CN107669267A - A kind of EEG signals unlocking system and method based on deep learning - Google Patents

A kind of EEG signals unlocking system and method based on deep learning Download PDF

Info

Publication number
CN107669267A
CN107669267A CN201710964522.7A CN201710964522A CN107669267A CN 107669267 A CN107669267 A CN 107669267A CN 201710964522 A CN201710964522 A CN 201710964522A CN 107669267 A CN107669267 A CN 107669267A
Authority
CN
China
Prior art keywords
eeg signals
unlocking
lockset
behavior
deep learning
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
CN201710964522.7A
Other languages
Chinese (zh)
Other versions
CN107669267B (en
Inventor
刘治
孔令爽
刘奕
魏冬梅
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.)
Shandong University
Original Assignee
Shandong University
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 Shandong University filed Critical Shandong University
Priority to CN201710964522.7A priority Critical patent/CN107669267B/en
Publication of CN107669267A publication Critical patent/CN107669267A/en
Application granted granted Critical
Publication of CN107669267B publication Critical patent/CN107669267B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/369Electroencephalography [EEG]
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7264Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00Individual registration on entry or exit
    • G07C9/00174Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
    • G07C9/00563Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns

Abstract

The invention discloses a kind of EEG signals unlocking system and method based on deep learning, including non-intruding collecting device and computer, the non-intruding collecting device, it is configured as gathering EEG signals of the lockset owner when thinking deeply unlocking behavior and not thinking deeply unlocking behavior, gathers the EEG signals for thinking deeply unlocking behavior of more people in addition to lockset owner;Computer, it is configured as EEG signals under each behavior pattern to collection and carries out feature extraction, obtained feature will be extracted and learnt and Classification and Identification, be confirmed whether matched in thinking unlocking behavior EEG signals with the lockset owner prestored, if it does, confirm as unlocking behavior.The identification of EEG signals has uniqueness, it is impossible to is forged, so that safety coefficient is higher.Classification and Identification is carried out to it using the method for deep learning, drastically increases accuracy of identification.

Description

A kind of EEG signals unlocking system and method based on deep learning
Technical field
The present invention relates to a kind of EEG signals unlocking system and method based on deep learning.
Background technology
More commonly used lockset equipment is usually to be unlocked using key on the market at present, if forgetting band key Spoon, then can bring very big trouble, and safety coefficient is also very low.And in lockset one used in the field of the high secrecy of some needs As be based on password, fingerprint or iris unblock, this equipment safety coefficient is some higher, but still there is the wind cracked Danger.
Substantial amounts of physiology and disease information are contained in EEG signals, in terms of clinical medicine, EEG Processing is not only Diagnosis basis can be provided for some cerebral diseases, but also effective treatment means are provided for some cerebral diseases.Because people is entering During the different thoughts of row, the biotic potential of the zone of action of each several part of brain is also different, therefore EEG signals It is and different.And everyone EEG signals have uniqueness, that is when different people carries out same thought, Caused EEG signals are also different, are fully able to distinguish different people using brain wave.
The content of the invention
The present invention is in order to solve the above problems, it is proposed that a kind of EEG signals unlocking system and side based on deep learning Method, the unlocking of the EEG's Recognition of the invention based on deep learning are simultaneously encrypted to it.
To achieve these goals, the present invention adopts the following technical scheme that:
A kind of EEG signals unlocking system based on deep learning, including non-intruding collecting device and computer, wherein:
The non-intruding collecting device, it is configured as gathering lockset owner in thinking unlocking behavior and does not think deeply unlocking behavior When EEG signals, gather the EEG signals of the thinking unlocking behavior of more people in addition to lockset owner;
The computer, the EEG signals being configured as under each behavior pattern to collection carry out feature extraction, will carried The feature obtained is learnt and Classification and Identification, and the lockset owner for being confirmed whether and prestoring is electric in thinking unlocking behavior brain Whether signal matches, if it does, confirming as unlocking behavior, and exports corresponding control result.
The non-intruding collecting device includes but is not limited to a kind of wearable helmet equipment, and the EEG signals collected are straight Connect or be sent into indirectly in computer.
The computer includes EEG signals receiving module, EEG feature extraction module, EEG signals features training Module, EEG signals test module and lockset control module, wherein:
The EEG signals receiving module, receive the brain wave of collection;
The EEG feature extraction module, the EEG signals being configured as under each behavior pattern to collection are carried out Feature extraction;
The EEG signals features training module, the EEG signals being configured as under each behavior pattern to collection are instructed Practice, obtain learning model;
The EEG signals test module, it is configured as receiving the eeg signal to be unlocked, and determines whether to unlock Signal, output test result;
The lockset control module, it is configured as generating lockset control signal according to test result.
The lockset equipment has the ability of WiFi or remote control, can receive the finger for the computer being attached thereto Order, so as to unlock.
When lockset receives unlocking instruction, lockset is opened.
Method based on said system, pre-process, EEG signals are gone for the EEG signals received Artefact processing, feature extraction is carried out to the EEG signals collected, characteristic quantity classified, by the label of each behavior pattern It is trained with sorting algorithm as one group of input with characteristic quantity, when training the degree of accuracy to reach setting accuracy, this is trained Model application;
Collection needs the EEG signals of unlocking person to carry out artefact and feature extraction processing, is then sent into characteristic quantity and preserves It is identified in good training pattern, judges whether to unlock.
The method of feature extraction is to extract EEG signals energy using wavelet analysis.
The EEG signals energy of same people's difference thought and different people same idea activity first to collecting adds Label, it is 0 that EEG signals label when unlocking is thought deeply to owner, and EEG signals label when owner does not think deeply unlocking is -1.
A kind of safety cabinet, using the above-mentioned EEG signals unlocking system based on deep learning.
A kind of encryption device, using the above-mentioned EEG signals unlocking system based on deep learning.
Compared with prior art, beneficial effects of the present invention are:
Band key can not had to when going out, so as to liberate both hands.For the place of the high secrecy of some needs, brain electricity The identification of signal has uniqueness, it is impossible to is forged, so that safety coefficient is higher.It is entered using the method for deep learning Row Classification and Identification, drastically increases accuracy of identification.
Brief description of the drawings
The Figure of description for forming the part of the application is used for providing further understanding of the present application, and the application's shows Meaning property embodiment and its illustrate be used for explain the application, do not form the improper restriction to the application.
Fig. 1 is the structured flowchart of the present invention;
Fig. 2 is the method flow diagram of classifying and identifying system in computer of the present invention;
Embodiment:
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
It is noted that described further below is all exemplary, it is intended to provides further instruction to the application.It is unless another Indicate, all technologies used herein and scientific terminology are with usual with the application person of an ordinary skill in the technical field The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative It is also intended to include plural form, additionally, it should be understood that, when in this manual using term "comprising" and/or " bag Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
In the present invention, term as " on ", " under ", "left", "right", "front", "rear", " vertical ", " level ", " side ", The orientation or position relationship of instructions such as " bottoms " are based on orientation shown in the drawings or position relationship, only to facilitate describing this hair Bright each part or component structure relation and the relative determined, not refer in particular to either component or element in the present invention, it is impossible to understand For limitation of the present invention.
In the present invention, term such as " affixed ", " connected ", " connection " should be interpreted broadly, and expression can be fixedly connected, Can also be integrally connected or be detachably connected;Can be joined directly together, can also be indirectly connected by intermediary.For The related scientific research of this area or technical staff, the concrete meaning of above-mentioned term in the present invention can be determined as the case may be, It is not considered as limiting the invention.
Such as the structured flowchart that Fig. 1 is the present invention.The present invention includes three parts, electroencephalogramsignal signal collection equipment 1, computer 2, Lockset 3 with the ability that is remotely controlled.
Electroencephalogramsignal signal collection equipment 1 includes but is not limited to a kind of head-wearing type collection EEG signals equipment, before being both used for The collection of phase training data, it may also be used for the collection of later stage test data.Electroencephalogramsignal signal collection equipment 1 gathers a large amount of masters first EEG signals of the people when thinking deeply unlocking and when not thinking deeply unlocking, then gather some non-owners and thinking deeply brain telecommunications when unlocking Number.The EEG signals collected are sent into computer 2.
After computer 2 receives EEG signals, the EEG signals collected are pre-processed first, pretreatment includes Go artefact, feature extraction etc..Then the feature extracted is sent into computer classes system and carries out classification processing.By a large amount of Training data, when accuracy of identification reaches certain standard, then this training pattern can be used for carry out next step identifying system in. When needing to unlock, the EEG signals of desired unlocking person are gathered by electroencephalogramsignal signal collection equipment 1, after EEG signals are extracted into feature Computer recognition system is sent into, is unlocked if being identified as owner and thinking deeply, computer sends a command to lockset, and lockset is opened.If It is identified as non-owner and thinks deeply unlocking, then master cellular phone is sent information to by computer.If being identified as owner does not think deeply unlocking, Then without any operation.
Lockset 3 is connected by wifi with computer, when computer recognition result is that owner thinks deeply unlocking, receives computer Instruction, lockset open.
Such as the method flow diagram that Fig. 2 is classifying and identifying system of the present invention.The classifying and identifying system is divided into three modules, training Module, identification module and control module.This process is described further below in conjunction with Fig. 2.
In training module, the first step pre-processes for the EEG signals received, first has to enter EEG signals Row goes artefact to handle.Because easily by noise pollution in electroencephalogramsignal signal collection equipment, so as to cause various artefacts, therefore to it Carrying out artefact operation is very necessary.Secondly, be to the brain telecommunications that collects in order to facilitate the training and identification of next step Number carry out feature extraction.The method for the feature extraction being related in the present invention is included but are not limited to one kind and carried using wavelet analysis EEG signals energy is taken as a kind of method of characteristic quantity.Next it is exactly that characteristic quantity is classified, this operation is included first The EEG signals energy of same people's difference thought and different people same idea activity to collecting tags, such as to master It is 0 that people, which thinks deeply EEG signals label when unlocking, and EEG signals label when owner does not think deeply unlocking is -1, and non-owner, which thinks deeply, to unlock The EEG signals label of behavior is 1.Label and characteristic quantity are trained as one group of input with sorting algorithm.This classification is calculated Method can be the associated depth learning classification algorithm such as ANN, DBN, CNN.When training the degree of accuracy to reach a higher precision, This training pattern is preserved for next module.
In test module, it would be desirable to which the eeg signal acquisition of unlocking person gets off, and as above carries out artefact and feature first Extraction process, then characteristic quantity is sent into the above-mentioned training pattern kept and is identified, by computer if being identified as 0 Unlocking instruction is sent, alarm command is sent if being identified as 1, if being identified as -1, does not make any operation.
In the control module, when lockset receives unlocking instruction, lockset is opened.Can root when mobile phone receives alarm command Choose whether to alarm according to situation.
The present invention can may be also used in safety cabinet, computer and encrypted computer file, mobile phone and mobile phone file encryption etc. one Cut the equipment that can be controlled by computer.
The preferred embodiment of the application is the foregoing is only, is not limited to the application, for the skill of this area For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair Change, equivalent substitution, improvement etc., should be included within the protection domain of the application.
Although above-mentioned the embodiment of the present invention is described with reference to accompanying drawing, model not is protected to the present invention The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not Need to pay various modifications or deformation that creative work can make still within protection scope of the present invention.

Claims (10)

1. a kind of EEG signals unlocking system based on deep learning, it is characterized in that:Including non-intruding collecting device and computer, Wherein:
The non-intruding collecting device, it is configured as gathering lockset owner and is thinking deeply unlocking behavior and when not thinking deeply unlocking behavior EEG signals, gather the EEG signals for thinking deeply unlocking behavior of more people in addition to lockset owner;
The computer, the EEG signals being configured as under each behavior pattern to collection carry out feature extraction, will extracted To feature learnt and Classification and Identification, be confirmed whether and the lockset owner that prestores be in thinking unlocking behavior EEG signals Whether match, if it does, confirming as unlocking behavior, and export corresponding control result.
2. a kind of EEG signals unlocking system based on deep learning as claimed in claim 1, it is characterized in that:The non-intruding Collecting device includes but is not limited to a kind of wearable helmet equipment, and the EEG signals collected are directly or indirectly sent into computer In.
3. a kind of EEG signals unlocking system based on deep learning as claimed in claim 1, it is characterized in that:The computer Include EEG signals receiving module, EEG feature extraction module, EEG signals features training module, EEG signals test mould Block and lockset control module, wherein:
The EEG signals receiving module, receive the brain wave of collection;
The EEG feature extraction module, the EEG signals being configured as under each behavior pattern to collection carry out feature Extraction;
The EEG signals features training module, the EEG signals being configured as under each behavior pattern to collection are trained, Obtain learning model;
The EEG signals test module, it is configured as receiving the eeg signal to be unlocked, and determines whether unlocking signal, Output test result;
The lockset control module, it is configured as generating lockset control signal according to test result.
4. a kind of EEG signals unlocking system based on deep learning as claimed in claim 1, it is characterized in that:The lockset is set The standby ability with WiFi or remote control, receives the instruction for the computer being attached thereto, so as to unlock.
5. a kind of EEG signals unlocking system based on deep learning as claimed in claim 1, it is characterized in that:Lockset receives Lockset is opened during unlocking instruction.
6. based on the method for the system as any one of claim 1-5, pair it is characterized in that:The EEG signals received enter EEG signals will be carried out artefact and handled by row pretreatment, carry out feature extraction to the EEG signals collected, characteristic quantity is entered Row classification, the label of each behavior pattern and characteristic quantity are trained as one group of input with sorting algorithm, when training is accurate When exactness reaches setting accuracy, by this training pattern application;
Collection needs the EEG signals of unlocking person to carry out artefact and feature extraction processing, and characteristic quantity then is sent into what is kept It is identified in training pattern, judges whether to unlock.
7. method as claimed in claim 6, pair it is characterized in that:The method of feature extraction is to extract brain telecommunications using wavelet analysis Number energy.
8. method as claimed in claim 6, pair it is characterized in that:Same people's difference thought and difference first to collecting The EEG signals energy of people's same idea activity tags, and it is 0 that EEG signals label when unlocking is thought deeply to owner, and owner does not think deeply EEG signals label during unlocking is -1.
9. a kind of safety cabinet, it is characterized in that:Using the brain telecommunications based on deep learning as any one of claim 1-5 Number unlocking system.
10. a kind of encryption device, it is characterized in that:Using the brain based on deep learning as any one of claim 1-5 Electric signal unlocking system.
CN201710964522.7A 2017-10-17 2017-10-17 Electroencephalogram unlocking system and method based on deep learning Active CN107669267B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710964522.7A CN107669267B (en) 2017-10-17 2017-10-17 Electroencephalogram unlocking system and method based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710964522.7A CN107669267B (en) 2017-10-17 2017-10-17 Electroencephalogram unlocking system and method based on deep learning

Publications (2)

Publication Number Publication Date
CN107669267A true CN107669267A (en) 2018-02-09
CN107669267B CN107669267B (en) 2020-06-19

Family

ID=61140635

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710964522.7A Active CN107669267B (en) 2017-10-17 2017-10-17 Electroencephalogram unlocking system and method based on deep learning

Country Status (1)

Country Link
CN (1) CN107669267B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102755162A (en) * 2012-06-14 2012-10-31 天津大学 Audio-visual cognitive event-related electroencephalogram-based identification method
CN105205966A (en) * 2015-08-13 2015-12-30 上海斐讯数据通信技术有限公司 Intelligent antitheft system and method
CN105389004A (en) * 2015-10-22 2016-03-09 上海斐讯数据通信技术有限公司 Brain wave unlocking terminal screen system and method
CN106251438A (en) * 2016-07-22 2016-12-21 三峡大学 A kind of E.E.G lock system and method
CN106453903A (en) * 2016-10-18 2017-02-22 珠海格力电器股份有限公司 Mobile terminal and mobile terminal automatic unlocking or screen lightening method and system
CN107067519A (en) * 2017-05-12 2017-08-18 广东工业大学 A kind of safety box based on the electric identification of brain
KR20170096279A (en) * 2016-02-15 2017-08-24 한양대학교 에리카산학협력단 Control mehtod for security system using brain wave

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102755162A (en) * 2012-06-14 2012-10-31 天津大学 Audio-visual cognitive event-related electroencephalogram-based identification method
CN105205966A (en) * 2015-08-13 2015-12-30 上海斐讯数据通信技术有限公司 Intelligent antitheft system and method
CN105389004A (en) * 2015-10-22 2016-03-09 上海斐讯数据通信技术有限公司 Brain wave unlocking terminal screen system and method
KR20170096279A (en) * 2016-02-15 2017-08-24 한양대학교 에리카산학협력단 Control mehtod for security system using brain wave
CN106251438A (en) * 2016-07-22 2016-12-21 三峡大学 A kind of E.E.G lock system and method
CN106453903A (en) * 2016-10-18 2017-02-22 珠海格力电器股份有限公司 Mobile terminal and mobile terminal automatic unlocking or screen lightening method and system
CN107067519A (en) * 2017-05-12 2017-08-18 广东工业大学 A kind of safety box based on the electric identification of brain

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李云昊等: "大脑能"开锁"——如何实现安卓手机的脑控屏幕解锁", 《发明与创新 中学生》 *

Also Published As

Publication number Publication date
CN107669267B (en) 2020-06-19

Similar Documents

Publication Publication Date Title
CN103345600B (en) A kind of ecg signal data processing method
CN104586387B (en) Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters
CN102184415B (en) Electroencephalographic-signal-based fatigue state recognizing method
CN104166548B (en) Deep learning method based on Mental imagery eeg data
CN101499134B (en) Iris recognition method and system based on field programmable gate array
CN203250345U (en) Access control system based on brain wave identity recognition
CN100411580C (en) Objectively detected identity recognition method based on human brain memory character
CN103248703A (en) Automatic monitoring system and method for live pig action
CN105654063B (en) Mental imagery brain power mode recognition methods based on the optimization of artificial bee colony time and frequency parameter
CN103632147A (en) System and method for implementing standardized semantic description of facial features
CN108577865A (en) A kind of psychological condition determines method and device
CN106725452A (en) Based on the EEG signal identification method that emotion induces
CN104809783A (en) Security access control system
CN103207963A (en) Two-factor authentication system based on fingerprint and vein recognition
CN106650253A (en) Dialectical system of traditional Chinese medicine
CN110013249A (en) A kind of Portable adjustable wears seizure monitoring instrument
CN105011951A (en) Device for extracting eye blinking times by brain waves and method
CN107122050A (en) Stable state of motion VEP brain-machine interface method based on CSFL GDBN
Botcharova et al. Power-law distribution of phase-locking intervals does not imply critical interaction
CN106874722A (en) A kind of personal identification method and its device based on electrocardiosignal
CN107669267A (en) A kind of EEG signals unlocking system and method based on deep learning
CN107822628B (en) Epileptic brain focus area automatic positioning device and system
CN104035563A (en) W-PCA (wavelet transform-principal component analysis) and non-supervision GHSOM (growing hierarchical self-organizing map) based electrocardiographic signal identification method
CN108670209A (en) A kind of method and system of automatic identification Chinese medicine pulse
CN107067519A (en) A kind of safety box based on the electric identification of brain

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant