CN107233103A - High ferro dispatcher's fatigue state assessment method and system - Google Patents

Abstract

The invention discloses a method and a system for evaluating the fatigue state of a high-speed rail dispatcher. Among them, the method may include obtaining the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement feature signal of the high-speed rail dispatcher; based on the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement feature signal Signal, extract the eigenvalues below the fatigue warning value; based on the eigenvalues below the fatigue warning value, use the multi-channel data fusion algorithm to determine the fatigue state of the high-speed rail dispatcher. The embodiment of the present invention adopts the above-mentioned technical scheme, takes the daily operation of the high-speed rail dispatcher as the test background, combines multiple signals for judgment, and solves the technical problem of how to improve the precision and accuracy of the evaluation, making monitoring and evaluation more practical. .

Description

Method and system for evaluating the fatigue state of high-speed rail dispatchers

technical field

The embodiments of the present invention relate to the technical field of high-speed rail, in particular to a method and system for evaluating the fatigue state of a high-speed rail dispatcher.

Background technique

The high-speed rail dispatchers work in shifts, which requires a high fatigue resistance. At present, domestic and foreign systems for fatigue monitoring of high-speed rail dispatchers are relatively rare.

The existing fatigue monitoring equipment involves personnel operating backgrounds that are quite different from those of high-speed railway dispatchers, and cannot be simply copied and applied to the fatigue monitoring and evaluation of high-speed railway dispatchers; moreover, the existing fatigue monitoring and evaluation Most of the equipment is based on single-channel analysis, and its precision and accuracy are not high.

Therefore, there is an urgent need for a set of fatigue monitoring and intervention devices to solve the hazards caused by fatigue work of high-speed rail dispatchers.

Contents of the invention

The main purpose of the embodiments of the present invention is to provide a method for evaluating the fatigue state of high-speed rail dispatchers, which at least partly solves the technical problem of how to improve the accuracy and precision of the evaluation. In addition, a high-speed rail dispatcher fatigue state evaluation system is also provided.

In order to achieve the above object, according to one aspect of the present invention, the following technical solutions are provided:

A method for evaluating the fatigue state of high-speed rail dispatchers. The method may include at least:

Obtaining the heart rate signal, electrocardiographic signal, electroencephalogram signal, facial image signal and eye movement characteristic signal of the high-speed rail dispatcher;

Based on the heart rate signal, the ECG signal, the EEG signal, the facial image signal and the eye movement characteristic signal, extracting a feature value below a fatigue warning value;

Based on the eigenvalues below the fatigue warning value, a multi-channel data fusion algorithm is used to determine the fatigue state of the high-speed rail dispatcher.

Further, the extraction of feature values below the fatigue warning value based on the heart rate signal, the ECG signal, the EEG signal, the facial image signal and the eye movement feature signal may specifically include:

Based on the heart rate signal, extracting feature values below the fatigue warning value of the heart rate index;

Based on the electrocardiographic signal, extract the eigenvalues below the fatigue warning value of the electrocardiographic index;

Based on the EEG signal, extract the eigenvalues below the EEG index fatigue warning value;

Based on the facial image signal, extract the feature value below the fatigue warning value of the facial feature index;

Based on the eye movement feature signal, feature values below the eye movement index fatigue warning value are extracted.

Further, based on the heart rate signal, extracting feature values below the heart rate index fatigue warning value may specifically include:

Obtaining a heart rate value based on the heart rate signal;

Draw a heart rate change curve based on the heart rate value;

Based on the heart rate change curve, feature values below the fatigue warning value of the heart rate index are extracted.

Further, based on the ECG signal, extracting the feature values below the fatigue warning value of the ECG index may specifically include:

filtering the ECG signal;

De-aliasing processing is performed on the filtered signal;

Transform the signal from the time domain to the frequency domain after removing the artifacts;

Based on the transformation result, extract frequency domain features;

Based on the frequency domain features, feature values below the fatigue warning value of the ECG index are extracted.

Further, the extraction of feature values below the fatigue warning value of the EEG index based on the EEG signal may specifically include:

filtering the EEG signal;

De-aliasing processing is performed on the filtered signal;

Transform the signal from the time domain to the frequency domain after removing the artifacts;

Extract frequency domain features based on the transformed signal;

Based on the frequency domain features, feature values below the fatigue warning value of the EEG index are extracted.

Further, the extraction of feature values below the fatigue warning value of the facial feature index based on the facial image signal may specifically include:

Carrying out digital image processing to described facial image signal;

Based on the processed results, determining facial features;

Based on the facial features, determine facial fatigue expression features;

Based on the facial fatigue expression features, feature values below the fatigue warning value of the facial feature index are extracted.

Further, the extraction of feature values below the eye movement indicator fatigue warning value based on the eye movement feature signal may specifically include:

Carrying out digital image processing on the eye movement feature signal;

Extract eye movement parameters based on the processed results;

Based on the eye movement parameters, feature values below the eye movement index fatigue warning value are extracted.

Further, the determination of the fatigue state of the high-speed rail dispatcher by using a multi-channel data fusion algorithm based on the eigenvalue below the fatigue warning value may specifically include:

Using the method of entropy, according to the following formula, the eigenvalues below the heart rate index fatigue warning value, the eigenvalues below the ECG index fatigue warning value, the eigenvalues below the EEG index fatigue warning value, the facial features The probability of eigenvalues below the fatigue warning value of the characteristic index and the characteristic value below the fatigue warning value of the eye movement index:

m _i (Θ)＝-k[q _iMF log ₂ q _iMF +(1-q _iMF )log ₂ (1-q _iMF )]

Among them, the The MF represents fatigue; the Represents no fatigue; said q _iMF represents the probability that the i-th channel judges that the high-speed rail dispatcher is in a fatigue state; said 1-q _iMF represents the probability that the i-th channel judges that the high-speed rail dispatcher is in a non-fatigue state, and said i=1 , 2, ... 5; the channels respectively input the eigenvalues below the heart rate index fatigue warning value, the eigenvalues below the ECG index fatigue warning value, the eigenvalues below the EEG index fatigue warning value, The feature value below the fatigue warning value of the facial feature index, the feature value below the fatigue warning value of the eye movement index; the k represents an adjustment factor, and k∈(0,1);

Calculate the basic distribution probability in the fatigue state and the basic distribution probability in the non-fatigue state according to the following formula:

Wherein, the m _i (MF) represents the basic distribution probability of being in a fatigue state; the Indicates the base distribution probability of being in a non-fatigue state;

Carry out multi-channel fusion based on the D-S evidence theory according to the following formula, calculate the probability that the high-speed rail dispatcher is in a fatigue state, the probability that the high-speed rail dispatcher is in a non-fatigue state, and the probability after the fusion of the eigenvalues below each fatigue warning value:

Wherein, the m(MF) represents the probability that the high-speed rail dispatcher is in a state of fatigue; the Represent the probability that the high-speed rail dispatcher is in a non-fatigue state; the m (Θ) represents the probability after the fusion of the eigenvalues below the fatigue warning value; the Or Θ, the i=1,2,...5, the j=1,2k;

The belief function and likelihood function for fatigue, and the belief function and likelihood function for non-fatigue are calculated according to the following formula:

Bel(MF)=m(MF)

Wherein, the Bel(MF) represents the belief function of the fatigue; the Pl(MF) represents the likelihood function of the fatigue; the Represents the non-fatigue trust function; the Represents the likelihood function of not being fatigued;

According to the fatigue trust function and likelihood function, and the non-fatigue trust function and likelihood function, it is determined whether the high-speed rail dispatcher is in a fatigue state.

Further, the method may also include:

comparing said determined fatigue state with a fatigue state threshold;

If the threshold is exceeded, an early warning intervention will be carried out.

According to another aspect of the present invention, a high-speed rail dispatcher fatigue state evaluation system is also provided. The system can include at least:

An acquisition module, configured to acquire heart rate signals, electrocardiographic signals, electroencephalogram signals, facial image signals and eye movement characteristic signals of the high-speed rail dispatcher;

An extraction module, configured to extract feature values below the fatigue warning value based on the heart rate signal, the ECG signal, the EEG signal, the facial image signal and the eye movement feature signal;

The determination module is used to determine the fatigue state of the high-speed rail dispatcher based on the feature value below the fatigue warning value and using a multi-channel data fusion algorithm.

Further, the extraction module may specifically include:

A first extraction unit, configured to extract feature values below the heart rate indicator fatigue warning value based on the heart rate signal;

The second extraction unit is used to extract, based on the ECG signal, a feature value below the fatigue warning value of the ECG index;

The third extraction unit is used to extract feature values below the fatigue warning value of the EEG index based on the EEG signal;

The fourth extraction unit is used to extract feature values below the fatigue warning value of the facial feature index based on the facial image signal;

The fifth extraction unit is configured to extract feature values below the eye movement index fatigue warning value based on the eye movement characteristic signal.

Further, the first extraction unit may specifically include:

an acquisition unit, configured to obtain a heart rate value based on the heart rate signal;

a drawing unit, configured to draw a heart rate change curve based on the heart rate value;

The first extracting subunit is configured to extract, based on the heart rate variation curve, feature values below the heart rate index fatigue warning value.

Further, the second extraction unit may specifically include:

a first filtering unit, configured to filter the electrocardiographic signal;

The first anti-aliasing unit is used to perform anti-artifact processing on the filtered signal;

The first transformation unit is used to transform the signal from the time domain to the frequency domain after de-aliasing;

The second extraction subunit is used to extract frequency domain features based on the transformation result;

The third extracting subunit is configured to extract feature values below the fatigue warning value of the ECG index based on the frequency domain features.

Further, the third extraction unit may specifically include:

a second filtering unit, configured to filter the EEG signal;

The second de-aliasing unit is used to perform de-aliasing processing on the filtered signal;

The second transformation unit is used to transform the signal from the time domain to the frequency domain after de-aliasing;

The fourth extraction subunit is used to extract frequency domain features based on the transformed signal;

The fifth extraction subunit is configured to extract feature values below the fatigue warning value of the EEG index based on the frequency domain feature.

Further, the fourth extraction unit may specifically include:

a first processing unit, configured to perform digital image processing on the facial image signal;

a first determining unit, configured to determine facial features based on the processed result;

The second determination unit is used to determine facial fatigue expression features based on the facial features;

The sixth extraction subunit is used to extract feature values below the fatigue warning value of the facial feature index based on the facial fatigue expression feature.

Further, the fifth extraction unit may specifically include:

a second processing unit, configured to perform digital image processing on the eye movement feature signal;

The seventh extraction subunit is used to extract eye movement parameters based on the processed results;

The eighth extraction subunit is configured to extract feature values below the fatigue warning value of the eye movement index based on the eye movement parameters.

Further, the determining module may specifically include:

The first calculation unit is used to use the method of entropy to calculate the eigenvalues below the heart rate index fatigue warning value, the eigenvalues below the ECG index fatigue warning value, and the EEG indicators below the fatigue warning value according to the following formula The probability of the eigenvalue of , the eigenvalue below the fatigue warning value of the facial feature index, and the eigenvalue below the fatigue warning value of the eye movement index:

m _i (Θ)＝-k[q _iMF log ₂ q _iMF +(1-q _iMF )log ₂ (1-q _iMF )]

Among them, the The MF represents fatigue; the Represents no fatigue; said q _iMF represents the probability that the i-th channel judges that the high-speed rail dispatcher is in a fatigue state; said 1-q _iMF represents the probability that the i-th channel judges that the high-speed rail dispatcher is in a non-fatigue state, and said i=1 , 2, ... 5; the channels respectively input the eigenvalues below the heart rate index fatigue warning value, the eigenvalues below the ECG index fatigue warning value, the eigenvalues below the EEG index fatigue warning value, The feature value below the fatigue warning value of the facial feature index, the feature value below the fatigue warning value of the eye movement index; the k represents an adjustment factor, and k∈(0,1);

The second calculation unit is used to calculate the basic distribution probability in the fatigue state and the basic distribution probability in the non-fatigue state according to the following formula:

Wherein, the m _i (MF) represents the basic distribution probability of being in a fatigue state; the Indicates the base distribution probability of being in a non-fatigue state;

The third calculation unit is used to carry out multi-channel fusion based on the D-S evidence theory according to the following formula, calculate the probability that the high-speed rail dispatcher is in a fatigue state, the probability that the high-speed rail dispatcher is in a non-fatigue state, and the eigenvalues below each fatigue warning value Combined probability:

Wherein, the m(MF) represents the probability that the high-speed rail dispatcher is in a state of fatigue; the Represent the probability that the high-speed rail dispatcher is in a non-fatigue state; the m (Θ) represents the probability after the fusion of the eigenvalues below the fatigue warning value; the Or Θ, the i=1,2,...5, the j=1,2k;

The fourth calculation unit is used to calculate the trust function and likelihood function of fatigue and the trust function and likelihood function of non-fatigue according to the following formula:

Bel(MF)=m(MF)

Wherein, the Bel(MF) represents the belief function of the fatigue; the Pl(MF) represents the likelihood function of the fatigue; the Represents the non-fatigue trust function; the Represents the likelihood function of not being fatigued;

A judging unit, configured to judge whether the high-speed rail dispatcher is in a fatigued state according to the fatigued belief function and likelihood function, and the non-fatigued belief function and likelihood function.

Further, the system may also include:

a comparison unit for comparing the determined fatigue state with a fatigue state threshold;

The early warning intervention unit is configured to perform early warning intervention when the fatigue state exceeds the fatigue state threshold.

Compared with the prior art, the above technical solution has at least the following beneficial effects:

Embodiments of the present invention provide a method and system for evaluating the fatigue state of high-speed rail dispatchers. Among them, the method may include obtaining the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement feature signal of the high-speed rail dispatcher; based on the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement feature signal Signal, extract the eigenvalues below the fatigue warning value; based on the eigenvalues below the fatigue warning value, use the multi-channel data fusion algorithm to determine the fatigue state of the high-speed rail dispatcher. The embodiment of the present invention adopts the above-mentioned technical scheme and takes the daily operation of the high-speed rail dispatcher as the test background, so that the monitoring and evaluation have more practical significance; higher.

Of course, any product implementing the present invention does not necessarily need to realize all the above-mentioned advantages at the same time.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the method particularly pointed out in the written description and claims hereof as well as the appended drawings.

Description of drawings

The accompanying drawings, as a part of the present invention, are used to provide a further understanding of the present invention, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention, but do not constitute improper limitations to the present invention. Apparently, the drawings in the following description are only some embodiments, and those skilled in the art can also obtain other drawings based on these drawings without creative efforts. In the attached picture:

Fig. 1 is a schematic flow diagram of a high-speed rail dispatcher fatigue state evaluation method shown according to an exemplary embodiment;

Fig. 2 is a structural schematic diagram of a high-speed rail dispatcher fatigue state evaluation system shown according to an exemplary embodiment;

Fig. 3 is a schematic structural diagram of a high-speed rail dispatcher fatigue state evaluation system according to another exemplary embodiment.

These drawings and written description are not intended to limit the scope of the inventive concept in any way, but to illustrate the inventive concept for those skilled in the art by referring to specific embodiments.

detailed description

The technical problems solved by the embodiments of the present invention, the technical solutions adopted and the technical effects achieved are clearly and completely described below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present application, not all of them. Based on the embodiments in the present application, all other equivalent or obviously modified embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention. Embodiments of the invention can be embodied in many different ways as defined and covered by the claims.

It should be noted that, in the following description, many specific details are given for the convenience of understanding. It may be evident, however, that the present invention may be practiced without these specific details.

It should also be noted that, in the absence of specific limitations or conflicts, various embodiments of the present invention and technical features therein can be combined with each other to form a technical solution.

In practical application, in order to solve the technical problem of how to improve the precision and accuracy of fatigue state evaluation of high-speed rail dispatchers, the embodiment of the present invention provides a fatigue state evaluation method of high-speed rail dispatchers. The method can be implemented through steps S100 to S120.

S100: Obtain heart rate signals, electrocardiographic signals, electroencephalogram signals, facial image signals and eye movement characteristic signals of the high-speed rail dispatcher.

In this step, the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement feature signal of the high-speed rail dispatcher can be obtained through the signal acquisition device. Among them, the signal acquisition equipment includes a monitoring bracelet, a monitoring brain ring, an image acquisition equipment (such as a camera, a camera, etc.) and an eye tracker. The monitoring bracelet is used to collect heart rate signals and ECG signals. The monitoring brain loop is used to collect EEG signals. The image acquisition device is used to acquire facial image signals. The eye tracker is used to collect eye movement characteristic signals.

In practical applications, the collected signals can be transferred to the database.

S110: Based on heart rate signals, electrocardiographic signals, electroencephalogram signals, facial image signals and eye movement characteristic signals, extract feature values below the fatigue warning value.

Specifically, this step can be implemented through S111 to S115.

S111: Based on the heart rate signal, extract feature values below the fatigue warning value of the heart rate index.

In some optional embodiments, step S111 may specifically include:

Step a1: Obtain a heart rate value based on the heart rate signal.

Step a2: Draw a heart rate variation curve based on the heart rate value.

Step a3: Based on the heart rate change curve, extract the feature values below the fatigue warning value of the heart rate index.

S112: Based on the electrocardiographic signal, extract the feature value below the fatigue warning value of the electrocardiographic index.

In some optional embodiments, step S112 may specifically include:

Step b1: filter the ECG signal.

Step b2: performing anti-artifact processing on the filtered signal.

Step b3: performing time-domain to frequency-domain transformation on the de-aliased signal.

Step b4: Extract frequency domain features based on the transformation result.

Step b5: Based on the frequency domain feature, extract the feature value below the fatigue warning value of the ECG index.

S113: Based on the EEG signal, extracting feature values below the fatigue warning value of the EEG index.

In some optional embodiments, step S113 may specifically include:

Step c1: filtering the EEG signal.

Step c2: performing anti-artifact processing on the filtered signal.

Step c3: performing time-domain to frequency-domain transformation on the de-aliased signal.

Step c4: Extract frequency domain features based on the transformed signal.

Step c5: Based on the frequency domain feature, extract the feature value below the fatigue warning value of the EEG index.

S114: Based on the facial image signal, extract feature values below the fatigue warning value of the facial feature index.

In some optional embodiments, step S114 may specifically include:

Step d1: Perform digital image processing on the facial image signal.

Step d2: Determine facial features based on the processed results.

Step d3: Determine facial fatigue expression features based on facial features.

Wherein, the feature of the facial fatigue expression may be, for example, a yawning facial fatigue expression and the like.

Step d4: Based on the facial fatigue expression feature, extract the feature value below the fatigue warning value of the facial feature index.

S115: Based on the eye movement feature signal, extract feature values below the fatigue warning value of the eye movement index.

In some optional embodiments, step S115 may specifically include:

Step e1: Carry out digital image processing on the eye movement characteristic signal.

Step e2: Extract eye movement parameters based on the processed results.

Wherein, the eye movement parameters include but not limited to eyelid opening and closing degree, blink frequency and eye movement trajectory.

Step e3: Based on the eye movement parameters, extract feature values below the eye movement index fatigue warning value.

S120: Based on the eigenvalues below the fatigue warning value, using a multi-channel data fusion algorithm to determine the fatigue state of the high-speed rail dispatcher.

Because according to a certain signal to judge whether the high-speed rail dispatcher is in a state of fatigue, the judgment accuracy cannot reach 100%. Therefore, the embodiment of the present invention uses means such as a multi-channel fusion algorithm based on the D-S evidence theory to fuse multiple signals for determination, thereby improving the determination precision and accuracy.

Specifically, this step may include:

Step f1: Using the entropy method, determine the eigenvalues below the fatigue warning value of the heart rate index, the eigenvalues below the fatigue warning value of the ECG index, the eigenvalues below the fatigue warning value of the EEG index, and the fatigue warning value of the facial feature index according to the following formula The following eigenvalues, the probability of eigenvalues below the eye movement index fatigue warning value:

m _i (Θ)＝-k[q _iMF log ₂ q _iMF +(1-q _iMF )log ₂ (1-q _iMF )]

in, MF means fatigue; Indicates no fatigue; q _iMF indicates the probability that the i-th channel judges that the high-speed rail dispatcher is in a fatigue state; 1-q _iMF represents the probability that the i-th channel judges that the high-speed rail dispatcher is in a non-fatigue state, i=1,2,...5; Input the eigenvalues below the fatigue warning value of the heart rate index, the eigenvalues below the fatigue warning value of the ECG index, the eigenvalues below the fatigue warning value of the EEG index, the eigenvalues of the facial feature index below the fatigue warning value, and the eye movement index to each channel respectively. Eigenvalues below the fatigue warning value; k represents the adjustment factor, and k∈(0,1).

Among them, each channel has only a limited number of identification results for whether the high-speed rail dispatcher is in a fatigue state: fatigue MF and non-fatigue Each channel passes through the heart rate signal, ECG signal, EEG signal, facial image signal, and eye movement characteristic signal respectively.

Step f2: Determine the basic distribution probability of being in the fatigue state and the basic distribution probability of being in the non-fatigue state according to the following formula:

Among them, m _i (MF) represents the basic distribution probability of being in a fatigue state; Indicates the base assigned probability of being in the non-fatigue state.

Step f3: Carry out multi-channel fusion based on the D-S evidence theory according to the following formula to determine the probability of the high-speed rail dispatcher being in a fatigue state, the probability of the high-speed rail dispatcher being in a non-fatigue state, and the probability of fused eigenvalues below each fatigue warning value:

Among them, m(MF) represents the probability that the high-speed rail dispatcher is in a state of fatigue; Indicates the probability that the high-speed rail dispatcher is in a non-fatigue state; m(Θ) indicates the probability of fused eigenvalues below the fatigue warning value; Or Θ, i=1,2,...5, j=1,2.

Step f4: Calculate the trust function and likelihood function of fatigue, and the trust function and likelihood function of non-fatigue according to the following formula:

Bel(MF)=m(MF)

Among them, Bel(MF) represents the trust function of fatigue; Pl(MF) represents the likelihood function of fatigue; Represents a trust function that is not fatigued; Represents the likelihood function of not being fatigued.

Step f5: According to the fatigue trust function and likelihood function, and the non-fatigue trust function and likelihood function, determine whether the high-speed rail dispatcher is in a fatigue state.

For example:

when , it is determined that the high-speed rail dispatcher is in a fatigue state; when , it cannot be determined; when , it is determined that the high-speed rail dispatcher is not fatigued.

In some optional embodiments, on the basis of the above-mentioned embodiments, the above-mentioned high-speed rail dispatcher fatigue state evaluation method may also include:

S130: Compare the determined fatigue state with a fatigue state threshold.

S140: If the threshold is exceeded, perform early warning intervention.

The embodiment of the present invention adopts the above-mentioned technical scheme and takes the daily operation of the high-speed rail dispatcher as the test background, so that the monitoring and evaluation have more practical significance; higher.

In the above embodiment, although the various steps are described according to the above sequence, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in this order, and they can be performed at the same time ( Parallel) execution or execution in reversed order, these simple changes are all within the protection scope of the present invention.

Based on the same technical concept as the method embodiment, the embodiment of the present invention also provides a high-speed rail dispatcher fatigue state evaluation system. As shown in FIG. 2 , the system 20 may at least include: an acquisition module 22 , an extraction module 24 and a determination module 26 . Wherein, the obtaining module 22 is used to obtain the heart rate signal, electrocardiographic signal, electroencephalogram signal, facial image signal and eye movement characteristic signal of the high-speed rail dispatcher. The extraction module 24 is used to extract feature values below the fatigue warning value based on heart rate signals, electrocardiographic signals, electroencephalogram signals, facial image signals and eye movement feature signals. The determination module 26 is used to determine the fatigue state of the high-speed rail dispatcher based on the feature value below the fatigue warning value and using a multi-channel data fusion algorithm.

In some optional embodiments, on the basis of the above embodiments, the extraction module may specifically include: a first extraction unit, a second extraction unit, a third extraction unit, a fourth extraction unit, and a fifth extraction unit. Wherein, the first extraction unit is used for extracting feature values below the fatigue warning value of the heart rate index based on the heart rate signal. The second extraction unit is used for extracting the feature values below the fatigue warning value of the ECG index based on the ECG signal. The third extraction unit is used for extracting feature values below the fatigue warning value of the EEG index based on the EEG signal. The fourth extraction unit is used to extract feature values below the fatigue warning value of the facial feature index based on the facial image signal. The fifth extraction unit is used to extract feature values below the eye movement index fatigue warning value based on the eye movement characteristic signal.

In some optional embodiments, on the basis of the above embodiments, the first extraction unit may specifically include: an acquisition unit, a rendering unit, and a first extraction subunit. Wherein, the acquiring unit is used for obtaining the heart rate value based on the heart rate signal. The drawing unit is used for drawing a heart rate change curve based on the heart rate value. The first extracting subunit is used for extracting feature values below the fatigue warning value of the heart rate index based on the heart rate change curve.

In some optional embodiments, on the basis of the above embodiments, the above-mentioned second extraction unit may specifically include: a first filtering unit, a first de-aliasing unit, a first transformation unit, a second extraction sub-unit, and a second Three extraction subunits. Wherein, the first filtering unit is used for filtering the ECG signal. The first anti-aliasing unit is used for performing anti-aliasing processing on the filtered signal. The first transformation unit is used for transforming the signal after de-aliasing from the time domain to the frequency domain. The second extraction subunit is used for extracting frequency domain features based on the transformation result. The third extraction subunit is used for extracting feature values below the fatigue warning value of the ECG index based on the frequency domain features.

In some optional embodiments, on the basis of the above embodiments, the third extraction unit specifically includes: a second filtering unit, a second de-aliasing unit, a second transformation unit, a fourth extraction subunit, and a fifth Extract subunits. Wherein, the second filtering unit is used for filtering the EEG signal. The second de-aliasing unit is used to perform de-aliasing processing on the filtered signal. The second transformation unit is used for transforming the de-aliased signal from the time domain to the frequency domain. The fourth extraction subunit is used to extract frequency domain features based on the transformed signal. The fifth extraction subunit is used to extract feature values below the fatigue warning value of the EEG index based on frequency domain features.

In some optional embodiments, on the basis of the foregoing embodiments, the fourth extracting unit specifically includes: a first processing unit, a first determining unit, a second determining unit, and a sixth extracting subunit. Wherein, the first processing unit is used for performing digital image processing on the facial image signal. The first determining unit is used for determining facial features based on the processed result. The second determination unit is used to determine facial fatigue expression features based on facial features. The sixth extraction subunit is used to extract feature values below the fatigue warning value of the facial feature index based on facial fatigue expression features.

In some optional embodiments, on the basis of the foregoing embodiments, the fifth extraction unit specifically includes: a second processing unit, a seventh extraction subunit, and an eighth extraction subunit. Wherein, the second processing unit is used for performing digital image processing on the eye movement characteristic signal. The seventh extracting subunit is used to extract eye movement parameters based on the processed result. The eighth extraction subunit is used to extract feature values below the eye movement index fatigue warning value based on the eye movement parameters.

In some optional embodiments, the above determination module may specifically include: a first calculation unit, a second calculation unit, a third calculation unit, a fourth calculation unit, and a determination unit. Wherein, the first calculation unit is used to use the entropy method to calculate the eigenvalues below the fatigue warning value of the heart rate index, the eigenvalues below the fatigue warning value of the ECG index, the eigenvalues below the fatigue warning value of the EEG index, and the facial features according to the following formula: Probability of the eigenvalues below the fatigue warning value of the feature index and the eigenvalues below the fatigue warning value of the eye movement index:

m _i (Θ)＝-k[q _iMF log ₂ q _iMF +(1-q _iMF )log ₂ (1-q _iMF )]

in, MF means fatigue; Indicates no fatigue; q _iMF indicates the probability that the i-th channel judges that the high-speed rail dispatcher is in a fatigue state; 1-q _iMF represents the probability that the i-th channel judges that the high-speed rail dispatcher is in a non-fatigue state, i=1,2,...5; Input the eigenvalues below the fatigue warning value of the heart rate index, the eigenvalues below the fatigue warning value of the ECG index, the eigenvalues below the fatigue warning value of the EEG index, the eigenvalues of the facial feature index below the fatigue warning value, and the eye movement index to each channel respectively. Eigenvalues below the fatigue warning value; k represents the adjustment factor, and k∈(0,1). The second calculation unit is used to calculate the basic distribution probability in the fatigue state and the basic distribution probability in the non-fatigue state according to the following formula:

Among them, m _i (MF) represents the basic distribution probability of being in a fatigue state; Indicates the base assigned probability of being in the non-fatigue state. The third calculation unit is used to carry out multi-channel fusion based on DS evidence theory according to the following formula, calculate the probability of the high-speed rail dispatcher being in a fatigue state, the probability of the high-speed rail dispatcher being in a non-fatigue state, and the eigenvalues below the fatigue warning value after fusion Probability:

Among them, m(MF) represents the probability that the high-speed rail dispatcher is in a state of fatigue; Indicates the probability that the high-speed rail dispatcher is in a non-fatigue state; m(Θ) indicates the probability of fused eigenvalues below the fatigue warning value; Or Θ, i=1,2,...5, j=1,2k. The fourth calculation unit is used to calculate the fatigue trust function and likelihood function according to the following formula, and the non-fatigue trust function and likelihood function:

Bel(MF)=m(MF)

Among them, Bel(MF) represents the trust function of fatigue; Pl(MF) represents the likelihood function of fatigue; Represents a trust function that is not fatigued; Represents the likelihood function of not being fatigued. The determination unit is used to determine whether the high-speed rail dispatcher is in a fatigue state according to the fatigue trust function and likelihood function, and the non-fatigue trust function and likelihood function.

In some optional embodiments, on the basis of the embodiment shown in FIG. 2 , the above-mentioned high-speed rail dispatcher fatigue state evaluation system may further include: a comparison unit and an early warning intervention unit. Wherein, the comparison unit is used for comparing the determined fatigue state with a fatigue state threshold. The early warning intervention unit is used to perform early warning intervention when the fatigue state exceeds the fatigue state threshold.

Fig. 3 exemplarily shows a preferred implementation of the high-speed rail dispatcher fatigue state evaluation system provided by the embodiment of the present invention. Among them, the wristband component, the brain ring component, the camera and the eye tracker are used to collect the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement characteristic signal of the high-speed rail dispatcher. The database is used to store the heart rate signal, ECG signal, EEG signal, facial image signal and eye movement characteristic signal of the high-speed rail dispatcher. The processing component is used to execute the operations of the above-mentioned extracting module and the above-mentioned determining module. The intervention component is used to execute the operations of the comparison unit and the warning intervention unit. The printer is used to print out the results.

Those skilled in the art can understand that the above-mentioned high-speed rail dispatcher fatigue state evaluation system can also include some other known structures, such as processors, memory, etc., wherein, memory includes but not limited to random access memory, flash memory, read-only memory, volatile memory , non-volatile memory, serial memory, parallel memory or registers, etc., processors include but not limited to CPLD/FPGA, DSP, ARM processors, MIPS processors, etc., in order to unnecessarily obscure the embodiments of the present disclosure, these Known structures are not shown in FIG. 2 .

It should be understood that the number of modules in Fig. 2 is only illustrative. There may be any number of acquiring modules, extracting modules and determining modules according to implementation requirements.

It should be noted that: when the high-speed rail dispatcher fatigue state evaluation system provided by the above-mentioned embodiment is performing fatigue state evaluation, the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functions can also be allocated according to needs. It is completed by different functional modules, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above.

As used herein, the term "module" may refer to software objects or routines that execute on a computing system. The different modules described herein may be implemented as objects or processes executing on a computing system (eg, as separate threads). While the systems and methods described herein are preferably implemented in software, implementations in hardware or a combination of software and hardware are also possible and contemplated.

The above-mentioned system embodiment can be used to execute the above-mentioned method embodiment, and its technical principles, technical problems solved and produced technical effects are similar, and those skilled in the art can clearly understand that for the convenience and brevity of the description, the above description For the specific working process of the system, reference may be made to the corresponding process in the aforementioned method embodiments, which will not be repeated here.

It should be noted that the above describes the system embodiment and the method embodiment of the present invention respectively, but the details described for one embodiment can also be applied to another embodiment. The names of the modules and steps involved in the embodiments of the present invention are only used to distinguish each module or step, and are not regarded as improperly limiting the present invention. Those skilled in the art should understand that the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments may be combined into one module, or further divided into multiple sub-modules.

The technical solutions provided by the embodiments of the present invention have been introduced in detail above. Although this paper uses specific examples to illustrate the principles and implementation methods of the present invention, the description of the above-mentioned embodiments is only applicable to help understand the principles of the embodiments of the present invention; meanwhile, for those skilled in the art, according to this In the embodiment of the invention, changes may be made within the scope of specific implementation and application.

Here, it should be noted that the flow charts or block diagrams involved in this document are not limited to the forms shown herein, and may also be divided and/or combined.

It should also be noted that: the signs and characters in the drawings are only for illustrating the present invention more clearly, and are not regarded as improperly limiting the protection scope of the present invention.

The term "comprising" or any other similar term is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus/apparatus comprising a set of elements includes not only those elements but also other elements not expressly listed, or Also included are elements inherent in these processes, methods, articles, or devices/devices.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed PC. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

The various steps of the present invention can be realized with general-purpose computing devices, for example, they can be concentrated on a single computing device, such as: personal computer, server computer, handheld device or portable device, tablet type device or multi-processor device, also may be distributed over a network of multiple computing devices, which may perform the steps shown or described in a different order than here, or they may be fabricated as individual integrated circuit modules, or multiple modules of them may be Or the steps are fabricated into a single integrated circuit module to realize. Accordingly, the invention is not limited to any specific hardware and software or combination thereof.

The method provided by the present invention can be implemented using programmable logic devices, and can also be implemented as computer program software or program modules (which include routines, programs, objects, components, or data structures that perform specific tasks or implement specific abstract data types, etc. ), for example, according to an embodiment of the present invention may be a computer program product, and the execution of the computer program product causes a computer to execute the exemplified method. The computer program product comprises a computer readable storage medium having computer program logic or code portions embodied thereon for implementing the method. The computer-readable storage medium may be a built-in medium installed in the computer or a removable medium detachable from the main body of the computer (for example, a storage device using a hot-swappable technology). The built-in medium includes but not limited to rewritable non-volatile memory, such as RAM, ROM, flash memory and hard disk. The removable media include but not limited to: optical storage media (such as: CD-ROM and DVD), magneto-optical storage media (such as: MO), magnetic storage media (such as: magnetic tape or mobile hard disk), with built-in Media that writes non-volatile memory (eg: memory card) and media with built-in ROM (eg: ROM cartridge).

The present invention is not limited to the above-mentioned embodiments, and without departing from the essence of the present invention, any deformation, improvement or replacement conceivable by those skilled in the art falls within the protection scope of the present invention.

Claims (18)

1. A method for evaluating fatigue state of a high-speed rail dispatcher, which is characterized by at least comprising the following steps:

acquiring a heart rate signal, an electrocardiosignal, an electroencephalogram signal, a facial image signal and an eye movement characteristic signal of the high-speed rail dispatcher;

extracting a characteristic value below a fatigue alert value based on the heart rate signal, the electrocardiosignal, the electroencephalogram signal, the facial image signal and the eye movement characteristic signal;

and determining the fatigue state of the high-speed rail dispatcher by utilizing a multi-channel data fusion algorithm based on the characteristic value below the fatigue warning value.

2. The method according to claim 1, wherein the extracting feature values below a fatigue alert value based on the heart rate signal, the cardiac signal, the electroencephalogram signal, the facial image signal, and the eye movement feature signal specifically comprises:

extracting a characteristic value below a heart rate index fatigue warning value based on the heart rate signal;

extracting a characteristic value below the fatigue warning value of the electrocardio index based on the electrocardio signal;

extracting characteristic values below the fatigue alert value of the electroencephalogram index based on the electroencephalogram signals;

extracting feature values below a fatigue alert value of a facial feature index based on the facial image signal;

and extracting a characteristic value below the eye movement index fatigue warning value based on the eye movement characteristic signal.

3. The method according to claim 2, wherein extracting, based on the heart rate signal, a characteristic value below a heart rate indicator fatigue alert value specifically comprises:

obtaining a heart rate value based on the heart rate signal;

drawing a heart rate change curve based on the heart rate value;

and extracting characteristic values below the fatigue warning value of the heart rate index based on the heart rate change curve.

4. The method according to claim 2, wherein the extracting, based on the electrocardiographic signal, a feature value below an electrocardiographic index fatigue alert value specifically comprises:

filtering the electrocardiosignals;

performing artifact removal processing on the filtered signal;

carrying out time domain to frequency domain transformation on the signal without the artifacts;

extracting frequency domain features based on the transformation result;

and extracting a characteristic value below the fatigue warning value of the electrocardio index based on the frequency domain characteristics.

5. The method according to claim 2, wherein the extracting, based on the electroencephalogram signal, a feature value below an electroencephalogram index fatigue alert value specifically comprises:

filtering the electroencephalogram signals;

performing artifact removal processing on the filtered signal;

carrying out time domain to frequency domain transformation on the signal without the artifacts;

extracting frequency domain features based on the transformed signal;

and extracting characteristic values below the fatigue warning value of the electroencephalogram index based on the frequency domain characteristics.

6. The method according to claim 2, wherein the extracting feature values below a facial feature index fatigue alert value based on the facial image signal specifically comprises:

performing digital image processing on the facial image signal;

determining facial features based on the processed results;

determining facial fatigue expression features based on the facial features;

and extracting a characteristic value below the fatigue warning value of the facial characteristic index based on the facial fatigue expression characteristic.

7. The method according to claim 2, wherein the extracting, based on the eye movement characteristic signal, characteristic values below an eye movement indicator fatigue alert value specifically comprises:

performing digital image processing on the eye movement characteristic signal;

extracting eye movement parameters based on the processed result;

and extracting characteristic values below the eye movement index fatigue warning value based on the eye movement parameters.

8. The method according to claim 2, wherein the determining the fatigue state of the high-speed rail dispatcher by using a multi-channel data fusion algorithm based on the eigenvalues below the fatigue alert value specifically comprises:

calculating the probability of the characteristic value below the heart rate index fatigue warning value, the characteristic value below the electrocardio index fatigue warning value, the characteristic value below the electroencephalogram index fatigue warning value, the characteristic value below the facial characteristic index fatigue warning value and the characteristic value below the eye movement index fatigue warning value according to the following formula by using an entropy method:

m_i(Θ)＝-k[q_iMFlog₂q_iMF+(1-q_iMF)log₂(1-q_iMF)]

wherein, theThe MF represents fatigue; the above-mentionedNo fatigue is indicated; q is a number of_iMFRepresenting the probability that the ith channel judges that the high-speed rail dispatcher is in a fatigue state; 1-q of the above_iMFThe probability that the ith channel judges that the high-speed rail dispatcher is in the fatigue-free state is represented, wherein i is 1,2 and … 5, the characteristic value below the heart rate index fatigue warning value, the characteristic value below the electrocardio index fatigue warning value, the characteristic value below the electroencephalogram index fatigue warning value, the characteristic value below the face characteristic index fatigue warning value and the characteristic value below the eye movement index fatigue warning value are input into each channel, k represents an adjusting factor, and k ∈ (0, 1);

calculating the base allocation probability in a fatigue state and the base allocation probability in a non-fatigue state according to the following formula:

m_i(MF)＝q_iMF(1-m_i(Θ))

m_i(MF)＝(1-q_iMF)(1-m_i(Θ))

wherein, said m_i(MF) representing a base distribution probability in a fatigue state; the above-mentionedRepresenting a base allocation probability in a non-fatigued state;

performing multi-channel fusion based on a D-S evidence theory according to the following formula, and calculating the probability of the high-speed rail dispatcher in a fatigue state, the probability of the high-speed rail dispatcher in a non-fatigue state and the probability after fusion of characteristic values below all fatigue warning values:

wherein M (MF) represents a probability that the high-speed rail dispatcher is in a fatigue state; the above-mentionedRepresenting a probability that the high-speed rail dispatcher is in an unworn state; the m (theta) represents the probability of fusion of characteristic values below the fatigue warning value; the above-mentionedOr Θ, said i being 1, 2.. 5, said j being 1,2 k;

the fatigue and non-fatigue belief and likelihood functions are calculated according to the 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>&amp;OverBar;</mo> </mover> <mo>)</mo> </mrow> <mo>=</mo> <mi>m</mi> <mrow> <mo>(</mo> <mover> <mrow> <mi>M</mi> <mi>F</mi> </mrow> <mo>&amp;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>&amp;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>&amp;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 said Bel (MF) represents a belief function for said fatigue; said pl (mf) represents a likelihood function of said fatigue; the above-mentionedA trust function representing said non-fatigue; the above-mentionedA likelihood function representing said lack of fatigue;

and judging whether the high-speed rail dispatcher is in a fatigue state or not according to the fatigue trust function and the fatigue likelihood function and the non-fatigue trust function and the fatigue likelihood function.

9. The method of claim 1, further comprising:

comparing the determined fatigue state to a fatigue state threshold;

and if the threshold value is exceeded, performing early warning intervention.

10. A high-speed rail dispatcher fatigue state assessment system, characterized in that the system at least comprises:

the acquisition module is used for acquiring a heart rate signal, an electrocardiosignal, an electroencephalogram signal, a facial image signal and an eye movement characteristic signal of the high-speed rail dispatcher;

the extraction module is used for extracting a characteristic value below a fatigue warning value based on the heart rate signal, the electrocardiosignal, the electroencephalogram signal, the facial image signal and the eye movement characteristic signal;

and the determining module is used for determining the fatigue state of the high-speed rail dispatcher by utilizing a multi-channel data fusion algorithm based on the characteristic value below the fatigue warning value.

11. The system according to claim 10, wherein the extraction module specifically comprises:

the first extraction unit is used for extracting a characteristic value below a fatigue warning value of a heart rate index based on the heart rate signal;

the second extraction unit is used for extracting a characteristic value below the fatigue warning value of the electrocardio index based on the electrocardio signal;

the third extraction unit is used for extracting a characteristic value below the fatigue warning value of the electroencephalogram index based on the electroencephalogram signal;

a fourth extraction unit configured to extract a feature value of a facial feature index fatigue alert value or less based on the facial image signal;

and a fifth extraction unit, configured to extract a feature value below the eye movement index fatigue warning value based on the eye movement feature signal.

12. The system according to claim 11, wherein the first extraction unit specifically comprises:

the acquisition unit is used for obtaining a heart rate value based on the heart rate signal;

the drawing unit is used for drawing a heart rate change curve based on the heart rate value;

and the first extraction subunit is used for extracting a characteristic value below the fatigue warning value of the heart rate index based on the heart rate change curve.

13. The system according to claim 11, wherein the second extraction unit comprises:

the first filtering unit is used for filtering the electrocardiosignals;

the first artifact removing unit is used for removing artifacts of the filtered signal;

the first transformation unit is used for carrying out time domain to frequency domain transformation on the signal without the artifacts;

a second extraction subunit, configured to extract frequency domain features based on the transform result;

and the third extraction subunit is used for extracting a characteristic value below the fatigue warning value of the electrocardio index based on the frequency domain characteristic.

14. The system according to claim 11, wherein the third extraction unit specifically comprises:

the second filtering unit is used for filtering the electroencephalogram signals;

the second artifact removing unit is used for removing artifacts of the filtered signal;

the second transformation unit is used for carrying out time domain to frequency domain transformation on the signal without the artifacts;

a fourth extraction subunit, configured to extract frequency domain features based on the transformed signal;

and the fifth extraction subunit is used for extracting a characteristic value below the electroencephalogram index fatigue warning value based on the frequency domain characteristics.

15. The system according to claim 11, wherein the fourth extraction unit specifically comprises:

a first processing unit for performing digital image processing on the face image signal;

a first determination unit configured to determine a facial feature based on a result after the processing;

a second determination unit configured to determine a facial fatigue expression feature based on the facial feature;

and the sixth extraction subunit is used for extracting a characteristic value below the fatigue warning value of the facial characteristic index based on the facial fatigue expression characteristic.

16. The system according to claim 11, wherein the fifth extraction unit specifically comprises:

the second processing unit is used for carrying out digital image processing on the eye movement characteristic signal;

a seventh extraction subunit, configured to extract an eye movement parameter based on the processed result;

and the eighth extraction subunit is used for extracting a characteristic value below the eye movement index fatigue warning value based on the eye movement parameter.

17. The system of claim 11, wherein the determining module specifically comprises:

a first calculating unit, configured to calculate, by using an entropy method, probabilities of feature values below the heart rate index fatigue alert value, feature values below the electrocardiogram index fatigue alert value, feature values below the electroencephalogram index fatigue alert value, feature values below the facial feature index fatigue alert value, and feature values below the eye movement index fatigue alert value according to the following formulas:

m_i(Θ)＝-k[q_iMFlog₂q_iMF+(1-q_iMF)log₂(1-q_iMF)]

wherein, theThe MF represents fatigue; the above-mentionedNo fatigue is indicated; q is a number of_iMFRepresenting the probability that the ith channel judges that the high-speed rail dispatcher is in a fatigue state; 1-q of the above_iMFThe probability that the ith channel judges that the high-speed rail dispatcher is in the fatigue-free state is represented, wherein i is 1,2 and … 5, the characteristic value below the heart rate index fatigue warning value, the characteristic value below the electrocardio index fatigue warning value, the characteristic value below the electroencephalogram index fatigue warning value, the characteristic value below the face characteristic index fatigue warning value and the characteristic value below the eye movement index fatigue warning value are input into each channel, k represents an adjusting factor, and k ∈ (0, 1);

a second calculation unit for calculating the basic distribution probability in the fatigue state and the basic distribution probability in the non-fatigue state according to the following formula:

m_i(MF)＝q_iMF(1-m_i(Θ))

m_i(MF)＝(1-q_iMF)(1-m_i(Θ))

wherein, said m_i(MF) representing a base distribution probability in a fatigue state; the above-mentionedRepresenting a base allocation probability in a non-fatigued state;

a third calculating unit, configured to perform multi-channel fusion based on the D-S evidence theory according to the following formula, and calculate a probability that the high-speed rail dispatcher is in a fatigue state, a probability that the high-speed rail dispatcher is in a non-fatigue state, and a probability that feature values below the fatigue warning values are fused:

wherein M (MF) represents a probability that the high-speed rail dispatcher is in a fatigue state; the above-mentionedRepresenting a probability that the high-speed rail dispatcher is in an unworn state; the m (theta) represents the probability of fusion of characteristic values below the fatigue warning value; the above-mentionedOr Θ, said i being 1, 2.. 5, said j being 1,2 k;

a fourth calculation unit for calculating the tired belief function and the likelihood function, and the tired belief function and the likelihood function according to the following equations:

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>&amp;OverBar;</mo> </mover> <mo>)</mo> </mrow> <mo>=</mo> <mi>m</mi> <mrow> <mo>(</mo> <mover> <mrow> <mi>M</mi> <mi>F</mi> </mrow> <mo>&amp;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>&amp;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>&amp;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 said Bel (MF) represents a belief function for said fatigue; said pl (mf) represents a likelihood function of said fatigue; the above-mentionedA trust function representing said non-fatigue; the above-mentionedA likelihood function representing said lack of fatigue;

and the judging unit is used for judging whether the high-speed rail dispatcher is in a fatigue state or not according to the fatigue trust function and the fatigue likelihood function and the non-fatigue trust function and the fatigue likelihood function.

18. The system of claim 10, further comprising:

a comparison unit for comparing the determined fatigue state with a fatigue state threshold;

and the early warning intervention unit is used for carrying out early warning intervention under the condition that the fatigue state exceeds the fatigue state threshold value.