CN107233103A - High ferro dispatcher's fatigue state assessment method and system - Google Patents
High ferro dispatcher's fatigue state assessment method and system Download PDFInfo
- Publication number
- CN107233103A CN107233103A CN201710397928.1A CN201710397928A CN107233103A CN 107233103 A CN107233103 A CN 107233103A CN 201710397928 A CN201710397928 A CN 201710397928A CN 107233103 A CN107233103 A CN 107233103A
- Authority
- CN
- China
- Prior art keywords
- tired
- mrow
- value
- characteristic value
- warning value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7242—Details of waveform analysis using integration
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Psychiatry (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (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 invention discloses a kind of high ferro dispatcher fatigue state assessment method and system.Wherein, this method can include heart rate signal, electrocardiosignal, EEG signals, face-image signal and the eye movement characteristics signal for obtaining high ferro dispatcher;Based on heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye movement characteristics signal, the characteristic value below tired warning value is extracted;Based on the characteristic value below tired warning value, using multi-channel data blending algorithm, the fatigue state of high ferro dispatcher is determined.The embodiment of the present invention is by taking above-mentioned technical proposal, using high ferro dispatcher ongoing operations as testing background, has merged multiple signals and has been judged, has solved the precision for how improving test and appraisal and the technical problem of the degree of accuracy so that monitoring is more of practical significance with test and appraisal.
Description
Technical field
The present embodiments relate to high ferro technical field, more particularly, to a kind of high ferro dispatcher fatigue state assessment method
And system.
Background technology
The working method of high ferro dispatcher's break tour determines that it needs higher anti-fatigue ability.At present, home and abroad
System for high ferro dispatcher's fatigue monitoring is more rarely seen.
Personnel's operation background that existing fatigue monitoring equipment is related to exists larger with high train dispatcher's operation background
Difference, it is impossible to simply copy and be applied in the fatigue monitoring and test and appraisal of high train dispatcher;Moreover, existing fatigue monitoring with
Test and appraisal equipment is to be based on Single channel analysis mostly, and its precision and the degree of accuracy be not high.
Therefore, it is badly in need of a set of fatigue monitoring and tampering devic to solve the harm that high ferro dispatcher's tired operation is brought.
The content of the invention
The main purpose of the embodiment of the present invention is to provide a kind of high ferro dispatcher fatigue state assessment method, its at least portion
Solve the precision for how improving test and appraisal and the technical problem of the degree of accuracy with dividing.In addition, also providing a kind of high ferro dispatcher fatigue
State evaluation system.
To achieve these goals, according to an aspect of the invention, there is provided following technical scheme:
A kind of high ferro dispatcher fatigue state assessment method.This method can at least include:
Obtain heart rate signal, electrocardiosignal, EEG signals, face-image signal and the eye movement characteristics of the high ferro dispatcher
Signal;
It is dynamic based on the heart rate signal, the electrocardiosignal, the EEG signals, the face-image signal and the eye
Characteristic signal, extracts the characteristic value below tired warning value;
Based on the characteristic value below the tired warning value, using multi-channel data blending algorithm, determine that the high ferro is adjusted
The fatigue state of degree person.
Further, it is described to be based on the heart rate signal, the electrocardiosignal, the EEG signals, the face-image
Signal and the eye movement characteristics signal, extract the characteristic value below tired warning value, can specifically include:
Based on the heart rate signal, the characteristic value below the tired warning value of heart rate index is extracted;
Based on the electrocardiosignal, the characteristic value below the tired warning value of electrocardiographicdata data is extracted;
Based on the EEG signals, the characteristic value below the tired warning value of the electric index of brain is extracted;
Based on the face-image signal, the characteristic value below the tired warning value of facial characteristics index is extracted;
Based on the eye movement characteristics signal, the characteristic value below the tired warning value of the dynamic index of eye is extracted.
Further, it is described to be based on the heart rate signal, the characteristic value below the tired warning value of heart rate index is extracted, specifically
It can include:
Based on the heart rate signal, heart rate value is obtained;
Based on the heart rate value, changes in heart rate curve is drawn;
Based on the changes in heart rate curve, the characteristic value below the tired warning value of the heart rate index is extracted.
Further, it is described to be based on the electrocardiosignal, the characteristic value below the tired warning value of electrocardiographicdata data is extracted, specifically
It can include:
The electrocardiosignal is filtered;
Filtered signal is carried out to go artefact to handle;
To going the signal after artefact to carry out time domain to the conversion of frequency domain;
Based on transformation results, frequency domain character is extracted;
Based on the frequency domain character, the characteristic value below the tired warning value of the electrocardiographicdata data is extracted.
Further, it is described to be based on the EEG signals, the characteristic value below the tired warning value of the electric index of brain is extracted, specifically
It can include:
The EEG signals are filtered;
Filtered signal is carried out to go artefact to handle;
To going the signal after artefact to carry out time domain to the conversion of frequency domain;
Based on the signal after conversion, frequency domain character is extracted;
Based on the frequency domain character, the characteristic value below the tired warning value of the electric index of the brain is extracted.
Further, it is described to be based on the face-image signal, extract the spy below the tired warning value of facial characteristics index
Value indicative, can specifically include:
Digital Image Processing is carried out to the face-image signal;
Based on the result after processing, facial characteristics is determined;
Based on the facial characteristics, it is determined that face fatigue expressive features;
Based on the tired expressive features of the face, the characteristic value below the tired warning value of the facial characteristics index is extracted.
Further, it is described to be based on the eye movement characteristics signal, the characteristic value below the tired warning value of the dynamic index of eye is extracted,
It can specifically include:
Digital Image Processing is carried out to the eye movement characteristics signal;
Based on the result after processing, extract eye and move parameter;
Parameter is moved based on the eye, the characteristic value below the tired warning value of the dynamic index of the eye is extracted.
Further, the characteristic value based on below the tired warning value, using multi-channel data blending algorithm, really
The fatigue state of the fixed high ferro dispatcher, can specifically include:
Using the method for entropy, according to the characteristic value below the tired warning value of the following formula calculating heart rate index, the electrocardio
The characteristic value below characteristic value, the tired warning value of the electric index of the brain below index fatigue warning value, the facial characteristics refer to
Characteristic value, the eye below the tired warning value of mark move the probability of the characteristic value below the tired warning value of index:
mi(Θ)=- k [qiMF log2qiMF+(1-qiMF)log2(1-qiMF)]
Wherein, it is describedThe MF represents fatigue;It is describedRepresent not tired;The qiMFRepresent
I-th of passage differentiates that high ferro dispatcher is in the probability of fatigue state;The 1-qiMFRepresent that i-th of passage differentiates high ferro scheduling
Probability of the member in not fatigue state, the i=1,2 ... 5;Each passage inputs the heart rate index fatigue warning respectively
Below characteristic value, the tired warning value of the electric index of the brain below the tired warning value of the following characteristic value of value, the electrocardiographicdata data
Characteristic value, the characteristic value below the tired warning value of the facial characteristics index, the eye moved below the tired warning value of index
Characteristic value;The k represents regulatory factor, and k ∈ (0,1);
Basic allocation probability in fatigue state and the basic allocation probability in not fatigue state are calculated according to following formula:
Wherein, the mi(MF) the basic allocation probability in fatigue state is represented;It is describedRepresent in not tired
The basic allocation probability of labor state;
Multichannel fusion based on D-S evidence theory is carried out according to following formula, high ferro dispatcher is calculated and is in fatigue state
Probability, high ferro dispatcher are in general after the characteristic value fusion below the not probability of fatigue state and each tired warning value
Rate:
Wherein, the m (MF) represents that the high ferro dispatcher is in the probability of fatigue state;It is describedRepresent institute
State the probability that high ferro dispatcher is in not fatigue state;The m (Θ) represents the characteristic value fusion below the tired warning value
Probability afterwards;It is describedOr Θ, the i=1,2 ... 5, the j=1,2k;
The belief function and likelihood function of fatigue, and untired belief function and likelihood function are calculated according to following formula:
Bel (MF)=m (MF)
Wherein, the Bel (MF) represents the tired belief function;The Pl (MF) represents the tired likelihood letter
Number;It is describedRepresent the untired belief function;It is describedRepresent the untired likelihood function;
According to the tired belief function and likelihood function, and the untired belief function and likelihood function,
Judge whether the high ferro dispatcher is in fatigue state.
Further, methods described can also include:
The identified fatigue state and fatigue state threshold value are compared;
If more than threshold value, carrying out preventive intervention procedure.
According to another aspect of the present invention, a kind of high ferro dispatcher fatigue state evaluation system is additionally provided.The system
It can at least include:
Acquisition module, heart rate signal, electrocardiosignal, EEG signals, face-image for obtaining the high ferro dispatcher
Signal and eye movement characteristics signal;
Extraction module, for based on the heart rate signal, the electrocardiosignal, the EEG signals, the face-image
Signal and the eye movement characteristics signal, extract the characteristic value below tired warning value;
Determining module, for based on the characteristic value below the tired warning value, using multi-channel data blending algorithm, really
The fatigue state of the fixed high ferro dispatcher.
Further, the extraction module can specifically include:
First extraction unit, for based on the heart rate signal, extracting the characteristic value below the tired warning value of heart rate index;
Second extraction unit, for based on the electrocardiosignal, extracting the characteristic value below the tired warning value of electrocardiographicdata data;
3rd extraction unit, for based on the EEG signals, extracting the characteristic value below the tired warning value of the electric index of brain;
4th extraction unit, for based on the face-image signal, extracting below the tired warning value of facial characteristics index
Characteristic value;
5th extraction unit, for based on the eye movement characteristics signal, extracting the spy below the tired warning value of the dynamic index of eye
Value indicative.
Further, first extraction unit can specifically include:
Acquiring unit, for based on the heart rate signal, obtaining heart rate value;
Drawing unit, for based on the heart rate value, drawing changes in heart rate curve;
First extracts subelement, for based on the changes in heart rate curve, extract the tired warning value of the heart rate index with
Under characteristic value.
Further, second extraction unit can specifically include:
First filter unit, for being filtered to the electrocardiosignal;
First removes artefact unit, for carrying out going artefact to handle to filtered signal;
First converter unit, for going the signal after artefact to carry out time domain to the conversion of frequency domain;
Second extracts subelement, for based on transformation results, extracting frequency domain character;
3rd extracts subelement, for based on the frequency domain character, extracting below the tired warning value of the electrocardiographicdata data
Characteristic value.
Further, the 3rd extraction unit can specifically include:
Second filter unit, for being filtered to the EEG signals;
Second removes artefact unit, for carrying out going artefact to handle to filtered signal;
Second converter unit, for going the signal after artefact to carry out time domain to the conversion of frequency domain;
4th extracts subelement, for based on the signal after conversion, extracting frequency domain character;
5th extracts subelement, for based on the frequency domain character, extracting below the tired warning value of the electric index of the brain
Characteristic value.
Further, the 4th extraction unit can specifically include:
First processing units, for carrying out Digital Image Processing to the face-image signal;
First determining unit, for based on the result after processing, determining facial characteristics;
Second determining unit, for based on the facial characteristics, it is determined that face fatigue expressive features;
6th extracts subelement, for based on the tired expressive features of the face, extracting the facial characteristics index fatigue
Characteristic value below warning value.
Further, the 5th extraction unit can specifically include:
Second processing unit, for carrying out Digital Image Processing to the eye movement characteristics signal;
7th extracts subelement, and parameter is moved for based on the result after processing, extracting eye;
8th extracts subelement, for moving parameter based on the eye, extracts the eye and moves below the tired warning value of index
Characteristic value.
Further, the determining module can specifically include:
First computing unit, for the method using entropy, is calculated below the tired warning value of the heart rate index according to following formula
Characteristic value, the characteristic value below the tired warning value of the electrocardiographicdata data, the feature below the tired warning value of the electric index of the brain
Characteristic value, the eye below the tired warning value of value, the facial characteristics index move the characteristic value below the tired warning value of index
Probability:
mi(Θ)=- k [qiMF log2qiMF+(1-qiMF)log2(1-qiMF)]
Wherein, it is describedThe MF represents fatigue;It is describedRepresent not tired;The qiMFRepresent
I-th of passage differentiates that high ferro dispatcher is in the probability of fatigue state;The 1-qiMFRepresent that i-th of passage differentiates high ferro scheduling
Probability of the member in not fatigue state, the i=1,2 ... 5;Each passage inputs the heart rate index fatigue warning respectively
Below characteristic value, the tired warning value of the electric index of the brain below the tired warning value of the following characteristic value of value, the electrocardiographicdata data
Characteristic value, the characteristic value below the tired warning value of the facial characteristics index, the eye moved below the tired warning value of index
Characteristic value;The k represents regulatory factor, and k ∈ (0,1);
Second computing unit, the basic allocation probability of fatigue state is in and in not tired shape for being calculated according to following formula
The basic allocation probability of state:
Wherein, the mi(MF) the basic allocation probability in fatigue state is represented;It is describedRepresent in not tired
The basic allocation probability of labor state;
3rd computing unit, for carrying out the Multichannel fusion based on D-S evidence theory according to following formula, calculates high ferro scheduling
Probability of the member in fatigue state, high ferro dispatcher are in below the not probability of fatigue state and each tired warning value
Probability after characteristic value fusion:
Wherein, the m (MF) represents that the high ferro dispatcher is in the probability of fatigue state;It is describedRepresent institute
State the probability that high ferro dispatcher is in not fatigue state;The m (Θ) represents the characteristic value fusion below the tired warning value
Probability afterwards;It is describedOr Θ, the i=1,2 ... 5, the j=1,2k;
4th computing unit, belief function and likelihood function for calculating fatigue according to following formula, and untired letter
Appoint function and likelihood function:
Bel (MF)=m (MF)
Wherein, the Bel (MF) represents the tired belief function;The Pl (MF) represents the tired likelihood letter
Number;It is describedRepresent the untired belief function;It is describedRepresent the untired likelihood function;
Identifying unit, for according to the tired belief function and likelihood function, and the untired trust letter
Number and likelihood function, judge whether the high ferro dispatcher is in fatigue state.
Further, the system can also include:
Comparing unit, for the identified fatigue state and fatigue state threshold value to be compared;
Preventive intervention procedure unit, in the case of exceeding the fatigue state threshold value in the fatigue state, carries out early warning
Intervene.
Compared with prior art, above-mentioned technical proposal at least has the advantages that:
The embodiment of the present invention provides a kind of high ferro dispatcher fatigue state assessment method and system.Wherein, this method can be with
Heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye movement characteristics signal including obtaining high ferro dispatcher;Base
In heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye movement characteristics signal, extract below tired warning value
Characteristic value;Based on the characteristic value below tired warning value, using multi-channel data blending algorithm, the fatigue of high ferro dispatcher is determined
State.The embodiment of the present invention is by taking above-mentioned technical proposal, using high ferro dispatcher ongoing operations as testing background so that monitoring
More it is of practical significance with test and appraisal;Again judged because the embodiment of the present invention has merged multiple signals, its judge precision with
The degree of accuracy is higher.
Certainly, any product for implementing the present invention is not necessarily required to while realizing all the above advantage.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
Obtain it is clear that or being understood by implementing the present invention.Objectives and other advantages of the present invention can be by the explanation write
Specifically noted method is realized and obtained in book, claims and accompanying drawing.
Brief description of the drawings
Accompanying drawing is as the part of the present invention, and for providing further understanding of the invention, of the invention is schematic
Embodiment and its illustrate to be used to explain the present invention, but do not constitute inappropriate limitation of the present invention.Obviously, drawings in the following description
Only some embodiments, to those skilled in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.In the accompanying drawings:
Fig. 1 is the schematic flow sheet of high ferro dispatcher's fatigue state assessment method according to an exemplary embodiment;
Fig. 2 is the structural representation of high ferro dispatcher's fatigue state evaluation system according to an exemplary embodiment;
Fig. 3 is the structural representation of high ferro dispatcher's fatigue state evaluation system according to another exemplary embodiment
Figure.
These accompanying drawings and word description are not intended as and limit concept of the invention in any way, but by reference to
Specific embodiment is that those skilled in the art illustrate idea of the invention.
Embodiment
Below in conjunction with the accompanying drawings and the specific embodiment technical problem solved to the embodiment of the present invention, the technical side that is used
Case and the technique effect of realization carry out clear, complete description.Obviously, described embodiment is only one of the application
Divide embodiment, be not whole embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not paying creation
Property work on the premise of, all other equivalent or substantially modification the embodiment obtained is all fallen within protection scope of the present invention.
The embodiment of the present invention can embody according to the multitude of different ways being defined and covered by claim.
It should be noted that in the following description, understanding for convenience, many details are given.But it is very bright
Aobvious, realization of the invention can be without these details.
It should also be noted that, it is clearly limit or do not conflict in the case of, each embodiment in the present invention and
Technical characteristic therein can be mutually combined and form technical scheme.
In actual applications, in order to solve how to improve the precision of high ferro dispatcher fatigue state test and appraisal and the skill of the degree of accuracy
Art problem, the embodiment of the present invention provides a kind of high ferro dispatcher fatigue state assessment method.This method can pass through step S100
Realized to step S120.
S100:Obtain the dynamic spy of heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye of high ferro dispatcher
Reference number.
In this step, the dynamic spy of heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye of high ferro dispatcher
Reference number can be obtained by signal collecting device.Wherein, signal collecting device includes monitoring bracelet, monitoring brain ring, image
Collecting device is (for example:Camera, camera etc.) and eye tracker.Monitoring bracelet is used to gather heart rate signal and electrocardiosignal.Prison
Control brain ring is used to gather EEG signals.Image capture device is used to gather face-image signal.Eye tracker is used to gather the dynamic spy of eye
Reference number.
In actual applications, the signal collected can be transferred in database.
S110:Based on heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye movement characteristics signal, extract tired
Characteristic value below labor warning value.
Specifically, this step can be realized by S111 to S115.
S111:Based on heart rate signal, the characteristic value below the tired warning value of heart rate index is extracted.
In some optional embodiments, step S111 can also specifically include:
Step a1:Based on heart rate signal, heart rate value is obtained.
Step a2:Based on heart rate value, changes in heart rate curve is drawn.
Step a3:Based on changes in heart rate curve, the characteristic value below the tired warning value of heart rate index is extracted.
S112:Based on electrocardiosignal, the characteristic value below the tired warning value of electrocardiographicdata data is extracted.
In some optional embodiments, step S112 can also specifically include:
Step b1:Electrocardiosignal is filtered.
Step b2:Filtered signal is carried out to go artefact to handle.
Step b3:To going the signal after artefact to carry out time domain to the conversion of frequency domain.
Step b4:Based on transformation results, frequency domain character is extracted.
Step b5:Based on frequency domain character, the characteristic value below the tired warning value of electrocardiographicdata data is extracted.
S113:Based on EEG signals, the characteristic value below the tired warning value of the electric index of brain is extracted.
In some optional embodiments, step S113 can also specifically include:
Step c1:EEG signals are filtered.
Step c2:Filtered signal is carried out to go artefact to handle.
Step c3:To going the signal after artefact to carry out time domain to the conversion of frequency domain.
Step c4:Based on the signal after conversion, frequency domain character is extracted.
Step c5:Based on frequency domain character, the characteristic value below the tired warning value of the electric index of brain is extracted.
S114:Based on face-image signal, the characteristic value below the tired warning value of facial characteristics index is extracted.
In some optional embodiments, step S114 can also specifically include:
Step d1:Digital Image Processing is carried out to facial picture signal.
Step d2:Based on the result after processing, facial characteristics is determined.
Step d3:Based on facial characteristics, it is determined that face fatigue expressive features.
Wherein, the tired expressive features of face are such as can be to yawn facial fatigue expression.
Step d4:Based on facial tired expressive features, the characteristic value below the tired warning value of facial characteristics index is extracted.
S115:Based on eye movement characteristics signal, the characteristic value below the tired warning value of the dynamic index of eye is extracted.
In some optional embodiments, step S115 can also specifically include:
Step e1:Digital Image Processing is carried out to eye movement characteristics signal.
Step e2:Based on the result after processing, extract eye and move parameter.
Wherein, the dynamic parameter of eye includes but is not limited to eyelid opening degree, frequency of wink and eye movement.
Step e3:Parameter is moved based on eye, the characteristic value below the tired warning value of the dynamic index of eye is extracted.
S120:Based on the characteristic value below tired warning value, using multi-channel data blending algorithm, high ferro dispatcher is determined
Fatigue state.
Because if differentiating whether high ferro dispatcher is in fatigue state according to a certain signal, judging that precision can not
Reach 100%.So, the embodiment of the present invention is using the means such as the Multichannel fusion algorithm based on D-S evidence theory, fusion
Multi-signal is judged, discrimination precision and the degree of accuracy are improved with this.
Specifically, this step can include:
Step f1:Using the method for entropy, determine that characteristic value below the tired warning value of heart rate index, electrocardio refer to according to following formula
The characteristic value below characteristic value, the tired warning value of the electric index of brain below the tired warning value of mark, the fatigue warning of facial characteristics index
The following characteristic value of value, eye move the probability of the characteristic value below the tired warning value of index:
mi(Θ)=- k [qiMF log2qiMF+(1-qiMF)log2(1-qiMF)]
Wherein,MF represents fatigue;Represent not tired;qiMFRepresent that i-th of passage differentiates high ferro
Dispatcher is in the probability of fatigue state;1-qiMFRepresent that i-th of passage differentiates high ferro dispatcher in the general of not fatigue state
Rate, i=1,2 ... 5;Characteristic value that each passage is inputted below the tired warning value of heart rate index respectively, electrocardiographicdata data fatigue warning
The spy below characteristic value, the tired warning value of facial characteristics index below the tired warning value of the electric index of the following characteristic value of value, brain
Value indicative, eye move the characteristic value below the tired warning value of index;K represents regulatory factor, and k ∈ (0,1).
Wherein, whether each passage only has limited individual to high ferro dispatcher in fatigue state recognition result:Tired MF and
It is not tiredThat each passage passes through respectively is heart rate signal, electrocardiosignal, EEG signals, face-image signal, the dynamic spy of eye
Reference number.
Step f2:Basic allocation probability in fatigue state and the basis in not fatigue state point are determined according to following formula
With probability:
Wherein, mi(MF) the basic allocation probability in fatigue state is represented;Represent in not fatigue state
Basic allocation probability.
Step f3:Multichannel fusion based on D-S evidence theory is carried out according to following formula, determines that high ferro dispatcher is in fatigue
Shape probability of state, high ferro dispatcher are in after the characteristic value fusion below the not probability of fatigue state and each tired warning value
Probability:
Wherein, m (MF) represents that high ferro dispatcher is in the probability of fatigue state;Represent that high ferro dispatcher is in
The not probability of fatigue state;M (Θ) represents the probability after the characteristic value fusion below tired warning value;Or
Θ, i=1,2 ... 5, j=1,2.
Step f4:The belief function and likelihood function of fatigue, and untired belief function and seemingly are calculated according to following formula
Right function:
Bel (MF)=m (MF)
Wherein, Bel (MF) represents the belief function of fatigue;Pl (MF) represents the likelihood function of fatigue;Represent not
The belief function of fatigue;Represent untired likelihood function.
Step f5:According to the belief function and likelihood function of fatigue, and untired belief function and likelihood function, sentence
Determine whether high ferro dispatcher is in fatigue state.
For example:
WhenWhen, then judge that high ferro dispatcher is in fatigue state;WhenWhen,
It not can determine that then;WhenWhen, then judge that high ferro dispatcher is in not fatigue state.
In some optional embodiments, on the basis of above-described embodiment, above-mentioned high ferro dispatcher fatigue state test and appraisal
Method can also include:
S130:Identified fatigue state is compared with fatigue state threshold value.
S140:If more than threshold value, carrying out preventive intervention procedure.
The embodiment of the present invention is by taking above-mentioned technical proposal, using high ferro dispatcher ongoing operations as testing background so that
Monitoring is more of practical significance with test and appraisal;Judged again because the embodiment of the present invention has merged multiple signals, its essence judged
Degree and the degree of accuracy are higher.
Although each step is described in the way of above-mentioned precedence in above-described embodiment, this area
Technical staff be appreciated that in order to realize between the effect of the present embodiment, different steps not necessarily in such order perform,
It (parallel) execution simultaneously or can be performed with reverse order, these simple changes all protection scope of the present invention it
It is interior.
Based on embodiment of the method identical technical concept, the embodiment of the present invention also provides a kind of high ferro dispatcher tired shape
State evaluation system.As shown in Fig. 2 the system 20 can at least include:Acquisition module 22, extraction module 24 and determining module 26.
Wherein, acquisition module 22 be used to obtaining the heart rate signal of high ferro dispatcher, electrocardiosignal, EEG signals, face-image signal and
Eye movement characteristics signal.Extraction module 24 is used for dynamic based on heart rate signal, electrocardiosignal, EEG signals, face-image signal and eye
Characteristic signal, extracts the characteristic value below tired warning value.Determining module 26 is used for based on the characteristic value below tired warning value,
Using multi-channel data blending algorithm, the fatigue state of high ferro dispatcher is determined.
In some optional embodiments, on the basis of above-described embodiment, said extracted module can specifically include:The
One extraction unit, the second extraction unit, the 3rd extraction unit, the 4th extraction unit and the 5th extraction unit.Wherein, first extract
Unit is used to be based on heart rate signal, extracts the characteristic value below the tired warning value of heart rate index.Second extraction unit is used to be based on
Electrocardiosignal, extracts the characteristic value below the tired warning value of electrocardiographicdata data.3rd extraction unit is used to be based on EEG signals, extracts
Characteristic value below the tired warning value of brain electricity index.4th extraction unit is used to be based on face-image signal, extracts facial characteristics
Characteristic value below index fatigue warning value.5th extraction unit is used to be based on eye movement characteristics signal, extracts eye and moves index fatigue
Characteristic value below warning value.
In some optional embodiments, on the basis of above-described embodiment, above-mentioned first extraction unit can specifically be wrapped
Include:Acquiring unit, drawing unit and first extract subelement.Wherein, acquiring unit is used to be based on heart rate signal, obtains heart rate
Value.Drawing unit is used to be based on heart rate value, draws changes in heart rate curve.First, which extracts subelement, is used for based on changes in heart rate song
Line, extracts the characteristic value below the tired warning value of heart rate index.
In some optional embodiments, on the basis of above-described embodiment, above-mentioned second extraction unit can specifically be wrapped
Include:First filter unit, first go artefact unit, the first converter unit, second to extract subelement and the 3rd and extract subelement.Its
In, the first filter unit is used to be filtered electrocardiosignal.First goes artefact unit to be used to remove filtered signal
Artefact processing.First converter unit is used for going the signal after artefact to carry out time domain to the conversion of frequency domain.Second extracts subelement
For based on transformation results, extracting frequency domain character.3rd, which extracts subelement, is used to be based on frequency domain character, extracts electrocardiographicdata data fatigue
Characteristic value below warning value.
In some optional embodiments, on the basis of above-described embodiment, above-mentioned 3rd extraction unit is specifically included:The
Two filter units, second go artefact unit, the second converter unit, the 4th to extract subelement and the 5th and extract subelement.Wherein,
Two filter units are used to be filtered EEG signals.Second goes artefact unit to be used to carry out going at artefact to filtered signal
Reason.Second converter unit is used for going the signal after artefact to carry out time domain to the conversion of frequency domain.4th, which extracts subelement, is used for base
In the signal after conversion, frequency domain character is extracted.5th, which extracts subelement, is used to be based on frequency domain character, extracts the electric index fatigue of brain alert
The following characteristic value of ring value.
In some optional embodiments, on the basis of above-described embodiment, above-mentioned 4th extraction unit is specifically included:The
One processing unit, the first determining unit, the second determining unit and the 6th extract subelement.Wherein, first processing units be used for pair
Face-image signal carries out Digital Image Processing.First determining unit is used for based on the result after processing, determines facial characteristics.The
Two determining units are used to be based on facial characteristics, it is determined that face fatigue expressive features.6th, which extracts subelement, is used for based on facial tired
Labor expressive features, extract the characteristic value below the tired warning value of facial characteristics index.
In some optional embodiments, on the basis of above-described embodiment, above-mentioned 5th extraction unit is specifically included:The
Two processing units, the 7th extract subelement and the 8th and extract subelement.Wherein, second processing unit is used for eye movement characteristics signal
Carry out Digital Image Processing.7th, which extracts subelement, is used for based on the result after processing, extracts eye and moves parameter.8th extracts son list
Member is used to move parameter based on eye, and extraction eye moves the characteristic value below the tired warning value of index.
In some optional embodiments, above-mentioned determining module can specifically include:First computing unit, second calculate single
Member, the 3rd computing unit, the 4th computing unit and identifying unit.Wherein, the first computing unit is used for the method using entropy, according to
Following formula calculates the characteristic value below the tired warning value of heart rate index, the characteristic value below the tired warning value of electrocardiographicdata data, brain electricity and referred to
The characteristic value below characteristic value, the tired warning value of facial characteristics index below the tired warning value of mark, eye move index fatigue warning
The probability of the following characteristic value of value:
mi(Θ)=- k [qiMF log2qiMF+(1-qiMF)log2(1-qiMF)]
Wherein,MF represents fatigue;Represent not tired;qiMFRepresent that i-th of passage differentiates high ferro
Dispatcher is in the probability of fatigue state;1-qiMFRepresent that i-th of passage differentiates high ferro dispatcher in the general of not fatigue state
Rate, i=1,2 ... 5;Characteristic value that each passage is inputted below the tired warning value of heart rate index respectively, the tired warning value of electrocardiographicdata data
The feature below characteristic value, the tired warning value of facial characteristics index below the tired warning value of the electric index of following characteristic value, brain
Value, eye move the characteristic value below the tired warning value of index;K represents regulatory factor, and k ∈ (0,1).Second computing unit is used for
Basic allocation probability in fatigue state and the basic allocation probability in not fatigue state are calculated according to following formula:
Wherein, mi(MF) the basic allocation probability in fatigue state is represented;Represent in not fatigue state
Basic allocation probability.3rd computing unit is used to carry out the Multichannel fusion based on D-S evidence theory according to following formula, calculates high ferro
Dispatcher is in the probability of fatigue state, high ferro dispatcher and is in below the not probability of fatigue state and each tired warning value
Probability after characteristic value fusion:
Wherein, m (MF) represents that high ferro dispatcher is in the probability of fatigue state;Represent that high ferro dispatcher is in not
The probability of fatigue state;M (Θ) represents the probability after the characteristic value fusion below tired warning value;Or Θ, i
=1,2 ... 5, j=1,2k.4th computing unit is used for the belief function and likelihood function that fatigue is calculated according to following formula, with
And untired belief function and likelihood function:
Bel (MF)=m (MF)
Wherein, Bel (MF) represents the belief function of fatigue;Pl (MF) represents the likelihood function of fatigue;Represent not
The belief function of fatigue;Represent untired likelihood function.Identifying unit is for the belief function according to fatigue and seemingly
Right function, and untired belief function and likelihood function, judge whether high ferro dispatcher is in fatigue state.
In some optional embodiments, on the basis of embodiment illustrated in fig. 2, above-mentioned high ferro dispatcher fatigue state is surveyed
System is commented to include:Comparing unit and preventive intervention procedure unit.Wherein, comparing unit be used for by identified fatigue state with
Fatigue state threshold value is compared.Preventive intervention procedure unit is used to, in the case where fatigue state exceedes fatigue state threshold value, carry out
Preventive intervention procedure.
Fig. 3 schematically illustrates the preferred reality of high ferro dispatcher fatigue state evaluation system provided in an embodiment of the present invention
Existing mode.Wherein, bracelet component, brain ring element, camera and eye tracker are used for heart rate signal, the electrocardio for gathering high ferro dispatcher
Signal, EEG signals, face-image signal and eye movement characteristics signal.Database be used for store high ferro dispatcher heart rate signal,
Electrocardiosignal, EEG signals, face-image signal and eye movement characteristics signal.Processing component be used for perform said extracted module and
State the operation of determining module.Intervene the operation that component is used to perform above-mentioned comparing unit and above-mentioned preventive intervention procedure unit.Printer
For printing out result.
It will be understood by those skilled in the art that above-mentioned high ferro dispatcher fatigue state evaluation system can also include some its
His known features, such as processor, memory, wherein, memory includes but is not limited to random access memory, flash memory, read-only deposited
Reservoir, volatile memory, nonvolatile memory, serial storage, parallel storage or register etc., processor include but
CPLD/FPGA, DSP, arm processor, MIPS processors etc. are not limited to, in order to unnecessarily obscure embodiment of the disclosure, this
A little known structures are not shown in fig. 2.
It should be understood that the quantity of the modules in Fig. 2 is only schematical.According to needs are realized, can have and appoint
Acquisition module, extraction module and the determining module for quantity of anticipating.
It should be noted that:High ferro dispatcher's fatigue state evaluation system that above-described embodiment is provided is carrying out fatigue state
During test and appraisal, only carried out with the division of above-mentioned each functional module for example, in actual applications, can also as needed will be upper
Function distribution is stated by different functional modules to complete, i.e., the internal structure of system is divided into different functional modules, with complete
Into all or part of function described above.
As used herein, term " module " may refer to software object or the routine performed on a computing system.
Disparate modules described herein can be embodied as to the object that performs on a computing system or process (for example, being used as independent
Thread).While it is preferred that system and method described herein are realized with software, but with hardware or software and firmly
The combination of part is realized also possible and can be conceived to.
Said system embodiment can be used for performing above method embodiment, its technical principle, the technical problem solved
And the technique effect produced is similar, person of ordinary skill in the field can be understood that, convenience and letter for description
Clean, the specific work process of the system of foregoing description may be referred to the corresponding process in preceding method embodiment, no longer go to live in the household of one's in-laws on getting married herein
State.
It should be noted that the system embodiment and embodiment of the method respectively to the present invention are described above, but it is right
The details of one embodiment description can also be applied to another embodiment.For module, the step being related in the embodiment of the present invention
Title, it is only for distinguish modules or step, be not intended as inappropriate limitation of the present invention.Those skilled in the art
It should be appreciated that:Module or step in the embodiment of the present invention can also be decomposed or combined again.The mould of such as above-described embodiment
Block can be merged into a module, can also be further split into multiple submodule.
The technical scheme provided above the embodiment of the present invention is described in detail.Although applying herein specific
Individual example to the present invention principle and embodiment be set forth, still, the explanation of above-described embodiment is only applicable to help and managed
Solve the principle of the embodiment of the present invention;For those skilled in the art, according to the embodiment of the present invention, in specific implementation
It can be made a change within mode and application.
Here, it is necessary to which explanation, the flow chart or block diagram being referred to herein is not limited solely to shape shown in this article
Formula, it can also be divided and/or be combined.
It can further be stated that:Mark and word in accompanying drawing are intended merely to be illustrated more clearly that the present invention, are not intended as pair
The improper restriction of the scope of the present invention.
Term " comprising " or any other like term are intended to including for nonexcludability, so that being including one
Process, method, article or the equipment/device of row key element not only includes those key elements, but also including being not expressly set out
Other key elements, or also include these processes, method, article or the intrinsic key element of equipment/device.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being realized by means of properly programmed PC.
If in the unit claim for listing equipment for drying, several in these devices can be come specific by same hardware branch
Embody.The use of word first, second, and third does not indicate that any order.These words can be construed to title.
The present invention each step can be realized with general computing device, for example, they can concentrate on it is single
On computing device, for example:Personal computer, server computer, handheld device or portable set, laptop device or many
Processor device, can also be distributed on the network that multiple computing devices are constituted, and they can be with different from order herein
Shown or described step is performed, they are either fabricated to each integrated circuit modules respectively or will be many in them
Individual module or step are fabricated to single integrated circuit module to realize.Therefore, the invention is not restricted to any specific hardware and soft
Part or its combination.
The method that the present invention is provided can use PLD to realize, can also be embodied as computer program soft
Part or program module (it include performing particular task or the routine for realizing particular abstract data type, program, object, component or
Data structure etc.), for example embodiments in accordance with the present invention can be a kind of computer program product, run the computer program
Product makes computer perform for demonstrated method.The computer program product includes computer-readable recording medium, should
Computer program logic or code section are included on medium, for realizing methods described.The computer-readable recording medium can
To be the removable medium (example that is mounted built-in medium in a computer or can be disassembled from basic computer
Such as:Using the storage device of hot plug technology).The built-in medium includes but is not limited to rewritable nonvolatile memory,
For example:RAM, ROM, flash memory and hard disk.The removable medium includes but is not limited to:Optical storage media is (for example:CD-
ROM and DVD), magnetic-optical storage medium (for example:MO), magnetic storage medium is (for example:Tape or mobile hard disk), can with built-in
Rewrite the media of nonvolatile memory (for example:Storage card) and media with built-in ROM are (for example:ROM boxes).
The present invention is not limited to above-mentioned embodiment, and in the case of without departing substantially from substantive content of the present invention, this area is common
Any deformation, improvement or the replacement that technical staff is contemplated that each fall within protection scope of the present invention.
Claims (18)
1. a kind of high ferro dispatcher fatigue state assessment method, it is characterised in that methods described at least includes:
Obtain heart rate signal, electrocardiosignal, EEG signals, face-image signal and the eye movement characteristics letter of the high ferro dispatcher
Number;
Based on the heart rate signal, the electrocardiosignal, the EEG signals, the face-image signal and the eye movement characteristics
Signal, extracts the characteristic value below tired warning value;
Based on the characteristic value below the tired warning value, using multi-channel data blending algorithm, the high ferro dispatcher is determined
Fatigue state.
2. according to the method described in claim 1, it is characterised in that described to be based on the heart rate signal, the electrocardiosignal, institute
EEG signals, the face-image signal and the eye movement characteristics signal are stated, the characteristic value below tired warning value is extracted, specifically
Including:
Based on the heart rate signal, the characteristic value below the tired warning value of heart rate index is extracted;
Based on the electrocardiosignal, the characteristic value below the tired warning value of electrocardiographicdata data is extracted;
Based on the EEG signals, the characteristic value below the tired warning value of the electric index of brain is extracted;
Based on the face-image signal, the characteristic value below the tired warning value of facial characteristics index is extracted;
Based on the eye movement characteristics signal, the characteristic value below the tired warning value of the dynamic index of eye is extracted.
3. method according to claim 2, it is characterised in that described to be based on the heart rate signal, extracts heart rate index tired
Characteristic value below labor warning value, is specifically included:
Based on the heart rate signal, heart rate value is obtained;
Based on the heart rate value, changes in heart rate curve is drawn;
Based on the changes in heart rate curve, the characteristic value below the tired warning value of the heart rate index is extracted.
4. method according to claim 2, it is characterised in that described to be based on the electrocardiosignal, extracts electrocardiographicdata data tired
Characteristic value below labor warning value, is specifically included:
The electrocardiosignal is filtered;
Filtered signal is carried out to go artefact to handle;
To going the signal after artefact to carry out time domain to the conversion of frequency domain;
Based on transformation results, frequency domain character is extracted;
Based on the frequency domain character, the characteristic value below the tired warning value of the electrocardiographicdata data is extracted.
5. method according to claim 2, it is characterised in that described to be based on the EEG signals, extracts the electric index of brain tired
Characteristic value below labor warning value, is specifically included:
The EEG signals are filtered;
Filtered signal is carried out to go artefact to handle;
To going the signal after artefact to carry out time domain to the conversion of frequency domain;
Based on the signal after conversion, frequency domain character is extracted;
Based on the frequency domain character, the characteristic value below the tired warning value of the electric index of the brain is extracted.
6. method according to claim 2, it is characterised in that described to be based on the face-image signal, extracts face special
The characteristic value below the tired warning value of index is levied, is specifically included:
Digital Image Processing is carried out to the face-image signal;
Based on the result after processing, facial characteristics is determined;
Based on the facial characteristics, it is determined that face fatigue expressive features;
Based on the tired expressive features of the face, the characteristic value below the tired warning value of the facial characteristics index is extracted.
7. method according to claim 2, it is characterised in that described to be based on the eye movement characteristics signal, extracts the dynamic finger of eye
Characteristic value below the tired warning value of mark, is specifically included:
Digital Image Processing is carried out to the eye movement characteristics signal;
Based on the result after processing, extract eye and move parameter;
Parameter is moved based on the eye, the characteristic value below the tired warning value of the dynamic index of the eye is extracted.
8. method according to claim 2, it is characterised in that the characteristic value based on below the tired warning value,
Using multi-channel data blending algorithm, the fatigue state of the high ferro dispatcher is determined, is specifically included:
Using the method for entropy, according to the characteristic value below the tired warning value of the following formula calculating heart rate index, the electrocardiographicdata data
The characteristic value below the tired warning value of the electric index of characteristic value, the brain, the facial characteristics index below tired warning value is tired
Characteristic value, the eye below labor warning value move the probability of the characteristic value below the tired warning value of index:
mi(Θ)=- k [qiMF log2qiMF+(1-qiMF)log2(1-qiMF)]
Wherein, it is describedThe MF represents fatigue;It is describedRepresent not tired;The qiMFRepresent i-th
Passage differentiates that high ferro dispatcher is in the probability of fatigue state;The 1-qiMFRepresent that i-th of passage differentiates that high ferro dispatcher is in
The not probability of fatigue state, the i=1,2 ... 5;Each passage is inputted below the tired warning value of the heart rate index respectively
Characteristic value, the characteristic value below the tired warning value of the electrocardiographicdata data, the feature below the tired warning value of the electric index of the brain
Characteristic value, the eye below the tired warning value of value, the facial characteristics index move the characteristic value below the tired warning value of index;
The k represents regulatory factor, and k ∈ (0,1);
Basic allocation probability in fatigue state and the basic allocation probability in not fatigue state are calculated according to following formula:
mi(MF)=qiMF(1-mi(Θ))
mi(MF)=(1-qiMF)(1-mi(Θ))
Wherein, the mi(MF) the basic allocation probability in fatigue state is represented;It is describedRepresent to be in not tired shape
The basic allocation probability of state;
Multichannel fusion based on D-S evidence theory is carried out according to following formula, calculate high ferro dispatcher be in fatigue state probability,
High ferro dispatcher is in the probability after the characteristic value fusion below the not probability of fatigue state and each tired warning value:
Wherein, the m (MF) represents that the high ferro dispatcher is in the probability of fatigue state;It is describedRepresent the high ferro
Dispatcher is in the probability of not fatigue state;The m (Θ) represents general after the characteristic value fusion below the tired warning value
Rate;It is describedOr Θ, the i=1,2 ... 5, the j=1,2k;
The belief function and likelihood function of fatigue, and untired belief function and likelihood function are calculated according to following formula:
Bel (MF)=m (MF)
<mrow>
<mi>B</mi>
<mi>e</mi>
<mi>l</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>P</mi>
<mi>l</mi>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mi>F</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>P</mi>
<mi>l</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mi>F</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein, the Bel (MF) represents the tired belief function;The Pl (MF) represents the tired likelihood function;
It is describedRepresent the untired belief function;It is describedRepresent the untired likelihood function;
According to the tired belief function and likelihood function, and the untired belief function and likelihood function, judge
Whether the high ferro dispatcher is in fatigue state.
9. according to the method described in claim 1, it is characterised in that methods described also includes:
The identified fatigue state and fatigue state threshold value are compared;
If more than threshold value, carrying out preventive intervention procedure.
10. a kind of high ferro dispatcher fatigue state evaluation system, it is characterised in that the system at least includes:
Acquisition module, heart rate signal, electrocardiosignal, EEG signals, face-image signal for obtaining the high ferro dispatcher
With eye movement characteristics signal;
Extraction module, for based on the heart rate signal, the electrocardiosignal, the EEG signals, the face-image signal
With the eye movement characteristics signal, the characteristic value below tired warning value is extracted;
Determining module, for based on the characteristic value below the tired warning value, using multi-channel data blending algorithm, determines institute
State the fatigue state of high ferro dispatcher.
11. system according to claim 10, it is characterised in that the extraction module is specifically included:
First extraction unit, for based on the heart rate signal, extracting the characteristic value below the tired warning value of heart rate index;
Second extraction unit, for based on the electrocardiosignal, extracting the characteristic value below the tired warning value of electrocardiographicdata data;
3rd extraction unit, for based on the EEG signals, extracting the characteristic value below the tired warning value of the electric index of brain;
4th extraction unit, for based on the face-image signal, extracting the spy below the tired warning value of facial characteristics index
Value indicative;
5th extraction unit, for based on the eye movement characteristics signal, extracting the characteristic value below the tired warning value of the dynamic index of eye.
12. system according to claim 11, it is characterised in that first extraction unit is specifically included:
Acquiring unit, for based on the heart rate signal, obtaining heart rate value;
Drawing unit, for based on the heart rate value, drawing changes in heart rate curve;
First extracts subelement, for based on the changes in heart rate curve, extracting below the tired warning value of the heart rate index
Characteristic value.
13. system according to claim 11, it is characterised in that second extraction unit is specifically included:
First filter unit, for being filtered to the electrocardiosignal;
First removes artefact unit, for carrying out going artefact to handle to filtered signal;
First converter unit, for going the signal after artefact to carry out time domain to the conversion of frequency domain;
Second extracts subelement, for based on transformation results, extracting frequency domain character;
3rd extracts subelement, for based on the frequency domain character, extracting the feature below the tired warning value of the electrocardiographicdata data
Value.
14. system according to claim 11, it is characterised in that the 3rd extraction unit is specifically included:
Second filter unit, for being filtered to the EEG signals;
Second removes artefact unit, for carrying out going artefact to handle to filtered signal;
Second converter unit, for going the signal after artefact to carry out time domain to the conversion of frequency domain;
4th extracts subelement, for based on the signal after conversion, extracting frequency domain character;
5th extracts subelement, for based on the frequency domain character, extracting the feature below the tired warning value of the electric index of the brain
Value.
15. system according to claim 11, it is characterised in that the 4th extraction unit is specifically included:
First processing units, for carrying out Digital Image Processing to the face-image signal;
First determining unit, for based on the result after processing, determining facial characteristics;
Second determining unit, for based on the facial characteristics, it is determined that face fatigue expressive features;
6th extracts subelement, for based on the tired expressive features of the face, extracting the facial characteristics index fatigue warning
The following characteristic value of value.
16. system according to claim 11, it is characterised in that the 5th extraction unit is specifically included:
Second processing unit, for carrying out Digital Image Processing to the eye movement characteristics signal;
7th extracts subelement, and parameter is moved for based on the result after processing, extracting eye;
8th extracts subelement, for moving parameter based on the eye, extracts the feature below the tired warning value of the dynamic index of the eye
Value.
17. system according to claim 11, it is characterised in that the determining module is specifically included:
First computing unit, for the method using entropy, the spy below the tired warning value of the heart rate index is calculated according to following formula
The characteristic value below characteristic value, the tired warning value of the electric index of the brain below the tired warning value of value indicative, the electrocardiographicdata data, institute
State the characteristic value below the tired warning value of facial characteristics index, the eye and move the general of characteristic value below the tired warning value of index
Rate:
mi(Θ)=- k [qiMFlog2qiMF+(1-qiMF)log2(1-qiMF)]
Wherein, it is describedThe MF represents fatigue;It is describedRepresent not tired;The qiMFRepresent i-th
Passage differentiates that high ferro dispatcher is in the probability of fatigue state;The 1-qiMFRepresent that i-th of passage differentiates that high ferro dispatcher is in
The not probability of fatigue state, the i=1,2 ... 5;Each passage is inputted below the tired warning value of the heart rate index respectively
Characteristic value, the characteristic value below the tired warning value of the electrocardiographicdata data, the feature below the tired warning value of the electric index of the brain
Characteristic value, the eye below the tired warning value of value, the facial characteristics index move the characteristic value below the tired warning value of index;
The k represents regulatory factor, and k ∈ (0,1);
Second computing unit, the basic allocation probability of fatigue state is in and in not fatigue state for being calculated according to following formula
Basic allocation probability:
mi(MF)=qiMF(1-mi(Θ))
mi(MF)=(1-qiMF)(1-mi(Θ))
Wherein, the mi(MF) the basic allocation probability in fatigue state is represented;It is describedRepresent to be in not tired shape
The basic allocation probability of state;
3rd computing unit, for carrying out the Multichannel fusion based on D-S evidence theory according to following formula, is calculated at high ferro dispatcher
Probability, high ferro dispatcher in fatigue state are in the feature below the not probability of fatigue state and each tired warning value
Probability after value fusion:
Wherein, the m (MF) represents that the high ferro dispatcher is in the probability of fatigue state;It is describedRepresent the high ferro
Dispatcher is in the probability of not fatigue state;The m (Θ) represents general after the characteristic value fusion below the tired warning value
Rate;It is describedOr Θ, the i=1,2 ... 5, the j=1,2k;
4th computing unit, belief function and likelihood function for calculating fatigue according to following formula, and untired trust letter
Number and likelihood function:
Bel (MF)=m (MF)
<mrow>
<mi>B</mi>
<mi>e</mi>
<mi>l</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>P</mi>
<mi>l</mi>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mi>F</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>P</mi>
<mi>l</mi>
<mrow>
<mo>(</mo>
<mover>
<mrow>
<mi>M</mi>
<mi>F</mi>
</mrow>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mi>F</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein, the Bel (MF) represents the tired belief function;The Pl (MF) represents the tired likelihood function;
It is describedRepresent the untired belief function;It is describedRepresent the untired likelihood function;
Identifying unit, for according to the tired belief function and likelihood function, and the untired belief function and
Likelihood function, judges whether the high ferro dispatcher is in fatigue state.
18. system according to claim 10, it is characterised in that the system also includes:
Comparing unit, for the identified fatigue state and fatigue state threshold value to be compared;
Preventive intervention procedure unit, in the case of exceeding the fatigue state threshold value in the fatigue state, carries out preventive intervention procedure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710397928.1A CN107233103B (en) | 2017-05-27 | 2017-05-27 | High-speed rail dispatcher fatigue state evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710397928.1A CN107233103B (en) | 2017-05-27 | 2017-05-27 | High-speed rail dispatcher fatigue state evaluation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107233103A true CN107233103A (en) | 2017-10-10 |
CN107233103B CN107233103B (en) | 2020-11-20 |
Family
ID=59985289
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710397928.1A Active CN107233103B (en) | 2017-05-27 | 2017-05-27 | High-speed rail dispatcher fatigue state evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107233103B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108852380A (en) * | 2018-07-09 | 2018-11-23 | 南京邮电大学 | Fatigue, mood analysis method based on ECG signal |
CN109431498A (en) * | 2018-11-14 | 2019-03-08 | 天津大学 | Wearable multi-modal physiological driver's condition monitoring system |
CN112450933A (en) * | 2020-11-10 | 2021-03-09 | 东北电力大学 | Driving fatigue monitoring method based on multiple types of characteristics of human body |
CN113509189A (en) * | 2021-07-07 | 2021-10-19 | 科大讯飞股份有限公司 | Learning state monitoring method and related equipment thereof |
CN113951903A (en) * | 2021-10-29 | 2022-01-21 | 西南交通大学 | High-speed railway dispatcher overload state identification method based on electroencephalogram data determination |
CN114081491A (en) * | 2021-11-15 | 2022-02-25 | 西南交通大学 | High-speed railway dispatcher fatigue prediction method based on electroencephalogram time series data determination |
CN115359545A (en) * | 2022-10-19 | 2022-11-18 | 深圳海星智驾科技有限公司 | Staff fatigue detection method and device, electronic equipment and storage medium |
US11813060B2 (en) | 2020-06-29 | 2023-11-14 | Lear Corporation | System and method for biometric evoked response monitoring and feedback |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
CN101540090A (en) * | 2009-04-14 | 2009-09-23 | 华南理工大学 | Driver fatigue monitoring device based on multivariate information fusion and monitoring method thereof |
CN101872171A (en) * | 2009-04-24 | 2010-10-27 | 中国农业大学 | Driver fatigue state recognition method and system based on information fusion |
WO2014204567A1 (en) * | 2013-06-19 | 2014-12-24 | Raytheon Company | Imaging-based monitoring of stress and fatigue |
CN104952210A (en) * | 2015-05-15 | 2015-09-30 | 南京邮电大学 | Fatigue driving state detecting system and method based on decision-making level data integration |
CN106462027A (en) * | 2014-06-23 | 2017-02-22 | 本田技研工业株式会社 | System and method for responding to driver state |
CN106580349A (en) * | 2016-12-07 | 2017-04-26 | 中国民用航空总局第二研究所 | Controller fatigue detection method and device and controller fatigue responding method and device |
-
2017
- 2017-05-27 CN CN201710397928.1A patent/CN107233103B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
CN101540090A (en) * | 2009-04-14 | 2009-09-23 | 华南理工大学 | Driver fatigue monitoring device based on multivariate information fusion and monitoring method thereof |
CN101872171A (en) * | 2009-04-24 | 2010-10-27 | 中国农业大学 | Driver fatigue state recognition method and system based on information fusion |
WO2014204567A1 (en) * | 2013-06-19 | 2014-12-24 | Raytheon Company | Imaging-based monitoring of stress and fatigue |
US20140375785A1 (en) * | 2013-06-19 | 2014-12-25 | Raytheon Company | Imaging-based monitoring of stress and fatigue |
CN106462027A (en) * | 2014-06-23 | 2017-02-22 | 本田技研工业株式会社 | System and method for responding to driver state |
CN104952210A (en) * | 2015-05-15 | 2015-09-30 | 南京邮电大学 | Fatigue driving state detecting system and method based on decision-making level data integration |
CN106580349A (en) * | 2016-12-07 | 2017-04-26 | 中国民用航空总局第二研究所 | Controller fatigue detection method and device and controller fatigue responding method and device |
Non-Patent Citations (1)
Title |
---|
邓三鹏等: "基于D-S证据理论的驾驶员疲劳监测方法研究", 《车辆与动力技术》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108852380A (en) * | 2018-07-09 | 2018-11-23 | 南京邮电大学 | Fatigue, mood analysis method based on ECG signal |
CN109431498A (en) * | 2018-11-14 | 2019-03-08 | 天津大学 | Wearable multi-modal physiological driver's condition monitoring system |
US11813060B2 (en) | 2020-06-29 | 2023-11-14 | Lear Corporation | System and method for biometric evoked response monitoring and feedback |
CN112450933A (en) * | 2020-11-10 | 2021-03-09 | 东北电力大学 | Driving fatigue monitoring method based on multiple types of characteristics of human body |
CN112450933B (en) * | 2020-11-10 | 2022-09-20 | 东北电力大学 | Driving fatigue monitoring method based on multiple types of characteristics of human body |
CN113509189A (en) * | 2021-07-07 | 2021-10-19 | 科大讯飞股份有限公司 | Learning state monitoring method and related equipment thereof |
CN113951903A (en) * | 2021-10-29 | 2022-01-21 | 西南交通大学 | High-speed railway dispatcher overload state identification method based on electroencephalogram data determination |
CN113951903B (en) * | 2021-10-29 | 2022-07-08 | 西南交通大学 | High-speed railway dispatcher overload state identification method based on electroencephalogram data determination |
CN114081491A (en) * | 2021-11-15 | 2022-02-25 | 西南交通大学 | High-speed railway dispatcher fatigue prediction method based on electroencephalogram time series data determination |
CN114081491B (en) * | 2021-11-15 | 2023-04-25 | 西南交通大学 | Fatigue prediction method for high-speed railway dispatcher based on electroencephalogram time sequence data measurement |
CN115359545A (en) * | 2022-10-19 | 2022-11-18 | 深圳海星智驾科技有限公司 | Staff fatigue detection method and device, electronic equipment and storage medium |
CN115359545B (en) * | 2022-10-19 | 2023-01-24 | 深圳海星智驾科技有限公司 | Staff fatigue detection method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107233103B (en) | 2020-11-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107233103A (en) | High ferro dispatcher's fatigue state assessment method and system | |
CN105991593B (en) | A kind of method and device identifying consumer's risk | |
CN106469181B (en) | User behavior pattern analysis method and device | |
RU2704869C2 (en) | Fingerprint authentication system, fingerprint authentication program and fingerprint authentication method | |
CN101246543A (en) | Examiner identity appraising system based on bionic and biological characteristic recognition | |
CN109684913A (en) | A kind of video human face mask method and system based on community discovery cluster | |
CN108664538A (en) | A kind of automatic identification method and system of the doubtful familial defect of power transmission and transforming equipment | |
CN106295547A (en) | A kind of image comparison method and image comparison device | |
CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
Vengatesan et al. | Face recognition of identical twins based on support vector machine classifier | |
Rodríguez-Ruiz et al. | A survey on minutiae-based palmprint feature representations, and a full analysis of palmprint feature representation role in latent identification performance | |
Ellingsgaard et al. | Detecting fingerprint alterations by orientation field and minutiae orientation analysis | |
Ambika et al. | Vibration signal based condition monitoring of mechanical equipment with scattering transform | |
CN110889338A (en) | Unsupervised railway track bed foreign matter detection and sample construction method and unsupervised railway track bed foreign matter detection and sample construction device | |
Ferreira et al. | A fuzzy c-means algorithm for fingerprint segmentation | |
Erbilek et al. | A methodological framework for investigating age factors on the performance of biometric systems | |
Assaf et al. | An anomaly detection and explainability framework using convolutional autoencoders for data storage systems | |
Moreira et al. | SNN Input Parameters: how are they related? | |
CN117033501A (en) | Big data acquisition and analysis system | |
CN107025293A (en) | A kind of second power equipment defective data method for digging and system | |
CN111598116A (en) | Data classification method and device, electronic equipment and readable storage medium | |
Li et al. | A novel fingerprint indexing approach focusing on minutia location and direction | |
Yadav et al. | Multiclass Fault Classification of an Induction Motor Bearing Vibration Data Using Wavelet Packet Transform Features and Artificial Intelligence | |
Vasquez et al. | Features extraction in images on finger veins with hybrid curves | |
Chen | Data Quality Assessment Methodology for Improved Prognostics Modeling |
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 |