CN116453289B - Bus driving safety early warning method and system based on electrocardiosignal - Google Patents
Bus driving safety early warning method and system based on electrocardiosignal Download PDFInfo
- Publication number
- CN116453289B CN116453289B CN202210013345.5A CN202210013345A CN116453289B CN 116453289 B CN116453289 B CN 116453289B CN 202210013345 A CN202210013345 A CN 202210013345A CN 116453289 B CN116453289 B CN 116453289B
- Authority
- CN
- China
- Prior art keywords
- bus driver
- bus
- emergency
- driver
- sequence
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012360 testing method Methods 0.000 claims abstract description 40
- 230000004044 response Effects 0.000 claims abstract description 20
- 238000004088 simulation Methods 0.000 claims description 33
- 230000008569 process Effects 0.000 claims description 28
- 230000010485 coping Effects 0.000 claims description 23
- 230000001734 parasympathetic effect Effects 0.000 claims description 17
- 230000002889 sympathetic effect Effects 0.000 claims description 15
- 206010039203 Road traffic accident Diseases 0.000 claims description 9
- 210000005037 parasympathetic nerve Anatomy 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 6
- 210000005036 nerve Anatomy 0.000 claims description 6
- 230000035484 reaction time Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 abstract description 7
- 238000011084 recovery Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 18
- 230000008451 emotion Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 5
- 238000010606 normalization Methods 0.000 description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000007794 irritation Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0233—System arrangements with pre-alarms, e.g. when a first distance is exceeded
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0236—Threshold setting
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Child & Adolescent Psychology (AREA)
- General Physics & Mathematics (AREA)
- Developmental Disabilities (AREA)
- Medical Informatics (AREA)
- Psychiatry (AREA)
- Theoretical Computer Science (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Hospice & Palliative Care (AREA)
- Computing Systems (AREA)
- Educational Technology (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Artificial Intelligence (AREA)
- Neurology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Cardiology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a bus driving safety early warning method and system based on electrocardiosignals. The model input is divided into two parts of psychological states and technical capability, the psychological states represent the tension state of a driver before an emergency arrives through an electrocardiosignal deconstructing and extracting SAI-PAI ratio sequence, the technical level is obtained through test evaluation, the output is divided into three parts of emergency completion degree, response and recovery time, the three parts are used for representing the degree of success of the response of the emergency of the driver, the time is reflected, the time for recovering the psychological states after the emergency is reflected, and the psychological states are combined into a capability value set, so that a regression model is obtained; on the basis, the electrocardiosignals obtained by implementation and the technical level scores of the drivers are input into a regression model to obtain the actual capability value of the bus drivers, and whether alarm information needs to be sent or not is judged by combining with a preset threshold value.
Description
Technical Field
The invention relates to the field of psychology and the field of computers, in particular to a bus driving safety early warning method and system.
Background
In the public transportation field, the emergency encountered by the bus driver is most frequent, and the emotional state of the bus driver can directly influence the processing capacity of the emergency and the calm speed after the processing, so as to directly influence the driving safety of the bus; when the emotion of the bus driver is unstable and is not suitable for continuous work, the driver should be early-warned and exchanged in time, however, no accurate monitoring means for monitoring the working state of the bus driver in real time exists at present, and no related early-warning mechanism and method exist.
For the above reasons, the present inventors have conducted intensive studies on the emotion of the challenge, and specifically analyzed the formation cause and influence factor of the emotion and the influence relationship of the emotion on the emergency handling capability, so as to expect to design a bus driving safety early warning method and system capable of solving the above problems.
Disclosure of Invention
In order to overcome the problems, the inventor performs intensive research and designs a bus driving safety early warning method and system based on electrocardiosignals, and the method predicts the capability of a bus driver to deal with emergency by constructing a regression model. The model input is divided into two parts of psychological states and technical capability, the psychological states represent the tension state of a driver before an emergency arrives through an electrocardiosignal deconstructing and extracting SAI-PAI ratio sequence, the technical level is obtained through test evaluation, the output is divided into three parts of emergency completion degree, response and recovery time, the three parts are used for representing the degree of success of the response of the emergency of the driver, the time is reflected, the time for recovering the psychological states after the emergency is reflected, and the psychological states are combined into a capability value set, so that a regression model is obtained; on the basis, the electrocardiosignals obtained by implementation and the technical level scores of the drivers are input into a regression model to obtain the actual capability value of the bus drivers, and when the actual capability value is found to be lower than the threshold value, alarm information is timely sent out to inform a bus company so as to facilitate timely treatment and ensure safety, so that the invention is completed.
Specifically, the invention aims to provide a bus driving safety early warning method based on electrocardiosignals, which comprises the following steps:
step 1, selecting a certain number of tested bus drivers to perform simulation test to obtain corresponding technical level scores of each bus driver, and constructing a regression model M suitable for bus driver emergency response capability assessment i ；
Step 2, in the actual driving process of the tested bus driver, monitoring and obtaining an electrocardio time sequence signal of the bus driver in real time, and obtaining a sympathology/parasympathetic ratio sequence through windowing and deconstructing;
step 3, combining the sympathology/parasympathetic ratio sequence obtained in step 2 with the bus driver skill level score obtained in step 1, based on a regression model M i Obtaining the actual capability value of the bus driver;
and when the true capability value is lower than a preset threshold value, sending out alarm information.
Wherein, in the step 1:
selecting m tested bus drivers, and enabling each bus driver to drive the bus in a simulation test scene in sequence; the simulation test process of any bus driver is as follows:
in the initial driving stage, the bus driver is in calm state for 5 min, and then first-stage emergency is introducedThe bus driver executes the coping operation, scores the execution condition of the bus driver, then enables the bus driver to continue driving, and introduces a secondary emergency after the bus driver recovers the calm state for 1-3 minutes>The bus driver executes the coping operation, scores the execution condition of the bus driver, then enables the bus driver to continue driving, and introduces three-level emergencies after the bus driver recovers the calm state for 1-3 minutes>Repeating the above operation until level I incident is introduced>The bus driver executes the coping operation, scores the execution condition of the bus driver, then enables the bus driver to continue driving, completes the simulation test of the bus driver after the bus driver recovers to a calm state, and scores the whole technical level of the bus driver comprehensively, namely scores the technical level.
Wherein, in the step 1: in the simulation test process of a bus driver, acquiring electrocardio time sequence signal data of the bus driver in real time through wearable equipment, introducing a Laguerre orthogonal function to deconstruct the electrocardio time sequence data into a sympathetic nerve sequence and a parasympathetic nerve sequence, and further acquiring a sympathetic/parasympathetic ratio sequence p;
preferably, in the simulation test process, any one emergency e is aimed at i Record e i Ratio sequence P before introduction i,j Reaction time t from occurrence of emergency to execution of coping operation by bus driver i1 Time t for bus driver to recover to calm state after bus driver executes handling operation and handling emergency i2 Completion degree omega of the emergency i 。
Wherein, in the step 1: p pair P i,j To make windowing operationThe obtained sequence is used as a first input, the technical level score obtained by the bus driver in the simulation test process is used as a second input, and t is i1 、t i2 And omega i Weighted set of capability values S i,j As an output, forming a regression model M suitable for bus driver emergency response capability assessment i And parameter tuning is performed on the regression model.
Wherein in step 1, the preset threshold is set to 0.6-0.9, preferably 0.65-0.8.
Wherein, in the step 1: after each incident is introduced, scoring the coping operation executed by the bus driver by at least 5 judges respectively and independently, and taking the average score as the completion degree omega of the incident of the bus driver i ；
When the commentary is evaluated, the timeliness and standardability of the treatment measures are comprehensively considered, whether traffic accidents exist or not is also considered, and the total score is between 0 and 1.
Wherein the capability value set S is obtained by weighting by the following formula (1) i,j ：
S i,j ＝a·t i1 +b·t i2 +c·ω i (1)
Wherein the weighted weight a+b+c=1.
The invention also provides a bus driving safety early warning system based on the electrocardiosignal, which is characterized in that,
the system adopts the method to give an early warning for the driving safety of the bus.
The invention has the beneficial effects that:
(1) According to the bus driving safety early warning method based on the electrocardiosignals, which is provided by the invention, the electrocardiosignals of the driver are collected, emotion evaluation is carried out by using an evaluation model, the emotion state of the driver is detected in real time, the normal driving of the driver is not influenced based on the non-invasive index, the individual difference index is added into the input characteristic of the neural network, the evaluation index of the driver is continuously learned based on the Laguerre autoregressive model tuning, the accuracy of the driver emotion evaluation is greatly improved, and the accuracy and timeliness of alarm information are greatly improved;
(2) According to the bus driving safety early warning method based on the electrocardiosignals, which is provided by the invention, the response time is short, the method can be used for judging the irritation emotion of a driver in real time and sending early warning information in time, and the occurrence probability of traffic accidents is reduced.
Drawings
Fig. 1 shows an overall logic diagram of a bus driving safety pre-warning method based on electrocardiosignals according to the invention.
Detailed Description
The invention is further described in detail below by means of the figures and examples. The features and advantages of the present invention will become more apparent from the description.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
According to the bus driving safety early warning method based on electrocardiosignals, as shown in fig. 1, the main idea of the method is as follows: by constructing regression model M i Predicting the ability of a bus driver to cope with an emergency. The model input is divided into two parts of psychological states and technical capability, the psychological states represent the tension state of a driver before an emergency arrives through an electrocardiosignal deconstructing and extracting SAI-PAI ratio sequence, the technical level is obtained through test evaluation, the output is divided into three parts of emergency completion degree, response and recovery time, the three parts are used for representing the degree of success of the response of the emergency of the driver, the time is reflected, the time for recovering the psychological states after the emergency is reflected, and the psychological states are combined into a capability value set, so that a regression model is obtained; inputting the electrocardiosignals obtained by implementation and the technical level scores of the drivers into a regression model on the basis of the electrocardiosignals and the technical level scores of the drivers to obtain a certain value in the actual capacity values of the bus drivers, such as 0-1; combining with a preset threshold value such as 0.7, when modelingWhen the predicted true capacity value is smaller than the threshold value, the driver is judged to be difficult to deal with the impending situation, adjustment is needed, and at the moment, alarm information is sent out.
Specifically, the method comprises the following steps:
step 1, selecting a preset number of tested bus drivers to perform simulation test, driving the buses in a simulation test scene in sequence, obtaining psychological states (represented by SAI-PAI ratio sequences extracted by electrocardiosignals) and technical level scores of the bus drivers before the emergency arrives as inputs of regression model training, obtaining the emergency completion degree, response time and recovery time weighting of the bus drivers to obtain output of regression model training, wherein the regression model can be used for obtaining real capacity values of the bus drivers in real time after training;
step 2, in the actual driving process of the tested bus driver, monitoring and obtaining an electrocardio time sequence signal of the bus driver in real time, and obtaining a sympathology/parasympathetic ratio sequence through windowing and deconstructing; in this application, the windowing deconstructing process fits an R-R interval sequence with a given window size through a set of Laguerre orthogonal functions defined by different orders j and specific values α to obtain corresponding Laguerre coefficients, where a weighting calculation of low-order Laguerre coefficient values yields a sympathetic Sequence (SAI), and a weighting calculation of high-order Laguerre coefficient values yields a parasympathetic sequence (PAI), and further yields a ratio sequence of the sympathetic/parasympathetic sequences, i.e., an SAI-PAI ratio sequence.
Step 3, combining the sympathology/parasympathetic ratio sequence obtained in step 2 with the bus driver skill level score obtained in step 1, based on a regression model M i Obtaining the actual capability value of the bus driver; wherein the SAI-PAI ratio sequence P is input into the regression model M i In the method, a multi-stage convolution layer and a gating circulation unit are used for obtaining a transformed time sequence characteristic, the characteristic is further connected with a normalized bus driver technical level grading value end to end, and then the time sequence characteristic is input into a regression model M i The full connection layer in the bus is subjected to characteristic transformation, and finally a Sigmoid function is connected to adjust the output value of the Sigmoid function to be between 0 and 1, thus obtaining the bus driverTrue capability value.
And when the true capability value is lower than a preset threshold value, sending out alarm information. Preferably, the alarm information is sent to a bus company where the bus driver is located, and the bus driver is prompted that the driving state of the bus driver is poor, and needs to be adjusted or replaced, namely, the bus driver is considered to be in an excited emotion state at the moment, and is not suitable for continuing to drive the bus. After receiving the alarm information, the public transport company should arrange other people to take over in time according to actual conditions so as to prevent danger.
In a preferred embodiment, in step 1, m tested bus drivers are selected, and each bus driver is sequentially caused to drive the bus in a simulated test scene; the value of m is 30, which is greatly beneficial to the improvement of accuracy, and meanwhile, the limitation of the quality of acquired data and algorithm is considered, so the applicant finds that the best accuracy can be obtained by setting the value of m to 30.
The simulation test process of any bus driver is as follows: in the initial driving stage, the bus driver is in calm state for 5 min, and then first-stage emergency is introducedThe bus driver executes the coping operation, scores the execution condition of the bus driver, then enables the bus driver to continue driving, and introduces a secondary emergency after the bus driver recovers the calm state for 1-3 minutes>The bus driver executes the coping operation, scores the execution condition of the bus driver, then enables the bus driver to continue driving, and introduces three-level emergencies after the bus driver recovers the calm state for 1-3 minutes>Repeating the above operation until level I incident is introduced>The bus driver executes the coping operation and the execution condition of the bus driverAnd grading, namely enabling the bus driver to continue driving, completing the simulation test of the bus driver after the bus driver is in a calm state, and grading the whole technical level of the bus driver after the test is completed, namely grading the technical level. The skill level score may be classified into 10 classes, specifically distributed in [0,1]]Such as 0.9, 0.5, etc.
The application, the emergency e i Represents the ith emergency event, i is E [1, l]The method comprises the steps of carrying out a first treatment on the surface of the First-level emergency eventCan also be expressed as +.>I.e. the first emergency has an emergency level 1, correspondingly,/->The emergency degree of the ith emergency event is represented as level I; preferably, for a bus driver, the emergency degree of the emergency encountered in the simulation test process is gradually increased, and the emergency degree of the first emergency is l-level. In the present application, the value of l is preferably 10 to 30, more preferably 20.
The emergency event is expressed as that the distance between the bus for simulating driving and the emergency object is approaching in a short time, each emergency event is classified into one grade according to the approaching time, and the shorter the time is, the faster the approaching is, and the higher the grade is; preferably, the approach time of the emergency of the 1 st stage is 10 seconds, and the approach time of the emergency of the first stage is 1 second. The abrupt object may be a nearby vehicle that suddenly changes lane, a front vehicle that suddenly decelerates, a pedestrian or a non-motor vehicle that suddenly enters a traffic lane.
In the application, after the bus driver recovers a calm state for 1-3 minutes, the next emergency is started, the calm state is determined by the measured SAI-PAI ratio sequence, and in the application, preferably, the calm state is that the SAI-PAI ratio sequence value fluctuates and changes up and down within a certain range, such as between 0.3 and 0.4, within a continuous period of 1 minute.
The execution of the coping operation means that actual effective operations such as brake stepping, clutch stepping, accelerator stepping, steering wheel turning, gear shifting, whistling, lamp turning-on and the like are adopted to avoid accidents, the smooth running of the vehicle is ensured as much as possible on the basis, and after the actual effective coping operation is completed and the normal running state is restored, the reaction time of the execution of the coping operation is ended.
In a preferred embodiment, in step 1, during a simulation test of a bus driver, acquiring electrocardiographic time sequence signal data of the bus driver in real time through a wearable device, introducing a Laguerre orthogonal function to deconstruct the electrocardiographic time sequence data into a sympathetic nerve sequence and a parasympathetic nerve sequence, and further obtaining a sympathetic/parasympathetic ratio sequence p;
in this application, the sympathetic, parasympathetic and ratio sequences are all matrices; preferably, the said
The Laguerre orthometric function is expressed as
Where j represents the order, α represents its index reduction rate, and n represents the current sequence number. For the resolution of the Laguerre orthometric function reference may be made to Gaetano V, luca C, philip S J, et al measures of Sympathetic and Parasympathetic Autonomic Outflow from Heartbeat Dynamics [ J ]. Journal of Applied Physiology,2018, 125 (1): 19-39.
The deconstructing refers to deconstructing the R-R interval sequence of the electrocardiosignal into a weighted set of Laguerre functions with different orders, and the weighted set is expressed as follows:
wherein Θ t R-R interval estimation value representing time t, [ p ] 0 p 1 (j,t)]Representing the parameter to be estimated, phi j *r N(t) Representing the convolution response of the Laguerre function with the historical R-R interval sequence prior to t, delta SAI And delta PAI The Laguerre function order representing the correspondence of the sympathetic and parasympathetic nerves, the required sympathetic and parasympathetic nerve sequence Γ SAI And Γ PAI Can be further expressed as p 1 (j, t), whereinFinally, the ratio sequence P=Γ is obtained SAI /Γ PAI 。
Preferably, in the simulation test process, any one emergency e is aimed at i Record e i Ratio sequence P of public bus driver sympatho/parasympathetic nerves before introduction i,j Reaction time t from occurrence of emergency to execution of coping operation by bus driver i1 Time t for bus driver to recover to calm state after bus driver executes handling operation and handling emergency i2 Completion degree omega of the emergency i ；
The P is i,j J in (a) represents a parameter corresponding to a jth bus driver, i represents a parameter corresponding to an ith emergency, namely P i,j Representing the ratio sequence of the sympathetic and parasympathetic sequences of the jth bus driver prior to encountering the ith incident.
In a preferred embodiment, in step 1, P is as follows i,j Performing windowing operation, taking the obtained sequence as a first input, smoothing through multistage convolution, and then sending the sequence to a gating circulation unit to extract time sequence characteristics; taking the technical level score obtained by the bus driver in the simulation test process as a second input, and sending the technical level score into a full-connection layer; let t i1 And t i2 Completion degree ω of emergency event i Weighted set of capability values S i,j As an output, forming a regression model M suitable for bus driver emergency response capability assessment i And parameter tuning is performed on the regression model. The data of m tested buses are sequentially called, the data of each bus is a group of samples, the data of m buses form a sample set, and accordingly parameter tuning is conducted on the regression model.
Preferably t i1 And t i2 AndCompletion degree of emergency omega i Weighting after normalization to obtain a capability value set S i,j Wherein the weights of the weights are a, b and c, a+b+c=1, i.e. S i,j ＝a·t i1 +b·t i2 +c·ω i Preferably, the ratio of the three weights is set to be greater than 3:1:6, i.e., a/b > 3 and c/a+b > 1; more preferably, a=0.15, b=0.1, c=0.75.
The set of capability values S described in this application i,j The response capability of a driver to the emergency is divided into three parts, namely the completion degree omega of the emergency i The reasonable degree and the proficiency degree of drivers on the emergency operation are shown, and the response time t is obtained by evaluation in the test process i1 And recovery time t i2 The response speed of the driver to the emergency and the speed of psychological recovery to the normal state after the emergency is finished are indicated.
Regression model M described in the present application i In the training process, SAI-PAI ratio sequence P in a sample is used as input, a transformed time sequence characteristic is obtained through a multistage convolution layer and a gating circulation unit, the characteristic is further connected with technical level grading values of a bus driver in the sample subjected to normalization in an end-to-end mode, the characteristic is input into a full connection layer to perform characteristic transformation, and finally a Sigmoid function is connected to adjust the output value of the characteristic to be between 0 and 1, and the characteristic is compared and fed back with the output value corresponding to the sample. Regression model M i The higher the driver skill level, the smaller the SAI/PAI sequence fluctuation before the emergency occurs, the higher the score is for the lower average value, and vice versa.
The parameter tuning process is a regression model M i Is a training process of (1); preferably M i The activation function in (a) is selected as the LeakyReLU function, the loss function is selected as the mean square error, and the optimizer selects Adam. The main tuning parameters are super parameters such as the number of convolution layers, the length of convolution kernels of each layer, the number and the step length, the number of layers of a gate control circulation unit, the output dimension of a full connection layer and the like. The selection/adjustment process of the parameters can be performed according to the following scheme, wherein the number of the convolution layers is 3, the convolution kernel length is 7, and the number of the convolution layers isThe step length is 16, the number of layers of the gating nerve unit is 1, and the output dimension of the full-connection layer is 16 for adjustment.
In a preferred embodiment, in step 1, the preset threshold is set to 0.6 to 0.9, preferably to 0.65 to 0.8, more preferably to 0.7.
In a preferred embodiment, in the step 1, after each incident is introduced, each of at least 5 judges independently score the coping operation performed by the bus driver, take the average score as the score of the bus driver in the incident, and the judges are senior drivers of at least 15 years of bus driving experience; or a score is given by the software system by comparison with a standard time, action, based on the time of operation and the action of the operation.
When the commentary is evaluated, the timeliness and normalization of the operation are comprehensively considered, whether traffic accidents exist or not is considered, and the total score is 0,1]Between them. The score can be given between 0 and 0.4 for timeliness, and the larger the score value is, the more ideal and timely the treatment is; for normalization, a score may be given between 0 and 0.3 points; aiming at the existence of traffic accidents, the traffic accidents are not caused, the traffic accidents are 0.3 points, and the traffic accidents are 0 points. And finally, summarizing the scores of the three small items, namely, scoring one commentary or scoring one system. The average value of multiple scores of the same emergency is the completion degree omega of the emergency of the bus driver i The method comprises the steps of carrying out a first treatment on the surface of the In addition, the panelist should give a driver skill level score, e.g., rating the skill level to a 10 level, score at 0,]1 as input.
In a preferred embodiment, in step 3, during the actual driving operation of the bus driver, a set of sympathology/parasympathetic ratio sequences is obtained every 1 second, so as to determine the emotional state of the driver, and when it is determined that the driving state of the bus driver is not good, an alarm prompt is sent, including sending information to a dispatching room of the bus company to remind the bus driver to schedule a rest or a shift replacement.
The invention also provides a bus driving safety early warning system based on the electrocardiosignal,
the system adopts the method to give an early warning for the driving safety of the bus.
Example 1
Step 1, selecting 30 bus drivers to be tested for simulation test, and enabling each bus driver to drive the bus in a simulation test scene in sequence; the simulation test process of any bus driver is as follows:
in the initial driving stage, the bus driver is in calm state for 5 min, and then first-stage emergency is introducedThe bus driver executes the coping operation, 5 judges score the execution condition, then the bus driver is enabled to continue driving, and after the bus driver recovers the calm state for 2 minutes, the second-level emergency is introduced>The bus driver executes the coping operation and scores the execution condition of the bus driver, then the bus driver is driven continuously, and after the bus driver recovers the calm state for 2 minutes, three-level emergencies +.>Repeating the above operation until 20-level emergency +.>And the bus driver is restored to a calm state after the coping operation is completed, and the simulation test of the bus driver is completed.
In the simulation test process of each bus driver, acquiring electrocardio time sequence signal data of the bus driver in real time, introducing a Laguerre orthogonal function to deconstruct the electrocardio time sequence data into a sympathetic nerve sequence and a parasympathetic nerve sequence, and further acquiring a sympathetic/parasympathetic ratio sequence p; recording the ratio sequence P before each incident is introduced i,j Reaction time t from occurrence of emergency to execution of coping operation by bus driver i1 For bus driver to recover to calm state after handling emergencyTime t i2 And the completion degree omega of the emergency i ；
Alignment value sequence P i,j Windowing, taking the obtained sequence as a first input, taking a technical level score obtained by the bus driver in the simulation test process as a second input, and taking t i1 、t i2 And omega i Weighted set of capability values S i,j As an output, forming a regression model M suitable for bus driver emergency response capability assessment i Parameter tuning is carried out on the regression model; wherein M is i The method comprises the steps that an activation function of a full-connection layer is selected as a LeakyReLU function, a loss function is selected as a mean square error, an optimizer is selected as Adam, main tuning parameters are super parameters such as the number of convolution layers, the length, the number and the step length of convolution kernels of each layer, the number of layers of a gate control circulation unit, the output dimension of the full-connection layer and the like, and in the parameter tuning process, the number of the convolution layers is 3, the length of the convolution kernels is 7, the number is 16, the step length is 1, the number of layers of the gate control nerve unit is 1, and the output dimension of the full-connection layer is 16.
After 30 groups of data are optimized, a stable regression model M suitable for bus driver emergency coping capability assessment is obtained i 。
Example 2
The regression model M of the emergency response capability assessment obtained in example 1 was invoked i Selecting one of 30 bus drivers participating in the test, monitoring electrocardiosignals in real time in the actual working process, calculating every 10 seconds to obtain a group of sympathology/parasympathetic ratio sequences, obtaining 6 groups of ratio sequences in 1 minute, combining each group of ratio sequences with the technical level score of the bus driver, and inputting the ratio sequences into the regression model M i Thereby obtaining a group of real capacity values of the bus driver at intervals of 10 seconds within 1 minute, namely 0.92, 0.91, 0.88, 0.91, 0.87 and 0.91;
the preset threshold value is set to 0.7,
therefore, the real capacity value of the bus driver is continuously larger than the threshold value, alarm information is not required to be sent out, and the driving state of the bus driver is good and is not required to be adjusted or replaced.
Example 3:
selecting two groups of drivers, wherein the group A is a driver with more than 10 years of driving age and a class A driving license, the group B is a driver with less than 1 year of driving age and a class C driving license, the number of each group of drivers is 35, and arranging the two groups of drivers to sequentially execute the simulation test of the step 1 to obtain the technical level score of each driver; the average value of the technical level scores of the drivers in the group A is 0.91 score, the average value of the technical level scores of the drivers in the group B is 0.72 score, and the technical level scores of the drivers in the two groups have obvious differences;
and then the number of people of all emergency situations in the simulation test can be effectively processed by two groups of drivers, the number of people of all emergency situations in the simulation test can be effectively processed by the group A drivers is 35, the number of people of all emergency situations in the simulation test can be effectively processed by the group B drivers is 28, the completion proportion of the group A drivers is obviously higher than that of the group B drivers, and the simulation test can actually identify the actual capability value of the bus drivers for coping with accidents, so that the bus driving safety early warning method based on electrocardiosignals in the application can make early warning prompts to the drivers with poor performance in local time intervals to a certain extent, thereby reducing the risk of traffic accidents.
Example 4:
invoking regression model M of the Emergency response capability assessment obtained in example 1 i Arranging the group a drivers and the group B drivers in the embodiment 3 to sequentially execute the operation process in the embodiment 2, wherein the group a drivers drive buses, the group B drivers drive household cars, and the safety states of the drivers in the driving activity process of one day are continuously recorded, wherein the actual capability value of the drivers is continuously greater than a threshold value and is in a safety state, alarm information is not required to be sent out, and otherwise, the drivers belong to a risk state and alarm information is required to be sent out; the statistical structure shows that 35 drivers in the group A drivers are in a safe state continuously, 13 drivers in the group B drivers are in a safe state continuously, and 22 drivers are in a risk state intermittently. According to the embodiment, the safety early warning method and the system provided by the application can be used for practically screening and identifying the risk factors, so that potential safety hazards can be eliminated in time, and particularlyThe method can timely eliminate potential safety hazards in public transportation driving which may threaten public safety.
The invention has been described above in connection with preferred embodiments, which are, however, exemplary only and for illustrative purposes. On this basis, the invention can be subjected to various substitutions and improvements, and all fall within the protection scope of the invention.
Claims (6)
1. A bus driving safety pre-warning method based on electrocardiosignals is characterized in that,
the method comprises the following steps:
step 1, selecting a predetermined number of tested bus drivers for simulation test, obtaining corresponding technical level scores of each bus driver, and constructing a regression model M suitable for bus driver emergency response capability assessment i ；
Step 2, in the actual driving process of the tested bus driver, monitoring and obtaining an electrocardio time sequence signal of the bus driver in real time, and obtaining a sympathology/parasympathetic ratio sequence through windowing and deconstructing;
step 3, combining the sympathology/parasympathetic ratio sequence obtained in step 2 with the bus driver skill level score obtained in step 1, based on a regression model M i Obtaining the actual capability value of the bus driver;
when the true capability value is lower than a preset threshold value, sending out alarm information;
in the step 1:
selecting m tested bus drivers, and enabling each bus driver to drive the bus in a simulation test scene in sequence; the simulation test process of any bus driver is as follows:
in the initial driving stage, the bus driver is in a calm state for 5 minutes, and then a first-stage emergency e is introduced i 1 The bus driver executes the coping operation and scores the execution condition of the bus driver, then the bus driver is driven continuously, and after the bus driver recovers the calm state for 1-3 minutes, the secondary emergency e is introduced i 2 By bus driversScoring the operation and the execution condition of the bus driver, then enabling the bus driver to continue driving, and introducing three-level emergency e after the bus driver recovers the calm state for 1-3 minutes i 3 Repeating the above operation until an l-level emergency e is introduced i l Executing coping operation by the bus driver, scoring the execution condition of the bus driver, enabling the bus driver to continue driving, completing the simulation test of the bus driver after the bus driver is in a calm state, and scoring the whole technical level of the bus driver comprehensively, namely scoring the technical level;
in the step 1: in the simulation test process of a bus driver, acquiring electrocardio time sequence signal data of the bus driver in real time through wearable equipment, introducing a Laguerre orthogonal function to deconstruct the electrocardio time sequence data into a sympathetic nerve sequence and a parasympathetic nerve sequence, and further acquiring a sympathetic/parasympathetic ratio sequence p;
in the simulation test process, aiming at any emergency e i Record e i Ratio sequence P before introduction i,j Reaction time t from occurrence of emergency to execution of coping operation by bus driver i1 Time t for bus driver to recover to calm state after bus driver executes handling operation and handling emergency i2 Completion degree omega of the emergency i ；
In the step 1: p pair P i,j Windowing, taking the obtained sequence as a first input, taking a technical level score obtained by the bus driver in the simulation test process as a second input, and taking t i1 、t i2 And omega i Weighted set of capability values S i,j As an output, forming a regression model M suitable for bus driver emergency response capability assessment i And parameter tuning is performed on the regression model.
2. The method for pre-warning bus driving safety based on electrocardiosignals according to claim 1, which is characterized in that,
in step 1, the preset threshold is set to 0.6-0.9.
3. The method for pre-warning bus driving safety based on electrocardiosignals according to claim 2, which is characterized in that,
in step 1, the preset threshold is set to 0.65-0.8.
4. The method for pre-warning bus driving safety based on electrocardiosignals according to claim 1, which is characterized in that,
in the step 1: after each incident is introduced, scoring the coping operation executed by the bus driver by at least 5 judges respectively and independently, and taking the average score as the completion degree omega of the incident of the bus driver i ；
When the commentary is scored by the commentary person, the timeliness and standardability of the operation are comprehensively considered, whether traffic accidents exist or not is also considered, and the total score is between [0,1 ].
5. The method for pre-warning bus driving safety based on electrocardiosignals according to claim 1, which is characterized in that,
the capability value set S is obtained by weighting the following (1) i,j ：
S i,j ＝a·t i1 +b·t i2 +c·ω i (1)
Wherein the weighted weight a+b+c=1.
6. A bus driving safety early warning system based on electrocardiosignals is characterized in that,
the system adopts the method of one of claims 1-5 to give an early warning for the driving safety of the bus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210013345.5A CN116453289B (en) | 2022-01-06 | 2022-01-06 | Bus driving safety early warning method and system based on electrocardiosignal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210013345.5A CN116453289B (en) | 2022-01-06 | 2022-01-06 | Bus driving safety early warning method and system based on electrocardiosignal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116453289A CN116453289A (en) | 2023-07-18 |
| CN116453289B true CN116453289B (en) | 2024-02-20 |
Family
ID=87120687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210013345.5A Active CN116453289B (en) | 2022-01-06 | 2022-01-06 | Bus driving safety early warning method and system based on electrocardiosignal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116453289B (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5888074A (en) * | 1996-09-16 | 1999-03-30 | Scientex Corporation | System for testing and evaluating driver situational awareness |
| CN101238985A (en) * | 2007-02-09 | 2008-08-13 | 中国科学院心理研究所 | Psychology and behavior monitoring system based on simulation driving platform |
| KR20080107845A (en) * | 2007-06-08 | 2008-12-11 | 샬롬엔지니어링 주식회사 | A simulation system for operating train |
| JP2009213636A (en) * | 2008-03-10 | 2009-09-24 | Denso Corp | State estimation device |
| CN101756706A (en) * | 2008-12-25 | 2010-06-30 | 中国科学院心理研究所 | Driving-situation awareness measuring system |
| CN104133720A (en) * | 2014-07-08 | 2014-11-05 | 公安部交通管理科学研究所 | Driving safety degree evaluating system for motor vehicle drivers |
| DE102015200775A1 (en) * | 2015-01-20 | 2016-07-21 | Bayerische Motoren Werke Aktiengesellschaft | Independent assessment of an emotional state and a cognitive burden |
| CN105869356A (en) * | 2016-06-15 | 2016-08-17 | 上海帝仪科技有限公司 | Railway driver work state evaluation intervening system and method |
| CN106919779A (en) * | 2015-12-28 | 2017-07-04 | 西南交通大学 | A kind of Forecasting Methodology of driver to the simple reaction time of time burst |
| CN107126223A (en) * | 2017-06-16 | 2017-09-05 | 武汉理工大学 | Time of driver's reaction measuring system and method under the conditions of real vehicle |
| CN107235045A (en) * | 2017-06-29 | 2017-10-10 | 吉林大学 | Consider physiology and the vehicle-mounted identification interactive system of driver road anger state of manipulation information |
| CN109567832A (en) * | 2018-11-06 | 2019-04-05 | 长安大学 | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet |
| CN110588512A (en) * | 2019-09-25 | 2019-12-20 | 武汉极目智能技术有限公司 | Dangerous driving identification and early warning device, method and system |
| CN112102681A (en) * | 2020-11-09 | 2020-12-18 | 成都运达科技股份有限公司 | Standard motor train unit driving simulation training system and method based on self-adaptive strategy |
| WO2021014228A1 (en) * | 2019-07-09 | 2021-01-28 | Nervtech, Raziskave In Razvoj, D.O.O. | Driver evaluation method and device for implementing the method |
| KR20210038791A (en) * | 2019-09-30 | 2021-04-08 | 한국자동차연구원 | Back warning apparatus for older driver and method thereof |
| KR20210074601A (en) * | 2019-12-12 | 2021-06-22 | 현대자동차주식회사 | Apparatus and method for controlling emergency driving situation using brain wave |
| DE102021108656A1 (en) * | 2021-04-07 | 2021-08-05 | Carl von Ossietzky Universität Oldenburg Körperschaft des öffentlichen Rechts | Vehicle security system |
| CN113222295A (en) * | 2021-06-07 | 2021-08-06 | 吉林大学 | Method for predicting takeover time in control right switching state of L3-level automatic driving automobile |
| CN113633296A (en) * | 2021-10-15 | 2021-11-12 | 西南交通大学 | Reaction time prediction model construction method, device, equipment and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080082372A1 (en) * | 2006-09-29 | 2008-04-03 | Burch Leon A | Driving simulator and method of evaluation of driver competency |
| WO2017027232A1 (en) * | 2015-08-12 | 2017-02-16 | The General Hospital Corporation | System and method for sympathetic and parasympathetic activity monitoring by heartbeat |
| CN111460892A (en) * | 2020-03-02 | 2020-07-28 | 五邑大学 | Electroencephalogram mode classification model training method, classification method and system |
-
2022
- 2022-01-06 CN CN202210013345.5A patent/CN116453289B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5888074A (en) * | 1996-09-16 | 1999-03-30 | Scientex Corporation | System for testing and evaluating driver situational awareness |
| CN101238985A (en) * | 2007-02-09 | 2008-08-13 | 中国科学院心理研究所 | Psychology and behavior monitoring system based on simulation driving platform |
| KR20080107845A (en) * | 2007-06-08 | 2008-12-11 | 샬롬엔지니어링 주식회사 | A simulation system for operating train |
| JP2009213636A (en) * | 2008-03-10 | 2009-09-24 | Denso Corp | State estimation device |
| CN101756706A (en) * | 2008-12-25 | 2010-06-30 | 中国科学院心理研究所 | Driving-situation awareness measuring system |
| CN104133720A (en) * | 2014-07-08 | 2014-11-05 | 公安部交通管理科学研究所 | Driving safety degree evaluating system for motor vehicle drivers |
| DE102015200775A1 (en) * | 2015-01-20 | 2016-07-21 | Bayerische Motoren Werke Aktiengesellschaft | Independent assessment of an emotional state and a cognitive burden |
| CN106919779A (en) * | 2015-12-28 | 2017-07-04 | 西南交通大学 | A kind of Forecasting Methodology of driver to the simple reaction time of time burst |
| CN105869356A (en) * | 2016-06-15 | 2016-08-17 | 上海帝仪科技有限公司 | Railway driver work state evaluation intervening system and method |
| CN107126223A (en) * | 2017-06-16 | 2017-09-05 | 武汉理工大学 | Time of driver's reaction measuring system and method under the conditions of real vehicle |
| CN107235045A (en) * | 2017-06-29 | 2017-10-10 | 吉林大学 | Consider physiology and the vehicle-mounted identification interactive system of driver road anger state of manipulation information |
| CN109567832A (en) * | 2018-11-06 | 2019-04-05 | 长安大学 | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet |
| WO2021014228A1 (en) * | 2019-07-09 | 2021-01-28 | Nervtech, Raziskave In Razvoj, D.O.O. | Driver evaluation method and device for implementing the method |
| CN110588512A (en) * | 2019-09-25 | 2019-12-20 | 武汉极目智能技术有限公司 | Dangerous driving identification and early warning device, method and system |
| KR20210038791A (en) * | 2019-09-30 | 2021-04-08 | 한국자동차연구원 | Back warning apparatus for older driver and method thereof |
| KR20210074601A (en) * | 2019-12-12 | 2021-06-22 | 현대자동차주식회사 | Apparatus and method for controlling emergency driving situation using brain wave |
| CN112102681A (en) * | 2020-11-09 | 2020-12-18 | 成都运达科技股份有限公司 | Standard motor train unit driving simulation training system and method based on self-adaptive strategy |
| DE102021108656A1 (en) * | 2021-04-07 | 2021-08-05 | Carl von Ossietzky Universität Oldenburg Körperschaft des öffentlichen Rechts | Vehicle security system |
| CN113222295A (en) * | 2021-06-07 | 2021-08-06 | 吉林大学 | Method for predicting takeover time in control right switching state of L3-level automatic driving automobile |
| CN113633296A (en) * | 2021-10-15 | 2021-11-12 | 西南交通大学 | Reaction time prediction model construction method, device, equipment and readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 基于改进长短时记忆网络的驾驶行为检测方法研究;施冬梅;汽车工程;20210825;第43卷(第8期);1203-1209 * |
| 基于驾驶员警觉度的交通标志适宜信息量研究;戚春华;科学技术与工程;第21卷(第34期);14829-14835 * |
| 驾驶员风险认知模型的研究概况;侯雪艳;人类工效学;第13卷(第4期);58-63 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116453289A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| CN106314428B (en) | Collision avoidance system, collision avoidance method and motor vehicle | |
| CN107161155A (en) | A kind of vehicle collaboration lane-change method and its system based on artificial neural network | |
| CN107918311A (en) | Multisensor precipitation classifying equipoment and method | |
| CN104598993B (en) | Driver tired driving Forecasting Methodology based on number of winks | |
| CN105956548A (en) | Driver fatigue state detection method and device | |
| US11144844B2 (en) | Refining customer financial security trades data model for modeling likelihood of successful completion of financial security trades | |
| CN113516846B (en) | Vehicle lane change behavior prediction model construction, prediction and early warning method and system | |
| CN109784586B (en) | Prediction method and system for danger emergence condition of vehicle danger | |
| CN111563555A (en) | Driver driving behavior analysis method and system | |
| CN115285135A (en) | Construction method of deep reinforcement learning vehicle following model fusing driving style | |
| Miyaji et al. | Driver’s cognitive distraction detection using AdaBoost on pattern recognition basis | |
| KR20220089772A (en) | Drive ability evaluated method for evaluating driving ability of driver and, human factor evaluation system for performing the method | |
| CN116453289B (en) | Bus driving safety early warning method and system based on electrocardiosignal | |
| Bao et al. | Data-driven risk-sensitive control for personalized lane change maneuvers | |
| CN113642114A (en) | Modeling method for humanoid random car following driving behavior capable of making mistakes | |
| Utomo et al. | Driver fatigue prediction using different sensor data with deep learning | |
| CN115192026B (en) | Tunnel driving load monitoring method and terminal | |
| CN113793074B (en) | Social cooperation evaluation method for automatic driving vehicle | |
| CN105496369A (en) | Angry driving state detection method | |
| Wang et al. | [Retracted] Prediction Model for Driver Reaction Time Based on PSO‐BP Neural Network Model | |
| Hoogendoorn et al. | Driver workload classification through neural network modeling using physiological indicators | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| CN114613130B (en) | Driving credibility analysis method in traffic and carrying system | |
| Yan et al. | [Retracted] A Take‐Over Performance Evaluation Model for Automated Vehicles from Automated to Manual Driving |
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 |