CN110477911A - The EEG signals characteristic detection method and system of concealment behavior based on consciousness conflict - Google Patents
The EEG signals characteristic detection method and system of concealment behavior based on consciousness conflict Download PDFInfo
- Publication number
- CN110477911A CN110477911A CN201910775030.2A CN201910775030A CN110477911A CN 110477911 A CN110477911 A CN 110477911A CN 201910775030 A CN201910775030 A CN 201910775030A CN 110477911 A CN110477911 A CN 110477911A
- Authority
- CN
- China
- Prior art keywords
- eeg signals
- stimulus material
- conflict
- concealment
- feature
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- 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
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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]
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Psychiatry (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychology (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention proposes the EEG signals characteristic detection method and system of a kind of concealment behavior based on consciousness conflict, this method is based on the conflict monitoring theory in cognitive psychology, due to concealment active consciousness with individual between stimulant subconsciousness exist conflict, cause cognitive conflict monitoring brain area activation, to generate relevant EEG signals feature.This method comprises: providing the psychological test stimulus material based on collision detection theory and its special operation reaction；Goal stimulus strengthens memory；Construct leading question or guidance scene；Measured is tested, the EEG signals of measured are obtained；A variety of processing are carried out to EEG signals, the event-related EEG characteristic pattern of concealment behavior is extracted, filters out the brain electrical feature index of concealment behavior, are based on features described above, conceal behavior using machine learning and mode identification method automatic identification.The present invention can fast and effeciently identify the brain electrical feature of concealment behavior, assess the answered credible result degree of measured, use scope extensively, strong applicability.
Description
Technical field
The present invention relates to brain electricity psychological test technical field, in particular to the brain of a kind of concealment behavior based on consciousness conflict
Signal characteristics detection method and system.
Background technique
Brain electricity psychological test technology refers to and is based on event related potential technology in lie field of detecting, with case investigation content
Or the Cognitive Processing event as measured such as psychological test problem, cognition of measured's brain to event is recorded and analyzed in real time
Scalp surface current potential is processed, the technology of the answered credible result degree of measured is assessed.
From the perspective of brain electricity psychological test, cognition brain electricity is measured to contents such as question sentence, view, voices, is carried out
Perception pays attention to, memory, understands, thinking and judging cerebral nerve electrophysiological change in this cognitive process.Recognizing brain electricity can be with
Reflect measured to the psychophysiological reactions process of case related content, has the characteristics that high time resolution and non-invasive and several
It is not influenced by measured's subjective desire.The neuroelectricity variation of measured's brain cognitive process is can not to pretend and be difficult to cover up
, and be associated with less with mood.Using EEG signals as analysis source, human brain cognitive function can be not only analyzed and determined, and current
The important research method of brain science, advantage and application value in the field of detecting a lie, just increasingly obtains International Evidence scientific domain
Be widely recognized as.
It is well known that the fields such as criminal investigation, information are frequently necessary to use lie-detection technology, but it is only through artificially cross-examinees at present
It detects a lie, concealment behavior can not be identified effectively, the confidence level for the result that causes to detect a lie is not high.
Summary of the invention
The present invention is directed at least solve one of above-mentioned technical problem.
For this purpose, an object of the present invention is to provide a kind of EEG signals features of concealment behavior based on consciousness conflict
Detection method, this method can rapidly identify the brain electrical feature of concealment behavior, assess the answered credible result degree of measured, can
It applies and detects a lie in fields such as criminal investigation, information, can also be applied to special personnel choice, use scope is wide, strong applicability.
Second object of the present invention is to propose a kind of brain physiological characteristic detection system of concealment behavior.
To achieve the goals above, one aspect of the present invention proposes a kind of brain telecommunications of concealment behavior based on consciousness conflict
Number characteristic detection method, comprising the following steps: psychological test stimulus material based on collision detection theory and its special is provided
Operation reaction；Goal stimulus strengthens memory；Construct leading question or guidance scene；Based on the psychological test stimulus material, in conjunction with
Leading question or guidance scene test measured, obtain the EEG signals of the measured；The EEG signals are carried out
A variety of processing extract the event-related EEG characteristic pattern of concealment behavior, filter out concealment behavior from event related brain electrical feature figure
EEG signals characteristic index；It is hidden based on pattern-recognition and machine learning automatic identification according to the EEG signals characteristic index
Hide behavior from.
The EEG signals characteristic detection method of concealment behavior according to an embodiment of the present invention based on consciousness conflict, is based on thing
Part related potential, the extraction of brain electrical feature, analysis and identification technology, combine the evaluation result of brain electricity and performance indicators, can be fast
Speed efficiently identifies the Electroencephalo feature of concealment behavior, assesses the answered credible result degree of measured, can be applicable to criminal investigation, feelings
The fields such as report are detected a lie, and can also be applied to special personnel choice, and use scope is wide, strong applicability.
In addition, the EEG signals feature detection side of the concealment behavior according to the above embodiment of the present invention based on consciousness conflict
Method can also have the following additional technical features:
In some instances, the process that the EEG signals are carried out with a variety of processing, comprising: to the EEG signals
Successively carry out: electrode positioning, refer to, filter again, segmentation and baseline correction, reject bad section and interpolation badly lead, independent component analysis,
Event related potential analysis, temporal signatures are extracted, frequency domain character extracts, time and frequency domain characteristics are extracted, brain network characterization extracts, mode
Identification, machine learning processing.
In some instances, the psychological test stimulus material include at least control stimulus material, achromatic stimulus material and
Related stimulus material and its special reaction situation record.
In some instances, psychological test stimulus material and its special operation of the offer based on collision detection theory
Reaction, comprising: choose and investigate, investigate relevant picture, voice, video, material object as the related stimulus material；Choose quilt
It is that survey person's understanding can simultaneously identify to be used as the control with picture that is investigating, investigate unrelated place and personage, voice, video, material object
Stimulus material processed；It chooses the picture unrelated with investigation content or testing requirement, voice, video, material object and is used as the achromatic stimulus
Material；The case where providing and react the special operation of operator, obtaining special operation reaction records.
In some instances, the EEG signals characteristic index includes at least: control stimulus material, achromatic stimulus material and
The event related potential waveform of related stimulus material, wave amplitude, incubation period, spontaneous brain electricity prosodic feature, power spectrum, time-frequency characteristics,
When the reaction of brain network characterization and every kind of stimulus material, error rate.
To achieve the goals above, another aspect of the present invention propose it is a kind of based on consciousness conflict concealment behavior brain
Signal characteristics detection system, comprising: material module, for provide psychological test stimulus material based on collision detection theory and
Its special operation reaction；Reinforced module strengthens memory for carrying out goal stimulus；Construct module, for construct leading question or
Guide scene；Test module, for be based on the psychological test stimulus material, in conjunction with leading question or guidance scene to measured into
Row test, obtains the EEG signals of the measured；Processing module is extracted for carrying out a variety of processing to the EEG signals
The event-related EEG characteristic pattern of concealment behavior filters out the EEG signals feature of concealment behavior from event related brain electrical feature figure
Index；Automatic identification module, for being based on pattern-recognition and machine learning automatic identification according to the EEG signals characteristic index
Concealment behavior.
The EEG signals feature detection system of concealment behavior according to an embodiment of the present invention based on consciousness conflict, is based on thing
Part related potential, the extraction of brain electrical feature, analysis and identification technology, combine the evaluation result of brain electricity and performance indicators, can be fast
Speed efficiently identifies the Electroencephalo feature of concealment behavior, assesses the answered credible result degree of measured, can be applicable to criminal investigation, feelings
The fields such as report are detected a lie, and can also be applied to special personnel choice, and use scope is wide, strong applicability.
In addition, the EEG signals feature detection system of the concealment behavior according to the above embodiment of the present invention based on consciousness conflict
System can also have the following additional technical features:
In some instances, the processing module is used for: the EEG signals are successively carried out: electrode positions, refers to again,
It filters, segmentation is badly led with baseline correction, rejecting bad section and interpolation, independent component analysis, event related potential are analyzed, temporal signatures
Extraction, frequency domain character extraction, time and frequency domain characteristics extraction, the extraction of brain network characterization, pattern-recognition, machine learning processing.
In some instances, the psychological test stimulus material include at least control stimulus material, achromatic stimulus material and
Related stimulus material and its special reaction situation record.
In some instances, the material module is used for: being chosen and is investigated, investigates relevant picture, voice, video, reality
Object is as the related stimulus material；Choose measured recognize and can identify with investigate, investigate unrelated place and personage
Picture, voice, video, material object are used as the control stimulus material；Choose the picture unrelated with investigation content or testing requirement, language
Sound, video, material object are used as the achromatic stimulus material；It provides and the special operation of operator is reacted, obtain special operation reaction
The case where record.
In some instances, the EEG signals characteristic index includes at least: control stimulus material, achromatic stimulus material and
The event related potential waveform of related stimulus material, wave amplitude, incubation period, spontaneous brain electricity prosodic feature, power spectrum, time-frequency characteristics,
When the reaction of brain network characterization and every kind of stimulus material, error rate.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is the EEG signals feature detection side of the concealment behavior according to an embodiment of the invention based on consciousness conflict
The flow chart of method；
Fig. 2 is the EEG signals feature inspection of the concealment behavior based on consciousness conflict accord to a specific embodiment of that present invention
The realization schematic diagram of a scenario of survey method；
Fig. 3 is distribution of electrodes schematic diagram accord to a specific embodiment of that present invention；
Fig. 4 is time parameter schematic diagram in test process accord to a specific embodiment of that present invention；
Fig. 5 is according to an embodiment of the invention to the pretreated process schematic of EEG signals progress；
Fig. 6 is the EEG signals feature detection system of the concealment behavior according to an embodiment of the invention based on consciousness conflict
The structural block diagram of system.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
The EEG signals for describing the concealment behavior according to an embodiment of the present invention based on consciousness conflict below in conjunction with attached drawing are special
Levy detection method and system.
Fig. 1 is the EEG signals feature detection side of the concealment behavior according to an embodiment of the invention based on consciousness conflict
The flow chart of method.This method is based on the conflict monitoring theory in cognitive psychology, since the active consciousness and individual of concealment are to thorn
Swash and there is conflict between object subconsciousness, causes cognitive conflict monitoring brain area activation, to generate relevant EEG signals feature.Such as
It, should be based on the EEG signals characteristic detection method of the concealment behavior of consciousness conflict shown in Fig. 1, comprising the following steps:
Step S1: the psychological test stimulus material based on collision detection theory and its special operation reaction are provided.
Step S2: goal stimulus strengthens memory.
Step S3: building leading question or guidance scene.
Specifically, psychological test stimulus material includes at least control stimulus material, achromatic stimulus material and related stimulus material
Material and its special reaction situation record.
Control stimulus material is unrelated with investigating, investigating, but requires measured to remember and make the judgement material of identification, this is
Critical stimulus whether analyses and comparison case correlation.Achromatic stimulus material is the stimulus information without attached case information, with investigation
Demand of inside perhaps detecting a lie is unrelated, is to realize to carry out stimulus material for the purpose of cognition setoff with case relevant information, in number of words, word
Property, position etc. should be identical as far as possible as the problem of detecting in sentence, this is the basis for comparing reference.Related stimulus material be with investigate or
Demand of detecting a lie is related, the cognitive stimulation material of reflection case content, be detect measured's case is related, answer cognition question sentence can
The core of reliability assessment.
In one embodiment of the invention, psychological test stimulus material based on collision detection theory and its special is provided
Operation reaction process, comprising: choose with investigation, investigate relevant picture, voice, video, in kind be used as related stimulus material
Material；It is that selection measured's understanding can simultaneously identify to make with picture, voice, video, material object that investigate, investigate unrelated place and personage
To control stimulus material；It chooses the picture unrelated with investigation content or testing requirement, voice, video, material object and is used as achromatic stimulus
Material；The case where providing and react the special operation of operator, obtaining special operation reaction records.
As specific embodiment, preparation process before step S1 to S3 is surveyed.For example, tester leads measured to enter one
A place guides measured to examine and keep firmly in mind the place with different view, and to measured explain place relevant historical with
It deepens the impression.After inform measured today is seen herein to investigate, investigate relevant picture, voice, video,
Material object maintains secrecy.Afterwards, it will investigate, investigate relevant picture, voice, video, material object and handle, as related stimulus material
Material.Optionally take measured to recognize and can identify with investigate, investigate picture, voice, video, the material object in unrelated place and personage
As control stimulus material；The picture unrelated with investigation content or demand of detecting a lie, voice, video, material object are chosen as neutral thorn
Swash material.Further, the special operation reaction to operator is provided, and is recorded in time, special operation reaction is obtained
Situation record.Above-mentioned three classes stimulation picture classification is worked out, by pixel, gray scale, brightness, visual angle, view display area etc.
Reason and the similar close design of pictorial information guarantee to allow measured when recognizing picture as far as possible, the cognitive classification of picture
Difference, but the meanings such as scene shown by picture, people, object are close.
Step S4: being based on psychological test stimulus material, tests in conjunction with leading question or guidance scene measured, obtains
The EEG signals of measured.
As specific embodiment, step S4, that is, test implementation process.For example, tester (it can be tester above-mentioned, or
Person other testers) psychological test is carried out to measured and acquires EEG signals.Electrode when acquisition EEG signals is according to 10-20
International system distribution, as shown in Figure 3.First cross image of certain time length is presented when psychological test, on screen first (as schemed
The cross image in left side in 3), after first cross disappears, certain time length is presented in stimulus material, occurs second after disappearance to be stimulated
The cross image cross image of right side (in such as Fig. 3), the second cross are presented certain time length, measured need it is not only fast during this period but also
" standard " carry out key, relevant time parameter is as shown in Figure 4.
Step S5: a variety of processing are carried out to EEG signals, the event-related EEG characteristic pattern of concealment behavior are extracted, from event
Related brain electrical feature figure filters out the EEG signals characteristic index of concealment behavior.
Step S6: it according to EEG signals characteristic index, is concealed and is gone based on pattern-recognition and machine learning algorithm automatic identification
For.
In one embodiment of the invention, EEG signals are carried out with the process of a variety of processing, comprising: to EEG signals according to
Secondary progress: electrode is positioned, is referred to again, filtering, segmentation is badly led with baseline correction, rejecting bad section and interpolation, independent component analysis, thing
The analysis of part related potential, temporal signatures are extracted, frequency domain character extracts, time and frequency domain characteristics are extracted, brain network characterization extracts, mode is known
Not, a variety of processing such as machine learning.Wherein, electrode is positioned, is referred to again, filtering, being segmented and baseline correction, rejecting bad section and interpolation
It is bad to lead as preprocessing process.
Specifically, electrode localization process, i.e. the scalp branch of reading electrode positions file.
Weight reference process, as guarantees effectively to pre-process eeg data, is reference according to bilateral mastoid electrode
Eeg data is handled.
Filtering processing as achievees the purpose that, to eeg data noise reduction, general recommendations takes suitable filtering model to data
It encloses and is filtered.
Segmentation with baseline correction handle, i.e., according to stimulus type label eeg data is segmented, in order to it is subsequent into
Row superposed average.To prevent baseline drift, baseline correction has been carried out.
It rejects bad section and interpolation badly leads processing, i.e., eeg data is browsed, see whether that there are bad electrodes.Bad electrode
Refer to the electrode that data and remaining electrode numerical value differ greatly.If it is observed that bad electrode, can be used spherical shape interpolation algorithm into
Row interpolation replacement.
Independent component analysis processing, i.e., eye electricity, electrocardio, head in removal brain electricity move the noises such as artefact.
Pretreated multiple subject eeg datas are carried out ERP (Event by event related potential analysis processing
Related potential, event related potential) analysis, the eeg data of all subjects is successively carried out to electrode positioning, is joined again
It examines, filter, being segmented and badly led with baseline correction, rejecting bad section and interpolation, after independent component analysis processing, carrying out the average ERP of group
Analysis obtains concealment behavior brain electricity ERP feature.
Wherein, EEG signals characteristic index includes at least: control stimulus material, achromatic stimulus material and related stimulus material
Event related potential waveform, wave amplitude, incubation period, spontaneous brain electricity prosodic feature, power spectrum, time-frequency characteristics, brain network characterization with
And every kind of stimulus material reaction when, error rate.
As specific embodiment, step S5 to S6, that is, test result analysis process.For example, to above-mentioned three classes psychological test
The EEG signals that stimulus material induces carry out a variety of processing, the event-related EEG characteristic pattern of concealment behavior are extracted, from event phase
Close the EEG signals characteristic index that brain electrical feature figure filters out concealment behavior.A variety of processing steps include electrode position, refer to again,
It filters, segmentation is badly led with baseline correction, rejecting bad section and interpolation, independent component analysis, event related potential are analyzed, temporal signatures
Extraction, frequency domain character extraction, time and frequency domain characteristics extraction, the extraction of brain network characterization, pattern-recognition, machine learning processing, such as Fig. 5
It is shown.
As specific embodiment, Fig. 2 illustrates the EEG signals feature detection side of the concealment behavior based on consciousness conflict
One realization scene of method.As shown in Fig. 2, this method is for example related to electric psychological test hardware device, cognition during realization
Brain electrical measurement lie software, the psychological test stimulus material based on collision detection theory.
Wherein, brain electricity psychological test hardware device includes that can mutually tie Cognitive task trigger with the acquisition in real time of cognition brain electricity
Computer workstation, electrode cap, stimulation trigger, the brain wave acquisition amplification case, the stimulation display for inducing cognition brain electricity, reality of conjunction
When recognize electroencephaloscope.Cognition brain electrical measurement lie software includes that can stimulate cognitive informations such as display statement or pictures to be programmed
Induced by Stimulation software (such as the experiment software write based on E-prime) and with cognition induce there is the brain electricity of strong lock when property to adopt
Collect software, brain electricity analytical processing software.
Psychological test stimulus material based on collision detection theory include control stimulation, achromatic stimulus and related stimulus and its
Special reaction situation record, control stimulation is unrelated with investigating, investigating, but requires tested person to remember and make the judgement material of identification
Material, critical stimulus whether this is analyses and comparison case correlation；Achromatic stimulus is the stimulus information without attached case information, with tune
Demand of perhaps detecting a lie in looking into is unrelated, is to realize to carry out stimulus material for the purpose of cognition setoff with case relevant information, number of words,
Position etc. should be identical as far as possible as the problem of detecting in part of speech, sentence, this is the basis for comparing reference；Related stimulus is and investigates or survey
Lie demand is related, the cognitive stimulation material of reflection case content, is to detect that measured's case is related, it is credible to answer cognition question sentence
Spend the core of assessment.
In test, it is broadly divided into three phases, it may be assumed that 1, the preceding preparation of survey provide control stimulation, achromatic stimulus and phase joint needling
Swash these three types psychological test stimulus material and its special operation reaction；2, test implementation, obtaining three classes psychological test stimulates material
Expect corresponding EEG signals；3, interpretation of result carries out a variety of processing to the EEG signals of three classes psychological test stimulus material, extracts
The event-related EEG characteristic pattern of concealment behavior filters out the EEG signals feature of concealment behavior from event related brain electrical feature figure
Index, and behavior is concealed based on pattern-recognition and machine learning algorithm automatic identification.Since cognition brain electricity can reflect measured
To the psychophysiological reactions process of case related content, has the characteristics that high time resolution and non-invasive, and hardly by tested
The influence of person's subjective desire.The neuroelectricity variation of measured's brain cognitive process can not be pretended and be difficult to cover up, and and feelings
Thread association less, can be used for assessing the answered credible result degree of measured, can be applicable to the fields such as case investigation to detect a lie.
The EEG signals characteristic detection method of concealment behavior according to an embodiment of the present invention based on consciousness conflict, is based on thing
Part related potential, the extraction of brain electrical feature, analysis and identification technology, combine the evaluation result of brain electricity and performance indicators, can be fast
Speed efficiently identifies the Electroencephalo feature of concealment behavior, assesses the answered credible result degree of measured, can be applicable to criminal investigation, feelings
The fields such as report are detected a lie, and can also be applied to special personnel choice, and use scope is wide, strong applicability.
Further embodiment of the present invention also proposed a kind of EEG signals feature of concealment behavior based on consciousness conflict
Detection system.
Fig. 6 is the EEG signals feature detection system of the concealment behavior according to an embodiment of the invention based on consciousness conflict
The structural block diagram of system.The system is based on the conflict monitoring theory in cognitive psychology, since active consciousness and the individual of concealment are right
There is conflict between stimulant subconsciousness, causes cognitive conflict monitoring brain area activation, to generate relevant EEG signals feature.
As shown in fig. 6, should based on consciousness conflict concealment behavior EEG signals feature detection system 100 include: material module 110,
Reinforced module 120, building module 130, test module 140, processing module 150 and automatic identification module 160.
Wherein, material module 110 is used to provide psychological test stimulus material based on collision detection theory and its special
Operation reaction.
Reinforced module 120 strengthens memory for carrying out goal stimulus.
Building module 130 is for constructing leading question or guidance scene.
Specifically, psychological test stimulus material includes at least control stimulus material, achromatic stimulus material and related stimulus material
Material and its special reaction situation record.
Control stimulus material is unrelated with investigating, investigating, but requires measured to remember and make the judgement material of identification, this is
Critical stimulus whether analyses and comparison case correlation.Achromatic stimulus material is the stimulus information without attached case information, with investigation
Demand of inside perhaps detecting a lie is unrelated, is to realize to carry out stimulus material for the purpose of cognition setoff with case relevant information, in number of words, word
Property, position etc. should be identical as far as possible as the problem of detecting in sentence, this is the basis for comparing reference.Related stimulus material be with investigate or
Demand of detecting a lie is related, the cognitive stimulation material of reflection case content, be detect measured's case is related, answer cognition question sentence can
The core of reliability assessment.
In one embodiment of the invention, material module 110 provides the psychological test stimulation based on collision detection theory
Material and its special process for operating reaction, comprising: choose and investigate, investigate relevant picture, voice, video, work in kind
For related stimulus material；Choose measured recognize and can identify with investigate, investigate picture, the language in unrelated place and personage
Sound, video, in kind be used as control stimulus material；Choose the picture unrelated with investigation content or testing requirement, voice, video, reality
Object is as achromatic stimulus material；The case where providing and react the special operation of operator, obtaining special operation reaction records.
Test module 140 is used to be based on psychological test stimulus material, carries out in conjunction with leading question or guidance scene to measured
Test, obtains the EEG signals of measured.
Processing module 150 is used to carry out a variety of processing to EEG signals, extracts the event-related EEG feature of concealment behavior
Figure, the EEG signals characteristic index of concealment behavior is filtered out from event related brain electrical feature figure.
Automatic identification module 160 is used to be based on pattern-recognition and machine learning algorithm certainly according to EEG signals characteristic index
Dynamic identification concealment behavior.In one embodiment of the invention, processing module 150 carries out the mistake of a variety of processing to EEG signals
Journey, comprising: electrode positioning, refer to, filter again, segmentation and baseline correction, reject bad section and interpolation badly lead, independent component analysis,
Event related potential analysis, temporal signatures are extracted, frequency domain character extracts, time and frequency domain characteristics are extracted, brain network characterization extracts, mode
A variety of processing such as identification, machine learning.Wherein, electrode positioning, again refer to, filter, segmentation with baseline correction, reject bad section and insert
Value is bad to be led as preprocessing process.
Specifically, electrode localization process, i.e. the scalp branch of reading electrode positions file.
Weight reference process, as guarantees effectively to pre-process eeg data, is reference according to bilateral mastoid electrode
Eeg data is handled.
Filtering processing as achievees the purpose that, to eeg data noise reduction, general recommendations carries out data decimation OK range
Filtering.
Segmentation with baseline correction handle, i.e., according to stimulus type label eeg data is segmented, in order to it is subsequent into
Row superposed average.To prevent baseline drift, baseline correction has been carried out.
It rejects bad section and interpolation badly leads processing, i.e., eeg data is browsed, see whether that there are bad electrodes.Bad electrode
Refer to the electrode that data and remaining electrode numerical value differ greatly.If it is observed that bad electrode, can be used spherical shape interpolation algorithm into
Row interpolation replacement.
Independent component analysis processing, i.e., eye electricity, electrocardio, head in removal brain electricity move the noises such as artefact.
Pretreated multiple subject eeg datas are carried out ERP analysis, will owned by event related potential analysis processing
The eeg data of subject successively carry out electrode positioning, refer to, filter again, segmentation and baseline correction, reject bad section and interpolation badly lead,
After independent component analysis processing, the average ERP analysis of group is carried out, concealment behavior brain electricity ERP feature is obtained.
Wherein, EEG signals characteristic index includes at least: control stimulus material, achromatic stimulus material and related stimulus material
Event related potential waveform, wave amplitude, incubation period, spontaneous brain electricity prosodic feature, power spectrum, time-frequency characteristics, brain network characterization with
And every kind of stimulus material reaction when, error rate.
It should be noted that the EEG signals feature detection system of the concealment behavior based on consciousness conflict of the embodiment of the present invention
The EEG signals characteristic detection method of the specific implementation of system and the concealment behavior of the embodiment of the present invention to be conflicted based on consciousness
Specific implementation it is similar, specifically refer to the description of method part, in order to reduce redundancy, details are not described herein again.
The EEG signals feature detection system of concealment behavior according to an embodiment of the present invention based on consciousness conflict, is based on thing
Part related potential, the extraction of brain electrical feature, analysis and identification technology, combine the evaluation result of brain electricity and performance indicators, can be fast
Speed efficiently identifies the Electroencephalo feature of concealment behavior, assesses the answered credible result degree of measured, can be applicable to criminal investigation, feelings
The fields such as report are detected a lie, and can also be applied to special personnel choice, and use scope is wide, strong applicability.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is by claim and its equivalent limits.
Claims (10)
1. a kind of EEG signals characteristic detection method of the concealment behavior based on consciousness conflict, which is characterized in that including following step
It is rapid:
Psychological test stimulus material based on collision detection theory and its special operation reaction are provided；
Goal stimulus strengthens memory；
Construct leading question or guidance scene；
Based on the psychological test stimulus material, measured is tested in conjunction with leading question or guidance scene, obtains the quilt
The EEG signals of survey person；
A variety of processing are carried out to the EEG signals, the event-related EEG characteristic pattern of concealment behavior are extracted, from event related brain
Electrical feature figure filters out the EEG signals characteristic index of concealment behavior；
According to the EEG signals characteristic index, behavior is concealed based on pattern-recognition and machine learning automatic identification.
2. the EEG signals characteristic detection method of the concealment behavior according to claim 2 based on consciousness conflict, feature
It is, the process that the EEG signals are carried out with a variety of processing, comprising:
Successively carry out to the EEG signals: bad section and interpolation are rejected in electrode positioning, again reference, filtering, segmentation and baseline correction
It is bad lead, the analysis of independent component analysis, event related potential, temporal signatures extract, frequency domain character extracts, time and frequency domain characteristics are extracted,
The extraction of brain network characterization, pattern-recognition, machine learning processing.
3. the EEG signals characteristic detection method of the concealment behavior according to claim 1 or 2 based on consciousness conflict, special
Sign is, the psychological test stimulus material include at least control stimulus material, achromatic stimulus material and related stimulus material and
Its special reaction situation record.
4. the EEG signals characteristic detection method of the concealment behavior according to claim 3 based on consciousness conflict, feature
It is, psychological test stimulus material and its special operation reaction of the offer based on collision detection theory, comprising:
It chooses and investigates, investigates relevant picture, voice, video, material object as the related stimulus material；
Choose measured recognize and can identify with investigate, investigate picture, voice, video, the material object in unrelated place and personage
As the control stimulus material；
It chooses the picture unrelated with investigation content or testing requirement, voice, video, material object and is used as the achromatic stimulus material；
The case where providing and react the special operation of operator, obtaining special operation reaction records.
5. the EEG signals characteristic detection method of the concealment behavior according to claim 1 based on consciousness conflict, feature
It is, the EEG signals characteristic index includes at least: the thing of control stimulus material, achromatic stimulus material and related stimulus material
Part related potential waveform, wave amplitude, incubation period, spontaneous brain electricity prosodic feature, power spectrum, time-frequency characteristics, brain network characterization and every
When the reaction of kind of stimulus material, error rate.
6. a kind of EEG signals feature detection system of the concealment behavior based on consciousness conflict characterized by comprising
Material module, for providing psychological test stimulus material and its special operation reaction based on collision detection theory；
Reinforced module strengthens memory for carrying out goal stimulus；
Module is constructed, for constructing leading question or guidance scene；
Test module surveys measured in conjunction with leading question or guidance scene for being based on the psychological test stimulus material
Examination, obtains the EEG signals of the measured；
Processing module, for extracting the event-related EEG characteristic pattern of concealment behavior to a variety of processing of EEG signals progress,
The EEG signals characteristic index of concealment behavior is filtered out from event related brain electrical feature figure；
Automatic identification module, for being based on pattern-recognition and machine learning automatic identification according to the EEG signals characteristic index
Concealment behavior.
7. the EEG signals feature detection system of the concealment behavior according to claim 6 based on consciousness conflict, feature
It is, the processing module is used for: the EEG signals is successively carried out: electrode positioning, again reference, filtering, segmentation and baseline
It corrects, reject that bad section is badly led with interpolation, the analysis of independent component analysis, event related potential, temporal signatures extract, frequency domain character mentions
It takes, time and frequency domain characteristics extraction, the extraction of brain network characterization, pattern-recognition, machine learning processing.
8. the EEG signals feature detection system of the concealment behavior according to claim 6 or 7 based on consciousness conflict, special
Sign is, the psychological test stimulus material include at least control stimulus material, achromatic stimulus material and related stimulus material and
Its special reaction situation record.
9. the EEG signals feature detection system of the concealment behavior according to claim 8 based on consciousness conflict, feature
It is, the material module is used for:
It chooses and investigates, investigates relevant picture, voice, video, material object as the related stimulus material；
Choose measured recognize and can identify with investigate, investigate picture, voice, video, the material object in unrelated place and personage
As the control stimulus material；
It chooses the picture unrelated with investigation content or testing requirement, voice, video, material object and is used as the achromatic stimulus material.
The case where providing and react the special operation of operator, obtaining special operation reaction records.
10. the EEG signals feature detection system of the concealment behavior according to claim 6 based on consciousness conflict, feature
It is, the EEG signals characteristic index includes at least: the thing of control stimulus material, achromatic stimulus material and related stimulus material
Part related potential waveform, wave amplitude, incubation period, spontaneous brain electricity prosodic feature, power spectrum, time-frequency characteristics, brain network characterization and every
When the reaction of kind of stimulus material, error rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910775030.2A CN110477911A (en) | 2019-08-21 | 2019-08-21 | The EEG signals characteristic detection method and system of concealment behavior based on consciousness conflict |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910775030.2A CN110477911A (en) | 2019-08-21 | 2019-08-21 | The EEG signals characteristic detection method and system of concealment behavior based on consciousness conflict |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110477911A true CN110477911A (en) | 2019-11-22 |
Family
ID=68552578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910775030.2A Pending CN110477911A (en) | 2019-08-21 | 2019-08-21 | The EEG signals characteristic detection method and system of concealment behavior based on consciousness conflict |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110477911A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111281382A (en) * | 2020-03-04 | 2020-06-16 | 徐州市健康研究院有限公司 | Feature extraction and classification method based on electroencephalogram signals |
| CN112641450A (en) * | 2020-12-28 | 2021-04-13 | 中国人民解放军战略支援部队信息工程大学 | Time-varying brain network reconstruction method for dynamic video target detection |
| CN113208634A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Attention detection method and system based on EEG brain waves |
| CN113662545A (en) * | 2021-08-09 | 2021-11-19 | 南京航空航天大学 | Personality assessment method based on emotion electroencephalogram signals and multitask learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4941477A (en) * | 1987-09-09 | 1990-07-17 | University Patents, Inc. | Method and apparatus for detection of deception |
| US20120226108A1 (en) * | 2011-03-04 | 2012-09-06 | Ivan Osorio | Detecting, assessing and managing extreme epileptic events |
| CN105852885A (en) * | 2016-03-23 | 2016-08-17 | 陕西师范大学 | N400 evoked potential lie detection method based on improved extreme learning machine |
| CN108309329A (en) * | 2018-02-08 | 2018-07-24 | 陕西师范大学 | A kind of CNV brain electricity lie detecting methods based on brain network analysis |
-
2019
- 2019-08-21 CN CN201910775030.2A patent/CN110477911A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4941477A (en) * | 1987-09-09 | 1990-07-17 | University Patents, Inc. | Method and apparatus for detection of deception |
| US20120226108A1 (en) * | 2011-03-04 | 2012-09-06 | Ivan Osorio | Detecting, assessing and managing extreme epileptic events |
| CN105852885A (en) * | 2016-03-23 | 2016-08-17 | 陕西师范大学 | N400 evoked potential lie detection method based on improved extreme learning machine |
| CN108309329A (en) * | 2018-02-08 | 2018-07-24 | 陕西师范大学 | A kind of CNV brain electricity lie detecting methods based on brain network analysis |
Non-Patent Citations (1)
| Title |
|---|
| 关楠思 等: "人隐瞒信息状态下多通道事件相关电位的研究", 《中国法医学杂志》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111281382A (en) * | 2020-03-04 | 2020-06-16 | 徐州市健康研究院有限公司 | Feature extraction and classification method based on electroencephalogram signals |
| CN111281382B (en) * | 2020-03-04 | 2023-08-18 | 徐州市健康研究院有限公司 | Feature extraction and classification method based on electroencephalogram signals |
| CN112641450A (en) * | 2020-12-28 | 2021-04-13 | 中国人民解放军战略支援部队信息工程大学 | Time-varying brain network reconstruction method for dynamic video target detection |
| CN112641450B (en) * | 2020-12-28 | 2023-05-23 | 中国人民解放军战略支援部队信息工程大学 | Time-varying brain network reconstruction method for dynamic video target detection |
| CN113208634A (en) * | 2021-04-07 | 2021-08-06 | 北京脑陆科技有限公司 | Attention detection method and system based on EEG brain waves |
| CN113662545A (en) * | 2021-08-09 | 2021-11-19 | 南京航空航天大学 | Personality assessment method based on emotion electroencephalogram signals and multitask learning |
| CN113662545B (en) * | 2021-08-09 | 2022-10-14 | 南京航空航天大学 | Personality assessment method based on emotion electroencephalogram signals and multitask learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110477911A (en) | The EEG signals characteristic detection method and system of concealment behavior based on consciousness conflict | |
| Kanna et al. | Systematic Design Of Lie Detector System Utilizing EEG Signals Acquisition | |
| CN105249963B (en) | N400 Evoked ptential lie detecting methods based on Sample Entropy | |
| KR101247748B1 (en) | Apparatus for analysing focus and nonfocus states and method therof | |
| CN113420624B (en) | Non-contact fatigue detection method and system | |
| US6804661B2 (en) | Drug profiling apparatus and method | |
| US10786173B2 (en) | Similarity evaluation method using brain waves, evaluation device, evaluation system, and program | |
| US20110227737A1 (en) | Physiological Sign Assessment Security Scanner System | |
| JP2004527313A (en) | Subject behavior analysis | |
| WO2009144735A4 (en) | Electronic investigative device and method for identifying the truth | |
| CN112150759A (en) | Real-time monitoring and early warning system and method based on video algorithm | |
| AU2003214007A1 (en) | Device for locating the target spot of electrodes used for brain stimulation, particularly deep brain stimulation | |
| CN113822164A (en) | Dynamic emotion recognition method and device, computer equipment and storage medium | |
| CN111616702A (en) | Lie detection analysis system based on cognitive load enhancement | |
| Voss et al. | 3.05 neural substrates of remembering–electroencephalographic studies | |
| CN109684296A (en) | Brain line identification database construction method, device, computer equipment and storage medium | |
| Erim et al. | Decomposition of intramuscular EMG signals using a heuristic fuzzy expert system | |
| CN113647950A (en) | Psychological emotion detection method and system | |
| CN111714089A (en) | Drug addiction evaluation system based on multi-stimulus short video event related potential | |
| García-Pérez et al. | The do’s and don’ts of psychophysical methods for interpretability of psychometric functions and their descriptors | |
| CN109965873A (en) | Biological function measuring and analysis system, method and recording medium | |
| CN112932485A (en) | Non-contact type conversation confidence rate testing system and method | |
| CN113180668A (en) | Real-time functional magnetic resonance lie detection system based on cognitive load change | |
| Marcelo et al. | Characterization and comparison of brain wave signals during deception | |
| JP7246716B2 (en) | Brain function state measuring device and program for determining brain function state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191122 |