopathy (Valvular heart disease) | 6 |
Myocarditis (Myocarditis) | 4 |
Other (Miscellaneous) | 4 |
Normal healthy controls group (Healthy controls) | 52 |
Totally 268 data in QT database, wherein Healthy People data are 52,216 of other heart patient's data.Its data sampling frequency is 1000HZ.
The present embodiment adopts above-mentioned a kind of personal identification method based on electrocardiosignal to carry out identification, and the difference sampling duration for PTB database comprises 5 seconds, 10 seconds, 20 seconds, 40 seconds, and electrocardio identity has been carried out analyzing identification.Result as in data after the processing of said method, its result represents with scale-of-two thermal map in database, as Fig. 4, sampling duration is the database scale-of-two thermal map of 5 seconds; As Fig. 5, sampling duration is the database scale-of-two thermal map of 10 seconds; As Fig. 6, sampling duration is the database scale-of-two thermal map of 20 seconds; As Fig. 7, sampling duration is the database scale-of-two thermal map of 40 seconds, and horizontal ordinate is training set, and ordinate is test set.The accuracy rate of its electrocardio identification is: sampling duration is the accuracy rate 94.23% of 5 seconds; Sampling duration is the accuracy rate 96.15% of 10 seconds; Sampling duration is the accuracy rate 98.07% of 20 seconds; Sampling duration is the accuracy rate 100% of 40 seconds.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (7)
1. the personal identification method based on electrocardiosignal, is characterized in that, comprising:
S1: gather ecg information data;
S2: to described information data pre-service;
S3: the information data after S2 processes is carried out to feature extraction;
S4: the information data after S3 processes is divided into training set and test set;
S5: obtain training set template base by training set;
S6: test set information data and template base information data are carried out to similarity comparison, determine ecg information data owner.
2. method according to claim 1, is characterized in that, gathers ecg information data, uses electrocardiogram acquisition equipment to gather the data of different object different time sections.
3. method according to claim 1, is characterized in that, described information data pre-service is comprised described information data is removed to noise and baseline wander.
4. method according to claim 3, is characterized in that, uses median filter and Wavelet Transformation Algorithm to remove noise and baseline wander.
5. method according to claim 1, is characterized in that, wherein, the method for the information data after S2 processes being carried out to feature extraction comprises:
S501: the QRS that adopts So and Chan QRS detection algorithm to detect electrocardiosignal involves R wave-wave peak;
S502: the crest of take is found out all monocycle signal as boundary, and each monocycle signal is as a proper vector;
S503: to each proper vector normalized, carry out cubic spline interpolation processing on transverse axis on the longitudinal axis;
S504: a plurality of normalized monocycle electrocardiosignals are carried out to cluster analysis;
S505: choose signal data in maximum classification as the set of eigenvectors of this sample objects.
6. method according to claim 1, is characterized in that, described information data after S3 processes is divided into training set and test set is mean allocation.
7. method according to claim 1, it is characterized in that, the described method that test set information data and template base information data are carried out to similarity comparison adopts the Euclidean distance comparison algorithm of matrix, comprising: the Euclidean distance comparison algorithm of average and the Euclidean distance algorithm of matrix;
The Euclidean distance comparison algorithm of average is: establish two n+1 dimensional vectors, X=[x
0, x
1, x
2..., x
n], Y=[y
0, y
1, y
2..., y
n], their Euclidean distance is:
Utilize Euclidean distance as the similarity measurement of two characteristic curvees.In training set, have N electrocardiosignal, the k group monocycle vector that each electrocardiosignal obtains after the processing of three steps, gets the average value vector of k group monocycle vector as template
the training set data storehouse that forms altogether N vectorial template.In test set, each electrocardiosignal obtains k group monocycle vector after pre-service and feature extraction, asks respectively k group vector to training set data N vectorial template
euclidean distance, the Euclidean distance of corresponding each vectorial template.After vote in majority, select its minimum value as final value, such electrocardiosignal and training set template relatively after, obtain N value.If test set data have M electrocardiosignal, just can obtain the matrix of a M*N, the row n at the minimum value place that wherein m is capable, maximum for n template signal similarity in m electrocardiosignal in test set and training set, be ecg information data owner;
The Euclidean distance algorithm of matrix is: the Euclidean distance algorithm of matrix is on the Euclidean distance algorithm basis of average, the N of a training set electrocardiosignal is got to its k group monocycle vector data, then compare with test set k group monocycle vector, get minimum value as the distance measure of two electrocardiosignals, finally obtain the distance matrix of M*N, equally, the row n at the minimum value place that wherein m is capable, maximum for n signal similar degree in m electrocardiosignal in test set and training set, be ecg information data owner.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310686789.6A CN103714281B (en) | 2013-12-12 | 2013-12-12 | A kind of personal identification method based on electrocardiosignal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310686789.6A CN103714281B (en) | 2013-12-12 | 2013-12-12 | A kind of personal identification method based on electrocardiosignal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103714281A true CN103714281A (en) | 2014-04-09 |
CN103714281B CN103714281B (en) | 2017-03-29 |
Family
ID=50407244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310686789.6A Active CN103714281B (en) | 2013-12-12 | 2013-12-12 | A kind of personal identification method based on electrocardiosignal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103714281B (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955677A (en) * | 2014-05-12 | 2014-07-30 | 南京大学 | Electrocardiogram recognizing method based on privacy protection |
CN104257389A (en) * | 2014-10-22 | 2015-01-07 | 哈尔滨华夏矿安科技有限公司 | Heart rate identifying equipment and underground coal mine blasting staff identifying method based on the equipment |
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 |
CN104771178A (en) * | 2015-04-13 | 2015-07-15 | 深圳市飞马与星月科技研究有限公司 | Method and device of identity recognition |
CN105022265A (en) * | 2014-04-18 | 2015-11-04 | 国民技术股份有限公司 | Smart wearable device and starting method thereof |
CN105373719A (en) * | 2014-09-01 | 2016-03-02 | 三星电子株式会社 | User authentication method and apparatus based on electrocardiogram (ecg) signal |
CN105468951A (en) * | 2015-11-17 | 2016-04-06 | 安徽华米信息科技有限公司 | Method and device for identity recognition through electrocardiographic feature and wearable device |
CN105654046A (en) * | 2015-12-29 | 2016-06-08 | 中国科学院深圳先进技术研究院 | Electrocardiosignal identity identification method and electrocardiosignal identity identification device |
CN106485213A (en) * | 2016-09-27 | 2017-03-08 | 鲁东大学 | A kind of utilization electrocardiosignal carries out the feature extracting method of automatic identification |
CN106650685A (en) * | 2016-12-29 | 2017-05-10 | 深圳先进技术研究院 | Electrocardiogram signal-based identity identification method and apparatus |
CN107088069A (en) * | 2017-03-29 | 2017-08-25 | 西安电子科技大学 | Personal identification method based on human body PPG signal subsections |
CN108009396A (en) * | 2017-11-29 | 2018-05-08 | 广东嘉博制药有限公司 | A kind of method using vector method evaluation pharmaceutical preparation dissolution rate similarity degree |
CN108304746A (en) * | 2017-01-11 | 2018-07-20 | 北京三星通信技术研究有限公司 | Method and apparatus of the update for the certification reference information of electrocardio authentication |
WO2018152724A1 (en) * | 2017-02-23 | 2018-08-30 | 深圳先进技术研究院 | Identity recognition method, device and system |
CN109492659A (en) * | 2018-09-25 | 2019-03-19 | 维灵(杭州)信息技术有限公司 | A kind of method of calculated curve similarity |
CN109497990A (en) * | 2018-12-27 | 2019-03-22 | 山东大学 | A kind of electrocardiosignal personal identification method and system based on canonical correlation analysis |
CN109620213A (en) * | 2019-02-25 | 2019-04-16 | 山东大学 | A kind of electrocardiogram recognition method and device based on multiple dimensioned Differential Characteristics |
CN110113664A (en) * | 2019-04-10 | 2019-08-09 | 华南理工大学 | A kind of method for identifying ID based on direct broadcast band user's watching behavior similitude |
CN110123289A (en) * | 2019-04-08 | 2019-08-16 | 清华大学深圳研究生院 | A kind of biometric discrimination method and relevant apparatus based on pulse wave |
CN110750770A (en) * | 2019-08-18 | 2020-02-04 | 浙江好络维医疗技术有限公司 | Method for unlocking electronic equipment based on electrocardiogram |
CN111324880A (en) * | 2020-03-09 | 2020-06-23 | 深圳连心电子科技有限公司 | Fingerprint and electrocardio characteristic double-authentication identity recognition system and method |
CN112115782A (en) * | 2020-08-12 | 2020-12-22 | 安徽心之声医疗科技有限公司 | Electrocardiosignal identity recognition method based on deep Hash neural network |
CN112587150A (en) * | 2020-12-01 | 2021-04-02 | 上海数创医疗科技有限公司 | Electrocardiosignal type identification method and device by using fuzzification similarity template |
CN112587148A (en) * | 2020-12-01 | 2021-04-02 | 上海数创医疗科技有限公司 | Template generation method and device comprising fuzzification similarity measurement method |
CN112932509A (en) * | 2021-01-28 | 2021-06-11 | 福建脉行人生医疗科技有限公司 | Method and device for picking up and optimizing analysis of eye electrical signals |
CN112971720A (en) * | 2021-02-07 | 2021-06-18 | 中国人民解放军总医院 | Method for detecting point of falling asleep |
CN114027853A (en) * | 2021-12-16 | 2022-02-11 | 安徽心之声医疗科技有限公司 | QRS complex detection method, device, medium and equipment based on feature template matching |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102324047A (en) * | 2011-09-05 | 2012-01-18 | 西安电子科技大学 | High spectrum image atural object recognition methods based on sparse nuclear coding SKR |
CN102542050A (en) * | 2011-12-28 | 2012-07-04 | 辽宁师范大学 | Image feedback method and system based on support vector machine |
CN103093133A (en) * | 2013-01-08 | 2013-05-08 | 西安电子科技大学 | Biological identity authentication method facing institute of electrical and electronic engineers (IEEE) 802.15.6 |
US20130254861A1 (en) * | 2011-06-03 | 2013-09-26 | Dell Products, Lp | System and Method for Providing Access to an Information Handling System |
CN103345600A (en) * | 2013-06-24 | 2013-10-09 | 中国科学院深圳先进技术研究院 | Electrocardiosignal data processing method |
-
2013
- 2013-12-12 CN CN201310686789.6A patent/CN103714281B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130254861A1 (en) * | 2011-06-03 | 2013-09-26 | Dell Products, Lp | System and Method for Providing Access to an Information Handling System |
CN102324047A (en) * | 2011-09-05 | 2012-01-18 | 西安电子科技大学 | High spectrum image atural object recognition methods based on sparse nuclear coding SKR |
CN102542050A (en) * | 2011-12-28 | 2012-07-04 | 辽宁师范大学 | Image feedback method and system based on support vector machine |
CN103093133A (en) * | 2013-01-08 | 2013-05-08 | 西安电子科技大学 | Biological identity authentication method facing institute of electrical and electronic engineers (IEEE) 802.15.6 |
CN103345600A (en) * | 2013-06-24 | 2013-10-09 | 中国科学院深圳先进技术研究院 | Electrocardiosignal data processing method |
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105022265A (en) * | 2014-04-18 | 2015-11-04 | 国民技术股份有限公司 | Smart wearable device and starting method thereof |
CN103955677A (en) * | 2014-05-12 | 2014-07-30 | 南京大学 | Electrocardiogram recognizing method based on privacy protection |
US10572637B2 (en) | 2014-09-01 | 2020-02-25 | Samsung Electronics Co., Ltd. | User authentication method and apparatus based on electrocardiogram (ECG) signal |
CN105373719A (en) * | 2014-09-01 | 2016-03-02 | 三星电子株式会社 | User authentication method and apparatus based on electrocardiogram (ecg) signal |
CN104257389B (en) * | 2014-10-22 | 2016-07-06 | 哈尔滨华夏矿安科技有限公司 | A kind of heart rate identification equipment and the underground coal mine based on this equipment blow out personal identification method |
CN104257389A (en) * | 2014-10-22 | 2015-01-07 | 哈尔滨华夏矿安科技有限公司 | Heart rate identifying equipment and underground coal mine blasting staff identifying method based on the equipment |
CN104573458B (en) * | 2014-12-30 | 2017-05-31 | 深圳先进技术研究院 | A kind of personal identification method based on electrocardiosignal, apparatus and system |
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 |
CN104771178A (en) * | 2015-04-13 | 2015-07-15 | 深圳市飞马与星月科技研究有限公司 | Method and device of identity recognition |
CN105468951A (en) * | 2015-11-17 | 2016-04-06 | 安徽华米信息科技有限公司 | Method and device for identity recognition through electrocardiographic feature and wearable device |
CN105654046A (en) * | 2015-12-29 | 2016-06-08 | 中国科学院深圳先进技术研究院 | Electrocardiosignal identity identification method and electrocardiosignal identity identification device |
CN105654046B (en) * | 2015-12-29 | 2019-01-18 | 中国科学院深圳先进技术研究院 | Electrocardiosignal personal identification method and device |
CN106485213B (en) * | 2016-09-27 | 2019-04-12 | 鲁东大学 | A kind of feature extracting method carrying out automatic identification using electrocardiosignal |
CN106485213A (en) * | 2016-09-27 | 2017-03-08 | 鲁东大学 | A kind of utilization electrocardiosignal carries out the feature extracting method of automatic identification |
CN106650685A (en) * | 2016-12-29 | 2017-05-10 | 深圳先进技术研究院 | Electrocardiogram signal-based identity identification method and apparatus |
CN106650685B (en) * | 2016-12-29 | 2020-06-05 | 深圳先进技术研究院 | Identity recognition method and device based on electrocardiogram signal |
CN108304746A (en) * | 2017-01-11 | 2018-07-20 | 北京三星通信技术研究有限公司 | Method and apparatus of the update for the certification reference information of electrocardio authentication |
CN108304746B (en) * | 2017-01-11 | 2022-09-13 | 北京三星通信技术研究有限公司 | Method and equipment for updating authentication reference information for electrocardio identity authentication |
WO2018152724A1 (en) * | 2017-02-23 | 2018-08-30 | 深圳先进技术研究院 | Identity recognition method, device and system |
CN107088069A (en) * | 2017-03-29 | 2017-08-25 | 西安电子科技大学 | Personal identification method based on human body PPG signal subsections |
CN107088069B (en) * | 2017-03-29 | 2019-10-11 | 西安电子科技大学 | Personal identification method based on human body PPG signal subsection |
CN108009396A (en) * | 2017-11-29 | 2018-05-08 | 广东嘉博制药有限公司 | A kind of method using vector method evaluation pharmaceutical preparation dissolution rate similarity degree |
CN109492659A (en) * | 2018-09-25 | 2019-03-19 | 维灵(杭州)信息技术有限公司 | A kind of method of calculated curve similarity |
CN109492659B (en) * | 2018-09-25 | 2021-10-01 | 维灵(杭州)信息技术有限公司 | Method for calculating curve similarity for electrocardio and electroencephalogram waveform comparison |
CN109497990A (en) * | 2018-12-27 | 2019-03-22 | 山东大学 | A kind of electrocardiosignal personal identification method and system based on canonical correlation analysis |
CN109620213A (en) * | 2019-02-25 | 2019-04-16 | 山东大学 | A kind of electrocardiogram recognition method and device based on multiple dimensioned Differential Characteristics |
CN110123289A (en) * | 2019-04-08 | 2019-08-16 | 清华大学深圳研究生院 | A kind of biometric discrimination method and relevant apparatus based on pulse wave |
CN110113664A (en) * | 2019-04-10 | 2019-08-09 | 华南理工大学 | A kind of method for identifying ID based on direct broadcast band user's watching behavior similitude |
CN110750770A (en) * | 2019-08-18 | 2020-02-04 | 浙江好络维医疗技术有限公司 | Method for unlocking electronic equipment based on electrocardiogram |
CN110750770B (en) * | 2019-08-18 | 2023-10-03 | 浙江好络维医疗技术有限公司 | Electrocardiogram-based method for unlocking electronic equipment |
CN111324880A (en) * | 2020-03-09 | 2020-06-23 | 深圳连心电子科技有限公司 | Fingerprint and electrocardio characteristic double-authentication identity recognition system and method |
CN112115782A (en) * | 2020-08-12 | 2020-12-22 | 安徽心之声医疗科技有限公司 | Electrocardiosignal identity recognition method based on deep Hash neural network |
CN112115782B (en) * | 2020-08-12 | 2023-09-29 | 安徽心之声医疗科技有限公司 | Electrocardiosignal identity recognition method based on deep hash neural network |
CN112587150A (en) * | 2020-12-01 | 2021-04-02 | 上海数创医疗科技有限公司 | Electrocardiosignal type identification method and device by using fuzzification similarity template |
CN112587148B (en) * | 2020-12-01 | 2023-02-17 | 上海数创医疗科技有限公司 | Template generation method and device comprising fuzzification similarity measurement method |
CN112587148A (en) * | 2020-12-01 | 2021-04-02 | 上海数创医疗科技有限公司 | Template generation method and device comprising fuzzification similarity measurement method |
CN112932509A (en) * | 2021-01-28 | 2021-06-11 | 福建脉行人生医疗科技有限公司 | Method and device for picking up and optimizing analysis of eye electrical signals |
CN112971720A (en) * | 2021-02-07 | 2021-06-18 | 中国人民解放军总医院 | Method for detecting point of falling asleep |
CN112971720B (en) * | 2021-02-07 | 2023-02-03 | 中国人民解放军总医院 | Method for detecting point of falling asleep |
CN114027853A (en) * | 2021-12-16 | 2022-02-11 | 安徽心之声医疗科技有限公司 | QRS complex detection method, device, medium and equipment based on feature template matching |
Also Published As
Publication number | Publication date |
---|---|
CN103714281B (en) | 2017-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103714281A (en) | Identity recognition method based on electrocardiosignals | |
CN106473750B (en) | Personal identification method based on photoplethysmographic optimal period waveform | |
Labati et al. | Deep-ECG: Convolutional neural networks for ECG biometric recognition | |
Aziz et al. | ECG-based biometric authentication using empirical mode decomposition and support vector machines | |
CN104102915B (en) | Personal identification method based on ECG multi-template matching under a kind of anomalous ecg state | |
CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
CN110811609B (en) | Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion | |
CN103345600B (en) | A kind of ecg signal data processing method | |
CN106951753B (en) | Electrocardiosignal authentication method and device | |
CN104055522A (en) | Electrocardiosignal identity recognition method under arrhythmia condition | |
CN105320969A (en) | A heart rate variability feature classification method based on multi-scale Renyi entropy | |
CN106874722A (en) | A kind of personal identification method and its device based on electrocardiosignal | |
EP3449409B1 (en) | Biometric method and device for identifying a person through an electrocardiogram (ecg) waveform | |
CN112257518A (en) | ECG identity recognition method based on WT and WOA-PNN algorithm | |
Singla et al. | ECG as biometric in the automated world | |
KR20150138559A (en) | self-organized real-time authentication method using ECG signal | |
Zeng et al. | A new statistical-based algorithm for ECG identification | |
CN111053552A (en) | QRS wave detection method based on deep learning | |
Zhang et al. | Practical human authentication method based on piecewise corrected Electrocardiogram | |
Wu et al. | ECG identification based on neural networks | |
Kouchaki et al. | ECG-based personal identification using empirical mode decomposition and Hilbert transform | |
Zhou et al. | A method of ECG template extraction for biometrics applications | |
Amiruddin et al. | Performance evaluation of human identification based on ECG signal | |
Shantha Selva Kumari et al. | Classification of cardiac arrhythmias based on morphological and rhythmic features | |
Tantawi et al. | A novel feature set for deployment in ECG based biometrics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |