CN106418757A - ECG identity authentication smart clothes - Google Patents

ECG identity authentication smart clothes Download PDF

Info

Publication number
CN106418757A
CN106418757A CN201610866465.4A CN201610866465A CN106418757A CN 106418757 A CN106418757 A CN 106418757A CN 201610866465 A CN201610866465 A CN 201610866465A CN 106418757 A CN106418757 A CN 106418757A
Authority
CN
China
Prior art keywords
module
ecg signal
ecg
data
matrix
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
Application number
CN201610866465.4A
Other languages
Chinese (zh)
Other versions
CN106418757B (en
Inventor
陈敏
马玉军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN201610866465.4A priority Critical patent/CN106418757B/en
Publication of CN106418757A publication Critical patent/CN106418757A/en
Application granted granted Critical
Publication of CN106418757B publication Critical patent/CN106418757B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A41WEARING APPAREL
    • A41DOUTERWEAR; PROTECTIVE GARMENTS; ACCESSORIES
    • A41D1/00Garments
    • A41D1/002Garments adapted to accommodate electronic equipment
    • A41D1/005Garments adapted to accommodate electronic equipment with embedded cable or connector
    • AHUMAN NECESSITIES
    • A41WEARING APPAREL
    • A41DOUTERWEAR; PROTECTIVE GARMENTS; ACCESSORIES
    • A41D31/00Materials specially adapted for outerwear
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/70Multimodal biometrics, e.g. combining information from different biometric modalities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/15Biometric patterns based on physiological signals, e.g. heartbeat, blood flow

Landscapes

  • Engineering & Computer Science (AREA)
  • Textile Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Alarm Systems (AREA)

Abstract

The invention discloses ECG identity authentication smart clothes. The smart clothes comprise a clothes body, a spinning dry electrode, an ECG signal processing system and a terminal. The clothes body mainly comprises a spinning material and materials woven in the spinning material and containing conductive fiber to serve as a carrier of the ECG signal processing system. The terminal is a personal terminal or a cloud platform and is used for processing requests sent by an identity authentication device and feeding back an identity authentication result. The spinning dry electrode is used for making contact with a human body and collecting human body ECG signals. The ECG signal processing system comprises a data processing module, a data storage module, a communication module, an identity authentication module, a warning module and a power source module. The modules work together to complete the whole identity authentication process. The materials used in the clothes are consistent with those of common spun clothes, the comfort degree of users is not affected, and the clothes have the advantages of being low in cost, high in identity authentication level, low in error rate and the like and are suitable for processing daily safety identity authentication requirements.

Description

A kind of ECG authentication wisdom clothing
Technical field
The invention belongs to identity security verifies field, the identity for providing user based on this wearable device of wisdom clothing is tested Card information, is a kind of new invention that identity security is combined with wearable device wisdom clothing.
Background technology
In the past decade, the quantity using electrocardiogram in the research of bio-identification is continuously increased.Electrocardiogram uniqueness Feature causes it to be especially suitable for identification field.However, although found in the literature a lot of for knowing method for distinguishing, but for Optimal method can be found always.And could not also find for how making full use of ECG signal characteristic in practice Beautiful solution.The authentication means of main flow are concentrated mainly on recognition of face checking and fingerprint recognition checking field at present.
The Touch ID of i Phone is exactly the example for fingerprint for authentication, it is true that fingerprint less Reliable, there is user to paste using fingerprint recently and successfully unlock, another kind of scheme is recognition of face, and this method is subject to illumination, sample Collection, the impact of edge problem is larger, and the work process of face identification system is mostly based on rest image, by with face number Comparison according to storehouse is carrying out recognition of face, it is adaptable to the not high scene of requirement of real-time.Based on the recognition of face of video, then need Dynamically still image is extracted from video, and then realize recognition of face, the complex and meter to system of its process Calculation ability and memory cost require higher.Be not suitable for the requirement in big data epoch, and accuracy is difficult to control.
And emerging authentication means-ECG authentication recently is gradually widely paid attention to, ECG identification As biological identification technology, it is the technology being identified according to the physiology of user and behavior characteristicss using statistical method.It is main For solving the problems, such as access control, there is provided the succedaneum more reliable, more safer than existing authentication method.Past 10 years In, electrocardiogram (ECG) has been confirmed to be the sign data for being suitable for identification.It is identified with which using ECG electrocardiogram Unique advantage:In biological identification technology, electrocardiogram is with universality and to be difficult to forge.In the measurement of overall precision, We calculate the weighted mean of the discrimination of proof scheme and error rate.The result and error rate of discrimination is respectively 94.95%, 0.92%.
Content of the invention
The invention provides a kind of authentication wisdom clothing based on ECG signal, identity of the wisdom clothing with ECG signal is tested Card technology combines, and reaches the high identification of accuracy rate, can ideally solve very much real-time, the standard of prior art presence The true not high defect of property.
A kind of ECG authentication wisdom clothing proposed by the present invention, including clothes, weave dry electrode, ECG signal processing system And terminal, wherein:
The clothes main component is textile material and braiding conductive fiber in the inner, used as ECG signal processing system Carrier;
The terminal is personal terminal or cloud platform, for processing the request that identity recognition device sends, and identity is tested Card result sends back ECG signal processing system;
Described dry electrode or so of weaving respectively sets one, and which is made up of compliant conductive fiber, and two pieces of dry electrodes are sewn to respectively Near the left and right sides of chest in clothes, for human body is contacted, human body ECG signal is gathered;
The ECG signal processing system includes data processing module, data memory module, communication module, authentication mould Block, alarm modules and power module;Cooperation completes whole identification procedure to these modules jointly;Wherein:The data processing Module, for carrying out denoising to the ECG primary signal of dry electrode collection of weaving, to ensure the accuracy of measurement result;
The data memory module, for preserving the ECG signal after data processing module is processed;
The authentication module, for being analyzed to the ECG signal after data processing module denoising, extracts special Data are levied, passes to communication module;Mated with remote data storehouse by communication module and drawn accordingly result;
The communication module is connected with terminal communication, for completing the data transfer of ECG signal processing system and terminal, will The characteristic that authentication module is extracted is mated with terminal database, is verified result, and result is passed back communication Module;
The alarm modules are connected with communication module, when receiving examination by message, send examination by signal;Receive and test When receiving not by signal, checking is sent not by signal.
Further, the power module is that thin battery module, which includes battery itself and electrode;The battery passes through Snap-fastener is mounted on the outside of clothes, the dry electrode of the weaving of the high degree of comfort that the electrode constitutes for compliant conductive fiber, the dry electricity of the weaving Pole is integrated in garment interior.
Further, being connected by snap-fastener with the outside of clothes of the ECG signal processing system, to facilitate ECG signal The installation of processing system and dismounting.
Further, the eigenvalue extracted by the authentication module includes cycle, crest value and valley value.
Further, between the communication module and terminal, realized using wired, bluetooth or WiFi technology.
Further, the authentication module includes following submodules for passing sequentially through signal connection:
(1) filtering and noise reduction submodule:Using Filtering Formula Y1=0.985* (X1-X0+Y0) initial signal is filtered, Remove the data of deviation average 20%;X0,Y0Initial value is 0.Y in formula1Represent this filter result for processing, X0Table Show the filtering intermediate value of previous step, X1Represent this filter result, X0Represent the intermediate value of previous step filtering;
(2) interference submodule is eliminated:Filtering is completed using the band logical iir filter of 0.05Hz to 100Hz, eliminates baseline drift The interference that shifting, Hz noise, myoelectricity interference and electromagnetic noise are brought;
(3) eigenvalue submodule is sought:The eigenvalue of filtered training data is obtained, including meansigma methodss, covariance matrix With covariance matrix eigenvalue, operate as follows:
Calculate meansigma methodss
WhereinIt is the ECG signal training sample set of prior collection, M=N*K represents total sample number, i=1, 2 ..., N, N represent the overall number of people who in training set, that is to say classification number to be distinguished, j=1,2 ..., K, and K represents each use The ECG signal data number at family,Represent j-th ECG signal data of i-th people;
Calculate covariance matrix Mw,
Obtain the eigenvalue λ of training sample covariance matrixi, i=1,2 ... p;P is the number of covariance matrix eigenvalue; Choose the corresponding orthogonal eigenvectors X of eigenvalue of maximum1…XpUsed as projector space, orthogonal eigenvectors are by formula λ Mw=XMw Try to achieve, wherein λ is characterized value, X is characterized vector;
By all of training sample to X1…XpSpatially project, matrix Y after being projectedj i
(4) covariance matrix submodule is sought:Obtain the inter _ class relationship matrix S of covariance matrixb;Using LDA method, public Formula is as follows:
Matrix S in formulabDimension is N*K;Best projection matrix is found using the method for feature decomposition:
SbXi=λ MwXi
Wherein, XiFor orthogonal eigenvectors, λ is matrix MwXiCorresponding eigenvalue, according to formula λ MwXi=wMwXi, ask Go out corresponding characteristic vector group w1…wpAnd its projection matrix W for constituting;
By sampleProjection properties matrix Ω=W is drawn to projection matrix w projectionTY
Ωj=[Ωj(1)…,Ωj(p)];
(5) submodule is recognized:If test sample is Q, the corresponding orthogonal eigenvectors group of eigenvalue of maximum in (4th) step Projection equation below obtains matrix N=QTX, N is projected to projection properties matrix W, obtains L=NTW;Using nearest neighbor classifier Discriminant classification is carried out to matrix Ω and L, to draw classification results, obtain by with not by two class conclusions.
The present invention has the advantages and positive effects that:Using the new technique such as ECG physiological signal and wisdom clothing, realize removing Recognition of face, the third authentication ECG authentication of fingerprint recognition, the present invention is with low cost, authentication rank height, 0.49% error rate enables this product to process daily safety identification authentication demand well.And by design low become This ECG sensor reduces overall finished product very well, replaces common biomedical electrode with the dry electrode of the weaving of high degree of comfort, And be integrated in clothes, user's its presence imperceptible.Wire for electrode lead is also integrated in clothes so that A whole set of wisdom apparatus of laundry all merges on clothes, additionally, the physiological signal of wearer is uploaded to smart machine or cloud in real time, If there is abnormal authentication information, providing at any time and equipment locked service is provided to user, protects user's to greatest extent Safety.
Description of the drawings
Fig. 1 is wisdom clothing schematic diagram of the present invention;
Fig. 2 is ECG signal processing system modules figure of the present invention
Fig. 3 is filtering and noise reduction sub-modular structure schematic diagram;
Fig. 4 is ECG authentication schematic diagram.
Specific embodiment
Below in conjunction with the accompanying drawings the specific embodiment of the present invention is described further.Here it should be noted that for The explanation of these embodiments is used to help understand the present invention, but does not constitute limitation of the invention.Additionally, disclosed below As long as each embodiment of the present invention in involved technical characteristic do not constitute conflict each other and can just be mutually combined.
The present invention can be acquired, be processed and transmitted to individual terminal devices to the ECG data of user, by any fortune The smart machine of row corresponding A pp can complete the identity information certification to user, when analysis ECG signal finds that identity information has By mistake, the dangerous access of this user of smart machine is informed about, and smart machine report high in the clouds data center is locked, if certification Success, smart machine can be unlocked, and this sample ECG authentication wisdom clothing can just reach the mesh of the ECG certification of user identity 's.
To achieve these goals, the present invention is as follows using hardware technology scheme:
Wisdom clothing ECG integration module:It is made up of medicated clothing itself, dry electrode of weaving, weaving flexible wire.
The wisdom clothing, for the carrier as miscellaneous part, clothes is consistent with common textile medicated clothing in material will not The comfort level of impact user.
The dry electrode of the weaving, quantity at least two, it is located on the inside of wisdom clothing thoracic cavity the right and left respectively and is sewn to In wisdom clothing, for gather user ECG signal data and by original clutter data through simple frequency range analysis reject unrelated Information.The accuracy of data can be improved according to greater number of dry electrode, two dry electrodes used in this patent.
The weaving flexible wire, for connecting the dry electrode of weaving and ECG signal processor.
ECG signal processing system, the ECG data for collecting to dry electrode of weaving is processed and is stored, and device leads to Cross on the outside of snap-fastener carry wisdom clothing.The ECG signal processing system includes data processing module, data memory module, communication mould Block, authentication module, alarm modules, power module.
The data processing module, for carrying out denoising to the ECG primary signal of dry electrode collection of weaving, human body signal Frequency and amplitude are all than relatively low, it is easy to disturbed by spatial electromagnetic ripple and other physiological signals of human body, therefore to which Enter line translation, analysis, storage, record before, it should carry out some pretreatment, to ensure the accuracy of measurement result.
As the frequency of human body signal and amplitude are all than relatively low, it is easy to by spatial electromagnetic ripple and other physiology of human body The interference of signal, therefore before line translation, analysis, storage and record is entered to which, it should carry out some pretreatment, to ensure to survey The accuracy of amount result.General pretreatment includes, prevents input signal excessive using overvoltage crowbar, prevents other lifes of human body Reason number interference, but the signal for most importantly obtaining sensor is amplified, while reducing throat sound and interference signal to improve Signal to noise ratio, realizes sampling, modulation, demodulation etc. to useful signal.Signal amplification to do is in Signal Pretreatment first.At this In invention, as the signal for obtaining from sensor is very faint, and some other interference signals are mixed.Therefore amplifying circuit Major function is to filter some common mode interference signals, while carrying out certain amplification.
Pretreatment includes, prevents input signal excessive using overvoltage crowbar, prevents other physiology number interference of human body, but The signal for most importantly obtaining sensor is amplified, while reduce throat sound and interference signal so that signal to noise ratio is improved, to having Signal realizes sampling, modulation, demodulation etc..
Signal amplifies, and the signal for obtaining from sensor is very faint, and has mixed some other interference signals.Therefore amplify The major function of circuit is to filter some common mode interference signals, while carrying out certain amplification.
Denoising is carried out, is amplified, data filtering, feature extraction operation, data results are passed in real time.Give display module With authentication analysis module.
The data memory module, for preserving the ECG signal after data processing module is processed.
The communication module, for completing ECG signal processing system and personal terminal or the data transfer of cloud platform, transmission Content mainly includes the feedback information that treated feature ECG signal and distal end are passed back, is realized by bluetooth and WiFi technology.
The authentication module, is analyzed to the ECG signal after pretreated, draws characteristic, and by logical Letter module is mated with remote data storehouse and is drawn accordingly result.Comprise the following steps that:
ECG feature extraction, this feature is typically based on ECG waveform form, extracts all ECG signal, obtain in this research The oscillogram of average period;
ECG feature selection, has multiple different crests in an average period, is divided into P, Q, R, S peak value, is typically different People have different PQRS intervals, choose PQ, PQS, QS, RS interval in this research as characteristic parameter;
Pattern match is carried out using PQ, PQS, QS, RS interval and intelligent movable equipment local data base, select immediate Sample;
Data interaction is carried out in real time using long-range medical data center to differentiate the identity information k of user, select most Close sample, verifies local authentication result.
The alarm modules, the result for analyzing when authentication module and the data of remote data center are mismatched or are worked as When data center analyzes abnormal authentication information, system can make some feedback behaviors, for example, notify Android end at once End takes measures, locking device access rights, and including playing out the prior language that records by phone, while making a phone call To relatives or warning.The result for analyzing when authentication module and the data of remote data center are mismatched or are worked as in data When the heart analyzes abnormal authentication information, system can make some feedback behaviors, for example, notify Android terminal to take at once Measure, locking device access rights, and including playing out the prior language that records by phone, while phoning relatives Or report to the police.
The power module, for providing power supply to ECG signal processing system, power module also includes charge function.
As shown in figure 1, the present invention provide based on ECG authentication wisdom apparatus of laundry by clothes itself 101, flexible textile Wire 102,103, two pieces of dry electrodes 104,105 of weaving, ECG signal processing system 106, snap-fastener 107,108 constitutes.
Wherein, wisdom clothing 101 is made up of close-fitting weaving face fabric, belongs to underclothes, meets requirement of the user to comfort level. Two pieces of dry electrodes 104,105 of weaving are connected by flexible textile wire 102,103 with ECG signal processing system 106, are ECG letter Number processing system 106 provides the signal data for being collected by dry electrode 104,105.Flexible textile wire 102,103 is sewn to On the inside of wisdom clothing, user will not perceive the presence of flexible textile wire 102,103.Dry electrode 104,105 weave for gathering The ECG signal of user, two pieces of dry electrodes are located at the left and right sides of clothes respectively, are sewn to 101 inner side of wisdom clothing, due to volume relatively Little and lighter in weight, will not cause the burden in weight to wearer.ECG signal processing system is solid by snap-fastener 107,108 It is scheduled on wisdom clothing, removes and installs extremely convenient.
ECG signal processing system includes data processing module 201, data memory module 202, communication module as shown in Figure 2 203, authentication module 204, alarm modules 205 and power module 206.Data processing module 201, collects for reception Raw ECG data simultaneously carries out pretreatment, and by the data is activation after process to data memory module 202, when user needs to check During historical data, data can be transferred to communication module 203 and send to personal terminal by data memory module 202.Communication module 203 For the communication between ECG signal processing system and personal mobile phone is realized, Bluetooth technology is mainly employed, it is achieved that low-power consumption is short The function of distance data transmission.Authentication module 204 is for analyzing the data for receiving from data processing module 201, right After ECG data waveform carries out the operation such as a series of feature extraction, feature selection, the characteristic vector data of subscriber signal is obtained. This feature vector data is transmitted to communication module 203 and is uploaded to and preserved in personal terminal and remote data storehouse or cloud platform Data are mated.Matched data is transmitted back to communication module 203 transmitted to authentication module 204, authentication module again 204 make corresponding operating according to matching result, if matching result is inconsistent, sends a signal to alarm modules 205 and make phase Alarm measure is answered, for example, notifies Android terminal to take measures at once, locking device access rights, and including being broadcast by phone The language of prior recording is put, while placement of emergency calls is to relatives or police.
In addition, the present invention gives a kind of ECG authentication algorithm of autonomous Design, and algorithm realizes flow process as schemed Shown in 4, the data in sample ECG data, terminal or high in the clouds ECG identity database are carried out with 2DPCA projection respectively, and In 2DPCA feature space, LDA projection is carried out to these characteristic vectors.In LDA feature space, entered using the difference of Euclidean distance Row classification, can obtain the classification results of sample ECG data, judge the identity of user with this.
It is an advantage of the invention that the process of authentication is completed using ECG signal, wrong with low cost, accuracy height The feature of the rate of mistake.The demand of safety identification authentication is simply achieved in the daily life of user very much.Product employs Gao Shu The dry electrode of weaving of appropriateness instead of common biomedical electrode and be sewn to inside medicated clothing so as to outward appearance and wearing sensuously with Common medicated clothing almost indifference.Additionally, the present invention also has matched software platform, in real time physiological signal can be passed to Smart machine or high in the clouds, if authentication information occurs extremely, it is provided that equipment locked service, farthest protect The information security of user.

Claims (6)

1. a kind of ECG authentication wisdom clothing, it is characterised in that including clothes, dry electrode of weaving, ECG signal processing system and Terminal, wherein:
The clothes main component is textile material and braiding conductive fiber in the inner, used as the load of ECG signal processing system Body;
The terminal is personal terminal or cloud platform, for processing the request that identity recognition device sends, and authentication is tied Fruit sends back ECG signal processing system;
Described dry electrode or so of weaving respectively sets one, and which is made up of compliant conductive fiber, and two pieces of dry electrodes are sewn to clothes respectively The interior left and right sides near chest, for contacting human body, gathers human body ECG signal;
The ECG signal processing system includes data processing module, data memory module, communication module, authentication module, police Report module and power module;Cooperation completes whole identification procedure to these modules jointly;Wherein:The data processing module, For carrying out denoising to the ECG primary signal of dry electrode collection of weaving, to ensure the accuracy of measurement result;
The data memory module, for preserving the ECG signal after data processing module is processed;
The authentication module, for being analyzed to the ECG signal after data processing module denoising, extracts characteristic number According to passing to communication module;Mated with remote data storehouse by communication module and drawn accordingly result;
The communication module is connected with terminal communication, for completing the data transfer of ECG signal processing system and terminal, by identity The characteristic that authentication module is extracted is mated with terminal database, is verified result, and result is passed back communication module;
The alarm modules are connected with communication module, when receiving examination by message, send examination by signal;Receive examination not During by signal, checking is sent not by signal.
2. identification wisdom clothing according to claim 1, it is characterised in that the power module be Group, which includes battery itself and electrode;The battery is mounted on the outside of clothes by snap-fastener, and the electrode is compliant conductive fiber group The dry electrode of the weaving of the high degree of comfort for becoming, the dry electrode of the weaving is integrated in garment interior.
3. identification wisdom clothing according to claim 1, it is characterised in that the ECG signal processing system and clothing Clothes outside is connected by snap-fastener, to facilitate the installation of ECG signal processing system and dismounting.
4. identification wisdom clothing according to claim 1, it is characterised in that the spy extracted by the authentication module Value indicative includes cycle, crest value and valley value.
5. identification wisdom clothing according to claim 1, it is characterised in that between the communication module and terminal, adopt Realized with wired, bluetooth or WiFi technology.
6. identity recognition device according to claim 1, it is characterised in that the authentication module include following successively The submodule for being connected by signal:
(1) filtering and noise reduction submodule:Using Filtering Formula Y1=0.985* (X1-X0+Y0) initial signal is filtered, remove partially Data from meansigma methodss 20%;X0,Y0Initial value is 0.Y in formula1Represent this filter result for processing, Y0Represent upper one The filtering intermediate value of step, X1Represent this filter result, X0Represent the intermediate value of previous step filtering;
(2) interference submodule is eliminated:Complete to filter using the band logical iir filter of 0.05Hz to 100Hz, elimination baseline drift, The interference that Hz noise, myoelectricity interference and electromagnetic noise are brought;
(3) eigenvalue submodule is sought:The eigenvalue of filtered training data is obtained, including meansigma methodss, covariance matrix and association Variance matrix eigenvalue, operates as follows:
Calculate meansigma methodss
WhereinIt is the ECG signal training sample set of prior collection, M=N*K represents total sample number, i=1,2 ..., N, N represent the overall number of people who in training set, that is to say classification number to be distinguished, j=1,2 ..., K, and K represents each user's ECG signal data number,Represent j-th ECG signal data of i-th people;
Calculate covariance matrix Mw
Obtain the eigenvalue λ of training sample covariance matrixi, i=1,2 ... p;P is the number of covariance matrix eigenvalue;Choose The corresponding orthogonal eigenvectors X of eigenvalue of maximum1…XpUsed as projector space, orthogonal eigenvectors are by formula λ Mw=XMwTry to achieve, Wherein λ is characterized value, and X is characterized vector;
By all of training sample to X1…XpSpatially project, matrix after being projected
Y j i = [ S j i X i , ... , S j i X p ] , Y j i ( 1 ) , ... , Y j i ( p ) ∈ R N * K
(4) covariance matrix submodule is sought:Obtain the inter _ class relationship matrix S of covariance matrixb;Using LDA method, formula is such as Under:
S b = Σ i = 1 N Σ j = 1 K S i ( Y j i - S i ) T ( Y j i - S i )
Matrix S in formulabDimension is N*K;Best projection matrix is found using the method for feature decomposition:
SbXi=λ MwXi
Wherein, XiFor orthogonal eigenvectors, λ is matrix MwXiCorresponding eigenvalue, according to formula λ MwXi=wMwXi, obtain institute Corresponding characteristic vector group w1…wpAnd its projection matrix W for constituting;
By sampleProjection properties matrix Ω=W is drawn to projection matrix w projectionTj=[Ωj(1)…, Ωj(p)];
(5) submodule is recognized:If test sample is the corresponding orthogonal eigenvectors group projection of eigenvalue of maximum Q, in (4th) step Equation below obtains matrix N=QTX, N is projected to projection properties matrix W, obtains L=NTW;Using nearest neighbor classifier to square Battle array Ω and L carries out discriminant classification, to draw classification results, obtain by with not by two class conclusions.
CN201610866465.4A 2016-09-29 2016-09-29 A kind of ECG authentications wisdom clothing Active CN106418757B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610866465.4A CN106418757B (en) 2016-09-29 2016-09-29 A kind of ECG authentications wisdom clothing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610866465.4A CN106418757B (en) 2016-09-29 2016-09-29 A kind of ECG authentications wisdom clothing

Publications (2)

Publication Number Publication Date
CN106418757A true CN106418757A (en) 2017-02-22
CN106418757B CN106418757B (en) 2018-06-12

Family

ID=58170162

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610866465.4A Active CN106418757B (en) 2016-09-29 2016-09-29 A kind of ECG authentications wisdom clothing

Country Status (1)

Country Link
CN (1) CN106418757B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111142671A (en) * 2019-12-27 2020-05-12 江西服装学院 Intelligent garment with intelligent interaction system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070177770A1 (en) * 2006-01-30 2007-08-02 Derchak P A System and method for identity confirmation using physiologic biometrics to determine a physiologic fingerprint
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
CN102231213A (en) * 2011-06-29 2011-11-02 哈尔滨工业大学深圳研究生院 ECG (electrocardiograph) access card identity identification method and system
CN102462494A (en) * 2010-11-11 2012-05-23 泉州市全通光电科技有限公司 Novel intelligent electrocardiogram test healthcare apparatus
CN104102915A (en) * 2014-07-01 2014-10-15 清华大学深圳研究生院 Multiple-template matching identity recognition method based on ECG (Electrocardiogram) under electrocardiogram abnormality state
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
US20160021535A1 (en) * 2014-04-29 2016-01-21 Tarik Tali Method and System for Authenticating an Individual's Geo-Location Via a Communication Network and Applications Using the Same
CN105938526A (en) * 2016-03-07 2016-09-14 李明 Identity authentication method and system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070177770A1 (en) * 2006-01-30 2007-08-02 Derchak P A System and method for identity confirmation using physiologic biometrics to determine a physiologic fingerprint
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
CN102462494A (en) * 2010-11-11 2012-05-23 泉州市全通光电科技有限公司 Novel intelligent electrocardiogram test healthcare apparatus
CN102231213A (en) * 2011-06-29 2011-11-02 哈尔滨工业大学深圳研究生院 ECG (electrocardiograph) access card identity identification method and system
US20160021535A1 (en) * 2014-04-29 2016-01-21 Tarik Tali Method and System for Authenticating an Individual's Geo-Location Via a Communication Network and Applications Using the Same
CN104102915A (en) * 2014-07-01 2014-10-15 清华大学深圳研究生院 Multiple-template matching identity recognition method based on ECG (Electrocardiogram) under electrocardiogram abnormality state
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
CN105938526A (en) * 2016-03-07 2016-09-14 李明 Identity authentication method and system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111142671A (en) * 2019-12-27 2020-05-12 江西服装学院 Intelligent garment with intelligent interaction system

Also Published As

Publication number Publication date
CN106418757B (en) 2018-06-12

Similar Documents

Publication Publication Date Title
CN101576772B (en) Brain-computer interface system based on virtual instrument steady-state visual evoked potentials and control method thereof
US20080214946A1 (en) Monitoring Method and Apparatus
CN108113663A (en) Cardiac event detection system and method
CN105232032A (en) Remote electrocardiograph monitoring and early warning system and method based on wavelet analysis
CN108968952A (en) A kind of brain myoelectricity and Inertia information synchronous acquisition device
CN109276242A (en) The method and apparatus of electrocardiosignal type identification
CN110074765A (en) A kind of method of discrimination of SAHS screening and sleep stage
Matta et al. Real-time continuous identification system using ECG signals
CN107080527A (en) A kind of wearable life physical sign monitoring device and state of mind monitoring method
CN109887594A (en) A kind of multi-lead arrhythmia cordis intelligent diagnosing method based on MODWT and TDCNN
CN106166065A (en) A kind of wearable electrocardio health interacting platform based on social networks and its implementation
CN106725455A (en) It is used for the training system and method for brain ability training based on sensor feedback
CN204379273U (en) The Apparatus and system of carry-on detection anemia of pregnant woman vital sign
CN110751131A (en) Arrhythmia detection device
CN106333671A (en) Electrocardiogram detection system
CN104809371A (en) Device and method for determining validity of authentication information of head-wearing intelligent device
CN112162634A (en) Digital input brain-computer interface system based on SEEG signal
CN206151454U (en) Heartbeat monitoring devices
CN206491347U (en) A kind of ECG authentications wisdom clothing
CN107595277A (en) A kind of cardioelectric monitor system and monitoring method with motion identification and positioning function
CN106418757A (en) ECG identity authentication smart clothes
CN106037714A (en) Heart beat monitoring device
CN109770920A (en) Intense strain method of discrimination and its system based on wearable ECG signal
CN106264517B (en) A kind of method and system selecting electrocardio measurement position
CN108470182A (en) A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification

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