CN112434623A - Individual identification method, system and storage medium based on brain network connectivity - Google Patents
Individual identification method, system and storage medium based on brain network connectivity Download PDFInfo
- Publication number
- CN112434623A CN112434623A CN202011363331.3A CN202011363331A CN112434623A CN 112434623 A CN112434623 A CN 112434623A CN 202011363331 A CN202011363331 A CN 202011363331A CN 112434623 A CN112434623 A CN 112434623A
- Authority
- CN
- China
- Prior art keywords
- individual
- identified
- category
- coding features
- coding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses an individual identification method, a system and a storage medium based on brain network connectivity, wherein the method obtains coding characteristics by calculating the causal connectivity of acquired electroencephalogram data of an individual to be identified; inputting the coding characteristics of the individual to be identified into a classifier to obtain the category of the individual to be identified; the space distances between the coding features of the individual to be identified and the coding features of multiple categories in the classification feature library are calculated through the classifier, category serial numbers corresponding to the category coding features of the individual to be identified, the space distances between the coding features of the individual to be identified and the category coding features of the individual to be identified meet set conditions, and finally the category serial number with the largest occurrence frequency in the recorded category serial numbers is used as the category serial number of the individual to be identified. Thus, the present invention encodes the characteristics of an individual based on differences in brain electrical causal connectivity between individuals, thereby enabling reliable identification of the individual.
Description
Technical Field
The invention relates to the field of electroencephalogram identification, in particular to an individual identification method, system and storage medium based on brain network connectivity.
Background
Biometric identification is the identification of individuals by various high-tech information detection means, using physiological or behavioral characteristics inherent to the human body. The biological characteristics mainly include two types of physiological characteristics and behavior characteristics: the physiological characteristics refer to inherent physical characteristics of human bodies, such as fingerprints, irises, palm shapes, human faces and the like; however, none of the biometrics is perfect, and the identification methods of various biometrics have certain application ranges and requirements, and a single biometrics identification system shows respective limitations in practical application. The first generation biometric identification technology such as wide fingerprint, face, iris and palm shape identification is used, and most of the technologies need to be matched with the monitored object, and sometimes the monitored object even needs to complete necessary actions.
These methods are cumbersome, slow in identification speed and inconvenient to use, and are not easily accepted by users. The reliability of fingerprint recognition is high but requires actual physical contact; the human face and the iris recognition do not need to be in physical contact, but are limited by more environment in practical application. Research shows that the artificial finger made of gelatin can easily cheat the fingerprint identification system, the iris of a person suffering from cataract can be changed, the characteristics of the artificial iris etched on the contact lens can make the iris identification system true and false, and the like. With the continuous intellectualization and the technological development of criminal means, the first generation of identity recognition technology faces the challenges of anti-counterfeiting and anti-theft. Therefore, the proposal of a new biometric authentication method is urgently required.
In recent years, researchers put more energy into healthy human bodies, and try to establish a one-to-one correspondence relationship between certain electroencephalogram characteristics of individuals and gene information carried by the individuals, so that the electroencephalogram is used as an effective characteristic for identity recognition, and a new idea in the field is opened.
At present, the identification technology based on electroencephalogram signals belongs to the starting stage at home and abroad, and although some researchers do a lot of related researches, a stable and reliable identification scheme based on electroencephalogram does not exist.
Disclosure of Invention
In view of the above-mentioned deficiencies of the prior art, the present invention aims to: provided is an individual identification method based on brain network connectivity, which can accurately identify the identity of an individual.
In order to achieve the purpose, the invention provides the following technical scheme:
an individual identification method based on brain network connectivity, comprising the following steps:
acquiring multi-channel electroencephalogram data of an individual to be identified, and calculating causal connectivity of the electroencephalogram data to obtain coding characteristics; inputting the coding features of the individual to be identified into the classifier to obtain the category to which the individual to be identified belongs;
calculating the spatial distance between the coding features of the individual to be identified and the coding features of a plurality of categories in the classification feature library through the classifier, and recording category serial numbers corresponding to the coding features of the categories, wherein the spatial distance between the coding features of the individual to be identified and the coding features of the categories in the classification feature library meets set conditions; and taking the category serial number with the largest occurrence frequency in the recorded category serial numbers as the category serial number of the individual to be identified.
According to a specific implementation mode, in the individual identification method based on brain network connectivity, the data length of multi-channel electroencephalogram data of an individual to be identified is at least more than 4 seconds.
According to a specific implementation mode, in the individual identification method based on brain network connectivity, the multi-channel electroencephalogram data of the individual to be identified are data acquired when the brain is in a resting state.
According to a specific embodiment, in the individual identification method based on brain network connectivity, the spatial distance is calculated by adopting a k-nearest neighbor classification algorithm.
In another aspect of the present invention, there is also provided an individual identification system based on brain network connectivity, including:
the data acquisition module is used for acquiring multi-channel electroencephalogram data of the individual to be identified;
the encoding characteristic calculation module is used for calculating causal connectivity of the electroencephalogram data to obtain encoding characteristics;
the classifier module is used for calculating the spatial distance between the coding features of the individual to be identified and the coding features of a plurality of classes in the classification feature library respectively, and recording class serial numbers corresponding to the coding features of the classes, the spatial distances between the coding features of the individual to be identified and the coding features of the classes meet set conditions; and taking the category serial number with the largest occurrence frequency in the recorded category serial numbers as the category serial number of the individual to be identified so as to determine the category to which the individual to be identified belongs.
In another aspect of the present invention, there is also provided a readable storage medium, on which one or more programs are stored, wherein the one or more programs, when executed by one or more processors, implement the individual identification method based on brain network connectivity according to the present invention.
Compared with the prior art, the invention has the beneficial effects that:
the individual identification method based on brain network connectivity obtains coding characteristics by calculating the causal connectivity of the acquired electroencephalogram data of the individual to be identified; inputting the coding characteristics of the individual to be identified into a classifier to obtain the category of the individual to be identified; the space distances between the coding features of the individual to be identified and the coding features of multiple categories in the classification feature library are calculated through the classifier, category serial numbers corresponding to the category coding features of the individual to be identified, the space distances between the coding features of the individual to be identified and the category coding features of the individual to be identified meet set conditions, and finally the category serial number with the largest occurrence frequency in the recorded category serial numbers is used as the category serial number of the individual to be identified. Thus, the present invention encodes the characteristics of an individual based on differences in brain electrical causal connectivity between individuals, thereby enabling reliable identification of the individual.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of the system of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
As shown in fig. 1, the individual identification method based on brain network connectivity of the present invention includes the following steps:
acquiring multi-channel electroencephalogram data of an individual to be identified, and calculating causal connectivity of the electroencephalogram data to obtain coding characteristics; inputting the coding features of the individual to be identified into the classifier to obtain the category to which the individual to be identified belongs;
calculating the spatial distance between the coding features of the individual to be identified and the coding features of a plurality of categories in the classification feature library through the classifier, and recording category serial numbers corresponding to the coding features of the categories, wherein the spatial distance between the coding features of the individual to be identified and the coding features of the categories in the classification feature library meets set conditions; and taking the category serial number with the largest occurrence frequency in the recorded category serial numbers as the category serial number of the individual to be identified.
The acquisition of the individual electroencephalogram data needs to be carried out in a preset state. It is desirable to ensure that an individual is in a relatively stable physiological state (typically awake and relaxed) prior to performing electroencephalographic data acquisition. Chaotic physiological conditions usually cause abnormal amplitude and interactive disorder of the acquired data, so that the individual coding characteristics deviate from the established characteristic range.
The individual brain electrical data can be collected from different brain activity states to enhance the diversity and complexity of individual coding features. The activity state of the brain can be artificially set within a certain range so as to meet the use habits of different individuals. Specifically, whole brain electroencephalogram signals of different individuals in a rest state under a stable physiological state, a given state such as left-right hand movement and simple cognitive behaviors imagined in the brain can be collected and used as a data source to extract characteristics of the individuals. Wherein the resting state or the brain activity state such as imagining the movement of the left hand and the right hand can be preset by the user. In addition, these states may be used alone or in combination according to individual usage habits. For example, the electroencephalogram signals of the individual brain in the resting state can be only acquired as the characteristics of the individual, and the electroencephalogram signals of the individual brain in the resting state and the imagination of left-hand movement can be acquired successively as the characteristics of the individual. It is worth noting that theoretically combining data from multiple brain states will yield more complex coding features that improve specificity among different individuals.
The BCI2000 electroencephalogram acquisition system can be referred to as the electroencephalogram signal acquisition method. The method is characterized in that 16-channel electroencephalogram signals are acquired according to the international 10-10 electroencephalogram electrode placement standard, or 64-channel electroencephalogram signals are acquired according to the international 10-20 electroencephalogram electrode placement standard. The more convenient mode is that the standard brain electricity electrode cap of design is utilized to carry out brain electricity collection. When the electroencephalogram electrode cap is used, an acquirer can immediately start to acquire electroencephalogram signals only by wearing the assembled electroencephalogram electrode cap according to specifications, and a complex electroencephalogram electrode positioning process is not needed. It is worth noting that a sufficient number of electrodes tends to result in a better acquisition. However, in practical applications, 64 channels of electrodes are sufficient to meet the data acquisition requirements.
When the method is implemented, the electroencephalogram data are collected in a resting state, and the length of the collected electroencephalogram data is more than 4 seconds.
Specifically, the feature coding is carried out by calculating the causal connectivity (granger causal connectivity) between two different channels of the electroencephalogram signal. For example, if a 16-channel electroencephalogram signal is acquired, a 16 × 16 coding feature can be obtained through causal connectivity calculation. For the case of using the electroencephalogram acquisition device with more than 32 channels, the dimension of the obtained brain network coding features can be reduced by a data dimension reduction method to reduce the storage consumption in consideration of the data storage capacity.
There is also considerable flexibility in the choice of computing devices in the system to accommodate different usage scenarios. It is basically required to satisfy higher-precision computation and a certain amount of memory functions. A conventional 8-bit or 16-bit microcomputer with a certain amount of memory is able to satisfy the requirements of operation and storage.
When the method is implemented, the k nearest neighbor classification algorithm with simpler operation logic is adopted; the k nearest neighbor classification algorithm belongs to a supervised classification algorithm, and the idea of the algorithm is as follows: in feature space, if most of the k nearest (i.e. nearest in feature space) samples in the vicinity of one sample data belong to a certain class, then the sample also belongs to this class. Therefore, for the k-nearest neighbor classification algorithm, a labeled training data set is given in advance, for a new input data sample, k data instances nearest to the sample are found in the training data set, most of the k instances belong to a certain class, and the input instance is classified into the class.
The adaptation and classification identification process of the k-nearest neighbor classification algorithm is as follows:
the first step is as follows: the feature data of a plurality of individuals and the individual serial number of each feature data are imported into a classification feature library and stored, and algorithm adaptation is completed at the moment
The second step is that: inputting the newly obtained feature data into a classification algorithm, and calculating the spatial distance (Euclidean distance) between the feature data and the feature data of other pre-stored individuals
The third step: selecting k data samples which are closest to the space distance of the newly obtained feature data and are stored in a classification feature library in advance from the second step, and recording the individual serial numbers which represent the categories of the data samples corresponding to the k data samples
The fourth step: and selecting the individual category with the highest occurrence frequency from the k individuals as the category to which the newly obtained feature data belongs through a voting mechanism.
As shown in fig. 2, the individual identification system based on brain network connectivity of the present invention comprises:
the data acquisition module is used for acquiring multi-channel electroencephalogram data of the individual to be identified;
the encoding characteristic calculation module is used for calculating causal connectivity of the electroencephalogram data to obtain encoding characteristics;
the classifier module is used for calculating the spatial distance between the coding features of the individual to be identified and the coding features of a plurality of classes in the classification feature library respectively, and recording class serial numbers corresponding to the coding features of the classes, the spatial distances between the coding features of the individual to be identified and the coding features of the classes meet set conditions; and taking the category serial number with the largest occurrence frequency in the recorded category serial numbers as the category serial number of the individual to be identified so as to determine the category to which the individual to be identified belongs.
In another aspect of the present invention, a readable storage medium is further provided, on which one or more programs are stored, where the one or more programs, when executed by one or more processors, implement the dynamic extension method for a blockchain consensus network of the present invention.
It should be understood that the disclosed system may be implemented in other ways. For example, the division of the modules into only one logical function may be implemented in another way, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the communication connection between the modules may be an indirect coupling or communication connection through some interfaces, devices or units, and may be electrical or in other forms.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Claims (6)
1. An individual identification method based on brain network connectivity, characterized by comprising the following steps:
acquiring multi-channel electroencephalogram data of an individual to be identified, and calculating causal connectivity of the electroencephalogram data to obtain coding characteristics; inputting the coding features of the individual to be identified into the classifier to obtain the category to which the individual to be identified belongs;
calculating the spatial distance between the coding features of the individual to be identified and the coding features of a plurality of categories in the classification feature library through the classifier, and recording category serial numbers corresponding to the coding features of the categories, wherein the spatial distance between the coding features of the individual to be identified and the coding features of the categories in the classification feature library meets set conditions; and taking the category serial number with the largest occurrence frequency in the recorded category serial numbers as the category serial number of the individual to be identified.
2. The individual identification method based on brain network connectivity according to claim 1, wherein the data length of the multi-channel electroencephalogram data of the individual to be identified is at least 4 seconds or more.
3. The individual identification method based on brain network connectivity of claim 1, wherein the multi-channel electroencephalogram data of the individual to be identified is data acquired when the brain is in a resting state.
4. The brain network connectivity-based individual identification method of claim 1, wherein the spatial distance is calculated using a k-nearest neighbor classification algorithm.
5. An individual identification system based on brain network connectivity, comprising:
the data acquisition module is used for acquiring multi-channel electroencephalogram data of the individual to be identified;
the encoding characteristic calculation module is used for calculating causal connectivity of the electroencephalogram data to obtain encoding characteristics;
the classifier module is used for calculating the spatial distance between the coding features of the individual to be identified and the coding features of a plurality of classes in the classification feature library respectively, and recording class serial numbers corresponding to the coding features of the classes, the spatial distances between the coding features of the individual to be identified and the coding features of the classes meet set conditions; and taking the category serial number with the largest occurrence frequency in the recorded category serial numbers as the category serial number of the individual to be identified so as to determine the category to which the individual to be identified belongs.
6. A readable storage medium on which one or more programs are stored, the one or more programs, when executed by one or more processors, implementing the method for brain network connectivity-based individual identification according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363331.3A CN112434623A (en) | 2020-11-27 | 2020-11-27 | Individual identification method, system and storage medium based on brain network connectivity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363331.3A CN112434623A (en) | 2020-11-27 | 2020-11-27 | Individual identification method, system and storage medium based on brain network connectivity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112434623A true CN112434623A (en) | 2021-03-02 |
Family
ID=74698637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011363331.3A Pending CN112434623A (en) | 2020-11-27 | 2020-11-27 | Individual identification method, system and storage medium based on brain network connectivity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112434623A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157101A (en) * | 2021-06-07 | 2021-07-23 | 成都华脑科技有限公司 | Fragmentation reading habit identification method and device, readable medium and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101716079A (en) * | 2009-12-23 | 2010-06-02 | 江西蓝天学院 | Brainprint identity identification authentication method based on multi-characteristics algorithm |
| CN105159443A (en) * | 2015-08-06 | 2015-12-16 | 杭州电子科技大学 | PCA and Granger causality based brain network feature extraction method |
| US20170091741A1 (en) * | 2015-09-24 | 2017-03-30 | Hand Held Products, Inc. | Product identification using electroencephalography |
| CN109766845A (en) * | 2019-01-14 | 2019-05-17 | 首都医科大学宣武医院 | A kind of Method of EEG signals classification, device, equipment and medium |
| CN109766751A (en) * | 2018-11-28 | 2019-05-17 | 西安电子科技大学 | Stable state vision inducting brain electricity personal identification method and system based on Frequency Domain Coding |
| CN109933204A (en) * | 2019-03-22 | 2019-06-25 | 河北雄安有份儿智慧科技有限公司 | A kind of man-machine interaction method of Behavior-based control action triggers and brain wave perception |
| CN111227829A (en) * | 2020-02-14 | 2020-06-05 | 广东司法警官职业学院 | Electroencephalogram signal analysis method based on complex network characteristic indexes |
-
2020
- 2020-11-27 CN CN202011363331.3A patent/CN112434623A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101716079A (en) * | 2009-12-23 | 2010-06-02 | 江西蓝天学院 | Brainprint identity identification authentication method based on multi-characteristics algorithm |
| CN105159443A (en) * | 2015-08-06 | 2015-12-16 | 杭州电子科技大学 | PCA and Granger causality based brain network feature extraction method |
| US20170091741A1 (en) * | 2015-09-24 | 2017-03-30 | Hand Held Products, Inc. | Product identification using electroencephalography |
| CN109766751A (en) * | 2018-11-28 | 2019-05-17 | 西安电子科技大学 | Stable state vision inducting brain electricity personal identification method and system based on Frequency Domain Coding |
| CN109766845A (en) * | 2019-01-14 | 2019-05-17 | 首都医科大学宣武医院 | A kind of Method of EEG signals classification, device, equipment and medium |
| CN109933204A (en) * | 2019-03-22 | 2019-06-25 | 河北雄安有份儿智慧科技有限公司 | A kind of man-machine interaction method of Behavior-based control action triggers and brain wave perception |
| CN111227829A (en) * | 2020-02-14 | 2020-06-05 | 广东司法警官职业学院 | Electroencephalogram signal analysis method based on complex network characteristic indexes |
Non-Patent Citations (1)
| Title |
|---|
| 宋旭琳: "基于EEG相位同步的脑电识别研究及应用", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157101A (en) * | 2021-06-07 | 2021-07-23 | 成都华脑科技有限公司 | Fragmentation reading habit identification method and device, readable medium and electronic equipment |
| CN113157101B (en) * | 2021-06-07 | 2022-08-19 | 成都华脑科技有限公司 | Fragmentation reading habit identification method and device, readable medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ko et al. | Multi-scale neural network for EEG representation learning in BCI | |
| Gui et al. | A survey on brain biometrics | |
| Komeili et al. | Feature selection for nonstationary data: Application to human recognition using medical biometrics | |
| Bianco et al. | Biometric recognition using multimodal physiological signals | |
| CN102509103A (en) | Identifying method based on visual evoked P3 potential | |
| Mu et al. | Comparison of different entropies as features for person authentication based on EEG signals | |
| Tatar | Biometric identification system using EEG signals | |
| CN101843491A (en) | Resting electroencephalogram identification method based on bilinear model | |
| Monsy et al. | EEG‐based biometric identification using frequency‐weighted power feature | |
| Singla et al. | Biometric system-Challenges and future trends | |
| Zheng et al. | A power spectrum pattern difference-based time-frequency sub-band selection method for MI-EEG classification | |
| Bashar | ECG and EEG based multimodal biometrics for human identification | |
| Fan et al. | CNN-based personal identification system using resting state electroencephalography | |
| Alzahab et al. | Efficient feature selection for electroencephalogram-based authentication | |
| Ghosh et al. | Symptoms-based biometric pattern detection and recognition | |
| CN112434623A (en) | Individual identification method, system and storage medium based on brain network connectivity | |
| Fallahi et al. | Brainnet: Improving brainwave-based biometric recognition with siamese networks | |
| Bak et al. | User biometric identification methodology via EEG-based motor imagery signals | |
| Panzino et al. | EEG personal recognition based on ‘qualified majority’over signal patches | |
| Lipps et al. | Distinguishing hearts: How machine learning identifies people based on their heartbeat | |
| Kaur et al. | E‐CNNet: Time‐reassigned Multisynchrosqueezing transform‐based deep learning framework for MI‐BCI task classification | |
| Yang | The use of EEG signals for biometric person recognition | |
| Behboodin et al. | Frequency analysis of brain signals for biometric application | |
| Khaliq et al. | The role of EEG-based brain computer interface using machine learning techniques: a comparative study | |
| Mathumitha et al. | A Secure Authentication System based on Emotion Analysis of EEG Signals using Deep Learning Technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210302 |