CN103750844B - A kind of based on the phase locked personal identification method of brain electricity - Google Patents
A kind of based on the phase locked personal identification method of brain electricity Download PDFInfo
- Publication number
- CN103750844B CN103750844B CN201410018604.9A CN201410018604A CN103750844B CN 103750844 B CN103750844 B CN 103750844B CN 201410018604 A CN201410018604 A CN 201410018604A CN 103750844 B CN103750844 B CN 103750844B
- Authority
- CN
- China
- Prior art keywords
- characteristic vector
- phase synchronization
- phase
- matrix
- classification
- 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
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention relates to a kind of based on the phase locked personal identification method of brain electricity.The present invention mainly adopts PGC demodulation value to calculate the Phase synchronization feature of EEG signals, and is realized the identification of Different Individual by linear discriminant analysis.The present invention includes data acquisition, data prediction, filtering, Phase synchronization feature calculation, characteristic vector dimensionality reduction, characteristic vector classification and classification accuracy to calculate.Classification results shows: adopt the Phase synchronization of EEG signals as biometric feature, obtain good classification results, effectively can identify the identity of Different Individual.Compared with traditional biometric feature, the Phase synchronization feature based on EEG signals is more safe and hidden, and can be applied to some physical disabilities or injured crowd.
Description
Technical field
The invention belongs to the EEG's Recognition field in living things feature recognition field, be specifically related to a kind of personal identification method carrying out classifying based on EEG signals Phase synchronization extraction Phase synchronization feature.
Background technology
The how identity of a precise Identification people, protection information is safely a crucial social problem that must solve the current information age.Traditional authentication is very easily forged and is lost, and is more and more difficult to the demand meeting society, and living things feature recognition is the current the most convenient solution with safety.
Living things feature recognition is differentiated individual identity by the physiological feature of people or behavior characteristics.Biological characteristic due to everyone has uniqueness and stability, not easily forges, so it is more reliable accurately to utilize biometrics identification technology to carry out identity identification.In addition, living things feature recognition realizes by means of computer technology, more easily integrates with safety, monitoring, management system, realizes automated management.The biometrics identification technology that current people have been developed comprises fingerprint recognition, personal recognition, the identification of hands shape, iris identification, recognition of face, voice recognition etc.
Summary of the invention
The present invention is directed to the deficiencies in the prior art, provide a kind of based on the phase locked personal identification method of brain electricity, the method utilizes PGC demodulation value calculate Phase synchronization feature and undertaken classifying realizing by linear discriminant analysis.
The technical solution adopted in the present invention:
1. eeg signal acquisition:
Contrived experiment, uses multichannel brain electric collecting device to gather the EEG signals of subjects in experimentation, completes subjects's Data Enter and brain electric data collecting.
2. data prediction:
Carry out data prediction to original EEG signals, object reduces the interference of artefact, improves signal to noise ratio, thus improve the accuracy of feature extraction.Preprocessing process comprises bandpass filtering and removes average reference.
3. filtering:
Create wave filter, by pretreated EEG signals filtering to the frequency range calculated needed for Phase synchronization feature.
4. Phase synchronization feature calculation:
The present invention adopts PGC demodulation value (PLV) to calculate phase relation between two passages, and concrete PLV computing formula is as follows:
PLV=|<exp(j{Φ
x(t)-Φ
y(t)})>|
Wherein Φ
x(t) and Φ
yt () is respectively the instantaneous phase of EEG signals x (t) and y (t).
Invention adopts Hilbert transform to carry out the phase value of signal calculated, the Hilbert transform of signal x (t)
be defined as follows:
P in formula is Cauchy's principal value.The analytic signal that can define x (t) is thus:
Wherein A
x(t) and Φ
xt () is respectively instantaneous amplitude and the instantaneous phase of signal x (t).
Similarly, can the analytic signal of definition signal y (t), and calculate instantaneous phase Φ
y(t).
In the present invention, we adopt suitable time window to calculate the PLV value of special frequency channel.Suppose that each experimental stage exists N number of nonoverlapping time slice, the PLV mean value computation of this N number of fragment is as follows:
Wherein ΔΦ is that signal x (t) is poor with the instantaneous phase of y (t).
Suppose that the brain electric channel number that the present invention selectes is M, utilize passage between two to build different passages pair, calculate all passages to the PLV average in a certain experimental stage, and be placed as the upper triangular matrix A of a M × M
This matrix not only contains different brain electric channels phase relation between any two, further comprises the spatial information of brain electric channel.
Next, we by stretching for the data of upper triangular matrix except null value be a column vector B, as the Phase synchronization feature of identification, B=[a
12..., a
1M, a
23..., a
(M-1) M]
t.
Finally, use the same method and calculate the Phase synchronization characteristic vector of all experimental stages.
5. classify:
First the Phase synchronization characteristic vector calculated utilizing said process carries out dimensionality reduction to characteristic vector before carrying out identification.
The present invention adopts principal component analysis (PCA) to reduce the dimension of characteristic vector.Suppose that the raw data set of characteristic vector is z, then the covariance matrix R=E (zz of z
t).
The orthogonal matrix V of compute matrix R characteristic vector and the diagonal matrix D of eigenvalue,
D=diag(d
1,d
2,...,d
n)。Then the computing formula of main constituent is as follows:
y=V
Tz
T。
The main constituent that selected characteristic value exceedes certain threshold value is rebuild Phase synchronization characteristic vector, and concrete formula is as follows:
Wherein
the corresponding main constituent chosen and their characteristic vector respectively.
Then, the present invention adopts linear discriminant analysis (LDA) to classify to the Phase synchronization characteristic vector after dimensionality reduction.
From each tested Phase synchronization feature, the characteristic vector of random selecting some known class is as training sample, and remaining characteristic vector is as test sample book.The discriminant function needed for classification can be obtained by the training of training sample:
Wherein { x
i| i=1,2 ..., D} is Phase synchronization characteristic vector, and D is the dimension of characteristic vector.Parameter w
iwith the calculation criterion of a is: make different classes of between distance maximum, the distance in classification is minimum, even if different classifications is separated as much as possible.
Suppose X={x
1, x
2..., x
mfor given D ties up the data set of training sample, each characteristic vector of data centralization distinguishes corresponding classification { X
1..., X
c..., X
cin a classification, then inter _ class relationship matrix S
bwith within class scatter matrix S
wbe respectively:
Wherein M
cfor classification X
cvectorial quantity, m
cfor class mean vector, m is the overall average of all samples.
Compute matrix W makes the ratio of inter _ class relationship matrix and within class scatter matrix maximum:
Required discriminant function can be tried to achieve.
The test sample book of discriminant function to unknown classification utilizing these training samples to obtain is classified, and just can realize the identification to Different Individual.
The invention has the beneficial effects as follows: provide a kind of can effectively identify Different Individual based on brain electricity phase locked personal identification method.The Phase synchronization feature of EEG signals is not easily forged, and has higher reliability and accuracy.Compared with other biological recognition feature, the Phase synchronization feature based on brain electricity is safer and hidden, and can be applied to some physical disabilities or injured crowd.
Accompanying drawing explanation
Fig. 1 is flow chart of the present invention;
Fig. 2 is the concrete implementing procedure figure of Fig. 1;
Fig. 3 is brain electric channel figure.
Detailed description of the invention
Below in conjunction with accompanying drawing, the invention will be further described.
As shown in Figure 1: first gather required EEG signals, then eeg data is carried out to filtering, goes the pretreatment such as average reference, then pretreated data filtering is calculated PGC demodulation value to special frequency channel.Calculated the Phase synchronization feature of EEG signals by PGC demodulation value, after principal component analysis dimensionality reduction, utilize linear discriminant analysis to classify to characteristic vector.
With reference to accompanying drawing 2, specific embodiment of the invention step is as follows:
Step S1: the EEG signals needed for being gathered by multichannel brain electric collecting device.The present embodiment adopts the g-tec equipment of 16 electrodes to obtain eeg data, sample frequency is 256Hz, electrode cap adopts international 10/20 system electrode placement methods, and 16 electrodes are respectively FPz, Fz, Cz, Pz, POz, AF3, Af4, F3, F4, T7, C3, C4, T8, P3, P4 and EKG.Ekg electrode is placed on left hand tremulous pulse place record electrocardiogram (ECG) data, and reference electrode is placed in auris dextra and hangs down.Except electrocardio, the position of 15 brain electric channels as shown in Figure 3.
Step S2: pretreatment is carried out, to reduce the interference of artefact to the eeg data gathered.Detailed process comprises:
1) bandpass filtering: create band filter, extracts the brain electricity composition of 2-47Hz frequency range from the eeg data chosen.The present embodiment uses 2 rank Butterworth filters to realize Filtering Processing.
2) remove average reference: after calculation of filtered except electrocardio the meansigma methods of 15 passage eeg datas, and the data of each brain electric channel are deducted this meansigma methods.
Step S3: utilize 2 rank Butterworth band filters by pretreated eeg data filtering to α (8-13Hz) or θ (4-8Hz) frequency range.
Step S4: calculate EEG signals in the Phase synchronization characteristic vector of special frequency channel, specifically comprise:
1) utilize PGC demodulation value (PLV) to calculate instantaneous phase relationship between two between passage, computing formula is as follows:
PLV=|<exp(j{Φ
x(t)-Φ
y(t)})>|
Wherein Φ
x(t) and Φ
yt () is respectively the instantaneous phase of EEG signals x (t) and y (t).In the present embodiment, the time window of 1 second is adopted to calculate the PLV value of selected passage.
2) by the instantaneous phase value of Hilbert change calculations EEG signals, the Hilbert transform of signal x (t)
for:
Wherein P is Cauchy's principal value.The analytic signal that can obtain x (t) is thus:
Wherein A
x(t) and Φ
xt () is respectively instantaneous amplitude and the instantaneous phase of signal x (t).
Similarly, can the analytic signal of definition signal y (t), and calculate instantaneous phase Φ
y(t).
3) in the present embodiment, there are 30 nonoverlapping time slices in each experimental stage, and the PLV average of these 30 time slices is by following formulae discovery:
Utilize passage between two to build different passages pair, in the present embodiment, have 15 different brain electric channels, 105 different passages pair can be built.Calculate the PLV average of all passages in a certain experimental stage, be placed as the upper triangular matrix A of 15 × 15, this matrix not only contains different brain electric channels phase relation between any two, further comprises the spatial information of brain electric channel.
4) by stretching for the data of above-mentioned upper triangular matrix except null value be 105 dimensional vector B, as the Phase synchronization feature of identification.
5) use the same method and calculate the Phase synchronization characteristic vector of all experimental stages.16 different experimental stages are had in the present embodiment.
Step S5: adopt principal component analysis (PCA) to reduce the dimension of Phase synchronization characteristic vector.Suppose that the raw data set of characteristic vector is z, then the covariance matrix R=E (zz of z
t).
The orthogonal matrix V of compute matrix R characteristic vector and the diagonal matrix D of eigenvalue, the computing formula of main constituent is as follows:
y=V
Tz
T。
The main constituent that selected characteristic value exceedes certain threshold value is rebuild Phase synchronization characteristic vector, and the threshold value choosing main constituent in the present embodiment is 0.95.Phase synchronization after reconstruction is characterized as:
Wherein
the corresponding main constituent chosen and their characteristic vector respectively.
Step S6: adopt linear discriminant analysis (LDA) to classify to the Phase synchronization characteristic vector after dimensionality reduction.
The characteristic vector of the present embodiment random selecting 8 known class from each tested Phase synchronization feature is as training sample, and 8 remaining characteristic vectors are as the test sample book of classification.
Discriminant function is obtained by the training sample of characteristic vector
Wherein { x
i| i=1,2 ..., D} is Phase synchronization characteristic vector, and D is the dimension of characteristic vector.Parameter w
iwith the calculation criterion of a is: make different classes of between distance maximum, the distance in classification is minimum, even if different classifications is separated as much as possible.
Use these discriminant functions to calculate the score of each test sample book, then test sample book is referred to the classification corresponding to the highest discriminant function of score.Finally the concrete class of classification results and these characteristic vectors is compared, obtain classification accuracy and the variance of this personal identification method.
Claims (1)
1., based on the phase locked personal identification method of brain electricity, it is characterized in that the method comprises the following steps:
Step 1, eeg signal acquisition: use multichannel brain electric collecting device to gather the EEG signals of subjects in experimentation, complete subjects's Data Enter and brain electric data collecting;
Step 2, data prediction: carry out data prediction to original EEG signals, comprise bandpass filtering and remove average reference;
Step 3, filtering: create wave filter, by pretreated EEG signals filtering to the frequency range calculated needed for Phase synchronization feature;
Step 4, Phase synchronization feature calculation: employing PGC demodulation value PLV calculates the phase relation between two passages, and concrete PGC demodulation value PLV computing formula is as follows:
PLV=|<exp(j{Φ
x(t)-Φ
y(t)})>|
Wherein Φ
x(t) and Φ
yt () is respectively the instantaneous phase of EEG signals x (t) and y (t);
Hilbert transform is adopted to carry out the phase value of signal calculated, the Hilbert transform of signal x (t)
be defined as follows:
P in formula is Cauchy's principal value; The analytic signal that can define x (t) is thus:
Wherein A
x(t) and Φ
xt () is respectively instantaneous amplitude and the instantaneous phase of signal x (t);
Similarly, can the analytic signal of definition signal y (t), and calculate instantaneous phase Φ
y(t);
Suitable time window is adopted to calculate the PLV value of special frequency channel; Suppose that each experimental stage exists N number of nonoverlapping time slice, the PLV mean value computation of this N number of fragment is as follows:
Wherein ΔΦ is that signal x (t) is poor with the instantaneous phase of y (t);
If selected brain electric channel number is M, utilizes passage between two to build different passages pair, calculate all passages to the PLV average in a certain experimental stage, and be placed as the upper triangular matrix A of a M × M
This matrix not only contains different brain electric channels phase relation between any two, further comprises the spatial information of brain electric channel;
Next, by stretching for the data of upper triangular matrix except null value be a column vector B, as the Phase synchronization feature of identification, B=[a
12..., a
1M, a
23..., a
(M-1) M]
t;
Finally, use the same method and calculate the Phase synchronization characteristic vector of all experimental stages;
Step 5, classification:
First the Phase synchronization characteristic vector calculated utilizing said process carries out dimensionality reduction to characteristic vector before carrying out identification;
Principal component analysis PCA is adopted to reduce the dimension of characteristic vector; Suppose that the raw data set of characteristic vector is z, then the covariance matrix R=E (zz of z
t);
The orthogonal matrix V of compute matrix R characteristic vector and the diagonal matrix D of eigenvalue, D=diag (d
1, d
2..., d
n); Then the computing formula of main constituent is as follows:
y=V
Tz
T;
The main constituent that selected characteristic value exceedes certain threshold value is rebuild Phase synchronization characteristic vector, and concrete formula is as follows:
Wherein
with
the corresponding main constituent chosen and their characteristic vector respectively;
Then, linear discriminant analysis LDA is adopted to classify to the Phase synchronization characteristic vector after dimensionality reduction;
From each tested Phase synchronization feature, the characteristic vector of random selecting some known class is as training sample, and remaining characteristic vector is as test sample book; The discriminant function needed for classification can be obtained by the training of training sample:
Wherein { x
i| i=1,2 ..., D} is Phase synchronization characteristic vector, and D is the dimension of characteristic vector; Parameter w
iwith the calculation criterion of a is: make different classes of between distance maximum, the distance in classification is minimum, even if different classifications is separated as much as possible;
Suppose X={x
1, x
2..., x
mfor given D ties up the data set of training sample, each characteristic vector of data centralization distinguishes corresponding classification { X
1..., X
c..., X
cin a classification, then inter _ class relationship matrix S
bwith within class scatter matrix S
wbe respectively:
Wherein M
cfor classification X
cvectorial quantity, m
cfor class mean vector, m is the overall average of all samples;
Compute matrix W makes the ratio of inter _ class relationship matrix and within class scatter matrix maximum:
Required discriminant function can be tried to achieve;
The test sample book of discriminant function to unknown classification utilizing these training samples to obtain is classified, and just can realize the identification to Different Individual.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410018604.9A CN103750844B (en) | 2014-01-15 | 2014-01-15 | A kind of based on the phase locked personal identification method of brain electricity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410018604.9A CN103750844B (en) | 2014-01-15 | 2014-01-15 | A kind of based on the phase locked personal identification method of brain electricity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103750844A CN103750844A (en) | 2014-04-30 |
CN103750844B true CN103750844B (en) | 2015-07-29 |
Family
ID=50518291
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410018604.9A Active CN103750844B (en) | 2014-01-15 | 2014-01-15 | A kind of based on the phase locked personal identification method of brain electricity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103750844B (en) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103971124B (en) * | 2014-05-04 | 2017-02-15 | 杭州电子科技大学 | Multi-class motor imagery brain electrical signal classification method based on phase synchronization |
CN104095630B (en) * | 2014-07-29 | 2016-02-10 | 杭州电子科技大学 | A kind of based on the phase locked fatigue detection method of brain electricity |
CN107066103B (en) * | 2017-05-27 | 2021-03-30 | 深圳市宏智力科技有限公司 | Method and device for recognizing living being by brain wave |
CN108764043B (en) * | 2018-04-26 | 2020-07-03 | 太原理工大学 | Dynamic function connection-based electroencephalogram classification method for entropy values |
CN108985029A (en) * | 2018-06-05 | 2018-12-11 | 中国科学院半导体研究所 | The brain electricity personal identification method of view-based access control model stimulation |
CN109002382A (en) * | 2018-07-13 | 2018-12-14 | 广东水利电力职业技术学院(广东省水利电力技工学校) | A kind of server master board monitoring system and monitoring method, the information processing terminal |
CN109190677A (en) * | 2018-07-30 | 2019-01-11 | 福建中医药大学附属人民医院(福建省人民医院) | The control system and control method of inserting needle equipment in single ubarachnoid block art |
CN109105176A (en) * | 2018-08-07 | 2019-01-01 | 漯河市豫禾农业科技发展有限公司 | A kind of tomato industrial seedling rearing system and management method |
CN109117790B (en) * | 2018-08-14 | 2021-10-22 | 杭州电子科技大学 | Brain print identification method based on frequency space index |
CN109235416A (en) * | 2018-10-23 | 2019-01-18 | 中国水利水电第四工程局有限公司 | A kind of 12000 kilonewton meter energy level dynamic compaction methods |
CN110135285B (en) * | 2019-04-26 | 2021-06-08 | 中国人民解放军战略支援部队信息工程大学 | Electroencephalogram resting state identity authentication method and device using single-lead equipment |
CN110269625B (en) * | 2019-05-31 | 2022-02-11 | 杭州电子科技大学 | Novel multi-feature fusion electrocardio authentication method and system |
CN112617860B (en) * | 2020-12-31 | 2022-09-13 | 山东师范大学 | Emotion classification method and system of brain function connection network constructed based on phase-locked value |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101491441A (en) * | 2009-02-26 | 2009-07-29 | 江西蓝天学院 | Identification method based on electroencephalogram signal |
CN101558997A (en) * | 2009-05-27 | 2009-10-21 | 江西蓝天学院 | Electroencephalograph signal identification method based on second-order blind identification |
CN102499676A (en) * | 2011-11-03 | 2012-06-20 | 北京工业大学 | Effective time sequence and electrode recombination based electroencephalograph signal categorizing system and method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7865235B2 (en) * | 2005-09-12 | 2011-01-04 | Tan Thi Thai Le | Method and system for detecting and classifying the mental state of a subject |
-
2014
- 2014-01-15 CN CN201410018604.9A patent/CN103750844B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101491441A (en) * | 2009-02-26 | 2009-07-29 | 江西蓝天学院 | Identification method based on electroencephalogram signal |
CN101558997A (en) * | 2009-05-27 | 2009-10-21 | 江西蓝天学院 | Electroencephalograph signal identification method based on second-order blind identification |
CN102499676A (en) * | 2011-11-03 | 2012-06-20 | 北京工业大学 | Effective time sequence and electrode recombination based electroencephalograph signal categorizing system and method |
Non-Patent Citations (4)
Title |
---|
A new method of face recognition with data field and PCA;Dakui Wang等;《2013 IEEE International Conference on Granular Computing》;20131231;第320-325页 * |
PCA-LDA算法在性别鉴别中的应用;何国辉等;《计算机工程》;20061031;第32卷(第19期);第208-213页 * |
一种基于FPGA的脑电分类算法实现;刘纪红等;《现代电子技术》;20121015;第35卷(第20期);第107-110页 * |
用主成分分析何Fisher准则的脑电信号分类;牟华英;《科学技术与工程》;20091130;第9卷(第22期);第6853-6855页 * |
Also Published As
Publication number | Publication date |
---|---|
CN103750844A (en) | 2014-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103750844B (en) | A kind of based on the phase locked personal identification method of brain electricity | |
CN101491441B (en) | Identification method based on electroencephalogram signal | |
CN104586387B (en) | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters | |
Khan et al. | Automatic heart sound classification from segmented/unsegmented phonocardiogram signals using time and frequency features | |
CN105956546A (en) | Emotion recognition method based on EEG signals | |
CN101716079B (en) | Brainprint identity identification authentication method based on multi-characteristics algorithm | |
Bashar et al. | Human identification from brain EEG signals using advanced machine learning method EEG-based biometrics | |
CN105956624A (en) | Motor imagery electroencephalogram classification method based on space-time-frequency optimization feature sparse representation | |
CN109497997A (en) | Based on majority according to the seizure detection and early warning system of acquisition | |
CN103971124A (en) | Multi-class motor imagery brain electrical signal classification method based on phase synchronization | |
CN109497990B (en) | Electrocardiosignal identity recognition method and system based on canonical correlation analysis | |
CN106803081A (en) | A kind of brain electricity sorting technique based on Multi-classifers integrated | |
CN107980151B (en) | Access control system based on electrocardio authentication and authentication method thereof | |
CA2722691A1 (en) | A method and system for concentration detection | |
CN101558997A (en) | Electroencephalograph signal identification method based on second-order blind identification | |
CN104887263A (en) | Identity recognition algorithm based on heart sound multi-dimension feature extraction and system thereof | |
CN112401902B (en) | Electrocardio identity recognition method and system based on neural network time-frequency analysis combination | |
CN105286860A (en) | Motor imagery brain electrical signal recognition method based on dual-tree complex wavelet energy difference | |
CN101703405A (en) | Wavelet analysis and Welch algorithm personal identification method | |
CN102961129A (en) | Method for analyzing abnormal electrocardiogram tension for remote medical care | |
Usman et al. | Principle components analysis for seizures prediction using wavelet transform | |
CN111368884B (en) | Motor imagery electroencephalogram feature extraction method based on matrix variable Gaussian model | |
CN104515905A (en) | CQT multi-resolution based subject EEG signal adaptive spectrum analysis method | |
He et al. | A method for extracting fetal ECG based on EMD-NMF single channel blind source separation algorithm | |
CN113128384B (en) | Brain-computer interface software key technical method of cerebral apoplexy rehabilitation system based on deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20140430 Assignee: Hangzhou Youfu Technology Co.,Ltd. Assignor: HANGZHOU DIANZI University Contract record no.: X2021330000026 Denomination of invention: An identification method based on EEG phase synchronization Granted publication date: 20150729 License type: Common License Record date: 20210319 |
|
EE01 | Entry into force of recordation of patent licensing contract |