CN113456078A - Fatigue driving identification method based on PDC intensive graph propagation - Google Patents
Fatigue driving identification method based on PDC intensive graph propagation Download PDFInfo
- Publication number
- CN113456078A CN113456078A CN202011287876.0A CN202011287876A CN113456078A CN 113456078 A CN113456078 A CN 113456078A CN 202011287876 A CN202011287876 A CN 202011287876A CN 113456078 A CN113456078 A CN 113456078A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram
- graph
- signal
- matrix
- fatigue driving
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000011159 matrix material Substances 0.000 claims abstract description 82
- 230000001364 causal effect Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 19
- 238000010586 diagram Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000001427 coherent effect Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 6
- 238000012880 independent component analysis Methods 0.000 claims description 3
- 206010039203 Road traffic accident Diseases 0.000 abstract 1
- 230000008569 process Effects 0.000 description 7
- 210000004556 brain Anatomy 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 description 1
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Developmental Disabilities (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Child & Adolescent Psychology (AREA)
- Mathematical Physics (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a fatigue driving identification method based on PDC dense graph propagation, which comprises the steps of obtaining first electroencephalogram data of a driver at the current time, then constructing a first causal connection matrix among first electroencephalogram signals of all channels by the PDC method, then obtaining a characteristic matrix, extracting information implied between space-time characteristics and effective connection of the electroencephalogram data, constructing a causal connection graph to obtain a graph signal, and identifying the graph signal by using trained dense graph propagation to determine whether the driver is in a fatigue driving state or not. Therefore, the method and the device can improve the identification accuracy of fatigue driving, remind a driver in time in the working environment of the driver and effectively prevent traffic accidents.
Description
Technical Field
The invention belongs to the field of safe driving, and particularly relates to a fatigue driving identification method based on PDC dense graph propagation.
Background
At present, electroencephalograms (EEG) cannot be artificially controlled and forged, can directly and objectively reflect the current mental state of the brain, and are regarded as the 'gold standard' for detecting fatigue driving in a plurality of physiological signal indexes. Different electroencephalogram data of a driver in a normal state and a fatigue state are analyzed and compared, fatigue driving of the driver can be effectively identified, and therefore effective fatigue early warning indication is made. In recent years, the fatigue driving detection method is mainly researched by acquiring data through an electroencephalogram cap, performing multiple feature selection on the acquired electroencephalogram data and then realizing the identification of the fatigue state of a driver through modeling.
In the prior art, the preprocessed electroencephalogram signals are synchronously transmitted to an electroencephalogram signal monitoring device; and extracting 7 characteristic signals from the signals preprocessed by the electroencephalogram signal acquisition device within one second according to the sequence of sampling time, taking the signal values of the 7 characteristic signals as 7 characteristic quantities of the received electroencephalogram signals, comparing the 7 characteristic quantities with preset 7 groups of fatigue driving judgment threshold values, and finally judging the driving fatigue state.
Because the electroencephalogram signal is a spatially discrete and unstable signal, the spatial characteristics of the signal change or the connection of the signal changes, so that the accuracy of the result of judging the driving fatigue state in the prior art is reduced.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a fatigue driving identification method based on PDC dense graph propagation. The technical problem to be solved by the invention is realized by the following technical scheme:
the invention provides a fatigue driving identification method based on PDC (polycrystalline Diamond compact) dense graph propagation, which comprises the following steps of:
acquiring first electroencephalogram data of a driver at the current time;
preprocessing the first electroencephalogram data;
performing band-pass filtering on the preprocessed electroencephalogram data to obtain first electroencephalogram signals of all wave bands;
wherein each band comprises a plurality of channels;
based on the first electroencephalogram signals of all channels under each wave band, a first causal connection matrix between the first electroencephalogram signals of all channels is constructed by using a partially directional coherent PDC method;
extracting the characteristics of the first electroencephalogram signals of all channels under each wave band to form a first characteristic matrix;
wherein the features include: power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics;
for each wave band, determining the characteristics in the first characteristic matrix as parameters of a factor effect connection diagram based on the factor effect connection diagram corresponding to the first factor effect connection matrix of the wave band, and obtaining a first diagram signal;
and identifying the first graph signal by using a trained dense graph propagation model to determine whether the driver is fatigue driving.
Optionally, the training step of the trained dense graph propagation model includes:
acquiring second electroencephalogram data of a driver in a fatigue state and a normal state;
preprocessing the second electroencephalogram data;
performing band-pass filtering on the preprocessed second electroencephalogram data to obtain second electroencephalogram signals of all wave bands;
based on the second electroencephalogram signals of all channels under each wave band, a second factor-effect connection matrix between the electroencephalogram signals of all channels is constructed by using a partially directional coherent PDC method;
extracting the characteristics of the second electroencephalogram signals of all channels under each wave band to form a second characteristic matrix;
for each wave band, determining the characteristics in a second characteristic matrix as parameters of a factor-effect connection structure model based on the factor-effect connection structure model corresponding to the second factor-effect connection matrix of the wave band to obtain a second map signal;
and iteratively training a preset dense graph propagation model by using the second graph signal to obtain a trained dense graph propagation model.
Optionally, the step of iteratively training a preset dense graph propagation model by using the second graph signal to obtain a trained dense graph propagation model includes:
composing the second map signals into a training set;
acquiring a test set, wherein the test set comprises an image signal determined by an electroencephalogram signal in a fatigue state or an image signal determined by an electroencephalogram signal in a normal state;
inputting the training set into a preset compact graph propagation model, and repeatedly adjusting the parameters of the compact graph propagation model until the accuracy of recognizing the test set by the compact graph propagation model after the parameters are adjusted reaches an accuracy threshold;
and determining the dense graph propagation model with the accuracy reaching the accuracy threshold as the trained dense graph propagation model.
Optionally, the step of preprocessing the first electroencephalogram data includes:
and preprocessing the first electroencephalogram data by using artifact subtraction and independent component analysis.
Optionally, the step of obtaining the first electroencephalogram signal of each band by using band-pass filtering on the preprocessed first electroencephalogram data includes:
and performing band-pass filtering on the preprocessed electroencephalogram data to obtain first electroencephalogram signals of 4 wave bands.
Optionally, the step of constructing a first causal connection matrix between the electroencephalograms of the channels by using a partially directional coherent PDC method based on the first electroencephalograms of the channels under each band includes:
for each wave band, calculating the strength of interaction between first electroencephalogram signals of all channels under the wave band and determining the direction of calculating the strength;
and (3) forming a cause-effect connection matrix by the strength of interaction between the electroencephalogram signals of all channels under each wave band according to the direction of calculating the strength.
Optionally, the step of extracting the features of the electroencephalogram data of each channel under each band to form a feature matrix includes:
extracting power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics of electroencephalogram data of each channel under each wave band;
determining the power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics of the electroencephalogram data of each channel as row elements of a matrix according to the front-back sequence;
the row elements are organized into a feature matrix in the order of the channels.
Optionally, the step of determining, for each band, features in the feature matrix as parameters of the factor-effect connection graph based on the factor-effect connection graph corresponding to the factor-effect connection matrix of the band, and obtaining the first graph signal includes:
aiming at each wave band, constructing a factor-effect connection diagram corresponding to the factor-effect connection matrix of the wave band;
the method comprises the following steps that rows and columns in an effective connection matrix represent nodes of an effective connection graph, elements in the effective connection matrix are weights of edges between two adjacent nodes in the effective connection matrix, and the effective connection graph comprises a plurality of nodes and edges;
and determining the row characteristics in the characteristic matrix as the characteristics of the nodes based on the corresponding relation between the characteristic matrix row and the factor-effect connection matrix row, and obtaining a first graph signal of the factor-effect connection graph.
Optionally, the step of identifying the first graph signal by using the trained dense graph propagation model to determine whether the driver is fatigue driving includes:
identifying the first graph signal by using a trained dense graph propagation model to obtain a result whether the first graph signal corresponds to the electroencephalogram signal in a fatigue state,
and when the first map signal corresponds to the electroencephalogram signal in the fatigue state, determining that the driver is in fatigue driving.
Optionally, after the step of determining that the driver is in fatigue driving, the fatigue driving identification method further includes:
and sending an early warning signal to remind a driver.
The invention provides a fatigue driving identification method based on PDC dense graph propagation, which comprises the steps of obtaining first electroencephalogram data of a driver at the current time, then constructing a first causal connection matrix among first electroencephalogram signals of all channels by the PDC method, then obtaining a characteristic matrix, extracting information implied between space-time characteristics and effective connection of the electroencephalogram data, constructing a causal connection graph to obtain a graph signal, and identifying the graph signal by using trained dense graph propagation to determine whether the driver is in a fatigue driving state or not. The present invention will be described in further detail with reference to the accompanying drawings and examples.
Drawings
FIG. 1 is a flow chart of a fatigue driving identification method based on PDC dense graph propagation according to an embodiment of the present invention;
FIG. 2 is a diagram of a cause-effect connection graph constructed according to a cause-effect connection matrix according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a feature assignment to a factor-dependent graph node according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific examples, but the embodiments of the present invention are not limited thereto.
Example one
As shown in fig. 1, a method for identifying fatigue driving based on PDC dense graph propagation according to an embodiment of the present invention includes:
s1, acquiring first electroencephalogram data of the driver at the current time;
the electroencephalogram cap collecting device has the advantages that the electroencephalogram cap collecting device can collect electroencephalogram data of a person in fatigue and normal states, and a driver can wear the electroencephalogram cap collecting device to obtain first electroencephalogram data.
S2, preprocessing the first electroencephalogram data;
wherein, the first brain electrical data can be preprocessed by using artifact subtraction and independent component analysis.
S3, performing band-pass filtering on the preprocessed electroencephalogram data to obtain first electroencephalogram signals of all wave bands;
the preprocessed electroencephalogram data can be subjected to band-pass filtering to obtain first electroencephalogram signals of 4 wave bands, and each wave band comprises a plurality of channels.
Wherein, the 4 wave bands are Theta (4-7Hz), Alpha (8-12Hz), Beta (13-30Hz) and Gamma (31-50 Hz).
S4, based on the first electroencephalogram signals of all channels under each wave band, constructing a first causal connection matrix among the first electroencephalogram signals of all channels by using a partially directional coherent PDC method;
s5, extracting the characteristics of the first electroencephalogram signal of each channel under each wave band to form a first characteristic matrix;
wherein the features include: power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics;
s6, determining the characteristics in the first characteristic matrix as parameters of a factor effect connection diagram based on the factor effect connection diagram corresponding to the first factor effect connection matrix of each wave band, and obtaining a first diagram signal;
wherein the parameter is a characteristic of the node.
And S7, identifying the first map signal by using the trained dense map propagation model, and determining whether the driver is fatigue driving.
The invention provides a fatigue driving identification method based on PDC dense graph propagation, which comprises the steps of obtaining first electroencephalogram data of a driver at the current time, then constructing a first causal connection matrix among first electroencephalogram signals of all channels by the PDC method, then obtaining a characteristic matrix, extracting information implied between space-time characteristics and effective connection of the electroencephalogram data, constructing a causal connection graph to obtain a graph signal, and identifying the graph signal by using trained dense graph propagation to determine whether the driver is in a fatigue driving state or not.
Example two
As an alternative embodiment of the present invention, the training step of the trained dense graph propagation model includes:
step a: acquiring second electroencephalogram data of a driver in a fatigue state and a normal state;
step b: preprocessing the second electroencephalogram data;
step c: performing band-pass filtering on the preprocessed second electroencephalogram data to obtain second electroencephalogram signals of all wave bands;
step d: based on the second electroencephalogram signals of all channels under each wave band, a second factor-effect connection matrix between the electroencephalogram signals of all channels is constructed by using a partially directional coherent PDC method;
step e: extracting the characteristics of the second electroencephalogram signals of all channels under each wave band to form a second characteristic matrix;
step f: for each wave band, determining the characteristics in the second characteristic matrix as parameters of a factor-effect connection structure model based on the factor-effect connection structure model corresponding to the second factor-effect connection matrix of the wave band to obtain a second map signal;
step g: and iteratively training a preset dense graph propagation model by using the second graph signal to obtain a trained dense graph propagation model.
It can be understood that, in the training process of the model, the electroencephalogram data needs to be processed, and the processing process is the same as the process of processing the electroencephalogram data at the current time, which is the same as the process in the first embodiment, and is not described herein again.
EXAMPLE III
As an alternative embodiment of the present invention, the step of iteratively training a preset dense graph propagation model by using a second graph signal to obtain a trained dense graph propagation model includes:
step a: forming the second graph signals into a training set;
step b: acquiring a test set, wherein the test set is a graph signal determined by an electroencephalogram signal in a fatigue state or a graph signal determined by an electroencephalogram signal in a normal state;
step c: inputting the training set into a preset compact graph propagation model, and repeatedly adjusting the parameters of the compact graph propagation model until the accuracy of the compact graph propagation model after the parameters are adjusted for identifying the test set reaches an accuracy threshold;
step d: and determining the dense graph propagation model with the accuracy reaching the accuracy threshold as the trained dense graph propagation model.
The preset dense graph propagation model is an improvement of a directed graph in a graph convolution neural network and mainly comprises 5 layers, two convolution layers, two pooling layers and a full connection layer. Different from the traditional graph convolution neural network, the preset dense graph propagation model does not directly use an undirected graph when the convolution layer is input, and instead, two independent connection modes are introduced, namely a connection mode of a node to all ancestors of the node and a connection mode of the node to all descendants of the node. The formula of the compact graph propagation model convolutional layer is as follows:
the formula of the preset compact graph propagation model convolution layer is as follows:
in the course of the above-mentioned propagation process,
respectively, a regularized parent/child adjacency matrix, X ∈ RN×SA feature matrix is represented.
Iterative optimization training can be performed on a preset dense graph propagation model through a training set graph signal, and dependency among parameters is reduced through a Relu activation function, so that the training accuracy is improved.
Example four
As an optional embodiment of the present invention, the step of constructing the first causal connection matrix between the electroencephalogram signals of the channels by using the partially directional coherent PDC method based on the first electroencephalogram signal of each channel under each band includes:
step a: for each wave band, calculating the strength of interaction between first electroencephalogram signals of all channels under the wave band and determining the direction of calculating the strength;
step b: and (3) forming a cause-effect connection matrix by the strength of interaction between the electroencephalogram signals of all channels under each wave band according to the direction of calculating the strength.
For example, assuming that the channel at each band is 3, 1, 2, and 3 respectively, the electroencephalogram signal of channel 1 is: {1.23, 1.34, 4.12, … }; the electroencephalogram signals of the channel 2 are: {5.2, 1.76, 0.2, … }; the electroencephalogram signals of the channel 3 are: {6.4, 3.65, 3.76, … }, the effective connection matrix is:
wherein, the intensity of the 1- >2 channel is 0.5, the intensity of the 2- >1 channel is 0.7, and the direction refers to the difference between the intensity of the brain signals of the 1- >2 channels and the intensity of the brain signals of the 2- >1 channels, which indicates that the signals have directionality.
EXAMPLE five
As an optional embodiment of the present invention, the step of extracting the features of the electroencephalogram data of each channel under each band and forming a feature matrix includes:
step a: extracting power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics of electroencephalogram data of each channel under each wave band;
step b: determining the power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics of the electroencephalogram data of each channel as row elements of a matrix according to the front-back sequence;
step c: the row elements are organized into a feature matrix in the order of the channels.
Wherein, the number of channels is N, the feature dimension is D dimension, and then the features of all channels form an N multiplied by D feature matrix.
For example, assuming that the number of channels is 3, the four features are extracted, and the obtained feature matrix is 3 × 4, as follows:
modeling the extracted electroencephalogram characteristics of each channel into image signals based on the factor-effect connection mode structure; each electroencephalogram channel corresponds to a node in the graph, four features extracted by each channel serve as the features of the node, and the effective connection between two different nodes corresponds to an edge in the graph.
EXAMPLE six
As an alternative embodiment of the present invention, for each band, determining features in the feature matrix as parameters of a factor-effective connection map based on the factor-effective connection map corresponding to the factor-effective connection matrix of the band, and obtaining a first map signal includes:
step a: aiming at each wave band, constructing a factor-effect connection diagram corresponding to the factor-effect connection matrix of the wave band;
the rows and columns in the effective connection matrix represent nodes of the effective connection graph, elements in the effective connection matrix are weights of edges between two adjacent nodes in the effective connection matrix, and the effective connection graph comprises a plurality of nodes and edges;
step b: and determining the row characteristics in the characteristic matrix as the characteristics of the nodes based on the corresponding relation between the characteristic matrix row and the factor-effect connection matrix row, and obtaining a first graph signal of the factor-effect connection graph.
The cause-effect join graph is composed of nodes and edges, G ═ V, E, V is the set of nodes, and E is the set of weights for the edges. Each channel represents a node in the graph, Eij represents the weight from the node i to the node j, and the following weight from the node 1 to the node 2 is 0.5, and the relationship between the effective connection matrix and the effective connection graph is as follows:
as shown in fig. 2, fig. 2 is a factor-dependent connection diagram constructed according to a factor-dependent connection matrix. The graph signal is given to an adjacency matrix a of any graph, and assuming that the number of nodes is N, any signal with the length of N can be used as the graph signal of the factor connection graph, and the value of each position thereof represents the value of the corresponding node. If the number of the corresponding nodes of the electroencephalogram signal is 3, the signal is four characteristics extracted from each channel, the length is 4, the value of the position of the node 1 is {1.2, 0.5, 2.3, 2.2}, and the characteristic matrix is as follows:
thus, node 1 corresponds to channel 1, node 2 corresponds to channel 2, and node 3 corresponds to channel 3. As shown in fig. 3, the structure based on the cause-effect connection mode is to first create a graph-effect connection graph, and then assign values to nodes of each graph on the basis of the graph, namely, the characteristics of the brain signals under the channels, and this process is called the graph signal obtaining process.
EXAMPLE seven
As an alternative embodiment of the present invention, the step of identifying the first graph signal by using the trained dense graph propagation model to determine whether the driver is fatigue driving comprises:
step a: identifying the first image signal by using the trained dense image propagation model to obtain a result of whether the first image signal corresponds to the electroencephalogram signal in the fatigue state;
step b: and when the first map signal corresponds to the electroencephalogram signal in the fatigue state, determining that the driver is in fatigue driving.
Example eight
As an alternative embodiment of the present invention, after the step of determining that the driver is in fatigue driving, the fatigue driving identification method further includes:
and sending an early warning signal to remind a driver.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, "above" or "below" a first feature means that the first and second features are in direct contact, or that the first and second features are not in direct contact but are in contact with each other via another feature therebetween. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly under and obliquely below the second feature, or simply meaning that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples described in this specification can be combined and combined by those skilled in the art.
While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (10)
1. A fatigue driving identification method based on PDC intensive graph propagation is characterized by comprising the following steps:
acquiring first electroencephalogram data of a driver at the current time;
preprocessing the first electroencephalogram data;
performing band-pass filtering on the preprocessed electroencephalogram data to obtain first electroencephalogram signals of all wave bands;
wherein each band comprises a plurality of channels;
based on the first electroencephalogram signals of all channels under each wave band, a first causal connection matrix between the first electroencephalogram signals of all channels is constructed by using a partially directional coherent PDC method;
extracting the characteristics of the first electroencephalogram signals of all channels under each wave band to form a first characteristic matrix;
wherein the features include: power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics;
for each wave band, determining the characteristics in the first characteristic matrix as parameters of a factor effect connection diagram based on the factor effect connection diagram corresponding to the first factor effect connection matrix of the wave band, and obtaining a first diagram signal;
and identifying the first graph signal by using a trained dense graph propagation model to determine whether the driver is fatigue driving.
2. The fatigue driving recognition method of claim 1, wherein the training step of the trained dense graph propagation model comprises:
acquiring second electroencephalogram data of a driver in a fatigue state and a normal state;
preprocessing the second electroencephalogram data;
performing band-pass filtering on the preprocessed second electroencephalogram data to obtain second electroencephalogram signals of all wave bands;
based on the second electroencephalogram signals of all channels under each wave band, a second factor-effect connection matrix between the electroencephalogram signals of all channels is constructed by using a partially directional coherent PDC method;
extracting the characteristics of the second electroencephalogram signals of all channels under each wave band to form a second characteristic matrix;
for each wave band, determining the characteristics in a second characteristic matrix as parameters of a factor-effect connection structure model based on the factor-effect connection structure model corresponding to the second factor-effect connection matrix of the wave band to obtain a second map signal;
and iteratively training a preset dense graph propagation model by using the second graph signal to obtain a trained dense graph propagation model.
3. The fatigue driving recognition method according to claim 1, wherein the step of iteratively training the preset dense graph propagation model using the second graph signal to obtain the trained dense graph propagation model comprises:
composing the second map signals into a training set;
acquiring a test set, wherein the test set comprises an image signal determined by an electroencephalogram signal in a fatigue state or an image signal determined by an electroencephalogram signal in a normal state;
inputting the training set into a preset compact graph propagation model, and repeatedly adjusting the parameters of the compact graph propagation model until the accuracy of recognizing the test set by the compact graph propagation model after the parameters are adjusted reaches an accuracy threshold;
and determining the dense graph propagation model with the accuracy reaching the accuracy threshold as the trained dense graph propagation model.
4. The fatigue driving identification method of claim 1, wherein the step of preprocessing the first electroencephalogram data comprises:
and preprocessing the first electroencephalogram data by using artifact subtraction and independent component analysis.
5. The fatigue driving identification method according to claim 1, wherein the step of obtaining the first electroencephalogram signal of each band by using band-pass filtering on the preprocessed first electroencephalogram data comprises:
and performing band-pass filtering on the preprocessed electroencephalogram data to obtain first electroencephalogram signals of 4 wave bands.
6. The fatigue driving identification method of claim 1, wherein the step of constructing the first causal connection matrix between the electroencephalograms of the channels using the partially oriented coherent PDC method based on the first electroencephalograms of the channels under each band comprises:
for each wave band, calculating the strength of interaction between first electroencephalogram signals of all channels under the wave band and determining the direction of calculating the strength;
and (3) forming a cause-effect connection matrix by the strength of interaction between the electroencephalogram signals of all channels under each wave band according to the direction of calculating the strength.
7. The fatigue driving recognition method according to claim 1, wherein the step of extracting the features of the electroencephalogram data of each channel in each band to form a feature matrix comprises:
extracting power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics of electroencephalogram data of each channel under each wave band;
determining the power spectral density, differential entropy, differential asymmetry and rational asymmetry characteristics of the electroencephalogram data of each channel as row elements of a matrix according to the front-back sequence;
the row elements are organized into a feature matrix in the order of the channels.
8. The fatigue driving recognition method according to claim 1, wherein the step of determining, for each band, features in the feature matrix as parameters of the factor-effect connection map based on the factor-effect connection map corresponding to the factor-effect connection matrix of the band, and obtaining the first map signal includes:
aiming at each wave band, constructing a factor-effect connection diagram corresponding to the factor-effect connection matrix of the wave band;
the method comprises the following steps that rows and columns in an effective connection matrix represent nodes of an effective connection graph, elements in the effective connection matrix are weights of edges between two adjacent nodes in the effective connection matrix, and the effective connection graph comprises a plurality of nodes and edges;
and determining the row characteristics in the characteristic matrix as the characteristics of the nodes based on the corresponding relation between the characteristic matrix row and the factor-effect connection matrix row, and obtaining a first graph signal of the factor-effect connection graph.
9. The fatigue driving identification method according to claim 1, wherein the identifying the first map signal using the trained dense map propagation model, and the determining whether the driver is fatigue driving includes:
identifying the first map signal by using a trained dense map propagation model to obtain a result of whether the first map signal corresponds to the electroencephalogram signal in a fatigue state;
and when the first map signal corresponds to the electroencephalogram signal in the fatigue state, determining that the driver is in fatigue driving.
10. The fatigue driving identification method according to claim 1, wherein after the step of determining that the driver is in fatigue driving, the fatigue driving identification method further comprises:
and sending an early warning signal to remind a driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011287876.0A CN113456078B (en) | 2020-11-17 | 2020-11-17 | Fatigue driving identification method based on PDC dense map propagation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011287876.0A CN113456078B (en) | 2020-11-17 | 2020-11-17 | Fatigue driving identification method based on PDC dense map propagation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113456078A true CN113456078A (en) | 2021-10-01 |
| CN113456078B CN113456078B (en) | 2024-06-11 |
Family
ID=77868246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011287876.0A Active CN113456078B (en) | 2020-11-17 | 2020-11-17 | Fatigue driving identification method based on PDC dense map propagation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113456078B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115620484A (en) * | 2022-09-30 | 2023-01-17 | 重庆长安汽车股份有限公司 | Fatigue driving alarm method and device, vehicle-mounted unit system, vehicle and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104473636A (en) * | 2014-12-30 | 2015-04-01 | 天津大学 | Brain fatigue network analysis method based on partial orientation coherence |
| CN109770924A (en) * | 2019-01-24 | 2019-05-21 | 五邑大学 | A kind of tired classification method based on Hadamard product building brain function network and Method Using Relevance Vector Machine |
| CN110399857A (en) * | 2019-08-01 | 2019-11-01 | 西安邮电大学 | A kind of brain electricity emotion identification method based on figure convolutional neural networks |
| CN110969108A (en) * | 2019-11-25 | 2020-04-07 | 杭州电子科技大学 | Limb action recognition method based on autonomic motor imagery electroencephalogram |
| CN111544017A (en) * | 2020-05-25 | 2020-08-18 | 五邑大学 | GPDC graph convolution neural network-based fatigue detection method and device and storage medium |
-
2020
- 2020-11-17 CN CN202011287876.0A patent/CN113456078B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104473636A (en) * | 2014-12-30 | 2015-04-01 | 天津大学 | Brain fatigue network analysis method based on partial orientation coherence |
| CN109770924A (en) * | 2019-01-24 | 2019-05-21 | 五邑大学 | A kind of tired classification method based on Hadamard product building brain function network and Method Using Relevance Vector Machine |
| CN110399857A (en) * | 2019-08-01 | 2019-11-01 | 西安邮电大学 | A kind of brain electricity emotion identification method based on figure convolutional neural networks |
| CN110969108A (en) * | 2019-11-25 | 2020-04-07 | 杭州电子科技大学 | Limb action recognition method based on autonomic motor imagery electroencephalogram |
| CN111544017A (en) * | 2020-05-25 | 2020-08-18 | 五邑大学 | GPDC graph convolution neural network-based fatigue detection method and device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 孟桂芳 等: "一种与N-Back诱发脑力疲劳相关的特异性脑电网络结构", 中国生物医学工程学报, 30 April 2017 (2017-04-30) * |
| 张春翠: "体疲劳对脑疲劳影响的脑电信息分析与处理", 中国优秀硕士学位论文全文数据库医药卫生科技辑, 15 March 2017 (2017-03-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115620484A (en) * | 2022-09-30 | 2023-01-17 | 重庆长安汽车股份有限公司 | Fatigue driving alarm method and device, vehicle-mounted unit system, vehicle and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113456078B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389059B (en) | P300 detection method based on CNN-LSTM network | |
| US5815413A (en) | Integrated method for chaotic time series analysis | |
| CN111310786B (en) | Traffic detector abnormality diagnosis method and device based on random forest classifier | |
| CN106874693A (en) | A kind of medical big data analysis process system and method | |
| CN106503799A (en) | Deep learning model and the application in brain status monitoring based on multiple dimensioned network | |
| CN107506692A (en) | A kind of dense population based on deep learning counts and personnel's distribution estimation method | |
| CN104720796A (en) | Automatic detecting system and method for epileptic attack time period | |
| CN105956623A (en) | Epilepsy electroencephalogram signal classification method based on fuzzy entropy | |
| CN108256453A (en) | A kind of method based on one-dimensional ECG signal extraction two dimension CNN features | |
| EP3913550A1 (en) | Model generation device, model generation method, model generation program, model generation system, inspection system, and monitoring system | |
| CN111597990B (en) | RSVP (resource reservation protocol) model-based brain-computer combined target detection method and system | |
| CN116881749B (en) | Pollution site construction monitoring method and system | |
| CN112089398A (en) | Method for detecting drug addiction degree | |
| CN107348964B (en) | Method for measuring psychological load of driver in extra-long tunnel environment based on factor analysis | |
| CN106446765A (en) | Health state evaluation system based on multidimensional physiological big data depth learning | |
| CN115455079A (en) | Accident multi-issue point recommendation method based on accident data and characteristic factors | |
| CN104794505A (en) | Multichannel electroencephalogram data fusion and dimension descending method | |
| CN112674782B (en) | Device and method for detecting epileptic-like electrical activity of epileptic during inter-seizure period | |
| CN111067513B (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
| CN116313132A (en) | Medical management system for chronic diseases | |
| CN111259949A (en) | Fault identification model construction method, model and identification method for aircraft environmental control system | |
| CN113456078A (en) | Fatigue driving identification method based on PDC intensive graph propagation | |
| KR20200099811A (en) | Apparatus and method for providing information on epilepsy symptoms based on resting-state EEG | |
| CN118094266B (en) | Intelligent terminal nuclear radiation detection analysis method and system | |
| JP2011060227A (en) | Method and device for generating region segmentation image, and computer program |
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 |