CN106407733A - Depression risk screening system and method based on virtual reality scene electroencephalogram signal - Google Patents
Depression risk screening system and method based on virtual reality scene electroencephalogram signal Download PDFInfo
- Publication number
- CN106407733A CN106407733A CN201611141740.2A CN201611141740A CN106407733A CN 106407733 A CN106407733 A CN 106407733A CN 201611141740 A CN201611141740 A CN 201611141740A CN 106407733 A CN106407733 A CN 106407733A
- Authority
- CN
- China
- Prior art keywords
- module
- virtual reality
- eeg signals
- depression
- eeg
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Medical Informatics (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a depression risk screening system and method based on a virtual reality scene electroencephalogram signal. Under the stimulation of a virtual reality scene, real-time acquisition, processing and analysis of data are carried out on the electroencephalogram signal by an electroencephalogram acquisition system, and finally, a depression risk is screened by a data mining method. The system provided by the invention comprises a virtual reality induction system, a electroencephalogram signal acquisition system and a data analysis system; the virtual reality induction system is used for establishing different virtual reality scenes; the electroencephalogram signal acquisition system is used for acquiring the electroencephalogram signal of a human brain, which is generated under the stimulation of the virtual reality scene and is continuously changed, and outputting the processed electroencephalogram signal and extracted real-time feature information; the data analysis system has a classification discrimination model trained by labeled healthy populations and depression risk populations, compares feature information required in a depression screening process with feature parameters of the classification discrimination model, and distinguishes and discriminates the healthy populations and the depression risk populations.
Description
Technical field
The present invention relates to computer-aided medical diagnosis technical field, more particularly to one kind are based on virtual reality scenario brain
The depression Risk Screening system and method for the signal of telecommunication.
Background technology
1. the related technical background information of eeg signal acquisition
Eeg signal acquisition from the epidermis of human body head, with brain area activity, affective state close relation.Existing grind
Study carefully and show, EEG signals can reflect the emotion change of the mankind in real time.The research of EEG signals can be applicable to understand cerebration machine
The aspects such as system, the cognitive process of people and diagnosis brain illness, and the brain-computer interface field receiving much concern in recent years.
EEG signals are to be produced and be present in all the time by brain neurological motion the autonomous potential activity of central nervous system, are
A kind of important bioelectrical signals.Tranquillization state EEG signals are used for studying mental illness patient with healthy population to score
Analysis, evoked brain potential is used for studying the change of the cognitive function of patient.EEG signals have the characteristics that as follows：It is by cranial nerve
Activity produces and is present in the autonomous potential of central nervous system all the time；EEG signals are very faint；Interference free performance is weak, Shandong
Rod is poor；It is stochastic signal, has non-stationary and the nonlinear feature of non-gaussian；State and the change of nervous system can be reflected
Change.Therefore, gather EEG signals, physiology and the mental status of people can be monitored by analysis, such that it is able to depression risk
Patient carries out examination.
Non-intervention type brain wave acquisition Technical comparing is complicated, the signal collecting excessively faint it is easy to be disturbed by noise,
Therefore only collect the sufficiently high EEG signals of signal to noise ratio, and signal is accurately amplified, the denoising such as filtering, with
The correct signal extraction of Shi Jinhang and analysis, just can obtain accurate pathological analysis result so that brain electricity more effectively reflects people
The physiology of body and mental status.Repeat rhythm and pace of moving things difference by EEG signals in the world to be classified, unified is following four frequency range：
δ ripple：1--3Hz, amplitude in the state of deep sleep or has seriously organic in 20 μ V-200 μ V dominant response people
Disease of brain are suffered from.
θ ripple：4--7Hz, amplitude in 100 μ V-150 μ V, main reflection people be in the sleep initial stage, meditation state, sleepy when,
When emotion is constrained.
α ripple：8--13Hz, in 20 μ V-100 μ V, main reflection people is in clear-headed, quiet and closed-eye state to amplitude.
β ripple：14--30Hz, amplitude in 5 μ V-20 μ V, main reflection people be in psychentonia, excited or excited with
And state during thought active, attention concentration.
The electroactive measurement of brain always needs complicated and expensive equipment, and needs to have received the employee behaviour of professional training
Make, the acquisition mode of EEG signals can be divided into two kinds of invasive, noinvasive again.Invasive acquisition mode needs to carry out operation of opening cranium, thus
Brain can be brought with certain damage；Noninvasive acquisition mode does not then need to perform the operation, and human brain is not damaged.EEG signal micro-
Weak property, be easily disturbed characteristic requirements hospital collection EEG signal must shielding in the environment of carry out.And with EEG measuring in people
Machine interacts the extensive application in the fields such as brain electric control, personalized health care, and portable brain electric collection biosensor becomes
Inevitable, therefore, portable brain electric biosensor should reach efficient and portability, ease for use, and is suitable for complex environment.
2. the related technical background information of virtual reality
Virtual reality (Virtual Reality, abbreviation VR), was formally proposed by U.S. Jarn Lanier in 1989, and
It is referred to as virtual tangible, virtual real mirror, clever border, face mirror.It refers to that comprehensively utilizing computer system and various display and control etc. connects
Jaws equipment, provides the technology immersing sensation in the three-dimensional environment interacting generating on computers.Wherein, computer generates
Virtual environment can be referred to as by interactive three-dimensional environment.
The feature triangle of virtual reality, i.e. " 3I " property of VR technology, the property immersed (Immersion), interactivity
(Interaction), imagination (Imagination).
A. the property immersed is the principal character of virtual reality technology.
B. interactivity refers to the ability that user is interacted with objects various in virtual scene.
C. imagination refers to be immersed in " real " virtual environment by user, carries out various interacting work with virtual environment
With obtaining perception and reasonable cognition from the environment of qualitative and quantitative comprehensive integration, producing the leap in understanding.
The aspects such as the application design engineering design of virtual reality, computer, medical treatment, artistic creation, game, amusement.
It is in a development, has the new technique in far-reaching potential application direction.It is from virtual reality system structure and features
Realize virtual reality key technology mainly have dynamic environment modeling technique, real time 3-D image generation technique, stereo display and
Sensor technology.Virtual reality technology application dynamic environment modeling technique obtains the three-dimensional data of actual environment, as needed, profit
Set up corresponding virtual environment model with the three-dimensional data obtaining.
3. data modeling and data analysiss related background art information
In EEG research and application, work the most primary is exactly to remove noise jamming, thus obtaining clean EEG signals,
This is the basis of brain electricity analytical.Environment and other Hz noise non-overlapping phenomenon with brain electricity on frequency domain, electro-ocular signal then and
Brain electricity has the overlap in frequency range.Earliest noise remove method is experiment control method, and this method is based primarily upon in experimentation
Requirement to subjectss' behavior.But because tested inevitable unintentional motion is reacted, necessarily lead to biological artefact；Technically
For simplest denoising method be directly to reject data manually, this cause data sample continuity be destroyed, information is lost
Lose.
Currently, some innovatory algorithm existing are capable of effective elimination of noise jamming, than more typical have regression algorithm,
Wavelet transformation, independent principal component analysiss, neutral net, digital filter, sef-adapting filter etc..But in the present invention be
Wavelet analysises and improved self adaptation dynamic AR model parameter carry out denoising, filtering, and it has：Parameter can automatically adjust, learn
And it is simple and practical to follow the tracks of time-varying input signal feature, algorithm；When EEG signals after to denoising carry out feature extraction it is contemplated that
Brain has non-stationary and randomness, has the characteristics that Kind of Nonlinear Dynamical System, based on nonlinear dynamics theory to brain
The signal of telecommunication is analyzed, and extracts the nonlinear characteristic of EEG signals；After feature extraction, by the feature choosing of correlation rule
Select algorithm (CFS) and the associated methods of K k-nearest neighbor (KNN) carry out feature selection and tagsort to data.
4. the prior art of depression Risk Screening diagnosis and shortcoming
The diagnosis of depression is still in symptom deduction phase, has no objective physico-chemical examination diagnosis index.Existing examination
Depression risk means and acquisition method have more defect, and it essentially consists in：
(1) depression examination scheme is few, means are single：Mostly it is according to hormone water in the patient for depression examination means
Gentle various biochemical indicator, as examination reference index, lacks general formula means and the corresponding scheme of depression examination on the market,
The index parameter lacking bioelectrical signals is so that the method for examination depression has certain limitation；
(2) electroencephalogramsignal signal collection equipment does not have general formula：Medical eeg signal acquisition instrument, equipment is complicated, high cost, needs
Special messenger is wanted to be responsible for collection；Portable brain electric Acquisition Instrument, the number of brain wave acquisition electrode, position do not know, brain wave acquisition electrode and
The mode of transmission data, and cost and application all different, main is exactly that power dissipation ratio is larger it is impossible to continuous use, A/D
Conversion digit is low；
(3) conventional stimulation protocols do not have good implementation：Traditional stimulation mode is many with picture, music, 2D video to be
Master is it is impossible to cause the attention of experimenter well.System experience is not good, and the property immersed is not enough, interactive with patient not enough it is impossible to very
Guiding patient uses well, easily affected by environment, affects Effect of screening, causes patient to drop by the wayside rate high；
(4) data modeling and analysis lack relative reliability：Modeling data is few, and information contained amount is little, makes data model not
There is good balance and effectiveness.Potentials extraction algorithm not good it is impossible to obtain pure physiology EEG signals.Single number
According to analysis method so that feature extraction and the result selecting lack representative and accuracy.These shortcomings cause to be directed to and are subject to
The characteristic information of examination person provides the depression Risk Results of rationalization.
Yet there are no the phase of the depression screening system based on general formula EEG signals under virtual reality scenario stimulates
Close report.
Content of the invention
The present invention provides a kind of depression Risk Screening system and method based on virtual reality scenario EEG signals, to cure
Based on the existing psychology of educational circles, the content of physiology, under the three-dimensional audiovisual of virtual reality scenario stimulates, by generalization
EEG signals are carried out the Real-time Collection of data, process, analysis, finally by the method pair of data mining by eeg collection system
Depression risk carries out examination.
The technical scheme is that：
1. a kind of depression Risk Screening system based on virtual reality scenario EEG signals is it is characterised in that include empty
Intend real induction system, eeg signal acquisition system, data analysis system；Described virtual reality induction system is used for setting up difference
Virtual reality scenario, described eeg signal acquisition system is used for gathering human brain and continuous change occurs under virtual reality scenario stimulation
The EEG signals changed, the EEG signals after output process and the real-time characteristic information of extraction；Described data analysis system have by
The discriminant classification model that labelled healthy population and depression risk population are trained out, for virtual reality scenario
The characteristic information by formula person's EEG signals being excited carries out tagsort, and by required characteristic information in depression examination
The discriminant classification aspect of model parameter good with training in advance is compared, and distinguishes and differentiates healthy population and depression risk population,
There is provided objective basis for depression Risk Screening.
2. eeg signal acquisition system described in includes EEG signals extraction module, real-time EEG Processing module；Described
EEG signals extraction module is used for extraction, amplification and the Filtering Processing of EEG signals, and the signal after processing is converted into through A/D
Digital signal sends into real-time EEG Processing module；Described real-time EEG Processing module is used for the numeral to A/D conversion
Signal carries out pretreatment, eliminates the noise that interference and physiology artifact are brought further.
3. virtual reality described in induce the initialization module that system includes being sequentially connected, virtual reality scenario stimulating module,
Obtain input information and logic processing module, render frame module, simultaneous display module；It is right that described initialization module is used for
Unity3D, acoustic processing, the initialization of input equipment；Described virtual reality scenario stimulating module is used for response system message, and
The model of audio-visual information is rendered；Described input information and the logic processing module of obtaining is for according to the brain electricity index setting
Judge whether to reach message, control virtual reality scenario to stimulate in Message Processing pattern, the message obtaining is counted simultaneously
Number, judges whether switching virtual reality scene stimulation protocol；The described frame module that renders is for inducing thorn to audio-visual information emotion
The various models occurring in swashing are rendered；The object that described simultaneous display module is used for showing is drawn by certain logic
On sightless lookaside buffer, then it is turned on visible front relief area, show the image of continuous pictures.
4. data analysis system described in includes acquisition module, off-line analysiss module, EEG signals after-treatment module, data
Analysis module, communication logic module；Described acquisition module collection is by the brain through pretreatment coming on communication logic module transfer
The signal of telecommunication and real-time characteristic packet；Described off-line analysiss module stores local hard drive to the EEG signals of acquisition module,
The feature analysiss that EEG signals after-treatment module carries out time-frequency domain can be sent into when there being demand, possess and recur analysis work(at any time
Can, fast searching specifies data；The data of acquisition module can also be sent directly into EEG signals after-treatment module, to real-time brain
The data of electric treatment module is further processed, and eliminates the distorted signals in transmitting procedure；Described data analysis module, adopts
Eliminate interference and physiology artifact with the method for wavelet packet analysis and using nonlinear dynamics theory to the EEG signals after denoising
Carry out feature extraction, the algorithm finally by CFS+KNN carries out feature selection and classification.
5. data analysis system described in also includes management module, data base's support module, display module；Described management module
For being managed to examination process and subject information, including the establishment of subject information, inquiry, modification, delete, and examine
The selection of disconnected examination scheme, the index required by setting examination depression scheme and the storage of form and data, real-time update
And change the content of communication logic module database module；Described data base's support module is used for storing examination scheme, tested
The information of person and its process of sieving and diagnosis depression；Described display module be used for real-time display subjectss Active electroencephalogram (EEG) and
Its situation of change.
6. a kind of depression Risk Screening method based on virtual reality scenario EEG signals it is characterised in that include with
Lower step：
1) start virtual reality induction system, setting up virtual reality stimulates scene；
2) start eeg signal acquisition system, collection human brain is not there being the quiet period of any stimulation, in virtual reality respectively
Scene stimulates continually varying EEG signals that are lower and occurring in emotion convalescent period；
3) Treatment Analysis are carried out to the EEG signals obtaining, by required characteristic information in the depression extracting examination
The discriminant classification aspect of model parameter good with training in advance is compared, and distinguishes and differentiates healthy population and depression risk population,
There is provided objective basis for depression Risk Screening.
7. step 1 described in) in, including the step of virtual reality scenario exploitation：Enter audio-visual information emotion induction system with
Afterwards, to Unity3D, acoustic processing first in initialization module, input equipment is initialized, subsequently into virtual reality field
Scape stimulating module, carrying out the induction of audio-visual information emotion stimulates, and controls virtual existing in obtaining input information and logic processing module
Real field scape stimulates, and the message obtaining is counted simultaneously, judges whether that terminating virtual reality scenario stimulates, and enters and renders frame figure
Module and simultaneous display module carries out next frame image rendering and real-time synchronization shows, after audio-visual information induction stimulation finishes,
Quit a program.
8. step 2 described in) in, the EEG signals of collection are the α ripple of subjectss' brain electricity, β ripple, δ ripple, θ ripple signal, original number
It is to be collected by three electrodes of eeg signal acquisition system according to each wave band aliasing EEG signals together；Described electrode quilt
It is positioned over Fp1, FpZ and Fp2 is located at the position of forehead.
9. step 3 described in) in, including the step of EEG signals pretreatment：Application wavelet transform first is to collecting
EEG signals carry out wavelet decomposition, obtain wavelet coefficient；Specific threshold process is done to the wavelet coefficient of low-frequency range, then right
Wavelet coefficient after process carries out wavelet reconstruction, thus extracting eye electricity reference signal；Finally, by the eye extracting electricity reference
Signal as the reference input of sef-adapting filter, using untreated EEG signals being originally inputted as sef-adapting filter,
The output of so system has just obtained the clean EEG signals after removing eye electrical noise.
10. step 3 described in) in, including the step of discriminant classification model modeling：First pass through virtual reality scenario to pasting
The healthy population of label and depression risk population carry out emotion induction and stimulate, and then gather EEG signals, former to collect
Beginning EEG signals carry out Signal Pretreatment by wavelet packet analysis, then by nonlinear dynamics theory to the brain electricity after denoising
Signal carries out feature extraction, and the hybrid algorithm finally by CFS+KNN carries out feature selection and tagsort, thus being classified
Arbiter model.
Step 3 described in 11.) in, including the step of depression risk analyses differentiation process：By virtual reality scenario to not
Know that individual subjects carry out emotion induction and stimulate, gather the EEG signals of this individual subjects and by pretreatment such as signal denoisings
After module, feature extraction is carried out to the EEG signals after denoising by nonlinear dynamics theory, the feature extracting is joined
Amount sends into discriminant classification model thus drawing depression Risk Screening result.
The technique effect of the present invention：
A kind of depression Risk Screening system and method based on virtual reality scenario EEG signals that the present invention provides.With
Based on the existing psychology of medical circle, the content of physiology, EEG signals are used as the examination depression wind of bio information
Dangerous signal, plays the advantage that sense is strong, interactivity is strong, imagination is strong of soaking of virtual reality, regards in the three-dimensional of virtual reality scenario
Listen under stimulation, so that subjectss is soaked in virtual environment, by generalization eeg collection system, detect subjectss' brain electricity α ripple,
β ripple, the feature of δ ripple, θ ripple signal and high frequency β wave energy percentage ratio are analyzed diagnosing, and carry out the real-time of data to EEG signals
Collection, process, analysis, finally by the method for data mining, are that the diagnosis of depression carries out objective appraisal and defines, and realize
Carrying out examination for depression risk provides the purpose of objective basis.Improve efficiency and the reliability of depression disorder Risk Screening.
Can examination symptom extensively, can process in time, store and transmission data, easy to use.Whole system noinvasive, has no side effect, no
Dependency, and with low cost, easily promote.
1. generalization eeg collection system advantage is as follows：
(1) there is higher motility：The EEG signals of leading that the multiple scalp electrode of system acquisition obtains extract examination letter more
Breath, its corresponding electrode slice can need to place different positions according to different, extracts and examination depression correlation maximum
EEG signals；Accurately gather EEG signals using general formula eeg collection system, process and extract pure brain telecommunications
Number, signal characteristic is processed, after comparison database analysis, obtains accurate pressure rank.
(2) there is more preferable convenience：Realize pretreatment and the feature extraction of real-time EEG signals using hardware, significantly carry
High arithmetic speed, real time OS, tested current state can be can be visually seen.Thus preferably ensureing the convenient of examination information
Property.
2. the advantage that virtual reality scenario stimulates is as follows：
Virtual reality scenario stimulates as induction stimulation means, makes stimulation more added with personalized and sense of reality.User is complete
It is immersed in the virtual environment of computer generation, user is in a kind of body in the three-dimensional virtual environment that computer is created and faces it
The sensation in border.The very strong virtual reality scenario of sense of reality, is equipped with suitable background music, and user can pass through multiple sensors
There is reciprocal action with the environment of multidimensional information.This scene from the angle of patient, relies on design psychology, in content and
Pro forma design all takes into full account the disease type of patient, age, sex, personality, so that subjectss is more had more true
Feeling of immersion and good bring sense, wherein interspersed special audio effect into, more effectively real induction stimulates subjectss'
Emotional state, makes every effort to more accurately to the tested examination carrying out depression risk.
3. the present invention adopts up-to-date data model and reliable data analysing method advantage as follows：
(1) system of data model is more sound：This data model is with the data of up-to-date " 973 " analysis of experimental data
Index parameter based on model, abundant database resource, its data structure is simple, clear, have good data independence,
Level security, user is understandable easy-to-use, can carry out cross validation with data with existing, the number arriving of huge experimental data system
There is according to model the low feature of disequilibrium of high precision, data model, improve accuracy and the specific aim of sieving and diagnosis.
(2) data analysing method is more accurate, more efficient：On noise remove, Hz noise is completed using wave trap,
The removal of eye electrical noise is based on wavelet transform and improved self adaptation dynamic AR model parameter carries out denoising, filters, its tool
Have：It is simple and practical that parameter can automatically adjust, learn and follow the tracks of time-varying input signal feature, algorithm；Studied the science using non-linear dynamic
By the nonlinear characteristic extracting EEG signals, more rapid can more accurately obtain useful feature value；By correlation rule
The associated methods of feature selecting algorithm (CFS) and K k-nearest neighbor (KNN) carry out feature selection and tagsort to data, this
The method of kind increased effectiveness and the accuracy of sorter model.Thus obtain more accurately model being easy to during examination depression
Relative analyses.
The system of the present invention, using friendly simple man machine interface, has very convenient very flexible general formula performance, uses
Simply, simultaneously friendly interface it is easy to doctor and patient accept.System does not require user to have programming experience, does not provide complexity
Operating environment.
Brief description
Fig. 1 is the system composition structural representation of the present invention.
Fig. 2 is data analysis system composition structural representation.
Fig. 3 is method of the present invention schematic flow sheet.
Fig. 4 is virtual reality scenario development process figure.
Fig. 5 is EEG signals pretreatment process figure.
Fig. 6 is discriminant classification model modeling process flow diagram flow chart.
Fig. 7 is that depression risk analyses differentiate process flow diagram flow chart.
Specific embodiment
Below in conjunction with accompanying drawing, embodiments of the invention are described in further detail.
As shown in figure 1, being the system composition structural representation of the present invention.
A kind of depression Risk Screening system based on virtual reality scenario EEG signals, induces system including virtual reality
System, eeg signal acquisition system, data analysis system；Described virtual reality induction system is used for setting up different virtual reality fields
Scape, described eeg signal acquisition system is used for gathering human brain generation continually varying brain telecommunications under virtual reality scenario stimulation
Number, output process after EEG signals and extraction real-time characteristic information；Described data analysis system has by labelled
The discriminant classification model that healthy population and depression risk population are trained out, for the quilt that virtual reality scenario is excited
The characteristic information of formula person's EEG signals carries out tagsort, and by required characteristic information in depression examination and training in advance
Good discriminant classification aspect of model parameter is compared, and distinguishes and differentiates healthy population and depression risk population, is depression wind
Dangerous examination provides objective basis.
1. the present invention adopts newly designed generalization eeg collection system.Using leading eeg collection system generalization more
(association patent：The patent No.：CN201520628152.6) EEG signals are gathered.Lead brain electric transducer has multiple scalp electrodes more,
For eeg signal acquisition, sample frequency is 256Hz, and the EEG signals of collection are sent into EEG signals extraction module；Brain electricity
Signal extraction module, for the extraction of EEG signals, amplification and Filtering Processing, the signal of amplification is converted into counting by 16 A/D
Hardware real-time EEG Processing module is sent into after word signal；EEG Processing module, for the digital signal that A/D is changed
Carry out pretreatment, the method using WAVELET PACKET DECOMPOSITION, wavelet threshold eliminates interference and physiology artifact further, and using non-linear
Kinetic theory carries out real-time feature information extraction to signal, and will be defeated to the EEG signals after processing and real-time characteristic information
Go out.
The eeg signal acquisition system of the embodiment of the present invention includes EEG signals extraction module, real-time EEG Processing mould
Block；Described EEG signals extraction module is used for extraction, amplification and the Filtering Processing of EEG signals, and by the signal after processing through A/
D is converted into digital signal and sends into real-time EEG Processing module；Described real-time EEG Processing module is used for A/D is changed
Digital signal carry out pretreatment, eliminate interference and the noise that brings of physiology artifact further.
2. the present invention adopts virtual reality technology, and virtual reality technology application dynamic environment modeling technique obtains actual environment
Three-dimensional data, as needed, using obtain three-dimensional data set up corresponding virtual environment model：Achieve brand-new interaction
Means and interactive scene design, this make tested patient not be passive impression but aggressive come into complete in scene scheme
Emotion induction is become to stimulate；Improve the feeling of immersion of whole system, this enables people to be immersed in completely in virtual environment, have and
The same sensation in true environment, increased emotion induction stimulation brings sense into, reduces patient and drops by the wayside rate.Virtual reality skill
Art can sufficiently cause patient to note and the maximized emotional state inducing patient's heart of energy, decreases ring to greatest extent
The interference in border, perfect guiding system tested positive use system of being more convenient for is possibly realized so that realizing more preferable diagnosis effect.
By wearing virtual reality glasses, reach visual scene and audio frequency double stimuli.
The virtual reality of the embodiment of the present invention induces initialization module, the virtual reality scenario thorn that system includes being sequentially connected
Sharp module, obtain input information and logic processing module, render frame module, simultaneous display module；Described initialization module is used
In to Unity3D, acoustic processing, the initialization of input equipment etc., carry out some Memory Allocation, collection of resources, from disk be loaded into
Data etc.；Described virtual reality scenario stimulating module is used for response system message, and the model of audio-visual information is rendered；Institute
State and obtain input information and logic processing module for judging whether according to the brain electricity index setting in depression Risk Screening scheme
Reaching message, if touching the mark, obtaining message, control virtual reality scenario to stimulate, simultaneously to acquisition in Message Processing pattern
Message counted, judge whether switching virtual reality scene stimulation protocol；Render frame module for audio-visual information feelings
The various models that thread induction occurs in stimulating are rendered；Simultaneous display module is used for removing sightless lookaside buffer, then
The object that will show is plotted on this block memory field by certain logic, after having drawn, is turned to visible front buffering
Qu Shang, the picture refreshing rate according to 60 frames/second shows the image of continuous pictures.
3. the present invention adopts brand-new data model and data analysis system.Acquisition module, collection by USB transmission come
EEG signals and real-time characteristic packet through pretreatment；Off-line analysiss module, the EEG signals storage to acquisition module
To local hard drive, can have afterwards and send into, during demand, the feature analysiss that EEG signals after-treatment module carries out time-frequency domain, possess
Recur analytic function at any time, fast searching specifies data；The data of acquisition module can also be sent directly into the secondary place of EEG signals
Reason module, is further processed to the data of hardware real-time brain electric treatment module, eliminates the distorted signals in transmitting procedure；
Data analysis module, eliminates interference and physiology artifact and using nonlinear dynamics theory to going using the method for wavelet packet analysis
EEG signals after making an uproar carry out feature extraction, and the algorithm finally by CFS+KNN obtains the model of grader, thus obtaining more
Accurate examination depression risk information.Management module, is managed to examination process and subject information, including subjectss' letter
The establishment of breath, inquiry, modification, deletion, and the selection of diagnosis examination scheme, the index required by setting examination depression scheme
With the storage of form and data, the content of management module class one real-time update modification communication logic module database module；
Data base, the process of storage examination scheme, the information of subjectss and its sieving and diagnosis depression；Display module, shows quilt in real time
The Active electroencephalogram (EEG) of examination person and its situation of change；Management module respectively with communication logic module, off-line analysiss module, collection mould
Block, depression Risk Screening data analysis module, data base, display module are directly connected to.Mutually auxiliary phase between each module of system
Become, mutually support so that last result just has the reliability of higher performance and accurate effectiveness.
As shown in Fig. 2 being data analysis system composition structural representation.The data analysis system of the embodiment of the present invention includes
Acquisition module, off-line analysiss module, EEG signals after-treatment module, data analysis module, communication logic module；Described collection
Module collection by communication logic module transfer come the EEG signals through pretreatment and real-time characteristic packet, described from
Wire module stores local hard drive to the EEG signals of acquisition module, can have feeding EEG signals after-treatment during demand afterwards
Module carries out the feature analysiss of time-frequency domain, possesses recurrence analytic function at any time, and fast searching specifies data；The data of acquisition module
EEG signals after-treatment module can also be sent directly into, the data of real-time brain electric treatment module is further processed,
Eliminate the distorted signals in transmitting procedure；The EEG signals obtaining after to pretreatment carry out more fine process, with
To EEG power spectrum array of figure and the brain electricity histogrammic Real time dynamic display of the index such as θ, α, β, realize brain electricity index real-time monitoring,
Doctor passes through this function Real Time Observation patient's brain electric information indices and changes, and intuitively, grasps patient's cerebral functional lateralitv exactly,
In order to monitor the process of examination.Intuitively reflect by the information of envoy, be more conducive to doctor and provide objective diagnostic result.Institute
State data analysis module, interference and physiology artifact are eliminated using the method for wavelet packet analysis and adopts nonlinear dynamics theory pair
EEG signals after denoising carry out feature extraction, and the algorithm finally by CFS+KNN carries out feature selection and classification.
Data analysis system also includes management module, data base's support module, display module；Management module is used for examination
Process and subject information are managed, and including the establishment of subject information, inquiry, modification, delete, and diagnosis examination scheme
Selection, setting examination depression scheme required by index and form and data storage, real-time update modification communication patrol
Collect the content of module and DBM.Data base's support module is used for storing examination scheme, the information of subjectss and its examination
The process of diagnosis depression；All data of the system are all to support that system (DBSS) is stored by data base, data
Storage mainly point two classes, the first kind is the essential information of patient, including：The numbering of patient, name, sex, age, diagnosis side
Case, the number of times accepting examination depression risk, contact address etc., Equations of The Second Kind is the brain electricity number in the last idagnostic logout for the patient
According to；In addition to the number of times of scheme and examination except accepting examination changes, primary sources are basically unchanged.Secondary sources can be through
Often change, the EEG signals data of examination each time can be stored；In addition, the system also can store data as XML format
File, for later transfers on network and far call.Display module is used for the real-time Active electroencephalogram (EEG) showing subjectss
And its situation of change, make and do not accept stimulation and --- -- accept the Active electroencephalogram (EEG) of patient that emotional distress --- -- terminates to stimulate
Variation diagram, the EEG signals waveform dynamic realtime accepting under virtual reality stimulates is shown over the display, the system is realized
The dynamic no pen of the variation diagram of electroencephalogram is traced.
As shown in figure 3, being method of the present invention schematic flow sheet.
A kind of depression Risk Screening method based on virtual reality scenario EEG signals, comprises the following steps：
1) start virtual reality induction system, setting up virtual reality stimulates scene；
2) start eeg signal acquisition system, collection human brain is not there being the quiet period of any stimulation, in virtual reality respectively
Scene stimulates continually varying EEG signals that are lower and occurring in emotion convalescent period；
3) Treatment Analysis are carried out to the EEG signals obtaining, by required characteristic information in the depression extracting examination
The discriminant classification aspect of model parameter good with training in advance is compared, and distinguishes and differentiates healthy population and depression risk population,
There is provided objective basis for depression Risk Screening.
First, start general formula EEG signals depression Risk Screening system under virtual reality scenario stimulates, accept wind
The patient of dangerous examination first registers the information of oneself, including information such as the numbering of patient, name, sex, ages.Then, cure
The raw position selecting placement brain electricity multilead electrode piece according to symptom to be directed to, opens real-time eeg recording.The brain electricity of patient
Signal passes through to lead after brain electrode sensor extracts more, by EEG preamplifier, faint EEG signals is put
Greatly, original EEG signals are carried out with power frequency Filtering Processing, the signal of amplification is converted into digital signal by 16 A/D simultaneously, lead to
Cross and call the preprocessor in EEG signals real-time processing module to carry out pretreatment to reduce the interference of artifact to EEG signals,
Ensure the effectiveness of depression Risk Screening, then computer is transferred to by bluetooth 2.0, is then shown in real time on screen.
Doctor calls corresponding signal handler in brain electricity analytical to carry out after-treatment to the signal of collection, obtains the spy of patient information
Value indicative, compares according to the relevant parameter of eigenvalue and sorter model.
Start virtual reality scenario stimulation programs.Brain after amplification, collection, pretreatment, to reading for the EEG signals
The signal of telecommunication carries out real-time decomposition, obtains different frequency composition, then known multi-source feature fusion technology is processed,
Finally show that one is directed to this individuality, the index parameter under emotion induction state that is eliminating uncertain factor, is used for carrying out
More accurate depression Risk Screening diagnosis.The design of virtual reality stimulation programs examination depression is from psychologic angle
On, for all ages and classes, different symptoms, the experimenter of different characters designs different types of stimulation protocol.In virtual reality thorn
Sharp exploitation aspect, to develop the game of virtual reality using the Unity3D of Unity Technologies company.Language function is strong
Big Unity3D can render the very strong three-dimensional scenic of sense of reality, is equipped with suitable background music, enabled the patient to body and faced
The sensation in its border, wherein interspersed special audio effect, more maximized can excite the emotional state of patient.
After starting virtual reality field stimulation programs, first each object is initialized, subsequently into virtual reality audiovisual letter
Breath emotion induction stimulating module, response system message, and the model in the induction stimulation of audio-visual information emotion is rendered, control
The carrying out that the induction of audio-visual information emotion stimulates.The concrete operations of virtual reality audio-visual information emotion induction are such：Work as startup
During this program, first give one section of sequential comfortable audiovisual fragment not carrying any emotional factor of 1 minute, collection patient's quiet period
EEG signals；After 1 minute, providing the three-dimensional audiovisual emotion induction of 3 minutes of one section of sequential stimulates fragment, and collection patient is luring at interval
EEG signals under heat not-ready status；Do not award within last five minutes any three-dimensional audiovisual fragment, patient is in convalescent brain for collection
The signal of telecommunication.Total duration 10 minutes.
The EEG signals of acquisition are processed by signal processing module, application wavelet transform is to the brain telecommunications collecting
Number carry out wavelet decomposition, obtain wavelet coefficient；Because eye electricity frequency is relatively low, so only doing specifically to the wavelet coefficient of low-frequency range
Threshold process, then carries out wavelet reconstruction to the wavelet coefficient after processing, thus extracting eye electricity reference signal；Finally, will
The eye electricity reference signal extracted, as the reference input of sef-adapting filter, untreated EEG signals is filtered as self adaptation
Being originally inputted of ripple device, the output of such system has just obtained the clean EEG signals after removing eye electrical noise.Obtain pure
EEG signals after after send into examination depression risk data analysis system, obtain patient eigenvalue and with existing number
Contrasted according to model parameter index, thus obtaining effective conclusion to supply doctor's reference.
During under virtual reality scenario, emotion induction stimulates, under system can store the EEG signals of patient automatically
Come, doctor can play back after patient finishes the process of whole depression Risk Screening scheme this EEG signals and be analyzed,
Print.
Step 1) in, including the step of virtual reality scenario exploitation, Fig. 4 is virtual reality scenario development process figure.
In the design, virtual reality scenario induction stimulates mainly using the focus point of the core of things and patient's heart as luring
The main foundation of heat sense, patient's heart understands the tendency of its attention to the point of interest list of certain part things, is designed with this,
It is mainly in view of：Mental activity rests on intensity or tensity on selected object, and it makes mental activity leave all no
The things closing, and suppresses unnecessary activity, and the maximized emotional state exciting patient is so that EEG signals characteristic reaction
Become apparent from.We by by emotion induce when the tendentiousness feature to things for the attention based on, for all ages and classes, different
Symptom, the dissimilar audiovisual diagnostic message with difficulty of experimenter's design of different characters.Require during sieving and diagnosis
Virgin trying one's best keeps attention to concentrate, and it requires and very strong captivation and body will be had to face child during audio-visual information examination depression
The sensation in its border is preferably to make examination.
After entering audio-visual information emotion induction system, first in initialization module, program each object (is related to
To Unity3D, acoustic processing, the initialization of input equipment etc.) initialized, then sequentially entering virtual reality scenario stimulates
Module, obtains input information and logic processing module, renders frame module and simultaneous display module, finally quit a program.
Virtual reality scenario stimulates initialization：This module is related to Unity3D, acoustic processing, input equipment etc.
Initialization.Mainly it is by some Memory Allocation, collection of resources, be loaded into data etc., audio-visual information emotion induction thorn from disk
Sharp preliminary examination flow process；
Enter virtual reality scenario stimulating module：In this module, this module is mainly response system message, and to audiovisual
The model of information is rendered.
Obtain input message and logical process：In the induction of this audio-visual information emotion stimulates, input message mostlys come from
The brain electricity threshold parameter message setting in depression Risk Screening scheme.The comparison of foundation and threshold point and be diagnosed as different
Crowd.
Render frame figure and display：The various models occurring in mainly the induction of audio-visual information emotion being stimulated render,
Control the carrying out that the induction of audio-visual information emotion stimulates.Figure shows process is：First remove lookaside buffer (invisible), then will
The object of display is plotted on this block memory field by certain logic, after having drawn, is turned on visible front relief area,
The picture refreshing rate of general audio-visual information emotion induction can reach 30 frames/second, and picture is overturn with this speed, adds eyes
Delay acts on, and so that the image seen is changed into continuously.
Step 2) in, the EEG signals of collection are the α ripple of subjectss' brain electricity, β ripple, δ ripple, θ ripple signal, each ripple of initial data
Section aliasing EEG signals together are the signals being collected by three electrodes of eeg signal acquisition system.Brain wave acquisition
When, electrode is placed on Fp1, FpZ and Fp2 is located at the position of forehead, will not be disturbed by hair, therefore can use medical plaster
Formula wet electrode, thus avoid the interference of electrode contact impedance.This design mainly adopts low energy-consumption electronic device to design, and transmission means adopts
Bluetooth 2.0, and it is furnished with power-supply management system, the state of power supply can be monitored.
δ ripple dominant response people in the state of deep sleep or has seriously organic disease of brain to suffer from；θ ripple mainly reflects at people
In sleep the initial stage, meditation state, sleepy when, emotion constrain when；α ripple mainly reflects that people is in clear-headed, quiet and closed-eye state；β
State when ripple mainly reflects that people is in psychentonia, excited or excited and thought active, attention are concentrated；This four kinds
Wave band will can reflect Analysis of Depression by crowd's by very accurate volume as main characteristic parameter with the energy ratio of high frequency β ripple
Information.
Step 3) in, including the step of EEG signals pretreatment, Fig. 5 is EEG signals pretreatment process figure.
Application wavelet transform first carries out wavelet decomposition to the EEG signals collecting, and obtains wavelet coefficient；Due to
The electric frequency of eye is relatively low, so only doing specific threshold process to the wavelet coefficient of low-frequency range, then to the wavelet systems after processing
Number carries out wavelet reconstruction, thus extracting eye electricity reference signal；Finally, the eye extracting electricity reference signal is filtered as self adaptation
The reference input of ripple device, using untreated EEG signals being originally inputted as sef-adapting filter, the output of such system is just
The clean EEG signals after removing eye electrical noise are obtained.
The real-time EEG Processing module of EEG signals pretreatment be by STM32F101 32 ARM microprocessor and
Its peripheral circuit is realized.Although analogue signal passes through analog filtering and processes, amplified by amplifier, adopted by A/D
The signal that collection is come in also has some to be disturbed and there are some physiology artifacts (for example：Electrocardio, eye electricity, myoelectricity etc.).In order to
Reduce and false judgment occurs in feedback procedure, need to carry out pretreatment to the signal of collection.We adopt WAVELET PACKET DECOMPOSITION, little
The technology such as ripple threshold value carry out real-time pretreatment to signal, to eliminate interference and physiology artifact further, for analyzing brain electricity further
Prepare with carrying out feature diagnosis.On-line analysis system midbrain electricity artifact can be met very well from suitable wavelet analysises to remove
Requirement.The application of particularly wavelet packet, so that domain space finely divides, is more beneficial for the removal of artifact and signal characteristic
Extract.It is proposed that the method to artifact signal subtraction can rapidly, effectively eliminate EEG signal eye move artifact, filter
Signal after ripple is more suitable for extracting EEG feature.Simultaneously for the requirement according to upper strata master computer to pretreated brain electricity number
Word signal carries out feature extraction using methods such as Kind of Nonlinear Dynamical System algorithms.These algorithms have arithmetic speed quickly,
The requirement of our real-time processings can be met.
Step 3) in, healthy population and depression risk population are differentiated using brand-new discriminant classification data model.Entirely
New discriminant classification data model is to be classified in systems according to different syndromes, the project " base planned according to national " 973 "
Potential depression Risk-warning theory and bio-sensing key technology research in biological, psychological multi-modal information " (project generation
Code：Latest data model 2014CB744600) tested and the concrete condition of sufferer, carry out corresponding feature selection, extraction,
Train suitable grader such that it is able to produce more reasonably physical signs parameter.There is abundant database resource, its
Data structure is simple, clear, has good data independence, level security, user is understandable easy-to-use, can enter with data with existing
Row cross validation, improves accuracy and the specific aim of sieving and diagnosis.
Step 3) in, including the step of discriminant classification model modeling, Fig. 6 is discriminant classification model modeling process flow diagram flow chart.
First pass through virtual reality scenario and labelled healthy population and depression risk population are carried out with emotion induction stimulation, then
The original EEG signals collecting are carried out Signal Pretreatment by wavelet packet analysis by collection EEG signals, then pass through non-thread
Property kinetic theory carries out feature extraction to the EEG signals after denoising, and the hybrid algorithm finally by CFS+KNN carries out feature
Select and tagsort, thus obtaining discriminant classification device model.
Accordingly, Fig. 7 is that depression risk analyses differentiate process flow diagram flow chart.Application class discrimination model carries out depression wind
The step of dangerous analysis and distinguishing process：By virtual reality scenario, unknown individual experimenter being carried out with emotion induction stimulates, and collection should
The EEG signals of individual subjects and by after the pretreatment module such as signal denoising by nonlinear dynamics theory to denoising
EEG signals afterwards carry out feature extraction, and the characteristic parameter extracting is sent into discriminant classification model thus immediately arriving at depression
Disease Risk Screening result.
Although having been presented for some embodiments of the present invention herein, it will be appreciated by those of skill in the art that
Without departing from the spirit of the invention, the embodiments herein can be changed.Above-described embodiment is exemplary, no
Should be using the embodiments herein as the restriction of interest field of the present invention.
Claims (11)
1. a kind of depression Risk Screening system based on virtual reality scenario EEG signals is it is characterised in that include virtual existing
Real induction system, eeg signal acquisition system, data analysis system；Described virtual reality induction system is used for setting up different void
Intend reality scene, described eeg signal acquisition system is used for gathering human brain generation continually varying under virtual reality scenario stimulation
EEG signals, the EEG signals after output process and the real-time characteristic information of extraction；Described data analysis system has by pasting
The discriminant classification model that the healthy population of label and depression risk population are trained out, for being swashed to virtual reality scenario
The characteristic information by formula person's EEG signals sent out carries out tagsort, and by required characteristic information in depression examination with pre-
The discriminant classification aspect of model parameter first training is compared, and distinguishes and differentiates healthy population and depression risk population, for suppression
Strongly fragrant disease Risk Screening provides objective basis.
2. depression Risk Screening system according to claim 1 is it is characterised in that described eeg signal acquisition system bag
Include EEG signals extraction module, real-time EEG Processing module；Described EEG signals extraction module is used for carrying of EEG signals
Take, put big and Filtering Processing, and the signal after processing is converted into digital signal through A/D and send into real-time EEG Processing mould
Block；Described real-time EEG Processing module be used for A/D conversion digital signal carry out pretreatment, further eliminate interference and
The noise that physiology artifact is brought.
3. depression Risk Screening system according to claim 1 and 2 is it is characterised in that the induction of described virtual reality is
System includes initialization module, virtual reality scenario stimulating module, acquisition input information and logic processing module, the wash with watercolours being sequentially connected
Dye frame module, simultaneous display module；Described initialization module is used for Unity3D, acoustic processing, input equipment initial
Change；Described virtual reality scenario stimulating module is used for response system message, and the model of audio-visual information is rendered；Described obtain
Input information and logic processing module is taken to be used for judging whether to reach message, in Message Processing pattern according to the electric index of the brain setting
Middle control virtual reality scenario stimulates, and the message obtaining is counted simultaneously, judges whether that switching virtual reality scene stimulates
Scheme；The described frame module that renders renders for the various models occurring during the induction of audio-visual information emotion is stimulated；Described
The object that simultaneous display module is used for showing is plotted in sightless lookaside buffer by certain logic, then is turned over
Go on visible front relief area, show the image of continuous pictures.
4. depression Risk Screening system according to claim 3 is it is characterised in that described data analysis system includes adopting
Collection module, off-line analysiss module, EEG signals after-treatment module, data analysis module, communication logic module；Described collection mould
Block collection is by the EEG signals through pretreatment come on communication logic module transfer and real-time characteristic packet；Described offline
Analysis module stores local hard drive to the EEG signals of acquisition module, can send into EEG signals after-treatment mould when there being demand
Block carries out the feature analysiss of time-frequency domain, possesses recurrence analytic function at any time, and fast searching specifies data；The data of acquisition module
EEG signals after-treatment module can be sent directly into, the data of real-time brain electric treatment module is further processed, disappears
Except the distorted signals in transmitting procedure；Described data analysis module, eliminates interference using the method for wavelet packet analysis and physiology is pseudo-
Difference simultaneously carries out feature extraction using nonlinear dynamics theory to the EEG signals after denoising, finally by the algorithm of CFS+KNN
Carry out feature selection and classification.
5. depression Risk Screening system according to claim 4 is it is characterised in that described data analysis system also includes
Management module, data base's support module, display module；Described management module is used for entering line pipe to examination process and subject information
Reason, including the establishment of subject information, inquiry, modification, deletes, and the selection of diagnosis examination scheme, arranges examination depression
Index required by scheme and the storage of form and data, real-time update simultaneously changes communication logic module database module
Content；Described data base's support module is used for storing the process of examination scheme, the information of subjectss and its sieving and diagnosis depression；
Described display module is used for Active electroencephalogram (EEG) and its situation of change of real-time display subjectss.
6. a kind of depression Risk Screening method based on virtual reality scenario EEG signals is it is characterised in that include following walking
Suddenly：
1) start virtual reality induction system, setting up virtual reality stimulates scene；
2) start eeg signal acquisition system, collection human brain is not there being the quiet period of any stimulation, in virtual reality scenario respectively
Stimulate continually varying EEG signals that are lower and occurring in emotion convalescent period；
3) Treatment Analysis are carried out to the EEG signals obtaining, by required characteristic information in the depression extracting examination and in advance
The discriminant classification aspect of model parameter first training is compared, and distinguishes and differentiates healthy population and depression risk population, for suppression
Strongly fragrant disease Risk Screening provides objective basis.
7. depression Risk Screening method according to claim 6 is it is characterised in that described step 1) in, including virtual
The step of reality scene exploitation：After entering audio-visual information emotion induction system, first to Unity3D in initialization module,
Acoustic processing, input equipment is initialized, and subsequently into virtual reality scenario stimulating module, carries out audio-visual information emotion induction
Stimulate, control virtual reality scenario to stimulate in obtaining input information and logic processing module, the message obtaining is carried out simultaneously
Count, judge whether that terminating virtual reality scenario stimulates, entrance renders frame module and simultaneous display module carries out next frame figure
Show as rendering simultaneously real-time synchronization, after audio-visual information induction stimulation finishes, quit a program.
8. the depression Risk Screening method according to claim 6 or 7 is it is characterised in that described step 2) in, collection
EEG signals are the electric α ripple of subjectss' brain, β ripple, δ ripple, θ ripple signal, initial data each wave band aliasing EEG signals together
It is to be collected by three electrodes of eeg signal acquisition system；Described electrode is placed on Fp1, FpZ and Fp2 is located at forehead
Position.
9. depression Risk Screening method according to claim 8 is it is characterised in that described step 3) in, including brain electricity
The step of Signal Pretreatment：Application wavelet transform first carries out wavelet decomposition to the EEG signals collecting, and obtains small echo
Coefficient；Specific threshold process is done to the wavelet coefficient of low-frequency range, then wavelet reconstruction is carried out to the wavelet coefficient after processing,
Thus extracting eye electricity reference signal；Finally, using the eye extracting electricity reference signal as sef-adapting filter reference input,
Using untreated EEG signals being originally inputted as sef-adapting filter, the output of such system has just obtained removal eye electricity and has made an uproar
Clean EEG signals after sound.
10. depression Risk Screening method according to claim 9 is it is characterised in that described step 3) in, including classification
The step of discrimination model modeling：First pass through virtual reality scenario labelled healthy population and depression risk population are entered
The induction of market thread stimulates, and then gathers EEG signals, carries out signal to the original EEG signals collecting by wavelet packet analysis
Then EEG signals after denoising are carried out feature extraction by nonlinear dynamics theory, finally by CFS+KNN by pretreatment
Hybrid algorithm carry out feature selection and tagsort, thus obtaining discriminant classification device model.
11. depression Risk Screening methods according to claim 10 are it is characterised in that described step 3) in, including suppression
The step that strongly fragrant disease risk analyses differentiate process：By virtual reality scenario, unknown individual experimenter being carried out with emotion induction stimulates,
Gather the EEG signals of this individual subjects and pass through nonlinear dynamics theory by after the pretreatment module such as signal denoising
Feature extraction is carried out to the EEG signals after denoising, the characteristic parameter extracting is sent into discriminant classification model thus drawing suppression
Strongly fragrant disease Risk Screening result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611141740.2A CN106407733A (en) | 2016-12-12 | 2016-12-12 | Depression risk screening system and method based on virtual reality scene electroencephalogram signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611141740.2A CN106407733A (en) | 2016-12-12 | 2016-12-12 | Depression risk screening system and method based on virtual reality scene electroencephalogram signal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106407733A true CN106407733A (en) | 2017-02-15 |
Family
ID=58084111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611141740.2A Pending CN106407733A (en) | 2016-12-12 | 2016-12-12 | Depression risk screening system and method based on virtual reality scene electroencephalogram signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407733A (en) |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107871537A (en) * | 2017-11-22 | 2018-04-03 | 山东师范大学 | A kind of Depression trend assessment device based on multi-modal feature, system |
| CN108281190A (en) * | 2018-02-07 | 2018-07-13 | 苏州中科先进技术研究院有限公司 | A kind of system and its rehabilitation householder method and device for rehabilitation auxiliary |
| CN108280120A (en) * | 2017-07-11 | 2018-07-13 | 厦门君沣信息科技有限公司 | Mental health early warning system and method based on association rule |
| CN108433721A (en) * | 2018-01-30 | 2018-08-24 | 浙江凡聚科技有限公司 | The training method and system of brain function network detection and regulation and control based on virtual reality |
| CN108652648A (en) * | 2018-03-16 | 2018-10-16 | 合肥数翼信息科技有限公司 | Depression monitoring device for depression of old people |
| CN109157231A (en) * | 2018-10-24 | 2019-01-08 | 阿呆科技（北京）有限公司 | Portable multi-channel Depression trend assessment system based on emotional distress task |
| CN109215804A (en) * | 2018-10-09 | 2019-01-15 | 华南理工大学 | Mental disorder assistant diagnosis system based on virtual reality technology and physio-parameter detection |
| CN109920498A (en) * | 2018-12-28 | 2019-06-21 | 清华大学 | Interpersonal relationships prediction technique based on mood brain electroresponse similitude |
| CN110013250A (en) * | 2019-04-30 | 2019-07-16 | 中南大学湘雅二医院 | A kind of multi-mode feature fusion prediction technique of depression suicide |
| CN110236572A (en) * | 2019-05-07 | 2019-09-17 | 平安科技（深圳）有限公司 | Depression forecasting system based on body temperature information |
| CN110265143A (en) * | 2019-06-18 | 2019-09-20 | 福州大学 | Intelligent auxiliary diagnosis system based on electroencephalogram |
| CN110287156A (en) * | 2019-06-28 | 2019-09-27 | 维沃移动通信有限公司 | Document handling method and mobile terminal |
| CN110292378A (en) * | 2019-07-02 | 2019-10-01 | 燕山大学 | Depression remote rehabilitation system based on the monitoring of E.E.G closed loop |
| CN110600127A (en) * | 2019-09-23 | 2019-12-20 | 上海市精神卫生中心（上海市心理咨询培训中心） | Video acquisition and analysis system and method for realizing cognitive disorder screening function by video excitation of facial expressions |
| CN110772699A (en) * | 2019-09-30 | 2020-02-11 | 浙江凡聚科技有限公司 | Attention training system for automatically adjusting heart rate variability based on virtual reality |
| CN111068159A (en) * | 2019-12-27 | 2020-04-28 | 兰州大学 | Music feedback depression mood adjusting system based on electroencephalogram signals |
| CN111447874A (en) * | 2017-10-03 | 2020-07-24 | 株式会社国际电气通信基础技术研究所 | Determination device, method for determining depression symptom, method for determining level of depression symptom, method for classifying depression patient, method for determining treatment effect of depression symptom, and brain activity training device |
| CN111462841A (en) * | 2020-03-12 | 2020-07-28 | 华南理工大学 | Depression intelligent diagnosis device and system based on knowledge graph |
| CN111920408A (en) * | 2020-08-11 | 2020-11-13 | 深圳大学 | Signal analysis method and component of electroencephalogram nerve feedback system combined with virtual reality |
| CN112037911A (en) * | 2020-08-28 | 2020-12-04 | 北京万灵盘古科技有限公司 | Machine learning-based mental assessment screening system and training method thereof |
| CN112190269A (en) * | 2020-12-04 | 2021-01-08 | 兰州大学 | Construction method of depression auxiliary identification model based on multi-source electroencephalogram data fusion |
| CN112445343A (en) * | 2021-01-27 | 2021-03-05 | 博睿康科技（常州）股份有限公司 | Electroencephalogram device, system, computer device, and storage medium |
| CN112545513A (en) * | 2020-12-04 | 2021-03-26 | 长春理工大学 | Music-induced electroencephalogram-based depression identification method |
| CN113397563A (en) * | 2021-07-22 | 2021-09-17 | 北京脑陆科技有限公司 | Training method, device, terminal and medium for depression classification model |
| CN114169366A (en) * | 2021-11-19 | 2022-03-11 | 北京师范大学 | Neurofeedback training system and method |
| CN114224341A (en) * | 2021-12-02 | 2022-03-25 | 浙大宁波理工学院 | Wearable forehead electroencephalogram-based depression rapid diagnosis and screening system and method |
| CN115363585A (en) * | 2022-09-04 | 2022-11-22 | 北京中科心研科技有限公司 | Standardized group depression risk screening system and method based on habituation removal and film watching tasks |
| CN115670463A (en) * | 2022-10-26 | 2023-02-03 | 华南理工大学 | Depression detection system based on electroencephalogram emotional nerve feedback signals |
| CN116301473A (en) * | 2023-01-19 | 2023-06-23 | 佛山创视嘉科技有限公司 | User behavior prediction method, device, equipment and medium based on virtual reality |
| CN116304642A (en) * | 2023-05-18 | 2023-06-23 | 中国第一汽车股份有限公司 | Emotion recognition early warning and model training method, device, equipment and storage medium |
| CN116570835A (en) * | 2023-07-12 | 2023-08-11 | 杭州般意科技有限公司 | Method for determining intervention stimulation mode based on scene and user state |
| CN117637117A (en) * | 2024-01-27 | 2024-03-01 | 南京元域绿洲科技有限公司 | Virtual reality training system for depressive disorder |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1833616A (en) * | 2005-12-15 | 2006-09-20 | 西安交通大学 | Multi-conduction brain biological information feedback instrument |
| CN102715903A (en) * | 2012-07-09 | 2012-10-10 | 天津市人民医院 | Method for extracting electroencephalogram characteristic based on quantitative electroencephalogram |
| CN204931634U (en) * | 2015-07-30 | 2016-01-06 | 华南理工大学 | Based on the depression evaluating system of physiologic information |
| CN105342569A (en) * | 2015-11-25 | 2016-02-24 | 新乡医学院 | Mental state detection system based on electroencephalogram analysis |
-
2016
- 2016-12-12 CN CN201611141740.2A patent/CN106407733A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1833616A (en) * | 2005-12-15 | 2006-09-20 | 西安交通大学 | Multi-conduction brain biological information feedback instrument |
| CN102715903A (en) * | 2012-07-09 | 2012-10-10 | 天津市人民医院 | Method for extracting electroencephalogram characteristic based on quantitative electroencephalogram |
| CN204931634U (en) * | 2015-07-30 | 2016-01-06 | 华南理工大学 | Based on the depression evaluating system of physiologic information |
| CN105342569A (en) * | 2015-11-25 | 2016-02-24 | 新乡医学院 | Mental state detection system based on electroencephalogram analysis |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280120A (en) * | 2017-07-11 | 2018-07-13 | 厦门君沣信息科技有限公司 | Mental health early warning system and method based on association rule |
| CN111447874A (en) * | 2017-10-03 | 2020-07-24 | 株式会社国际电气通信基础技术研究所 | Determination device, method for determining depression symptom, method for determining level of depression symptom, method for classifying depression patient, method for determining treatment effect of depression symptom, and brain activity training device |
| US12020427B2 (en) | 2017-10-03 | 2024-06-25 | Advanced Telecommunications Research Institute International | Differentiation device, differentiation method for depression symptoms, determination method for level of depression symptoms, stratification method for depression patients, determination method for effects of treatment of depression symptoms, and brain activity training device |
| CN107871537A (en) * | 2017-11-22 | 2018-04-03 | 山东师范大学 | A kind of Depression trend assessment device based on multi-modal feature, system |
| CN108433721A (en) * | 2018-01-30 | 2018-08-24 | 浙江凡聚科技有限公司 | The training method and system of brain function network detection and regulation and control based on virtual reality |
| CN108281190A (en) * | 2018-02-07 | 2018-07-13 | 苏州中科先进技术研究院有限公司 | A kind of system and its rehabilitation householder method and device for rehabilitation auxiliary |
| CN108652648A (en) * | 2018-03-16 | 2018-10-16 | 合肥数翼信息科技有限公司 | Depression monitoring device for depression of old people |
| CN109215804B (en) * | 2018-10-09 | 2023-10-31 | 华南理工大学 | Mental disease auxiliary diagnosis system based on virtual reality technology and physiological parameter detection |
| CN109215804A (en) * | 2018-10-09 | 2019-01-15 | 华南理工大学 | Mental disorder assistant diagnosis system based on virtual reality technology and physio-parameter detection |
| CN109157231B (en) * | 2018-10-24 | 2021-04-16 | 阿呆科技（北京）有限公司 | Portable multichannel depression tendency evaluation system based on emotional stimulation task |
| CN109157231A (en) * | 2018-10-24 | 2019-01-08 | 阿呆科技（北京）有限公司 | Portable multi-channel Depression trend assessment system based on emotional distress task |
| CN109920498A (en) * | 2018-12-28 | 2019-06-21 | 清华大学 | Interpersonal relationships prediction technique based on mood brain electroresponse similitude |
| CN110013250A (en) * | 2019-04-30 | 2019-07-16 | 中南大学湘雅二医院 | A kind of multi-mode feature fusion prediction technique of depression suicide |
| CN110236572A (en) * | 2019-05-07 | 2019-09-17 | 平安科技（深圳）有限公司 | Depression forecasting system based on body temperature information |
| CN110265143A (en) * | 2019-06-18 | 2019-09-20 | 福州大学 | Intelligent auxiliary diagnosis system based on electroencephalogram |
| CN110265143B (en) * | 2019-06-18 | 2022-05-13 | 福州大学 | Intelligent auxiliary diagnosis system based on electroencephalogram |
| CN110287156A (en) * | 2019-06-28 | 2019-09-27 | 维沃移动通信有限公司 | Document handling method and mobile terminal |
| CN110292378B (en) * | 2019-07-02 | 2021-02-23 | 燕山大学 | Depression remote rehabilitation system based on brain wave closed-loop monitoring |
| CN110292378A (en) * | 2019-07-02 | 2019-10-01 | 燕山大学 | Depression remote rehabilitation system based on the monitoring of E.E.G closed loop |
| CN110600127A (en) * | 2019-09-23 | 2019-12-20 | 上海市精神卫生中心（上海市心理咨询培训中心） | Video acquisition and analysis system and method for realizing cognitive disorder screening function by video excitation of facial expressions |
| CN110772699A (en) * | 2019-09-30 | 2020-02-11 | 浙江凡聚科技有限公司 | Attention training system for automatically adjusting heart rate variability based on virtual reality |
| CN111068159A (en) * | 2019-12-27 | 2020-04-28 | 兰州大学 | Music feedback depression mood adjusting system based on electroencephalogram signals |
| CN111462841A (en) * | 2020-03-12 | 2020-07-28 | 华南理工大学 | Depression intelligent diagnosis device and system based on knowledge graph |
| CN111920408A (en) * | 2020-08-11 | 2020-11-13 | 深圳大学 | Signal analysis method and component of electroencephalogram nerve feedback system combined with virtual reality |
| CN111920408B (en) * | 2020-08-11 | 2023-04-07 | 深圳大学 | Signal analysis method and component of electroencephalogram nerve feedback system combined with virtual reality |
| CN112037911A (en) * | 2020-08-28 | 2020-12-04 | 北京万灵盘古科技有限公司 | Machine learning-based mental assessment screening system and training method thereof |
| CN112037911B (en) * | 2020-08-28 | 2024-03-05 | 北京万灵盘古科技有限公司 | Screening system for mental assessment based on machine learning and training method thereof |
| CN112190269A (en) * | 2020-12-04 | 2021-01-08 | 兰州大学 | Construction method of depression auxiliary identification model based on multi-source electroencephalogram data fusion |
| CN112545513A (en) * | 2020-12-04 | 2021-03-26 | 长春理工大学 | Music-induced electroencephalogram-based depression identification method |
| CN112190269B (en) * | 2020-12-04 | 2024-03-12 | 兰州大学 | Depression auxiliary identification model construction method based on multisource brain electric data fusion |
| CN112445343A (en) * | 2021-01-27 | 2021-03-05 | 博睿康科技（常州）股份有限公司 | Electroencephalogram device, system, computer device, and storage medium |
| WO2022160557A1 (en) * | 2021-01-27 | 2022-08-04 | 博睿康科技（常州）股份有限公司 | Electroencephalograph device and system, computer device, and storage medium |
| US12029904B2 (en) | 2021-01-27 | 2024-07-09 | Neuracle Technology (Changzhou) Co., Ltd. | Electroencephalograph device and system, computer device, and storage medium |
| CN113397563A (en) * | 2021-07-22 | 2021-09-17 | 北京脑陆科技有限公司 | Training method, device, terminal and medium for depression classification model |
| CN114169366A (en) * | 2021-11-19 | 2022-03-11 | 北京师范大学 | Neurofeedback training system and method |
| CN114169366B (en) * | 2021-11-19 | 2023-10-20 | 北京师范大学 | Neural feedback training system and method |
| CN114224341B (en) * | 2021-12-02 | 2023-12-15 | 浙大宁波理工学院 | Wearable forehead electroencephalogram-based depression rapid diagnosis and screening system and method |
| CN114224341A (en) * | 2021-12-02 | 2022-03-25 | 浙大宁波理工学院 | Wearable forehead electroencephalogram-based depression rapid diagnosis and screening system and method |
| CN115363585B (en) * | 2022-09-04 | 2023-05-23 | 北京中科心研科技有限公司 | Standardized group depression risk screening system and method based on habit removal and film watching tasks |
| CN115363585A (en) * | 2022-09-04 | 2022-11-22 | 北京中科心研科技有限公司 | Standardized group depression risk screening system and method based on habituation removal and film watching tasks |
| CN115670463A (en) * | 2022-10-26 | 2023-02-03 | 华南理工大学 | Depression detection system based on electroencephalogram emotional nerve feedback signals |
| CN116301473A (en) * | 2023-01-19 | 2023-06-23 | 佛山创视嘉科技有限公司 | User behavior prediction method, device, equipment and medium based on virtual reality |
| CN116304642A (en) * | 2023-05-18 | 2023-06-23 | 中国第一汽车股份有限公司 | Emotion recognition early warning and model training method, device, equipment and storage medium |
| CN116304642B (en) * | 2023-05-18 | 2023-08-18 | 中国第一汽车股份有限公司 | Emotion recognition early warning and model training method, device, equipment and storage medium |
| CN116570835A (en) * | 2023-07-12 | 2023-08-11 | 杭州般意科技有限公司 | Method for determining intervention stimulation mode based on scene and user state |
| CN117637117A (en) * | 2024-01-27 | 2024-03-01 | 南京元域绿洲科技有限公司 | Virtual reality training system for depressive disorder |
| CN117637117B (en) * | 2024-01-27 | 2024-04-02 | 南京元域绿洲科技有限公司 | Virtual reality training system for depressive disorder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407733A (en) | Depression risk screening system and method based on virtual reality scene electroencephalogram signal | |
| Zhang et al. | A survey on deep learning-based non-invasive brain signals: recent advances and new frontiers | |
| CN106725462B (en) | Acousto-optic Sleep intervention system and method based on EEG signals | |
| CN110765920B (en) | Motor imagery classification method based on convolutional neural network | |
| Li et al. | Sensitivity analysis of changes in human physiological indicators observed in soundscapes | |
| CN107024987B (en) | Real-time human brain attention testing and training system based on EEG | |
| CN104902806B (en) | The assessment system and method for europathology | |
| Greco et al. | Advances in electrodermal activity processing with applications for mental health | |
| CN109224242B (en) | Psychological relaxation system and method based on VR interaction | |
| Miller et al. | Rapid online language mapping with electrocorticography | |
| Zhang et al. | Real-time mental stress detection using multimodality expressions with a deep learning framework | |
| CN107644682A (en) | Mood regulation ability based on frontal lobe EEG lateralities and ERP checks and examine method | |
| CN108335728A (en) | A kind of name of calling out for disturbance of consciousness patient promotees system of waking up | |
| WO2024083059A1 (en) | Working memory task magnetoencephalography classification system based on machine learning | |
| CN108721048A (en) | Rehabilitation training control method, computer readable storage medium and terminal | |
| CN112951449A (en) | Cloud AI (artificial intelligence) regulation diagnosis and treatment system and method for neurological dysfunction diseases | |
| CN106901727A (en) | A kind of depression Risk Screening device based on EEG signals | |
| Pavlov et al. | Recognition of electroencephalographic patterns related to human movements or mental intentions with multiresolution analysis | |
| CN109102862A (en) | Concentrate the mind on breathing depressurized system and method, storage medium, operating system | |
| CN104367306A (en) | Physiological and psychological career evaluation system and implementation method | |
| Li et al. | Multi-modal emotion recognition based on deep learning of EEG and audio signals | |
| Bastos-Filho | Introduction to non-invasive EEG-Based brain-computer interfaces for assistive technologies | |
| Kawala-Janik | Efficiency evaluation of external environments control using bio-signals | |
| Smith | Electroencephalograph based brain computer interfaces | |
| CN117281479A (en) | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |
|
| RJ01 | Rejection of invention patent application after publication |