CN106175757A - Behaviour decision making prognoses system based on brain wave - Google Patents
Behaviour decision making prognoses system based on brain wave Download PDFInfo
- Publication number
- CN106175757A CN106175757A CN201610552350.8A CN201610552350A CN106175757A CN 106175757 A CN106175757 A CN 106175757A CN 201610552350 A CN201610552350 A CN 201610552350A CN 106175757 A CN106175757 A CN 106175757A
- Authority
- CN
- China
- Prior art keywords
- eeg
- making
- decision
- data
- brain
- 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
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Psychiatry (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychology (AREA)
- Power Engineering (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of behaviour decision making prognoses system based on brain wave, including eeg signal acquisition portion, EEG Processing analysis portion, Tactic selection differentiation portion and prognoses system portion, described signal acquisition part is provided with wearable device and eeg amplifier, obtains original eeg data by wearable device and eeg amplifier；EEG Processing analysis portion is overlapped average treatment to EEG signals；Tactic selection differentiation portion, by the process respectively of different decision-making EEG signals and set up EEG signals data warehouse, carries out time and frequency domain analysis afterwards and sets up the differentiation quantization method of behaviour decision making EEG signals handled data；Prognoses system portion sets up detailed forecast model according to the differentiating method that quantifies set up and provides concrete computation model, to the Forecasting Methodology test prediction effect set up the accuracy rate counting prediction.Technique scheme, this system can be that behaviour decision making is effectively predicted according to eeg signal.
Description
Technical field
The present invention relates to brain science decision-making technic field, being specifically related to the prediction of a kind of behaviour decision making based on brain wave is
System.
Background technology
Brain wave be brain when activity, the postsynaptic potential that a large amount of neurons synchronize to occur is formed after summation.It
Electric wave change during record cerebral activity, is overall anti-in cerebral cortex or scalp surface of the bioelectrical activity of cranial nerve cell
Should.Brain wave derives from the postsynaptic potential of pyramidal cell top dendron, synchronize the formation of the rhythm and pace of moving things also with cortex thalamic nonspecific
The activity of property projection system is relevant.What electroencephalogram was cranial nerve cell bioelectrical activity in cerebral cortex or scalp surface is overall anti-
Should.Generally electroencephalogram (Electroencephalograph, the EEG) detection of indication is by being placed on head according to certain rule
Electrode on skin observes the process of brainwave activity.EEG brain wave not only kind is many but also changes various, various different feelings
Thread, phychology all can affect the change of brain wave.EEG is the overall activity of cranial nerve cell, including ion exchange, metabolism etc.
Comprehensive outward manifestation, the exploration of self brain is carried out by the feature in depth studying brain wave by propelling people, strengthens it to row
Detection and predictive ability for decision-making.
Behaviour decision making is the science of research people's Behavior law in decision making process, at present in west, this
Section is the most in the ascendant.Its purposes is quite extensive, not only facilitates individual and makes the decision-making of rationality, more can be in business administration, political affairs
The aspects such as plan formulation play positive obvious action.
In behaviour decision making and Cognitive Study, Evoked ptential is one of current Main Means.As far back as nineteen forty-seven Pawson
First proposed the concept of Evoked ptential, Jewett in 1971 et al. reports the fact that relevant brainstem auditory evoked responds.80 years
The research that generation plays Evoked ptential is the most popular.Because the specificity of Evoked ptential, i.e. its pertinence with particular stimulation and with
The specific close ties feeling loop so that it carries the more information about brain structure and function.Therefore electricity is induced
Position has the highest Research Significance.The research method of the ERPs that nineteen sixty-five Sutton is pioneering, finds event-related potential N400；
Within 1980, Kutas is found that N400.Research thinks that the Electrophysiology of ERPs reaction cognitive process deutocerebrum changes, and therefore has people
Being referred to as again cognitive potential, meaning is when people carries out Cognitive Processing to certain objective things, by superposed average method from head
The brain potential that surface recording is arrived.Event related potential merges the psychology of the neuro physiology of brain with cognitive process to get up,
ERP is made to become the most important information source in understanding cognition neural basis.
With losing, William in 2002 et al. must find that medial prefrontal region be brain the research mankind in economic behaviour
The major part of participative decision making, and the mankind must from lose when show the most different in this region.2010
Fabrizio et al. records, by Game Experiments, the EEG that participant cooperates or betrays, and sets up detailed model by the back of the body
The EEG betrayed or cooperate carries out classifying and strategy to participant can carry out a prediction before decision-making.
Although behaviour decision making aspect based on brain wave makes great progress, but still there is also many imperfections it
Place, the row that seldom advances decision-making after such as the differentiation to decision-making essentially consists in decision-making is distinguished, it was predicted that accuracy rate also need to be carried
Rise.Additionally there are spatial resolution relatively low, signal disturbing is too many, and the precision of collecting device need the problems such as raising.
Summary of the invention
The deficiency existed for prior art, it is an object of the invention to provide one and can effectively analyze people and exist
Carry out the EEG signal feature before different decision-makings, and to people's EEG signal reductive analysis before different decision-makings, and can root
The behaviour decision making prognoses system based on the brain wave selection of decision-making being predicted according to the EEG signals before decision-making.
For achieving the above object, the technical scheme is that a kind of behaviour decision making based on brain wave is predicted
System, including eeg signal acquisition portion, EEG Processing analysis portion, Tactic selection differentiation portion and prognoses system portion, described brain
Interconnect between electrical signal collection portion, EEG Processing analysis portion, Tactic selection differentiation portion and prognoses system portion, described letter
Number collection portion is provided with wearable device and eeg amplifier, obtains original eeg data by wearable device and eeg amplifier；
EEG Processing analysis portion is overlapped average treatment to EEG signals；Tactic selection differentiation portion is by different decision-making brain electricity
The process respectively of signal also sets up EEG signals data warehouse, afterwards handled data is carried out time and frequency domain analysis and builds
The differentiation quantization method of vertical behaviour decision making EEG signals；Prognoses system portion sets up detailed according to the differentiating method that quantifies set up
Forecast model also provides concrete computation model, the Forecasting Methodology set up is tested prediction effect and counts the accurate of prediction
Rate.
By using technique scheme, it is possible to effectively analyze people's EEG signal before carrying out different decision-makings
Feature, and to people's EEG signal reductive analysis before different decision-makings, and can be according to the EEG signals before decision-making to decision-making
Selection is predicted.
Behaviour decision making prediction comprises the following steps:
(1) original EEG signals is obtained: with eeg amplifier and combine Experiment of Psychology software and carry out decision-making choosing to tested
Selecting stimulation and obtain original EEG signals, sample frequency is 1KHz；The brain electricity sample gathered, record is by whole before and after envoy's decision-making
Process continuous print eeg data；Gather different sexes, all ages and classes layer, the data of experimenter, set up decision-making eeg data storehouse
Storehouse；
(2) method using superposed average is overlapped average treatment to the brain wave before the original brain electricity decision-making of collection,
Eeg data after processing is used time domain approach and frequency domain method analysis, carries out characteristic parameter extraction, feature ginseng to be extracted
Number includes time domain parameter and frequency domain parameter；
(3) eeg data before selecting different decision-making is classified, for have selected the eeg data of different decision-making
It is respectively processed, and extracts time domain parameter therein and frequency domain parameter respectively；The characteristic parameter extracted is analyzed place
Reason, is desirably to obtain and can be reflected in the method selecting different decision-making forebrain electricity data differences；Use statistical method, in a large number
Under the checking of sample set, it is determined to reflect the quantization method of different decision-making forebrain electricity data target.
(4) according to the quantization method that can reflect different decision-making forebrain electricity data target obtained to the unknown result of decision before
Eeg data be predicted test, and obtain predicting successful probability.
As preferably, described eeg amplifier is that NeuroScan40 leads eeg amplifier.
As preferably, described wearable device is electrode cap.
As preferably, tested Tactic selection is stimulated and uses Experiment of Psychology software E-prime.
The invention have the advantage that the present invention uses NeuroScan40 lead eeg amplifier and combine E-prime psychology in fact
Test software carry out policy selection stimulation to tested and obtain original EEG signals, so can obtain tested certainly more accurately
Eeg data before and after plan and can indicating according to the code that E-prime Experiment of Psychology software is transmitted through be overlapped average
Process.The tested eeg data of different sexes, all ages and classes can be overlapped averagely, and before extracting different decision-making
Time domain parameter and frequency domain parameter；According to being analyzed the characteristic parameter extracted and under the checking of great amount of samples set, it is possible to relatively
For accurately tested result before decision-making to decision-making being carried out a prediction.
Below in conjunction with Figure of description and specific embodiment, the invention will be further described.
Accompanying drawing explanation
Fig. 1 is that embodiment of the present invention brain electricity behaviour decision making predicts flow chart；
Fig. 2 is embodiment of the present invention eeg signal acquisition flow chart；
Fig. 3 is embodiment of the present invention signal processing analysis flow chart；
Fig. 4 is that flow chart is distinguished in embodiment of the present invention decision-making；
Fig. 5 is that the present invention implements prognoses system schematic diagram.
Detailed description of the invention
Seeing Fig. 1 to Fig. 5, a kind of behaviour decision making prognoses system based on brain wave disclosed by the invention, including brain telecommunications
Number collection portion, EEG Processing analysis portion, Tactic selection differentiation portion and prognoses system portion, described eeg signal acquisition portion, brain
Interconnecting between Electric signal processing analysis portion, Tactic selection differentiation portion and prognoses system portion, described signal acquisition part is provided with
Wearable device and eeg amplifier, obtain original eeg data by wearable device and eeg amplifier；EEG Processing is divided
Analysis portion is overlapped average treatment to EEG signals；Tactic selection differentiation portion is by the process respectively to different decision-making EEG signals
And set up EEG signals data warehouse, afterwards handled data are carried out time and frequency domain analysis and sets up behaviour decision making brain electricity
The differentiation quantization method of signal；Prognoses system portion sets up detailed forecast model according to the differentiating method that quantifies set up and is given
Concrete computation model, to the Forecasting Methodology test prediction effect set up the accuracy rate counting prediction.
As preferably, described eeg signal acquisition portion, EEG Processing analysis portion, Tactic selection differentiation portion and prediction
Existing screw or the connector such as wire or data wire is used to interconnect between Account Dept.
Behaviour decision making prediction comprises the following steps:
(1) original EEG signals is obtained: with eeg amplifier and combine Experiment of Psychology software and carry out decision-making choosing to tested
Selecting stimulation and obtain original EEG signals, sample frequency is 1KHz；The brain electricity sample gathered, record is by whole before and after envoy's decision-making
Process continuous print eeg data；Gather different sexes, all ages and classes layer, the data of experimenter, set up decision-making eeg data storehouse
Storehouse；
(2) method using superposed average is overlapped average treatment to the brain wave before the original brain electricity decision-making of collection,
Eeg data after processing is used time domain approach and frequency domain method analysis, carries out characteristic parameter extraction, feature ginseng to be extracted
Number includes time domain parameter and frequency domain parameter；
(3) eeg data before selecting different decision-making is classified, for have selected the eeg data of different decision-making
It is respectively processed, and extracts time domain parameter therein and frequency domain parameter respectively；The characteristic parameter extracted is analyzed place
Reason, is desirably to obtain and can be reflected in the method selecting different decision-making forebrain electricity data differences；Use statistical method, in a large number
Under the checking of sample set, it is determined to reflect the quantization method of different decision-making forebrain electricity data target.
(4) according to the quantization method that can reflect different decision-making forebrain electricity data target obtained to the unknown result of decision before
Eeg data be predicted test, and obtain predicting successful probability.
As preferably, described eeg amplifier is that existing NeuroScan40 leads eeg amplifier.
As preferably, described wearable device is existing electrode cap.
As preferably, Experiment of Psychology software uses existing Experiment of Psychology software E-prime.Experiment of Psychology is soft
Part E-prime is mainly used to stimulate tested policy selection, say, which type of strategy of tested selection is at the heart
Complete on experiment software E-prime of science.
As preferably, EEG Processing analysis part uses existing brain wave to analyze software Curry7 to brain telecommunications
Number it is overlapped a series of process such as average treatment.
The detailed process of the collection of EEG signals is, the most tested electrode cap of wearing, electrode cap for have about some right
The electrode composition claimed, contacts tested left brain and right brain respectively when wearing；Electrode cap connects NeuroScan40 and leads eeg amplifier
And led by each in electrode cap and to squeeze into conductive paste and make impedance drop to suitable numerical value, now can pass through Curry7 software
Can be with each impedance led of Real time displaying；Experiment of Psychology software E-prime writes for stimulating tested strategy choosing
Select program and can pass to indicating code in Curry7 software tested making a choice when.The process gathered is tested
Carrying out policy selection according to the prompting in E-prime software, carry out mousebutton selecting when now can be by E-simultaneously
The selection that prime makes indicates code and passes in Curry7, is making according to E-prime prompting with Curry7 software records is tested
Eeg datas whole before and after decision-making.
EEG Processing analysis includes baseline correction, removal eye electricity and artefact, brain electricity segmentation superposed average, filters and select
Select reference electrode, as shown in Figure 3.
The detailed process of signal processing analysis is, first obtains the initial data gathering EEG signals.Original to obtain
First data carry out baseline correction, and the method for baseline correction is selection " constant " in baseline type, can be to brain wave
Shape carries out the baseline of baseline correction, i.e. waveform " X-axis " corresponding with label and overlaps.Before baseline correction brain wave patterns baseline not and
Label is corresponding and amplitude is very big, and amplitude of much leading is more than 1000uv, arranges that rear brain wave patterns baseline is corresponding with label and amplitude
Within 100uv.
Next it is removed eye electricity and artefact processes, for 40 data led to carrying out baseline correction data
Channel selects the difference (nictation) subtracted each other of<VEOL-U>the most vertical eye electricity VEOL and VEOU, eye electricity may be on the occasion of be likely to for
Negative value carries out suitable adjustment according to real data, makes the absolute value of difference up and down of selection as far as possible less than minimum secondary value nictation
Absolute value, and select the covariance method to remove the impact on data of the eye electricity；The removal of artefact we select automatically select, generally we
Brain electricity amplitude exceed ± 100uv is considered artefact, this scope can also be adjusted by we certainly, and then software can be from
Dynamic identifying exceedes the artefact of this scope and is removed.
The human brain lived always constantly electric discharge, becomes brain electricity (EEG), but complicated component and irregular.Normal spontaneous brain electricity
It is typically in a few microvolt between 75 microvolts.And more weak than spontaneous brain electricity by the brain electricity caused by mental activity, general only have 2 to arrive
10 microvolts, can often drown out in spontaneous potential.So ERP needs to extract from EEG.Event related potential has two important spies
Property: incubation period is constant, waveform is constant；On the other hand, spontaneous brain electricity is then change at random.So can by same facts repeatedly
The multistage eeg recording caused gets off, but each section of brain electricity is all the comprehensive of various composition, including spontaneous brain electricity.
Brain electricity segmentation superposed average is that the multistage brain electricity caused by identical stimulation is carried out multiple stacking, due to spontaneous brain electricity
Be change at random, have height to have low, arise that when being overlapped mutually the situation of positive and negative counteracting, ERP signal then have two constant, institute
Being cancelled, its wave amplitude can be continuously increased on the contrary, when be added to certain number of times time, ERP signal just displays.Superposition
ERP wave amplitude after n time increases n times, so that again divided by n, make ERP resile, is i.e. reduced to the ERP number once stimulated
Value.So ERP is also referred to as average evoked potential, averagely refer to after superposition is average.Thus obtain the desired time
Related potential oscillogram.
Finally being filtered data and with reference to the setting selected, filtering is generally selected User Defined (Auto), also
Different filtering modes can be suitably selected according to research direction.It is typically chosen the filtering of low pass 30Hz；The selection of reference can root
According to the study content select different reference electrode, typically have bilateral mastoid process to make reference, full head averagely makes reference.In the present invention
Select averagely makees reference for full head.
Tactic selection is distinguished and is included that different decision-making computer signal processes respectively, sets up data warehouse, time-domain analysis and frequency domain
Analyze and quantify differentiating method, as shown in Figure 4.
The detailed process that Tactic selection is distinguished is, the method being first according in EEG Processing analysis 2 is to selecting difference
The EEG signals of decision-making is respectively processed, and the EEG signals before selecting same decision-making is carried out segmentation superposed average process.Example
As, in an experiment having two policy selection, tested can select A or B, before all selection strategy A one section is entered
Row superposed average processes, and is also carried out same process during for selection strategy B.Different sexes, all ages and classes tested
The eeg data that have selected same strategy is overlapped average treatment, and sets up brain electricity policy selection data warehouse.
The discovery when brain electricity policy selection data warehouse carries out time and frequency domain analysis, for have selected Different Strategies
Behavior eeg data before policy selection has bigger difference, therefore can set up the strategy distinguishing quantization method to selecting
It is predicted.Prefrontal lobe region is the major part that brain carries out decision-making, controls the social behavior of individuality, emotion, and decision-making
Behavior.The Fz in the electrode for eeg signal acquisition in the present invention leads and is mainly used in gathering the brain electricity in prefrontal lobe region
By the electroencephalogramsignal signal analyzing at place of leading Fz, signal, finds that the EEG signals for selecting Different Strategies is before making a policy
There is bigger difference in 100ms, be mainly manifested on voltage swing and have obvious difference.
For this, we can set up the differentiation quantization method of behaviour decision making EEG signals, according to brain electricity policy selection data bins
Data in storehouse to select same policy EEG signals be overlapped average treatment, these EEG signals from different sexes,
All ages and classes tested.Before Fz leads place's trade-off decision in 100ms the magnitude of voltage of brain wave as the amount of a certain specific decision-making
Change standard.
Prognoses system includes forecast model, tests prediction effect and actuarial prediction accuracy rate, as shown in Figure 5.
According to the differentiation quantization method of the behaviour decision making EEG signals that we set up, detailed forecast model can be set up.
The magnitude of voltage of the brain wave having been set up in 100ms before Fz leads decision-making due to us is as the quantization of a certain specific decision-making
Standard, so we can be carried out score with the quantitative criteria of specific decision-making EEG signals according to the unknown EEG signals of decision-making
Analysis, with the EEG signals of which specific decision-making closer to then predicting that unknown decision-making will be for this specific decision-making.
Such as, in the experiment having three trade-off decisions, we establish the differentiation quantization side of behaviour decision making EEG signals
Method, draws decision-making A respectively, the magnitude of voltage of B, C each time point brain wave in 100ms before Fz leads and with this to predict the unknown
Decision-making would is that A, tri-kinds of decision-makings of B, C any.Use Mi(A) (-100≤i≤-1) represents that decision-making A makes certainly at the Fz place of leading
The magnitude of voltage of special time in 100ms before plan, and in this, as the quantitative criteria predicted whether as decision-making A.Same decision-making B, plan
Slightly C is also such.For unknown decision-making N, first it is understood that this decision-making will be A, a certain kind in B, C decision-making, in advance
Survey unknown decision-making N by for which kind of decision-making then also according to unknown decision-making N before the Fz place of leading makes a policy the magnitude of voltage of 100ms with
The decision-making A set up, the quantitative criteria of B, C is any closer to judge will be as which kind of decision-making.Concrete grammar is for obtain not respectively
Knowing decision-making N and decision-making A, the absolute value of B, C each millisecond of voltage in 100ms before decision-making is also sued for peace, then unknown decision-making N with
Value that any decision-making is tried to achieve minimum then think the unknown brain wave of decision-making N and the brain wave of this decision-making closer to, and to the unknown
Decision-making N is predicted as this decision-making, it may be assumed that
Wherein DA(N),DB(N),DC(N) representing unknown decision-making N and decision-making A respectively, the degree of closeness of B, C, value is the least to be shown
The EEG signals of the EEG signals of unknown decision-making and wherein decision-making closer to because decision-making N will be for decision-making A, in B, C
Kind, then DA(N),DB(N),DC(N) result for forecast and decision that intermediate value is minimum.This judged result can be as predicting tested choosing
Select a foundation of which kind of strategy.Such as at DA(N),DB(N),DC(N) D inB(N) the most measurable unknown decision-making N of value minimum is
Decision-making B.
The random tested decision-making made to different sexes, all ages and classes carries out the effect of test prediction, take tested
Before making a policy, in 100ms, Fz leads the EEG signals at place and the forecast model set up according to us is analyzed, and right
The result of prediction carries out statistical analysis and draws the accuracy rate of prediction.
So far, present example is described in detail.According to above description, those skilled in the art should
Behaviour decision making prognoses system based on brain wave to the present invention has had and has clearly recognized.
Additionally, the above-mentioned definition to various elements and method be not limited in embodiment is mentioned various concrete structures,
Shape or mode, it can be changed or replace by those of ordinary skill in the art simply, such as, setting of eeg signal acquisition
Standby, to tested stimulation form and software, the method for Data Analysis Services and software are not limited in being previously mentioned in the present invention.
In sum, the present invention use NeuroSc an40 lead eeg amplifier and combine E-prime software to tested enter
Row policy selection stimulates and obtains original EEG signals.By Curry7 software, the EEG signals obtained is processed and sets up
EEG signals data warehouse.Set up decision-making distinguish quantization method and forecast model and be predicted test and actuarial prediction success
Rate, result shows, the method can according to the data warehouse set up and forecast model accurately dope tested will
Make which kind of decision-making.
Particular embodiments described above, has been carried out the most specifically technical scheme and beneficial effect
Bright, be it should be understood that the specific embodiment that the foregoing is only the present invention, be not limited to the present invention, all at this
Within the spirit of invention and principle, any modification, equivalent substitution and improvement etc. done, should be included in the protection model of the present invention
Within enclosing.
Claims (5)
1. a behaviour decision making prognoses system based on brain wave, it is characterised in that: include eeg signal acquisition portion, EEG signals
Treatment Analysis portion, Tactic selection differentiation portion and prognoses system portion, described eeg signal acquisition portion, EEG Processing analysis portion,
Interconnecting between Tactic selection differentiation portion and prognoses system portion, described signal acquisition part is provided with wearable device and brain is electrically amplified
Device, obtains original eeg data by wearable device and eeg amplifier；EEG signals is carried out by EEG Processing analysis portion
Superposed average processes；Tactic selection differentiation portion is by the process respectively of different decision-making EEG signals and set up EEG signals data
Handled data are carried out time and frequency domain analysis and set up the differentiation quantization side of behaviour decision making EEG signals by warehouse afterwards
Method；Prognoses system portion sets up detailed forecast model according to the differentiating method that quantifies set up and provides concrete computation model, right
The Forecasting Methodology test prediction effect set up the accuracy rate counting prediction.
A kind of behaviour decision making prognoses system based on brain wave the most according to claim 1, it is characterised in that: behaviour decision making
Prediction comprises the following steps:
(1) original EEG signals is obtained: with eeg amplifier and combine Experiment of Psychology software and carry out Tactic selection thorn to tested
Swashing and obtain original EEG signals, sample frequency is 1KHz；The brain electricity sample gathered, record is by whole process before and after envoy's decision-making
Continuous print eeg data；Gather different sexes, all ages and classes layer, the data of experimenter, set up decision-making eeg data warehouse；
(2) method using superposed average is overlapped average treatment, to place to the brain wave before the original brain electricity decision-making of collection
Eeg data after reason uses time domain approach and frequency domain method analysis, carries out characteristic parameter extraction, characteristic parameter bag to be extracted
Include time domain parameter and frequency domain parameter；
(3) eeg data before selecting different decision-making is classified, for have selected the eeg data of different decision-making respectively
Process, and extract time domain parameter therein and frequency domain parameter respectively；It is analyzed the characteristic parameter extracted processing, with
Phase obtains being reflected in the method selecting different decision-making forebrain electricity data differences；Use statistical method, in great amount of samples
Under the checking of set, it is determined to reflect the quantization method of different decision-making forebrain electricity data target.
(4) according to the quantization method that can reflect different decision-making forebrain electricity data target obtained to the brain before the unknown result of decision
Electricity data are predicted test, and obtain predicting successful probability.
A kind of behaviour decision making prognoses system based on brain wave the most according to claim 2, it is characterised in that: described brain electricity
Amplifier is that NeuroScan40 leads eeg amplifier.
A kind of behaviour decision making prognoses system based on brain wave the most according to claim 3, it is characterised in that: described wearing
Equipment is electrode cap.
A kind of behaviour decision making prognoses system based on brain wave the most according to claim 4, it is characterised in that: to tested
Tactic selection stimulates employing Experiment of Psychology software E-prime.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610552350.8A CN106175757B (en) | 2016-07-11 | 2016-07-11 | Behaviour decision making forecasting system based on brain wave |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610552350.8A CN106175757B (en) | 2016-07-11 | 2016-07-11 | Behaviour decision making forecasting system based on brain wave |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106175757A true CN106175757A (en) | 2016-12-07 |
| CN106175757B CN106175757B (en) | 2019-10-01 |
Family
ID=57478141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610552350.8A Expired - Fee Related CN106175757B (en) | 2016-07-11 | 2016-07-11 | Behaviour decision making forecasting system based on brain wave |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106175757B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919956A (en) * | 2017-03-09 | 2017-07-04 | 温州大学 | Brain wave age forecasting system based on random forest |
| CN107813307A (en) * | 2017-09-12 | 2018-03-20 | 上海谱康电子科技有限公司 | Mechanical arm control system based on Mental imagery EEG signals |
| CN108836365A (en) * | 2018-05-14 | 2018-11-20 | 中国人民解放军第四军医大学 | Decision aiding assessment device and its assessment method based on VR and eeg signal acquisition |
| CN109460145A (en) * | 2018-10-16 | 2019-03-12 | 北京机械设备研究所 | A kind of quick interference method of automated system decision based on brain understanding |
| CN109521873A (en) * | 2018-10-26 | 2019-03-26 | 蓝色传感（北京）科技有限公司 | Based on collaborative brain-computer interface control system and signal collaboration method |
| CN109784027A (en) * | 2019-01-11 | 2019-05-21 | 西安电子科技大学 | Auth method based on dual EEG signals feature |
| WO2021203719A1 (en) * | 2020-04-08 | 2021-10-14 | 江苏贝泰福医疗科技有限公司 | Acoustic-electric stimulation neuromodulation therapy and apparatus combining electroencephalogram testing, analysis and control |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130005915A (en) * | 2011-07-08 | 2013-01-16 | 서울대학교산학협력단 | Methods for detecting seizure termination with using sample entropy of electroencephalography |
| US20130267866A1 (en) * | 2012-04-05 | 2013-10-10 | Sony Corporation | Electroencephalogram analysis apparatus, electroencephalogram analysis program, and electroencephalogram analysis method |
| CN103413050A (en) * | 2013-08-20 | 2013-11-27 | 北京工业大学 | Motor imagery electroencephalogram voting strategy sorting method based on extreme learning machines |
| KR20140077693A (en) * | 2012-12-14 | 2014-06-24 | 한국전자통신연구원 | Apparatus for controlling internet usage using eeg and method thereof |
| CN105068663A (en) * | 2015-09-18 | 2015-11-18 | 中国石油大学(华东) | Object selecting method and device based on electroencephalogram signal |
| CN105740887A (en) * | 2016-01-26 | 2016-07-06 | 杭州电子科技大学 | Electroencephalogram feature classification method based on PSO-SVM (Particle Swarm Optimization-Support Vector Machine) |
-
2016
- 2016-07-11 CN CN201610552350.8A patent/CN106175757B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130005915A (en) * | 2011-07-08 | 2013-01-16 | 서울대학교산학협력단 | Methods for detecting seizure termination with using sample entropy of electroencephalography |
| US20130267866A1 (en) * | 2012-04-05 | 2013-10-10 | Sony Corporation | Electroencephalogram analysis apparatus, electroencephalogram analysis program, and electroencephalogram analysis method |
| KR20140077693A (en) * | 2012-12-14 | 2014-06-24 | 한국전자통신연구원 | Apparatus for controlling internet usage using eeg and method thereof |
| CN103413050A (en) * | 2013-08-20 | 2013-11-27 | 北京工业大学 | Motor imagery electroencephalogram voting strategy sorting method based on extreme learning machines |
| CN105068663A (en) * | 2015-09-18 | 2015-11-18 | 中国石油大学(华东) | Object selecting method and device based on electroencephalogram signal |
| CN105740887A (en) * | 2016-01-26 | 2016-07-06 | 杭州电子科技大学 | Electroencephalogram feature classification method based on PSO-SVM (Particle Swarm Optimization-Support Vector Machine) |
Non-Patent Citations (1)
| Title |
|---|
| 毕路拯等: "基于脑信息特征人才选拔的决策模型", 《中国管理科学》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919956A (en) * | 2017-03-09 | 2017-07-04 | 温州大学 | Brain wave age forecasting system based on random forest |
| CN107813307A (en) * | 2017-09-12 | 2018-03-20 | 上海谱康电子科技有限公司 | Mechanical arm control system based on Mental imagery EEG signals |
| CN108836365A (en) * | 2018-05-14 | 2018-11-20 | 中国人民解放军第四军医大学 | Decision aiding assessment device and its assessment method based on VR and eeg signal acquisition |
| CN109460145A (en) * | 2018-10-16 | 2019-03-12 | 北京机械设备研究所 | A kind of quick interference method of automated system decision based on brain understanding |
| CN109460145B (en) * | 2018-10-16 | 2021-09-07 | 北京机械设备研究所 | Automatic system decision rapid intervention method based on brain recognition |
| CN109521873A (en) * | 2018-10-26 | 2019-03-26 | 蓝色传感（北京）科技有限公司 | Based on collaborative brain-computer interface control system and signal collaboration method |
| CN109784027A (en) * | 2019-01-11 | 2019-05-21 | 西安电子科技大学 | Auth method based on dual EEG signals feature |
| CN109784027B (en) * | 2019-01-11 | 2022-03-22 | 西安电子科技大学 | Identity verification method based on dual electroencephalogram signal characteristics |
| WO2021203719A1 (en) * | 2020-04-08 | 2021-10-14 | 江苏贝泰福医疗科技有限公司 | Acoustic-electric stimulation neuromodulation therapy and apparatus combining electroencephalogram testing, analysis and control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106175757B (en) | 2019-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106175757B (en) | Behaviour decision making forecasting system based on brain wave | |
| US20200367800A1 (en) | Method for identifying driving fatigue based on cnn-lstm deep learning model | |
| Farina et al. | Decoding the neural drive to muscles from the surface electromyogram | |
| Fazel-Rezai | Human error in P300 speller paradigm for brain-computer interface | |
| CN110070105B (en) | Electroencephalogram emotion recognition method and system based on meta-learning example rapid screening | |
| Krusienski et al. | Toward enhanced P300 speller performance | |
| CN102319067B (en) | Nerve feedback training instrument used for brain memory function improvement on basis of electroencephalogram | |
| CN106919956A (en) | Brain wave age forecasting system based on random forest | |
| CN108143411A (en) | A kind of tranquillization state brain electricity analytical system towards Autism Diagnostic | |
| Oby et al. | Extracellular voltage threshold settings can be tuned for optimal encoding of movement and stimulus parameters | |
| Denman et al. | On parallel streams through the mouse dorsal lateral geniculate nucleus | |
| CN113576496B (en) | Vision tracking brain-computer interface detection system | |
| Castaño-Candamil et al. | A pilot study on data-driven adaptive deep brain stimulation in chronically implanted essential tremor patients | |
| CN106510702B (en) | The extraction of sense of hearing attention characteristics, identifying system and method based on Middle latency auditory evoked potential | |
| CN106502410A (en) | Improve the transcranial electrical stimulation device of Mental imagery ability and method in brain-computer interface | |
| CN111414835B (en) | Detection and determination method for electroencephalogram signals caused by love impulsion | |
| Schuerch et al. | Objectification of intracochlear electrocochleography using machine learning | |
| Yuan et al. | Cortical neural responses to previous trial outcome during learning of a directional choice task | |
| CN115281692A (en) | Closed-loop self-adaptive transcranial electrical stimulation device and method | |
| CN112735595B (en) | Comprehensive assessment method for working memory capacity | |
| Zambalde et al. | Influence of stimuli spatial proximity on a SSVEP-based BCI performance | |
| CN110192877A (en) | Based on the lie detecting method for more leading the EEG signals degree of bias | |
| Xing et al. | Application of mental fatigue classification in cross task paradigm | |
| Rai et al. | Expert system analysis of electromyogram | |
| Chang et al. | Responses of midbrain auditory neurons to two different environmental sounds—A new approach on cross-sound modeling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191001 Termination date: 20200711 |