CN110192876A - Based on the lie detecting method for more leading EEG signals kurtosis - Google Patents
Based on the lie detecting method for more leading EEG signals kurtosis Download PDFInfo
- Publication number
- CN110192876A CN110192876A CN201910441347.2A CN201910441347A CN110192876A CN 110192876 A CN110192876 A CN 110192876A CN 201910441347 A CN201910441347 A CN 201910441347A CN 110192876 A CN110192876 A CN 110192876A
- Authority
- CN
- China
- Prior art keywords
- eeg signals
- kurtosis
- lie
- subject
- leading
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000010801 machine learning Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000007619 statistical method Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000010276 construction Methods 0.000 claims abstract description 7
- 238000002790 cross-validation Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 230000004936 stimulating effect Effects 0.000 claims description 9
- 210000000869 occipital lobe Anatomy 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000000692 Student's t-test Methods 0.000 claims description 4
- 238000012353 t test Methods 0.000 claims description 4
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 230000011218 segmentation Effects 0.000 claims 1
- 230000000638 stimulation Effects 0.000 abstract description 17
- 210000004556 brain Anatomy 0.000 abstract description 15
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 230000001537 neural effect Effects 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 23
- 238000005516 engineering process Methods 0.000 description 12
- 238000001514 detection method Methods 0.000 description 9
- 238000002474 experimental method Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000035479 physiological effects, processes and functions Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 210000000467 autonomic pathway Anatomy 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 210000003169 central nervous system Anatomy 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000034303 cell budding Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003920 cognitive function Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000010832 independent-sample T-test Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000009781 safety test method Methods 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 230000021317 sensory perception Effects 0.000 description 1
Classifications
-
- 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
- A61B5/164—Lie detection
-
- 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
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/291—Bioelectric electrodes therefor specially adapted for particular uses for electroencephalography [EEG]
-
- 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]
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychology (AREA)
- Psychiatry (AREA)
- Child & Adolescent Psychology (AREA)
- Educational Technology (AREA)
- Developmental Disabilities (AREA)
- Social Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of based on the lie detecting method for more leading EEG signals kurtosis, it is calculated including the kurtosis to each lead EEG signals, then the Variant statistical analysis of honest subject and the subject that lies are carried out to the kurtosis for more leading EEG signals, utilize the kurtosis index construction feature vector of discrepant electrode, it is sent in machine learning algorithm, carry out the model training of machine learning, extract real-time is carried out by EEG signals of the multi-lead electrode for encephalograms to tester, it obtains the multi-lead EEG signals of tester and saves, and it will be after each pretreatment operation of each lead EEG signals progress, each kurtosis for leading EEG signals in the data set of the stimuli responsive of tester is calculated using kurtosis calculation formula, and it is sent in trained classifier as input, obtain result of detecting a lie.The program is based on brain neural signal, greatly reduces the stimulation number needed when test, eventually passes through test, accuracy rate of detecting a lie is greatly improved.
Description
Technical field
It is the present invention relates to the field of detecting a lie, in particular to a kind of based on the lie detecting method for more leading EEG signals kurtosis.
Background technique
Lie is the generally existing society of human society and psychological phenomena.Lie become influence that the country is stable with solidarity because
Element, and property to the people and life security are constituted and are seriously threatened.Therefore psychophysiologist and other related fields
Expert, which has been working hard, finds effective lie detecting method.The validity detected a lie at home and abroad is widely applied practice for a long time
In be confirmed.Lie-detection technology has important application value firstly for the detection of case of criminal detection.In addition, lie identification for
The treatment of mental disease and mental handicape also has important meaning.In addition, current worldwide campaign against terrorism situation is still severe, China
Also there is an urgent need to establish effective anti-terrorism means.And study the lie detecting method based on brain cognitive behavior will widen it is existing anti-
Probably means are enriched to the monitoring channel and the precautionary measures of terrorist, are striven eliminating terroristic attack activity in budding state, from
And threat of the terrorist activity to people's life and national security is reduced to the greatest extent.
Traditional lie detecting method is that the psychoreactions such as fear and anxiety when recalling information relevant to crime according to subject are drawn
The variations of the physiological parameters such as pulse, blood pressure measure subject with the presence or absence of behavior of lying, referred to as multi-path physiology signal is surveyed
Instrument technology is tried, the method is based on, polygraph has been invented by the police, the U.S..But in recent years, this multi-path physiology is detected a lie skill
Art is by query.Main cause be the behavior of lying be by central nervous system regulate and control physical signs, and multiple tracks instrument record blood
Pressure, body temperature, respiration rate etc. are the physical signs regulated and controled by autonomic nerves system, these features can not reflect brain depth completely
The variation in portion.In addition, limb motion and conscious cognition are easy to change multi-path physiology index, usually subject is to avoid punishment
Interference behavior can be taken to hinder being normally carried out for experiment, that is, there is the anti-behavior detected a lie.
Modern lie-detection technology mainly utilizes brain neurological motion signal of people when in face of criminal activity or deceptive information
Analysis is detected a lie, for example is reflected using the event related potential (Event related potential, ERP) of EEG signals
The process of brain cognition, carries out analysis of detecting a lie by event related potential.Relative to traditional lie detecting method, the modern times detect a lie
Technology compares emphasis from nervous physiology level analysis brain in psychology such as sensory perception, memory, thinking, the imaginations in terms of research contents
Information coding and extraction feature in phenomenon generating process.Numerous scientific research personnel's researchs have shown that the ERP ingredient of EEG signal contains
It is difficult to the automatic process inhibited, thus relative to polygraph, modern lie-detection technology can be resisted relatively efficiently
Anti- behavior of detecting a lie.
Most widely used in lie detecting method based on EEG signals is the method based on ERP (event related potential), should
Technology infers whether subject lies according to Scalp Potential difference caused by different stimulated.ERP reflection is central nervous system
Activity related with Information procession, is not rely on periphery autonomic nerves system, thus subject be difficult it is counter detected a lie, compensate for
Traditional multichannel physiograph is easy during detecting a lie by anti-the shortcomings that detecting a lie.But it currently based on the lie detecting method of ERP, needs
Mass data superposition, experimental period is longer, is tested and is easy fatigue, while also will affect test effect i.e. with time of test information
Number is more and more, and the susceptibility of testee will be greatly reduced in crime or deceptive information.It studies a kind of efficiently based on few
The lie detection system of secondary stimulation and seem especially urgent to the research of several key technologies around the system.
Summary of the invention
The purpose of the present invention is being directed to the corresponding deficiency of the prior art, provide a kind of based on the survey for more leading EEG signals kurtosis
Lie method, present invention firstly provides taken in lie-detection technology lead brain wave acquisition mode, and make full use of and lead signals analysis more
And the newest fruits technology of processing, calculate the kurtosis for leading signal more, it is special using the kurtosis of the electrode with significant difference as classification
Sign is sent in machine learning algorithm and realizes classification.
The purpose of the present invention is what is realized using following proposal: the present invention provides one kind to lead EEG signals kurtosis based on more
Lie detecting method, include the following steps:
1) extract real-time is carried out to the EEG signals of honesty and the two class subjects that lie respectively by multi-lead electrode for encephalograms,
It respectively obtains the multi-lead EEG signals of two class subjects and saves；
2) selecting step 1) obtained each lead EEG signals of subject are successively filtered, divide, baseline correction,
Artefact and superposed average pretreatment operation are removed, obtains the two each leads of class subject and lie to stimulate corresponding EEG signals, is formed
Data set；
3) each EEG signals of leading in the data set of the stimuli responsive of two class subjects are calculated separately after above-mentioned pretreatment
Kurtosis；The calculation formula of kurtosis are as follows: set xiFor collected vibration signal sequence, i=1,2 ..., N, kurtosisXRMSFor root-mean-square value, N is signal xiSampling number, the present invention in N=
800；
4) Variant statistical analysis of honest subject and the subject that lies, benefit are then carried out to the kurtosis for more leading EEG signals
Use the kurtosis index construction feature vector of the electrode with significant difference as sample data, by sample data to initial machine
Device learning model carries out the cross validation based on subject of K folding, obtains the classifier with optimal parameter combination；
5) extract real-time is carried out by EEG signals of the multi-lead electrode for encephalograms of step 1) to tester, obtains tester
Multi-lead EEG signals and save, and by each lead EEG signals carry out step 2) pretreatment operation after, utilize step
3) each kurtosis building for leading EEG signals is special in the data set for the stimuli responsive that tester is calculated in kurtosis calculation formula
Vector is levied, and is sent in the classifier with optimal parameter combination that step 4) obtains as input, result of detecting a lie is obtained.
Filtering parameter setting in step 1) is respectively 0.05-30Hz bandpass filtering；300ms is extremely pierced before stimulating after filtering
The eeg data of 1300ms is split as an epoch after swashing, this epoch is referred to as a P stimuli responsive；Before stimulation
300ms data carry out baseline correction as baseline, then carry out a superposed average to 5 epoch every in two groups of data.
The cross validation based on subject of K folding is carried out to initial machine learning model by sample data, comprising: handing over
Every compromise of verifying is pitched, the lie sample data of subject of the sample data of (K-1) name honesty subject and (K-1) name is used for
Training set, the sample data of remaining 1 honest subject and the sample data of 1 subject that lies are used for test set.
M folding cross validation is executed to each training set in honesty and two groups of data of lying, wherein M-1 sample is as son instruction
Practice collection, remaining sample is as checksum set, in this process, combines using different parameters, using sub- training set training classifier, connects
With verifying collection verified, when verify accuracy rate highest, can obtain with optimal parameter combine classifier.
The machine learning model uses support vector machines.
Extract real-time, packet are carried out to the EEG signals of honesty and the two class subjects that lie respectively by multi-lead electrode for encephalograms
It includes: choosing this six conductive electrode of P4, PZ, P3, O2, OZ, O1 and be located at top and occipital lobe, for acquiring top and occipital lobe position respectively
The EEG signals set.
The Variant statistical analysis of honest subject and the subject that lies are carried out to the kurtosis for more leading EEG signals, comprising: ask
The kurtosis average value for respectively leading EEG signals of honest subject and the kurtosis average value for respectively leading EEG signals for the subject that lies,
The kurtosis average value for respectively leading EEG signals of the kurtosis average value for respectively leading EEG signals and the subject that lies to honest subject
It carries out t-test statistical check and obtains the electrode with significant difference using the multiple correction of Bonferroni.
Present invention has the advantage that the method for calculating the kurtosis for leading EEG signals is applied to brain electricity for the first time by the present invention more
It detects a lie in field, the kurtosis of each lead EEG signals is calculated, then the kurtosis for more leading EEG signals is carried out honest
The Variant statistical analysis of subject and the subject that lies are sent into using the kurtosis index construction feature vector of discrepant electrode
Into machine learning algorithm, the model training of machine learning is carried out.Volume is located to tester head by multi-lead electrode for encephalograms
Leaf, middle section, top position EEG signals carry out extract real-time, obtain the multi-lead EEG signals of tester and save,
And by after each pretreatment operation of each lead EEG signals progress, the stimulation of tester is calculated using kurtosis calculation formula
Each kurtosis for leading EEG signals in the data set of response, and be sent in trained classifier as input, it is detected a lie
As a result, to achieve the purpose that detect a lie, and substantially increase accuracy rate of detecting a lie.
The program is based on brain neural signal, overcomes interference of traditional multiple tracks a lie detector vulnerable to anti-behavior of detecting a lie, and
Measuring technology (need largely to stimulate and be easy to cause fatigue to reduce susceptibility of detecting a lie) to tradition based on event related potential,
The stimulation number needed when test is greatly reduced, test is eventually passed through, accuracy rate of detecting a lie also has obtained large increase.
Detailed description of the invention
Fig. 1 is the flow chart of the invention based on the lie detecting method for more leading EEG signals kurtosis；
Fig. 2 is the specific process flow of EEG EEG signals of the invention；
Fig. 3 is experiment model schematic diagram of detecting a lie.
Specific embodiment
Referring to Fig. 1, the present invention provides a kind of based on the lie detecting method for more leading EEG signals kurtosis, includes the following steps:
1) extract real-time is carried out to the EEG signals of honesty and the two class subjects that lie respectively by multi-lead electrode for encephalograms,
It respectively obtains the multi-lead EEG signals of two class subjects and saves；
2) selecting step 1) obtained each lead EEG signals of subject are successively filtered, divide, baseline correction,
Artefact and superposed average pretreatment operation are removed, obtains the two each leads of class subject and lie to stimulate corresponding EEG signals, is formed
Data set；
3) each EEG signals of leading in the data set of the stimuli responsive of two class subjects are calculated separately after above-mentioned pretreatment
Kurtosis；The calculation formula of kurtosis are as follows: set xiFor collected vibration signal sequence, i=1,2 ..., N, N are signal xiSampling
The N of points, the present embodiment is equal to 800.Kurtosis XRMSFor root-mean-square value；
4) Variant statistical analysis that honest subject and the subject that lies then are carried out to the kurtosis for more leading EEG signals, obtains
To the corresponding electrode of kurtosis with significant difference, using the electrode with significant difference kurtosis index construction feature to
Amount is used as sample data, carries out the cross validation based on subject of K folding to initial machine learning model by sample data, obtains
The classifier that must have optimal parameter to combine；
5) extract real-time is carried out by EEG signals of the multi-lead electrode for encephalograms of step 1) to tester, obtains tester
Multi-lead EEG signals and save, and by each lead EEG signals carry out step 2) pretreatment operation after, utilize step
3) each kurtosis building for leading EEG signals is special in the data set for the stimuli responsive that tester is calculated in kurtosis calculation formula
Vector is levied, and is sent in the classifier with optimal parameter combination that step 4) obtains as input, result of detecting a lie is obtained.
Filtering parameter setting in step 1) is respectively 0.05-30Hz bandpass filtering；300ms is extremely pierced before stimulating after filtering
The eeg data of 1300ms is split as an epoch after swashing, this epoch is referred to as a P stimuli responsive；Before stimulation
300ms data carry out baseline correction as baseline, then carry out a superposed average to 5 epoch every in two groups of data.
The cross validation based on subject of K folding is carried out to initial machine learning model by sample data, comprising: handing over
Every compromise of verifying is pitched, the lie sample data of subject of the sample data of (K-1) name honesty subject and (K-1) name is used for
Training set, the sample data of remaining 1 honest subject and the sample data of 1 subject that lies are used for test set.
M folding cross validation is executed to each training set in honesty and two groups of data of lying, wherein M-1 sample is as son instruction
Practice collection, remaining sample is as checksum set, in this process, combines using different parameters, using sub- training set training classifier, connects
With verifying collection verified, when verify accuracy rate highest, can obtain with optimal parameter combine classifier.
The present embodiment respectively carries out the EEG signals of honesty and the two class subjects that lie by multi-lead electrode for encephalograms real
When extract, comprising: choose this six conductive electrode of P4, PZ, P3, O2, OZ, O1 be located at top and occipital lobe, for respectively acquisition top
The EEG signals of leaf and occipital lobe position.
The present embodiment carries out the Variant statistical analysis of honest subject and the subject that lies to the kurtosis for more leading EEG signals,
Obtain the electrode with significant difference, comprising: seek the kurtosis average value for respectively leading EEG signals of honest subject and lie
The kurtosis average value for respectively leading EEG signals of subject to the kurtosis average value for respectively leading EEG signals of honest subject and is lied
The kurtosis average value for respectively leading EEG signals of subject is carried out t-test statistical check and is obtained using the multiple correction of Bonferroni
To the electrode with significant difference.Its P value and selected is judged by independent samples t test and Bonferroni multiple check
Relationship between P value, the P value of Chang Xuanding is 0.01 or 0.05, if being less than selected P value, then it is assumed that is had between two samples aobvious
Write sex differernce.
The machine learning model uses support vector machines.
Kurtosis is the quadruplicate ratio of fourth central square and standard deviation；Kurtosis indicates waveform gradual degree, is used for
The distribution of variable is described.The kurtosis of normal distribution is equal to 3, and the curve being distributed when kurtosis is less than 3 can be distributed when greater than 3 compared with " flat "
Curve compared with " steep ".Kurtosis coefficient is a dimensionless factor, reflects the degree of expansion of probability density function p (x) curve.In vehicle
Safety testing field, when bearing generates abnormal sound, the probability density of amplitude increases in bearing vibration signal, so that probability is close
The both sides tail for spending distribution function curve tilts, and deviates normal distribution, thus kurtosis coefficient is greater than the corresponding kurtosis of normal distribution
Coefficient 3.Kurtosis coefficient is related with number of pulses and pulse amplitude, to the higher magnitude in signal with biggish power, even if pulse
Number is more, but if amplitude is not very greatly, the increase of kurtosis coefficient will be unobvious, it is possible to less than 2.Present invention firstly provides handles
This index is applied to brain electrical measurement lie field, it can be achieved that honesty and the differentiation of subject's EEG type number of lying.
The present invention will introduce integral experiment by signal acquisition and the sequence of pretreatment, feature extraction and pattern recognition classifier
Process, specific embodiment are as follows:
Detect a lie agreement: this experiment has chosen 30 average ages in 21 years old or so student enrollment as subject,
To reduce the influence of gender and age factor to statistical result, by all subjects principle impartial as far as possible according to gender and age
Be assigned to honest group and group of lying, and two group memberships in terms of age, gender and handedness without significant difference.
The tristimulus experiment model that this experiment is proposed using Frawell and Donchin, has prepared 6 in advance before testing
Different bangles and a safety box.To honest group, it is put into any one bangle in the safe, it is desirable that subject conscientiously observes
The appearance informations such as size, color, the shape of the bangle, and as target stimulation (Target, T), then select one at random again
Bangle is as detection stimulation (Probe, P), remaining four bangle is as indifferent stimulus (Irrelevant, I).Thereafter, all referred to as
For T stimulation, P stimulation and I stimulation.To group of lying, it is arbitrarily put into two bangles in preprepared safety box, allows subject
Conscientiously observe two bangles and take away wherein one as P stimulate, another bangle be then T stimulation, remaining bangle as I thorn
Swash.During the experiment, can occur the picture of every bangle on the computer screen in face of subject at random, subject needs to every
Picture makes corresponding key reaction, it may be assumed that whether met the bangle and (met, left button of clicking the mouse slightly；It does not see, then dubs mouse
Mark right button).It is required that honest group membership tells the truth, and the group membership that lies only makes the behavior of lying to P stimulation.Each experimentation
In, six different bangle pictures occur 30 times, and each duration is 1.6s, the frequency that wherein tri- kinds of T, P, I stimulations occur
It respectively may be about 16.7%, 16.7%, 66.7%, and each subject need to do 5 identical experiments (specifically as shown in Figure 3).
EEG data acquisition and pretreatment: due to had numerous studies confirm to lie in P stimulation subject and it is honest by
There were significant differences for the brain wave patterns of examination person, therefore the present invention mainly studies the corresponding EEG signals of P stimulation.The present embodiment will be continuous
EEG waveform be successively filtered, divide, baseline correction, the operation such as remove artefact and superposed average, filtering parameter setting is respectively
0.05-30Hz bandpass filtering.300ms eeg data of 1300ms to after stimulating is split as an epoch before stimulating,
This epoch is referred to as a P stimuli responsive, carries out baseline correction using 300ms data before stimulating as baseline；Original EEG signals
Signal-to-noise ratio is extremely low, and in order to remove noise, the present invention is using few averaging, by every 5 on all electrodes of every subject
Epoch carries out a superposed average, obtains the data set of the P stimuli responsive of two class subjects.
Selection, which is lied, stimulates corresponding EEG signals (EEG), is successively filtered, divides, baseline correction, removing artefact and fold
Add flat equalization operation, filtering parameter setting is respectively 0.05-30Hz bandpass filtering, 300ms 1300ms to after stimulating before stimulating
Eeg data be split as an epoch, this epoch is referred to as a P stimuli responsive；To stimulate preceding 300ms data to make
Baseline correction is carried out for baseline, a superposed average then is carried out to every 5 epoch in honesty and two groups of data of lying respectively.
The present embodiment chooses P4, PZ, P3, O2, OZ, O1 this six conductive electrode respectively and is distributed in top and occipital lobe.Top has
The function of expression body signal (breathe and the physiological signals such as accelerate, palpitate quickly), rear top also participates in vision attention function, such as eye
It is dynamic；Occipital lobe is responsible for handling visual information, carries out the processing and integration of visual information.
Feature extraction: it calculates separately and each in the data set of the P stimuli responsive of two class crowds after above-mentioned pretreatment leads brain
The kurtosis of electric signal, in the present embodiment, respectively lead eeg data kurtosis calculate after the completion of, generate the honest and two class subjects that lie
Respective kurtosis matrix (300 × 6), i.e., each kurtosis matrix include 6 data for leading electrode for encephalograms, and it is corresponding often to lead electrode for encephalograms
300 samples include 15 subjects, corresponding 20 sample datas of each subject.
The Variant statistical analysis that honesty person and liar are carried out to above-mentioned two kurtosis matrix, specifically includes: high and steep to two
Two groups of kurtosis data that each identical lead is corresponded in degree matrix carry out t-test statistical check, and use the multiple school Bonferroni
Just, using the feature with significant difference as final characteristic of division.
Pattern recognition classifier: the cross validation (Subject-Wise based on subject of 15 foldings is carried out to features described above collection
Cross-Validation, SWCV), such as if it is 30 subjects, in every compromise of SWCV, by the sample of 28 subjects
Data (14 honest subjects and 14 subjects that lie) are used for training set, and (1 really for the sample data of remaining 2 subjects
Real subject and 1 subject that lies) it is used for test set.
In addition, 10 folding cross validations are executed to each training set in honesty and two groups of data of lying, wherein 9 sample conducts
Sub- training set, remaining sample is as checksum set.In this process, it combines using different parameters, is classified using the training of sub- training set
Device is then verified with verifying collection.Therefore, it when verifying accuracy rate highest, can obtain with optimal parameter combination
Classifier.
The model of machine learning selects support vector machines (Support Vector Machine, SVM) to be used as classifier.
Then test set is sent into the classifier, the training result before foundation, judges that the test data belongs to and lies people still
Honest people is to complete to test.The EEG signal process flow of this programme is as shown in Fig. 2, this programme pair and other lie detecting methods compare
Situation is shown in Table 1.
Classification accuracy result under the different lie detecting methods of table 1
The present invention proposes that it can greatly reduce test period based on the lie-detection technology of few stimulation (low frequency stimulating), from
And substantially reduce the degree of fatigue of testee., brain entirety difficult for EEG feature extraction in current lie detecting method
The case where cognitive function analysis is increasingly taken seriously in brain cognitive science research, the present invention will calculate lead EEG signals more for the first time
The method of kurtosis be applied in brain electrical measurement lie field.The present invention calculates the kurtosis of each lead EEG signals, then
The Variant statistical analysis that honest subject and the subject that lies are carried out to the kurtosis for more leading EEG signals, utilizes discrepant electrode
Kurtosis index construction feature vector, be sent in machine learning algorithm, carry out the model training of machine learning, and then improve and survey
Lie accuracy rate.
The above description is only a preferred embodiment of the present invention, is not intended to restrict the invention, it is clear that those skilled in the art
Various changes and modifications can be made to the invention by member without departing from the spirit and scope of the present invention.If in this way, of the invention
Within the scope of the claims of the present invention and its equivalent technology, then the present invention is also intended to encompass these to these modifications and variations
Including modification and variation.
Claims (7)
1. a kind of based on the lie detecting method for more leading EEG signals kurtosis, which comprises the steps of:
1) extract real-time is carried out to the EEG signals of honesty and the two class subjects that lie respectively by multi-lead electrode for encephalograms, respectively
It obtains the multi-lead EEG signals of two class subjects and saves；
2) selecting step 1) obtained each lead EEG signals of subject are successively filtered, divide, baseline correction, going puppet
Mark and superposed average pretreatment operation obtain the two each leads of class subject and lie to stimulate corresponding EEG signals, form data
Collection；
3) each kurtosis for leading EEG signals in the data set of the stimuli responsive of two class subjects is calculated separately after above-mentioned pretreatment；
The calculation formula of kurtosis are as follows: set xiFor collected vibration signal sequence, i=1,2 ..., N, kurtosisXRMSFor root-mean-square value, N is signal xiSampling number, the present invention in N
=800；
4) Variant statistical analysis that honest subject and the subject that lies then are carried out to the kurtosis for more leading EEG signals, utilizes tool
There is the kurtosis index construction feature vector of the electrode of significant difference as sample data, by sample data to initial machine
The cross validation based on subject that model carries out K folding is practised, the classifier with optimal parameter combination is obtained；
5) extract real-time is carried out by EEG signals of the multi-lead electrode for encephalograms of step 1) to tester, obtains the more of tester
Lead EEG signals simultaneously save, and by after the pretreatment operation of each lead EEG signals progress step 2), utilize step 3)
Kurtosis calculation formula be calculated in the data set of the stimuli responsive of tester each kurtosis construction feature for leading EEG signals to
Amount, and be sent in the classifier with optimal parameter combination that step 4) obtains as input, obtain result of detecting a lie.
2. lie detecting method according to claim 1, it is characterised in that: the filtering parameter in step 1), which is arranged, is respectively
0.05-30Hz bandpass filtering；After filtering will stimulate before 300ms to stimulate after 1300ms eeg data as an epoch into
Row segmentation, this epoch is referred to as a P stimuli responsive；Baseline correction is carried out using 300ms data before stimulating as baseline, it is then right
Every 5 epoch carry out a superposed average in two groups of data.
3. lie detecting method according to claim 1, it is characterised in that: by sample data to initial machine learning model into
The cross validation based on subject of row K folding, comprising: in every compromise of cross validation, by the sample number of K-1 honest subjects
It is used for training set according to the sample data with the K-1 subjects that lie, the sample data of remaining 1 honest subject and 1 to lie
The sample data of subject is used for test set.
4. lie detecting method according to claim 3, it is characterised in that: to each training set in honesty and two groups of data of lying
It executes M and rolls over cross validation, wherein M-1 sample is as sub- training set, and remaining sample is as checksum set, in this process, application
Different parameters combination is then verified with verifying collection using sub- training set training classifier, when verifying accuracy rate highest
When, the classifier with optimal parameter combination can be obtained.
5. lie detecting method according to claim 1, it is characterised in that: the machine learning model uses support vector machines
SVM。
6. lie detecting method according to claim 1, it is characterised in that: to honesty and said respectively by multi-lead electrode for encephalograms
The EEG signals of two class subject of lie carry out extract real-time, comprising: choose this six conductive electrode of P4, PZ, P3, O2, OZ, O1 and distinguish position
In top and occipital lobe, for acquiring the EEG signals of top and occipital lobe position respectively.
7. lie detecting method according to claim 1, it is characterised in that: carried out to the kurtosis for more leading EEG signals honest tested
Person and the Variant statistical analysis of subject of lying, comprising: ask honest subject the kurtosis average value for respectively leading EEG signals and
Lie the kurtosis average value for respectively leading EEG signals of subject, the kurtosis average value for respectively leading EEG signals to honest subject and
Lie subject respectively lead EEG signals kurtosis average value carry out t-test statistical check, use the multiple school Bonferroni
Just, the electrode with significant difference is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910441347.2A CN110192876A (en) | 2019-05-24 | 2019-05-24 | Based on the lie detecting method for more leading EEG signals kurtosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910441347.2A CN110192876A (en) | 2019-05-24 | 2019-05-24 | Based on the lie detecting method for more leading EEG signals kurtosis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110192876A true CN110192876A (en) | 2019-09-03 |
Family
ID=67751663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910441347.2A Pending CN110192876A (en) | 2019-05-24 | 2019-05-24 | Based on the lie detecting method for more leading EEG signals kurtosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110192876A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2456302A1 (en) * | 2001-08-07 | 2003-02-20 | Lawrence Farwell | Method for psychophysiological detection of deception through brain function analysis |
| WO2006093513A3 (en) * | 2004-06-14 | 2007-07-12 | Cephos Corp | Question and control paradigms for detecting deception by measuring brain activity |
| CN103699230A (en) * | 2014-01-14 | 2014-04-02 | 东南大学 | Digital interface interaction method on basis of icon electrocerebral control |
| CN105054928A (en) * | 2015-07-17 | 2015-11-18 | 张洪振 | Emotion display equipment based on BCI (brain-computer interface) device electroencephalogram acquisition and analysis |
| CN105249963A (en) * | 2015-11-16 | 2016-01-20 | 陕西师范大学 | N400 evoked potential lie detection method based on sample entropy |
| CN108498106A (en) * | 2018-02-08 | 2018-09-07 | 陕西师范大学 | CNV brain electricity lie detecting methods based on multi-fractal detrend fluctuation analysis |
-
2019
- 2019-05-24 CN CN201910441347.2A patent/CN110192876A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2456302A1 (en) * | 2001-08-07 | 2003-02-20 | Lawrence Farwell | Method for psychophysiological detection of deception through brain function analysis |
| WO2006093513A3 (en) * | 2004-06-14 | 2007-07-12 | Cephos Corp | Question and control paradigms for detecting deception by measuring brain activity |
| CN103699230A (en) * | 2014-01-14 | 2014-04-02 | 东南大学 | Digital interface interaction method on basis of icon electrocerebral control |
| CN105054928A (en) * | 2015-07-17 | 2015-11-18 | 张洪振 | Emotion display equipment based on BCI (brain-computer interface) device electroencephalogram acquisition and analysis |
| CN105249963A (en) * | 2015-11-16 | 2016-01-20 | 陕西师范大学 | N400 evoked potential lie detection method based on sample entropy |
| CN108498106A (en) * | 2018-02-08 | 2018-09-07 | 陕西师范大学 | CNV brain electricity lie detecting methods based on multi-fractal detrend fluctuation analysis |
Non-Patent Citations (3)
| Title |
|---|
| 夏阳: "《神经信息学基础》", 30 September 2015, 电子科技大学出版社 * |
| 梁静坤: "《基于想象驾驶行为的脑机接口控制》", 31 December 2015, 国防工业出版社 * |
| 高军峰 等: "多导脑电复杂度特征的谎言测试研究", 《电子科技大学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Klein Selle et al. | Orienting versus inhibition in the Concealed Information Test: Different cognitive processes drive different physiological measures | |
| US8684926B2 (en) | System and method for knowledge verification utilizing biopotentials and physiologic metrics | |
| CN104768449B (en) | Device for examining a phase distribution used to determine a pathological interaction between different areas of the brain | |
| US6804661B2 (en) | Drug profiling apparatus and method | |
| Pfurtscheller et al. | Discrimination of motor imagery‐induced EEG patterns in patients with complete spinal cord injury | |
| US20050124863A1 (en) | Drug profiling apparatus and method | |
| KR20150082322A (en) | Systems and methods for evaluation of neuropathologies | |
| CN101477405A (en) | Stable state vision inducting brain-machine interface method based on two frequency stimulation of left and right view field | |
| CN110192874B (en) | Lie detection method based on multi-lead electroencephalogram signal margin factors | |
| Farahani et al. | A concealed information test with combination of ERP recording and autonomic measurements | |
| Yeom et al. | EEG-based person authentication using face stimuli | |
| CN110192875B (en) | Lie detection method based on multi-lead electroencephalogram signal form factor | |
| Chowdhury et al. | A machine learning approach for person authentication from EEG signals | |
| Miraglia | Unreliability of the gas discharge visualization (GDV) device and the bio-well for biofield science: Kirlian photography revisited and investigated | |
| Demir et al. | Bio-inspired filter banks for SSVEP-based brain-computer interfaces | |
| CN118634403A (en) | A method for promoting awakening by integrating personalized multimodal biofeedback stimulation into the detection of consciousness disorders | |
| CN110192877A (en) | Based on the lie detecting method for more leading the EEG signals degree of bias | |
| CN110192878A (en) | Based on the lie detecting method for more leading EEG signals orientation transfer function | |
| CN117357114A (en) | Auxiliary diagnosis system for attention deficit hyperactivity disorder syndrome based on omnibearing cognition experiment set and multi-flow double-row decision neural network model | |
| CN110192880A (en) | Based on the lie detecting method for more leading EEG signals Granger Causality | |
| CN110192876A (en) | Based on the lie detecting method for more leading EEG signals kurtosis | |
| Cmiel et al. | EEG biofeedback | |
| Liu et al. | The role of featural processing in other-race face classification advantage: An ERP study | |
| CN110192879A (en) | Based on the lie detecting method for more leading the EEG signals pulse factor | |
| CN107595295A (en) | A kind of recognition methods of the lower extremity movement resistive state based on brain hemoglobin information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190903 |
|
| RJ01 | Rejection of invention patent application after publication |