CN109394248A - Driving fatigue detection method and system - Google Patents
Driving fatigue detection method and system Download PDFInfo
- Publication number
- CN109394248A CN109394248A CN201811576142.7A CN201811576142A CN109394248A CN 109394248 A CN109394248 A CN 109394248A CN 201811576142 A CN201811576142 A CN 201811576142A CN 109394248 A CN109394248 A CN 109394248A
- Authority
- CN
- China
- Prior art keywords
- sample
- fatigue
- driver
- value
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 239000013598 vector Substances 0.000 claims abstract description 76
- 238000004364 calculation method Methods 0.000 claims abstract description 47
- 238000005070 sampling Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 23
- 210000001061 forehead Anatomy 0.000 claims abstract description 13
- 210000004556 brain Anatomy 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 45
- 230000008859 change Effects 0.000 claims description 17
- 238000002474 experimental method Methods 0.000 claims description 2
- 238000010835 comparative analysis Methods 0.000 claims 1
- 238000012935 Averaging Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 230000002360 prefrontal effect Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000000737 periodic effect Effects 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect 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
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- 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
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Educational Technology (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Social Psychology (AREA)
- Hospice & Palliative Care (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 invention discloses a kind of driving fatigue detection method and systems, this method comprises: according to the EEG signals of multiple two lead of continuous acquisition driver forehead of preset sample frequency, to obtain EEG signals sample；EEG signals sample is divided according to the sampling period, is formed using the sampling period as the sample vector set of length；Calculate the synchronism of two leads of each sample vector set；Period discretization is carried out to the synchronism result being calculated, to screen out unusual sample, obtains target sample；According to target sample and the driving fatigue state variation characteristic of driver, fatigue threshold is determined；Whether the EEG signals of online acquisition driver calculate synchronism as a result, the synchronism result calculated in real time is compared and analyzed with fatigue threshold in real time, are fatigue state to determine driver currently.The present invention be able to solve full brain area lead it is difficult in practical applications, can not successional detection driver fatigue state and the excessively complicated problem of calculation method.
Description
Technical field
The present invention relates to driving safety technical fields, more particularly to a kind of driving fatigue detection method and system.
Background technique
Driver information acquisition, information processing and manipulation caused by driving fatigue refers to due to continuous driving for a long time
The phenomenon that ability declines.Driver is during long-duration driving, and Yi Yinfa driving fatigue is anti-to emergency event so as to cause it
Extension between seasonable, influences driving safety.In order to avoid driving fatigue it is necessary to when there is fatigue state in driver to driving
Member is reminded.
Driving fatigue detection method based on EEG signals is the primary solutions of current driving fatigue detection, but at present
The driving fatigue detection method based on EEG signals there is problems:
One, signal acquisition uses full brain area, although the accuracy of fatigue detecting can be improved in laboratory using full brain area,
But in addition to two leads of prefrontal area are not covered by hair, other leads are had any problem in practical applications；
Two, fatigue detecting of today is fatigue state to be divided into extremely tired and not tired two states mostly, realizes two
Value detection, but fatigue is a continuity, a kind of gradual physiological change, and the fatigue detecting of binaryzation is likely to make
It is extremely tired at driver, just it is detected, and be likely to have occurred that traffic accident at this time；
Three, fatigue detecting calculation method is excessively complicated, and fatigue detection result is caused to lag.
Summary of the invention
For this purpose, being existed an object of the present invention is to provide a kind of driving fatigue detection method with solving full brain area lead
It is difficult in practical application, can not successional detection driver fatigue state and the excessively complicated problem of calculation method.
A kind of driving fatigue detection method, comprising:
According to the EEG signals of multiple two lead of continuous acquisition driver forehead of preset sample frequency, to obtain in tired
The EEG signals sample of labor state；
The EEG signals sample is divided according to the sampling period, is formed using the sampling period as the sample vector of length
Set；
Calculate the synchronism of two leads of each sample vector set；
Period discretization is carried out to the synchronism result being calculated, to screen out unusual sample, obtains target sample；
According to the target sample and the driving fatigue state variation characteristic of driver, fatigue threshold is determined；
The EEG signals of online acquisition driver, in real time calculate synchronism as a result, by the synchronism result calculated in real time with
Whether the fatigue threshold compares and analyzes, be fatigue state to determine driver currently.
The driving fatigue detection method provided according to the present invention, at least has the advantages that
1) present invention can be avoided its EEG signals and lead in acquisition because covered using two lead of forehead as signal source
Cause acquires difficult problem, and can be realized the detection effect of high-accuracy by two lead synchronism calculation methods；
2) present invention is using two lead synchronism values as output as a result, passing through the output successive value conduct of each sampling period
Foundation is detected, real-time data output may be implemented, so as to the fatigue state of real-time, successional detection driver；
3) in the prior art, output real number value is carried out using prefrontal area lead mainly to be exported using the method for entropy,
But the output method of entropy needs that time domain periodic signal is reconstructed, time complexity is high, and the present invention uses synchronism meter
It calculates, time complexity is small, and calculating process is simpler, it is easy to accomplish, it can be avoided fatigue detection result lag.
In addition, above-mentioned driving fatigue detection method according to the present invention, can also have the following additional technical features:
Further, phase is used in the step of synchronism of two leads for calculating each sample vector set
Bit synchronization calculation method, specifically:
The calculation method of locking phase value PLV between two leads is as follows:
It is thereinIt is time series xi(t) and xj(t) instantaneous phase, when being calculated using Hilbert transform
The phase change of domain signal, for a continuous time series x (t), Hilbert transform is obtained by following formula:
PV therein indicates that Cauchy's principal value, phase change are calculated by following formula:
Further, when being used in the step of synchronism of two leads for calculating each sample vector set
Domain vector synchronizes calculation method, specifically:
Wherein t is the time component in EEG signals sample, and N is a sample period lengths, xiAnd xjRespectively indicate two
The sample time-series of electrode.
Further, described to divide to the EEG signals sample according to the sampling period, composition is with the sampling period
The step of sample vector set of length includes:
According to sample frequency truncated data, for once testing the signal for M minutes, by the square of sample composition 2*60M*H
Battle array, wherein 60M is the number of seconds of sampling, and H is the H data point of acquisition in one second, and 2 be two leads.
Further, the described pair of synchronism result progress period discretization being calculated is obtained with screening out unusual sample
Target sample the step of include:
In the matrix for the synchronism result being calculated, choose every a line, according to step-length 60 by the matrix to
Amount is divided into the vector of M, then retains 2 significant digits, to obtain the matrix of L*60, wherein L is sample number；
The distance between the every row of matrix of L*60 is calculated, to reject unusual sample, calculation method is to calculate row vector first
Between Fisher distance, calculation formula are as follows:
The wherein mean value of μ representation vector, the standard deviation of σ representation vector, Fi,jCalculated result is the matrix of L*L, and limits
Fi,jValue；
Statistical sample, if it exists vector m, wherein FimOr FjmMore than the F of restrictioni,jValue, it is determined that m is unusual sample,
The unusual sample m is rejected.
Further, described according to the target sample and the driving fatigue state variation characteristic of driver, it determines tired
The step of labor threshold value includes:
Calculate the matrix of the target sample；
Using M/2 as step-length, the matrix of the target sample is averaging according to row, is then averaging according to column, finally
To being two number of front half section numerical value and second half section numerical value；
The second half section numerical value is determined as fatigue threshold.
Further, the EEG signals of the online acquisition driver calculate synchronism in real time as a result, will calculate in real time
Synchronism result is compared and analyzed with the fatigue threshold, with the step of whether determine driver currently be fatigue state packet
It includes:
The EEG signals of online acquisition driver, the synchronism of calculating in every 1 second, obtain a numerical value, if the value is super
Cross the fatigue threshold, then the fatigue state of this second be labeled as 1, be otherwise labeled as 0, Continuous plus 1 minute, obtain marking to
Amount sums to the label vector, if summed result is more than preset value, determines that driver is currently at fatigue state, and export
The fatigue data of last second.
It is another object of the present invention to propose a kind of driving fatigue detection system, to solve full brain area lead in reality
It is difficult in, can not successional detection driver fatigue state and the excessively complicated problem of calculation method.
A kind of driving fatigue detection system, the system comprises:
Acquisition module, for the brain telecommunications according to multiple two lead of continuous acquisition driver forehead of preset sample frequency
Number, to obtain EEG signals sample in a state of fatigue；
Division module, for dividing to the EEG signals sample according to the sampling period, composition is with the sampling period
The sample vector set of length；
Computing module, the synchronism of two leads for calculating each sample vector set；
Discrete block is obtained for carrying out period discretization to the synchronism result being calculated with screening out unusual sample
Obtain target sample；
Threshold determination module, for the driving fatigue state variation characteristic according to the target sample and driver, really
Determine fatigue threshold；
Tired determining module calculates synchronism as a result, will count in real time for the EEG signals of online acquisition driver in real time
Whether the synchronism result of calculation is compared and analyzed with the fatigue threshold, be fatigue state to determine driver currently.
The driving fatigue detection system provided according to the present invention, at least has the advantages that
1) present invention can be avoided its EEG signals and lead in acquisition because covered using two lead of forehead as signal source
Cause acquires difficult problem, and can be realized the detection effect of high-accuracy by two lead synchronism calculation methods；
2) present invention is using two lead synchronism values as output as a result, passing through the output successive value conduct of each sampling period
Foundation is detected, real-time data output may be implemented, so as to the fatigue state of real-time, successional detection driver；
3) in the prior art, output real number value is carried out using prefrontal area lead mainly to be exported using the method for entropy,
But the output method of entropy needs that time domain periodic signal is reconstructed, time complexity is high, and the present invention uses synchronism meter
It calculates, time complexity is small, and calculating process is simpler, it is easy to accomplish, it can be avoided fatigue detection result lag.
In addition, above-mentioned driving fatigue detection system according to the present invention, can also have the following additional technical features:
Further, the computing module can calculate synchronism using Phase synchronization calculation method and calculate each sample
The synchronism of two leads of this vector set, specifically:
The calculation method of locking phase value PLV between two leads is as follows:
It is thereinIt is time series xi(t) and xj(t) instantaneous phase, when being calculated using Hilbert transform
The phase change of domain signal, for a continuous time series x (t), Hilbert transform is obtained by following formula:
PV therein indicates that Cauchy's principal value, phase change are calculated by following formula:
Further, the computing module can calculate each sample vector using the synchronous calculation method of time-domain vector
The synchronism of two leads of set, specifically:
Wherein t is the time component in EEG signals sample, and N is a sample period lengths, xiAnd xjRespectively indicate two
The sample time-series of electrode.
Further, the division module is specifically used for:
According to sample frequency truncated data, for once testing the signal for M minutes, by the square of sample composition 2*60M*H
Battle array, wherein 60M is the number of seconds of sampling, and H is the H data point of acquisition in one second, and 2 be two leads.
Further, the discrete block is specifically used for:
In the matrix for the synchronism result being calculated, choose every a line, according to step-length 60 by the matrix to
Amount is divided into the vector of M, then retains 2 significant digits, to obtain the matrix of L*60, wherein L is sample number；
The distance between the every row of matrix of L*60 is calculated, to reject unusual sample, calculation method is to calculate row vector first
Between Fisher distance, calculation formula are as follows:
The wherein mean value of μ representation vector, the standard deviation of σ representation vector, Fi,jCalculated result is the matrix of L*L, and limits
Fi,jValue；
Statistical sample, if it exists vector m, wherein FimOr FjmMore than the F of restrictioni,jValue, it is determined that m is unusual sample,
The unusual sample m is rejected.
Further, the threshold determination module is specifically used for:
Calculate the matrix of the target sample；
Using M/2 as step-length, the matrix of the target sample is averaging according to row, is then averaging according to column, finally
To being two number of front half section numerical value and second half section numerical value；
The second half section numerical value is determined as fatigue threshold.
Further, the tired determining module is specifically used for:
The EEG signals of online acquisition driver, the synchronism of calculating in every 1 second, obtain a numerical value, if the value is super
Cross the fatigue threshold, then the fatigue state of this second be labeled as 1, be otherwise labeled as 0, Continuous plus 1 minute, obtain marking to
Amount sums to the label vector, if summed result is more than preset value, determines that driver is currently at fatigue state, and export
The fatigue data of last second.
Detailed description of the invention
The above-mentioned and/or additional aspect and advantage of the embodiment of the present invention are from the description of the embodiment in conjunction with the following figures
It will be apparent and be readily appreciated that, in which:
Fig. 1 is the flow chart of driving fatigue detection method according to a first embodiment of the present invention；
Fig. 2 is the structural schematic diagram of driving fatigue detection system according to a second embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, the driving fatigue detection method that first embodiment of the invention proposes, including step S101~S103:
S101, according to the EEG signals of multiple two lead of continuous acquisition driver forehead of preset sample frequency, to obtain
EEG signals sample in a state of fatigue；
Wherein it is possible to utilize existing portable electroencephalogramsignal signal collection equipment (such as the two lead brain electricity of forehead of neurosky
Signal collecting device) acquisition two lead of driver's forehead EEG signals, multiple continuous acquisition, sample frequency are carried out to driver
It may be configured as 256Hz or 512Hz or 1000Hz or 1024Hz etc., can be selected according to the actual situation using frequency
It selects, herein with no restrictions.
In the present embodiment, sample frequency is illustrated by taking 1000Hz as an example, continuous acquisition driver EEG signals 40 minutes,
Repeatedly to each subject (i.e. driver) acquisition, a questionnaire is done to subject, is determined tested after the completion of acquisition every time
Whether person there is fatigue, when subject's questionnaire result is fatigue occur, then saves the sample, is otherwise acquired, this
In embodiment, sample number is more than or equal to 30 in final subject's sample set, then can stop acquisition experiment.
S102 divides the EEG signals sample according to the sampling period, forms using the sampling period as the sample of length
This vector set；
Wherein, when it is implemented, can be according to sample frequency truncated data, it, will for once testing the signal for M minutes
Sample forms the matrix of 2*60M*H, and wherein 60M is the number of seconds of sampling, and H is the H data point of acquisition in one second, and 2 be two leads.
Specifically in the present embodiment, according to sample frequency truncated data, for once testing the signal for 40 minutes, then should
Sample can form the matrix of 2*2400*1000, wherein 2400 be 40 minutes sampling times (number of seconds), 1000 be to acquire for one second
1000 data points (corresponding sample frequency 1000Hz), 2 be to represent two leads.
S103 calculates the synchronism of two leads of each sample vector set；
Wherein, calculate two leads of each sample vector set synchronism can using Phase synchronization or time domain to
The multiple synchronizations calculation methods such as amount synchronizes.
The detailed process of the synchronism of two leads is calculated using Phase synchronization calculation method are as follows:
The calculation method of locking phase value PLV between two leads is as follows:
It is thereinIt is time series xi(t) and xj(t) instantaneous phase, when being calculated using Hilbert transform
The phase change of domain signal, for a continuous time series x (t), Hilbert transform is obtained by following formula:
PV therein indicates that Cauchy's principal value, phase change are calculated by following formula:
Following formula is used using the specific of synchronism that the synchronous calculation method of time-domain vector calculates two leads:
Wherein t is the time component in EEG signals sample, and N is a sample period lengths, xiAnd xjRespectively indicate two
The sample time-series of electrode.
Specifically in the present embodiment, the calculating of the synchronism of two leads is carried out using the synchronous calculation method of time-domain vector.
Wherein, N=1000 is a sample period lengths, xiAnd xjSample time-series for respectively indicating two electrodes, to each sample
Originally one 2400 vector can be calculated, each value of the vector indicates the two lead EEG signals synchronisms at this second moment
Value, 30 samples can be constructed as the matrix of 30*2400, wherein 30 be sample number.
S104 carries out period discretization to the synchronism result being calculated, and to screen out unusual sample, obtains target sample
This；
Wherein, specifically unusual sample can be screened out using following methods:
In the matrix for the synchronism result being calculated, choose every a line, according to step-length 60 by the matrix to
Amount is divided into the vector of M, then retains 2 significant digits, to obtain the matrix of L*60, wherein L is sample number；
The distance between the every row of matrix of L*60 is calculated, to reject unusual sample, calculation method is to calculate row vector first
Between Fisher distance, calculation formula are as follows:
The wherein mean value of μ representation vector, the standard deviation of σ representation vector, Fi,jCalculated result is the matrix of L*L, and limits
Fi,jValue；
Statistical sample, if it exists vector m, wherein FimOr FjmMore than the F of restrictioni,jValue, it is determined that m is unusual sample,
The unusual sample m is rejected.
Specifically in the present embodiment, every a line is chosen, the vector that 2400 vector is divided into 40 (i.e. will according to step-length 60
It is divided within 2400 seconds 40 minutes), then retain 2 significant digits, obtains the matrix of 30*60 in this way, wherein L=30；
Calculate the distance between the every row of matrix of 30*60, to reject unusual sample, calculation method is, firstly, calculate row to
Fisher distance between amount, calculation formula are as follows:
Wherein μ represents the mean value of the vector, and σ represents the standard deviation of the vector, and F calculated result is the matrix of 30*30.Then
The value for limiting F limits F in this implementation as 1.8, works as Fi,jGreater than 1.8, then having one in i j row sample is unusual sample,
Statistical sample, if there is some F value, it is assumed that it is i and j row, which shows that distance is not above 1.8 between i and j row,
So tentative i and j row is not singular vector, if any another vector m, wherein FimOr FjmMore than 1.8, then can be with
Determine that m is unusual sample.In the present embodiment, 25 samples are finally filtered out from 30 samples.
S105 determines fatigue threshold according to the target sample and the driving fatigue state variation characteristic of driver；
Wherein, it since the appearance of fatigue is a progressive process, in order to simplify threshold value determination process, can use following
Method determines fatigue threshold:
Calculate the matrix of the target sample, in the present embodiment, (1) calculates the matrix (25 for the 25*40 that step S104 is obtained
It is the sample number deleted after choosing, 40 be the vector that step S104 is calculated)；
Using M/2 as step-length, the matrix of the target sample is averaging according to row, is then averaging according to column, finally
Be step-length with 20 in the present embodiment to being two number of front half section numerical value and second half section numerical value, to the matrix of meter target sample according to
Row is averaging, and finally obtains the matrix of 25*2, is then averaging according to column, finally obtaining is two numbers, in the present embodiment, most
After obtain being front half section numerical value and two number of second half section numerical value being specially (0.64,0.35)；
Since the appearance of fatigue is a progressive process, and usually by not fatigue state to fatigue state, therefore will
Second half section numerical value is determined as fatigue threshold, i.e. fatigue threshold is 0.35.
In addition, as a specific example, since everyone cognition whether in a state of fatigue to oneself may not
Together, therefore, when calculating fatigue threshold, driver can be right in a certain range on the basis of calculated fatigue threshold
Fatigue threshold is adjusted, such as driver's fatigue resistance is stronger, fatigue threshold can be adjusted to 0.4, conversely, if driving
Member's fatigue resistance is weaker, fatigue threshold can be adjusted to 0.3, will be adjusted tired more to meet itself fatigue state
The standard of labor threshold value judgement subsequent.
S106, the EEG signals of online acquisition driver calculate synchronism as a result, the synchronism knot that will be calculated in real time in real time
Whether fruit compares and analyzes with the fatigue threshold, be fatigue state to determine driver currently.
Wherein, the EEG signals of online acquisition driver, the synchronism of calculating in every 1 second, obtain a numerical value, if should
Value is more than the fatigue threshold, then the fatigue state of this second is labeled as 1, otherwise labeled as 0, Continuous plus 1 minute (i.e. 60
Second), obtain label vector, to the label vector sum, if summed result be more than preset value (preset value can be adjusted,
Preset value is, for example, 40, if summed result is more than 40), to determine that driver's current (minute) is in a state of fatigue.In addition, by
In under normal circumstances, if it is determined that being fatigue state, within 1 minute time, the fatigue data of last usual second is maximum, therefore can
To export the fatigue data of last second, as final detection result.
According to driving fatigue detection method provided in this embodiment, at least have the advantages that
1) present invention can be avoided its EEG signals and lead in acquisition because covered using two lead of forehead as signal source
Cause acquires difficult problem, and can be realized the detection effect of high-accuracy by two lead synchronism calculation methods；
2) present invention is using two lead synchronism values as output as a result, passing through the output successive value conduct of each sampling period
Foundation is detected, real-time data output may be implemented, so as to the fatigue state of real-time, successional detection driver；
3) in the prior art, output real number value is carried out using prefrontal area lead mainly to be exported using the method for entropy,
But the output method of entropy needs that time domain periodic signal is reconstructed, time complexity is high, and the present invention uses synchronism meter
It calculates, time complexity is small, and calculating process is simpler, it is easy to accomplish, it can be avoided fatigue detection result lag.
Referring to Fig. 2, based on the same inventive concept, the driving fatigue detection system that second embodiment of the invention proposes, institute
The system of stating includes:
Acquisition module 10, for the brain telecommunications according to multiple two lead of continuous acquisition driver forehead of preset sample frequency
Number, to obtain EEG signals sample in a state of fatigue；
Division module 20 is formed for dividing to the EEG signals sample according to the sampling period with the sampling period
For the sample vector set of length；
Computing module 30, the synchronism of two leads for calculating each sample vector set；
Discrete block 40, for carrying out period discretization to the synchronism result being calculated, to screen out unusual sample,
Obtain target sample；
Threshold determination module 50, for the driving fatigue state variation characteristic according to the target sample and driver,
Determine fatigue threshold；
Tired determining module 60 calculates synchronism as a result, by real-time for the EEG signals of online acquisition driver in real time
Whether the synchronism result of calculating is compared and analyzed with the fatigue threshold, be fatigue state to determine driver currently.
Wherein, the computing module 30 can calculate synchronism using Phase synchronization calculation method and calculate each sample
The synchronism of two leads of vector set, specifically:
The calculation method of locking phase value PLV between two leads is as follows:
It is thereinIt is time series xi(t) and xj(t) instantaneous phase, when being calculated using Hilbert transform
The phase change of domain signal, for a continuous time series x (t), Hilbert transform is obtained by following formula:
PV therein indicates that Cauchy's principal value, phase change are calculated by following formula:
Wherein, the computing module 30 can calculate each sample vector collection using the synchronous calculation method of time-domain vector
The synchronism for two leads closed, specifically:
Wherein t is the time component in EEG signals sample, and N is a sample period lengths, xiAnd xjRespectively indicate two
The sample time-series of electrode.
Wherein, the division module 20 is specifically used for:
According to sample frequency truncated data, for once testing the signal for M minutes, by the square of sample composition 2*60M*H
Battle array, wherein 60M is the number of seconds of sampling, and H is the H data point of acquisition in one second, and 2 be two leads.
Wherein, the discrete block 40 is specifically used for:
In the matrix for the synchronism result being calculated, choose every a line, according to step-length 60 by the matrix to
Amount is divided into the vector of M, then retains 2 significant digits, to obtain the matrix of L*60, wherein L is sample number；
The distance between the every row of matrix of L*60 is calculated, to reject unusual sample, calculation method is to calculate row vector first
Between Fisher distance, calculation formula are as follows:
The wherein mean value of μ representation vector, the standard deviation of σ representation vector, Fi,jCalculated result is the matrix of L*L, and limits
Fi,jValue；
Statistical sample, if it exists vector m, wherein FimOr FjmMore than the F of restrictioni,jValue, it is determined that m is unusual sample,
The unusual sample m is rejected.
Wherein, the threshold determination module 50 is specifically used for:
Calculate the matrix of the target sample；
Using M/2 as step-length, the matrix of the target sample is averaging according to row, is then averaging according to column, finally
To being two number of front half section numerical value and second half section numerical value；
The second half section numerical value is determined as fatigue threshold.
Wherein, the tired determining module 60 is specifically used for:
The EEG signals of online acquisition driver, the synchronism of calculating in every 1 second, obtain a numerical value, if the value is super
Cross the fatigue threshold, then the fatigue state of this second be labeled as 1, be otherwise labeled as 0, Continuous plus 1 minute, obtain marking to
Amount sums to the label vector, if summed result is more than preset value, determines that driver is currently at fatigue state, and export
The fatigue data of last second.
According to driving fatigue detection system provided in this embodiment, at least have the advantages that
1) present invention can be avoided its EEG signals and lead in acquisition because covered using two lead of forehead as signal source
Cause acquires difficult problem, and can be realized the detection effect of high-accuracy by two lead synchronism calculation methods；
2) present invention is using two lead synchronism values as output as a result, passing through the output successive value conduct of each sampling period
Foundation is detected, real-time data output may be implemented, so as to the fatigue state of real-time, successional detection driver；
3) in the prior art, output real number value is carried out using prefrontal area lead mainly to be exported using the method for entropy,
But the output method of entropy needs that time domain periodic signal is reconstructed, time complexity is high, and the present invention uses synchronism meter
It calculates, time complexity is small, and calculating process is simpler, it is easy to accomplish, it can be avoided fatigue detection result lag.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.
The more specific example (non-exhaustive list) of computer-readable medium include the following: there are one or more wirings
Electrical connection section (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: logic gates specifically for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
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 defined by the claims and their equivalents.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576142.7A CN109394248B (en) | 2018-12-22 | 2018-12-22 | Driving fatigue detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576142.7A CN109394248B (en) | 2018-12-22 | 2018-12-22 | Driving fatigue detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109394248A true CN109394248A (en) | 2019-03-01 |
| CN109394248B CN109394248B (en) | 2022-02-22 |
Family
ID=65460650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811576142.7A Active CN109394248B (en) | 2018-12-22 | 2018-12-22 | Driving fatigue detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109394248B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111450380A (en) * | 2020-03-30 | 2020-07-28 | 重庆大学 | Driving fatigue intelligent detection warning wake-up system based on near-infrared brain functional imaging |
| CN114435373A (en) * | 2022-03-16 | 2022-05-06 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN116616794A (en) * | 2023-05-18 | 2023-08-22 | 中国人民解放军海军特色医学中心 | Underwater operator fatigue adjustment method and system based on electroencephalogram signals |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130009761A1 (en) * | 2011-07-05 | 2013-01-10 | Saudi Arabian Oil Company | Systems, Computer Medium and Computer-Implemented Methods for Monitoring Health and Ergonomic Status of Drivers of Vehicles |
| CN105286890A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Driver sleepy state monitoring method based on electroencephalogram signal |
| CN205582206U (en) * | 2016-04-14 | 2016-09-14 | 江西科技学院 | A brain wave fatigue driving detector |
| CN206007246U (en) * | 2016-06-01 | 2017-03-15 | 南京工程学院 | A kind of wear-type brain concentration degree monitoring and alarm equipment |
| US20170071525A1 (en) * | 2015-09-16 | 2017-03-16 | National Chiao Tung University | Device of drowsiness detection and alarm and method of the same |
| US20180186234A1 (en) * | 2017-01-03 | 2018-07-05 | General Electric Company | Control system and method |
| EP3387995A1 (en) * | 2017-04-14 | 2018-10-17 | Hyundai Motor Company | Apparatus and method for controlling vehicle based on degree of fatigue |
| CN108903958A (en) * | 2018-05-11 | 2018-11-30 | 南京邮电大学 | Driver attention evaluates early warning system and its implementation method |
| CN108926352A (en) * | 2017-05-22 | 2018-12-04 | 北京大学 | A kind of driving fatigue detection method and system |
-
2018
- 2018-12-22 CN CN201811576142.7A patent/CN109394248B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130009761A1 (en) * | 2011-07-05 | 2013-01-10 | Saudi Arabian Oil Company | Systems, Computer Medium and Computer-Implemented Methods for Monitoring Health and Ergonomic Status of Drivers of Vehicles |
| US20170071525A1 (en) * | 2015-09-16 | 2017-03-16 | National Chiao Tung University | Device of drowsiness detection and alarm and method of the same |
| CN105286890A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Driver sleepy state monitoring method based on electroencephalogram signal |
| CN205582206U (en) * | 2016-04-14 | 2016-09-14 | 江西科技学院 | A brain wave fatigue driving detector |
| CN206007246U (en) * | 2016-06-01 | 2017-03-15 | 南京工程学院 | A kind of wear-type brain concentration degree monitoring and alarm equipment |
| US20180186234A1 (en) * | 2017-01-03 | 2018-07-05 | General Electric Company | Control system and method |
| EP3387995A1 (en) * | 2017-04-14 | 2018-10-17 | Hyundai Motor Company | Apparatus and method for controlling vehicle based on degree of fatigue |
| CN108926352A (en) * | 2017-05-22 | 2018-12-04 | 北京大学 | A kind of driving fatigue detection method and system |
| CN108903958A (en) * | 2018-05-11 | 2018-11-30 | 南京邮电大学 | Driver attention evaluates early warning system and its implementation method |
Non-Patent Citations (4)
| Title |
|---|
| 周展鹏: "基于生物电信号的疲劳驾驶检测", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 胡剑锋等: "基于二阶盲辨识的运动想象脑电信号分类", 《中国组织工程研究与临床康复》 * |
| 胡剑锋等: "基于相位同步的脑电信号分类算法研究", 《微电子学与计算机》 * |
| 菲利普.贝塞纳尔等著: "《电磁混响室》", 31 May 2017, 国防工业出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111450380A (en) * | 2020-03-30 | 2020-07-28 | 重庆大学 | Driving fatigue intelligent detection warning wake-up system based on near-infrared brain functional imaging |
| CN114435373A (en) * | 2022-03-16 | 2022-05-06 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN114435373B (en) * | 2022-03-16 | 2023-12-22 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN116616794A (en) * | 2023-05-18 | 2023-08-22 | 中国人民解放军海军特色医学中心 | Underwater operator fatigue adjustment method and system based on electroencephalogram signals |
| CN116616794B (en) * | 2023-05-18 | 2024-02-20 | 中国人民解放军海军特色医学中心 | Underwater operator fatigue adjustment method and system based on electroencephalogram signals |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109394248B (en) | 2022-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Olsen | The Tobii I-VT fixation filter | |
| Rosazza et al. | Functional connectivity during resting-state functional MR imaging: study of the correspondence between independent component analysis and region-of-interest− based methods | |
| Torrielli et al. | Extreme wind speeds from long-term synthetic records | |
| CN109394248A (en) | Driving fatigue detection method and system | |
| Wen et al. | Exploring resting-state functional connectivity with total interdependence | |
| CN107095669A (en) | A kind of processing method and system of epileptic's EEG signals | |
| WO2006025504A1 (en) | Sensitive state judging method | |
| Mahan et al. | White Noise Test: detecting autocorrelation and nonstationarities in long time series after ARIMA modeling. | |
| Zhu et al. | An efficient visibility graph similarity algorithm and its application on sleep stages classification | |
| DE102017217438A1 (en) | Synchronization of machine vibration data after acquisition | |
| Moser et al. | Classification and detection of single evoked brain potentials using time-frequency amplitude features | |
| Sheppard et al. | Detecting the harmonics of oscillations with time-variable frequencies | |
| Gospodinova | Time series analysis using fractal and multifractal methods | |
| de l'Aulnoit et al. | Baseline fetal heart rate analysis: eleven automatic methods versus expert consensus | |
| CN109785924A (en) | A kind of cross-platform the oral medical method of inspection and device | |
| TWI685326B (en) | Wearable blood pressure detecting device and detecting method thereof | |
| Stevenson et al. | A nonlinear model of newborn EEG with nonstationary inputs | |
| Shangkai et al. | An Autoregressive Model of the BAEP Signal for Hearng-Threshold Testing | |
| Lennartz et al. | Sparse estimation of resting-state effective connectivity from fMRI cross-spectra | |
| CN108388846B (en) | Detection and recognition method of EEG alpha wave based on canonical correlation analysis | |
| CN106333677A (en) | Method and system for detecting blink activity in sleep state analysis | |
| WO2022111203A1 (en) | Heart rate detection method and device | |
| JP6830597B2 (en) | Biosignal processing device, biosignal processing system, and control program | |
| Bykhovskaia et al. | An algorithm for high-resolution detection of postsynaptic quantal events in extracellular records | |
| US10457144B2 (en) | Real time prediction device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |