CN113887896A - Method for evaluating driving safety level of commercial truck driver - Google Patents
Method for evaluating driving safety level of commercial truck driver Download PDFInfo
- Publication number
- CN113887896A CN113887896A CN202111092084.2A CN202111092084A CN113887896A CN 113887896 A CN113887896 A CN 113887896A CN 202111092084 A CN202111092084 A CN 202111092084A CN 113887896 A CN113887896 A CN 113887896A
- Authority
- CN
- China
- Prior art keywords
- driver
- response
- data
- driving
- early warning
- 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 32
- 230000004044 response Effects 0.000 claims abstract description 105
- 239000013598 vector Substances 0.000 claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000006399 behavior Effects 0.000 claims description 69
- 230000015654 memory Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000000926 separation method Methods 0.000 claims description 6
- 238000002922 simulated annealing Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 230000003245 working effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for evaluating the driving safety level of a driver of an operation truck based on an active safety early warning system and the response behavior of the driver, which extracts a high-dimensional vector of the driving safety characteristic of the driver by performing time-space variation rule statistics on video data, vehicle data and the intrinsic attribute of the driver; according to various parameters of the early warning data, scoring is carried out on the driving safety state of the driver when the warning occurs, and meanwhile, scoring is provided for the response behavior of the driver to the early warning information; and predicting the response behavior of the driver to the alarm according to the driver information, the vehicle running state and the alarm data so as to urge the person with poor response to improve the driving behavior. According to the invention, the driving safety level of the driver is graded, and intervention measures are made in advance for the driver with low safety grade in a targeted manner, so that the driving safety level of the driver is effectively improved, and the problem that the existing driving safety evaluation system for the driver of the commercial truck is incomplete is solved.
Description
Technical Field
The invention relates to the field of evaluation of active safety technology of commercial trucks, in particular to a method for evaluating the driving safety level of a driver of a commercial truck based on active safety early warning and response behavior of the driver.
Background
The severity and the degree of influence of commercial vehicles as important components of road traffic are far greater than those of general accidents. The occurrence of accidents is mostly closely related to negligence of drivers, and the safety level of the drivers has important influence on road safety, so that the evaluation system developed for commercial truck drivers has great significance.
And 7 days 3 and 7 in 2017, the department of transportation issues 'technical and safety conditions for commercial passenger cars', and the large-scale commercial passenger cars are required to be provided with a lane departure early warning system and a forward collision early warning system in the standard. At present, the popularity of active safety equipment of commercial vehicles reaches more than 80%, so a set of method for evaluating the driving safety level of a commercial truck driver under the influence of active safety early warning information is needed. The operation vehicle returns data frequency in the active safety system, and the management mode is obviously different from that of the private vehicle, so the operation vehicle cannot carry the driving safety level evaluation method of the private vehicle. A new evaluation system which meets the characteristics of the freight car and takes the consideration into consideration needs to be constructed, so that the more accurate safe driving level scoring is carried out on the drivers of the commercial trucks.
Disclosure of Invention
The invention provides an evaluation method for a driver of an operation truck based on active safety early warning and driver response behaviors, and aims to solve the problems that the number of evaluation systems for the driver of a freight truck is small and the evaluation method is not accurate enough at present.
The invention adopts the following technical scheme for solving the technical problems:
a method for evaluating a driver of an operating truck based on active safety early warning and driver response behaviors comprises the following steps:
s1, extracting a high-dimensional vector of the characteristics of the driver based on the video data of the driver, the video data of the road, the vehicle data and the intrinsic attribute of the driver, wherein the elements of the high-dimensional vector comprise the driving speed, the driving behavior when the alarm occurs, the GPS information of the vehicle and the driving direction angle;
s2, taking the response time of the driver to the active safety early warning information as a dependent variable, taking the high-dimensional vector and the warning grade in S1 as independent variables, and performing a logistic regression analysis method on the response behavior of the driver to the early warning information under different road conditions to obtain key factors influencing the acceptance degree of the driver to the active safety early warning information: driving speed and alarm level;
s3, classifying the response behavior of the driver to the active safety early warning information by using a semi-supervised support vector machine, and dividing the response behavior into two types of positive response and negative response;
s4, comprehensively scoring the driving safety level of the driver by using the latest N times of response behaviors of the driver to the active safety early warning information, wherein the lower the score is, the lower the driving safety level of the driver is; wherein the score calculation formula is as follows:
wherein score is comprehensive grade of driving safety level of the driver; xaThe response value X of the driver's latest response behavior to the active safety pre-warning informationa-nAnd the response value is the response value of the driver to the response behavior of the active safety early warning information for the latest a-n times, if the response behavior is positive, the corresponding response value is 1, and if not, the corresponding response value is 0.
Further: in the step S1, the driver video data includes bad driving behavior of the driver, response behavior to the warning information, and response time to the active safety warning information; the vehicle video data comprises driving speed, acceleration, vehicle distance, lane departure data, driving direction angle and vehicle GPS information; the driver intrinsic attributes comprise the driver age, the driving duration and the driving mileage data.
Further: in the step S3, a semi-supervised support vector machine is used to classify the response behavior of the driver to the active safety pre-warning information, and the operation steps are as follows:
step one, taking the high-dimensional vector of S1 as the input of a semi-supervised support vector machine;
step two, according to a set proportion, carrying out partial manual category calibration on the high-dimensional vector extracted in the step S1, wherein the calibrated high-dimensional vector forms a label data set, and the uncalibrated high-dimensional vector forms a non-label data set;
step three, solving the optimal separation hyperplane of the positive response and the negative response by using a simulated annealing algorithm, specifically comprising the following steps:
assuming the hyperplane equation as: f (x) ═ ωTΦ (x) + b, where b is a parameter representing intercept, ω is a parameter representing slope,
is a gaussian kernel function representing the mapping transformation, x represents a high-dimensional vector;
the prediction function for the classification is: y isi＝sign(ωTΦ (x) + b), wherein,
let l (y, f (x)) max {0, 1-yf (x) }, the objective function for solving the best separating hyperplane is as follows:
in the formula | · | non-conducting phosphor2Denotes the 2-norm, C1Is the penalty factor, C, corresponding to the tag data set2Is a penalty factor corresponding to the unlabeled dataset, and C1＞C2；yiThe prediction result of the ith data in the label data set is obtained, and l is the number of data in the label data;
representing the prediction result of the jth data in the unlabeled data set, wherein u is the number of data in the unlabeled data;
and solving the objective function by adopting a simulated annealing method to obtain the optimal separation hyperplane, namely the classification standard of the positive response and the negative response.
Further: the method further comprises the steps of building a long-term and short-term memory network, training by using the high-dimensional vector extracted in the S1 and the corresponding response behavior classification result to obtain a driver response behavior prediction model, achieving prediction of the driver response behavior, and implementing upgrading early warning on a driver with a prediction result of negative response according to a set rule.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
(1) the invention can effectively extract the driving state and the vehicle running state of the driver from the video data and the vehicle-mounted sensor and obtain real-time early warning data, thereby carrying out statistical analysis on the early warning data, extracting the characteristics of the driver and obtaining the factors influencing the safe running level of the driver so as to improve pertinence;
(2) the invention analyzes the response behavior of the driver to the early warning system, researches the acceptance degree of the driver to the early warning system, extracts key factors influencing the acceptance degree of the driver to the early warning system, and effectively pre-judges the acceptance behavior of the driver, thereby realizing the optimization and improvement of the early warning system, reasonably regulating and controlling the acceptance degree of the driver to the early warning system, giving full play to the expected effect of the early warning system as much as possible and reducing the dangerous driving behavior of the driver;
(3) the method for evaluating the driver of the commercial truck based on the active safety early warning and the response behavior of the driver is constructed, a large amount of data are trained through deep learning, the safe driving level of the driver of the commercial truck can be judged reasonably and efficiently, the effectiveness of taking management measures is further ensured, the safety awareness and the safe driving level of the driver are effectively improved, and the occurrence of dangerous accidents caused by unsafe driving behaviors of the driver is reduced and even avoided as much as possible.
Drawings
FIG. 1 is a schematic workflow diagram of the present invention.
Detailed Description
The technical scheme of the invention is further described in detail by combining the drawings and the specific embodiments:
in one embodiment, a method for evaluating a driver of a commercial truck based on active safety early warning and driver response behavior is provided, as shown in fig. 1, and includes the steps of analyzing early warning data, analyzing driver response behavior, establishing a driver scoring mechanism and a real-time driver response behavior prediction model:
s1, early warning data analysis
High-dimensional vectors of the characteristics of the driver, including driving speed, driving behaviors when alarming occurs, vehicle GPS information and driving direction angles, are extracted by counting driver video data, road video data, vehicle data and driver intrinsic attributes.
S2, analyzing the response behavior of the driver
By taking the response time of the driver to the active safety early warning information as a dependent variable and taking the high-dimensional vector and the warning grade in S1 as independent variables, a logistic regression analysis method is carried out on the response behavior of the driver to the early warning information under different road conditions, and key factors influencing the acceptance degree of the driver to the active safety early warning information are obtained: speed of travel and alarm level (alarm level difference is in decibel magnitude of alarm sound).
S3 driver scoring mechanism
And classifying the response behavior of the driver to the early warning information by using a semi-supervised support vector machine.
S4, the driver is comprehensively scored according to the latest N times of response behaviors of the driver to the active safety early warning information, and the driver is conveniently managed, rewarded and punished.
And S5, establishing a driver response behavior prediction model, predicting the response behavior of the driver to the early warning information, and timely correcting the unsafe driving behavior of the driver who may generate negative response through additional measures.
Further, in step S1, the driver video data includes facial expressions and hand movements of the driver, the facial expressions are divided into sub-positions such as an eye region and a mouth region, and whether the eyelid is slouched, eastern periscope, or smoking is determined by an image recognition technique; the hand action collection judges whether dangerous driving behaviors such as smoking, calling and the like are generated or not through an image recognition technology when hands leave a steering wheel; the road video data comprise dangerous driving states such as too close distance and lane departure; the intrinsic data of the vehicle comprises the speed, the turning angle, the acceleration, the alarm occurrence time and the alarm occurrence place; the driver intrinsic attributes comprise the driver age, the driving duration and the driving mileage data. And through counting the various data, extracting high-dimensional vectors of the characteristics of the driver, including information such as driving speed, driving behaviors when alarming occurs, vehicle GPS information, driving direction angles and the like.
Further, in step S2, the response behavior of the driver to the warning information under different road conditions is analyzed, the response behavior of the driver to the warning information may be divided into positive and negative types, and the different types of response behaviors may cause the driver to appear to depend on the warning system excessively, lack the personal judgment capability, or excessively trust the judgment capability and driving level of the driver and ignore the warning for the dangerous condition; the key factors influencing the acceptance degree of the driver on the early warning information are extracted, so that the early warning system can adapt to the driving habit of the driver, and the working effect of the early warning system is improved.
Further, in the step S3, for the semi-supervised support vector machine to classify the driver response behavior, the significant advantages are that: in the case of labeling a small number of labels, better classification effect than supervised learning can be achieved generally. The operation steps are as follows:
step one, inputting the driver high-dimensional vector collected in S1, and deleting the outlier and obvious false alarm.
And step two, manually calibrating about 1% of high-dimensional vectors in the data set obtained in the step one according to the classification target, wherein the calibrated high-dimensional vectors form a label data set, and uncalibrated high-dimensional vectors form a label-free data set.
Step three, solving the optimal separation hyperplane of the positive response and the negative response of the driver by using a simulated annealing algorithm, and assuming that the solved hyperplane equation is as follows: f (x) ═ ωTΦ (x) + b. Where b is a parameter representing intercept, ω is a parameter representing slope,
is a kernel function representing mapping transformation, where a gaussian kernel is chosen and x represents a high-dimensional vector.
The prediction function for the classification is: y isi＝sign(ωTΦ (x) + b), wherein,
let l (y, f (x)) max {0, 1-yf (x) }, the objective function for solving the best separating hyperplane is as follows:
the (| non-conducting phosphor) in the formula2Is 2-norm, C1The penalty coefficient corresponding to the label data should be taken as a larger value at C2The penalty coefficient corresponding to the label-free data is small in value. y isiThe prediction result of the ith data in the label data set is obtained, and l is the number of data in the label data;
and u is the number of data in the unlabeled data. The problem can be solved by adopting a simulated annealing method, and the classification standard (optimal separation hyperplane) of the early warning positive response and the early warning negative response of the driver can be obtained.
Further, in the step S4, for evaluating the scoring mode of the driver for the early warning response behavior, a sliding window method is used, and the driving response behavior after the label is utilized, and the driver performs comprehensive scoring in the latest N early warning responses. In general applications, N may be 50. The score calculation formula is as follows:
score in the formula is safe water for drivers to driveGrading the average comprehensive value; xaThe response value X of the driver's latest response behavior to the active safety pre-warning informationa-nAnd the response value is the response value of the driver to the response behavior of the active safety early warning information for the latest a-n times, if the response behavior is positive, the corresponding response value is 1, and if not, the corresponding response value is 0.
The score may indicate the driver's response to the warning over a period of time, and the score may reflect the driver's usage of the warning system over a period of time, with lower scores being more negative for the driver's warning of the warning system. And evaluating the driving level and the safety consciousness of the driver by using the established safe driving scoring model, and adopting different management methods according to the evaluation effect.
Further, in step S5, the driver response behavior real-time prediction model is trained by using the high-dimensional vector extracted in step S1 and the corresponding response behavior classification result through a method of establishing a long-term and short-term memory neural network model, so as to obtain a driver response behavior prediction model, thereby realizing prediction of the driver response behavior, and the prediction result is divided into two types, namely positive response and negative response. For drivers who may have negative responses, the driver can be reminded by improving the alarm level and providing other types of alarms, and unsafe driving behaviors of the drivers can be corrected in time, so that the acceptance of a driving system is improved.
In one embodiment, a terminal device is provided, which includes a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the steps of the method for evaluating a driver of a commercial truck based on active safety precaution and driver response behavior.
In one embodiment, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, performs the steps of the above-described method for evaluating a driver of a commercial truck based on active safety warnings and driver response behavior.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can understand that the modifications or substitutions within the technical scope of the present invention are included in the scope of the present invention, and therefore, the scope of the present invention should be subject to the protection scope of the claims.
Claims (6)
1. A method for evaluating a driver of an operation truck based on active safety early warning and driver response behaviors is characterized by comprising the following steps of: the method comprises the following steps:
s1, extracting a high-dimensional vector of the characteristics of the driver based on the video data of the driver, the video data of the road, the vehicle data and the intrinsic attribute of the driver, wherein the elements of the high-dimensional vector comprise the driving speed, the driving behavior when the alarm occurs, the GPS information of the vehicle and the driving direction angle;
s2, taking the response time of the driver to the active safety early warning information as a dependent variable, taking the high-dimensional vector and the warning grade in S1 as independent variables, and performing a logistic regression analysis method on the response behavior of the driver to the early warning information under different road conditions to obtain key factors influencing the acceptance degree of the driver to the active safety early warning information: driving speed and alarm level;
s3, classifying the response behavior of the driver to the active safety early warning information by using a semi-supervised support vector machine, and dividing the response behavior into two types of positive response and negative response;
s4, comprehensively scoring the driving safety level of the driver by using the latest N times of response behaviors of the driver to the active safety early warning information, wherein the lower the score is, the lower the driving safety level of the driver is; wherein the score calculation formula is as follows:
wherein score is comprehensive grade of driving safety level of the driver; xaThe response value X of the driver's latest response behavior to the active safety pre-warning informationa-nAnd the response value is the response value of the driver to the response behavior of the active safety early warning information for the latest a-n times, if the response behavior is positive, the corresponding response value is 1, and if not, the corresponding response value is 0.
2. The method of claim 1 for driver evaluation of a commercial truck based on active safety warnings and driver response behavior, wherein: in the step S1, the driver video data includes bad driving behavior of the driver, response behavior to the warning information, and response time to the active safety warning information; the vehicle video data comprises driving speed, acceleration, vehicle distance, lane departure data, driving direction angle and vehicle GPS information; the driver intrinsic attributes comprise the driver age, the driving duration and the driving mileage data.
3. The method of claim 1 for driver evaluation of a commercial truck based on active safety warnings and driver response behavior, wherein: in the step S3, a semi-supervised support vector machine is used to classify the response behavior of the driver to the active safety pre-warning information, and the operation steps are as follows:
step one, taking the high-dimensional vector of S1 as the input of a semi-supervised support vector machine;
step two, according to a set proportion, carrying out partial manual category calibration on the high-dimensional vector extracted in the step S1, wherein the calibrated high-dimensional vector forms a label data set, and the uncalibrated high-dimensional vector forms a non-label data set;
step three, solving the optimal separation hyperplane of the positive response and the negative response by using a simulated annealing algorithm, specifically comprising the following steps:
assuming the hyperplane equation as: f (x) ═ ωTΦ (x) + b, where b is a parameter representing intercept, ω is a parameter representing slope,
is a gaussian kernel function representing the mapping transformation, x represents a high-dimensional vector;
the prediction function for the classification is: y isi＝sign(ωTΦ (x) + b), wherein,
let l (y, f (x)) max {0, 1-yf (x) }, the objective function for solving the best separating hyperplane is as follows:
in the formula | · |)2Denotes the 2-norm, C1Is the penalty factor, C, corresponding to the tag data set2Is a penalty factor corresponding to the unlabeled dataset, and C1>C2；yiThe prediction result of the ith data in the label data set is obtained, and l is the number of data in the label data;
represents the prediction result of the jth data in the unlabeled dataset, u is unlabeledThe number of data in the data;
and solving the objective function by adopting a simulated annealing method to obtain the optimal separation hyperplane, namely the classification standard of the positive response and the negative response.
4. The method of claim 1 for driver evaluation of a commercial truck based on active safety warnings and driver response behavior, wherein: the method further comprises the steps of building a long-term and short-term memory network, training by using the high-dimensional vector extracted in the S1 and the corresponding response behavior classification result to obtain a driver response behavior prediction model, achieving prediction of the driver response behavior, and implementing upgrading early warning on a driver with a prediction result of negative response according to a set rule.
5. A terminal device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: the processor, when executing the computer program, realizes the steps of the method according to any of claims 1 to 4.
6. A computer-readable storage medium storing a computer program, characterized in that: the computer program realizing the steps of the method according to any one of claims 1 to 4 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111092084.2A CN113887896B (en) | 2021-09-17 | 2021-09-17 | Driving safety level evaluation method for operating truck driver |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111092084.2A CN113887896B (en) | 2021-09-17 | 2021-09-17 | Driving safety level evaluation method for operating truck driver |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113887896A true CN113887896A (en) | 2022-01-04 |
| CN113887896B CN113887896B (en) | 2024-08-02 |
Family
ID=79009446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111092084.2A Active CN113887896B (en) | 2021-09-17 | 2021-09-17 | Driving safety level evaluation method for operating truck driver |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887896B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662143A (en) * | 2022-11-21 | 2023-01-31 | 吉林大学 | Dynamic prediction system and method for operation safety situation of public transport enterprise |
| CN115862391A (en) * | 2022-11-22 | 2023-03-28 | 东南大学 | Airport runway vehicle following safety evaluation method oriented to intelligent networking environment |
| CN117993937A (en) * | 2024-04-07 | 2024-05-07 | 永立数智(北京)科技有限公司 | Network freight driver credibility level identification method based on large-scale freight data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268701A (en) * | 2014-09-29 | 2015-01-07 | 清华大学 | Commercial vehicle driving safety evaluation system and method |
| US20170001648A1 (en) * | 2014-01-15 | 2017-01-05 | National University Of Defense Technology | Method and Device for Detecting Safe Driving State of Driver |
| CN109664894A (en) * | 2018-12-03 | 2019-04-23 | 盐城工学院 | Fatigue driving safety pre-warning system based on multi-source heterogeneous data perception |
-
2021
- 2021-09-17 CN CN202111092084.2A patent/CN113887896B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170001648A1 (en) * | 2014-01-15 | 2017-01-05 | National University Of Defense Technology | Method and Device for Detecting Safe Driving State of Driver |
| CN104268701A (en) * | 2014-09-29 | 2015-01-07 | 清华大学 | Commercial vehicle driving safety evaluation system and method |
| CN109664894A (en) * | 2018-12-03 | 2019-04-23 | 盐城工学院 | Fatigue driving safety pre-warning system based on multi-source heterogeneous data perception |
Non-Patent Citations (1)
| Title |
|---|
| WEI YE 等: "Investigation of Bus Drivers\' Reaction to ADAS Warning System: Application of the Gaussian Mixed Model", SUSTAINABILITY, pages 1 - 19 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662143A (en) * | 2022-11-21 | 2023-01-31 | 吉林大学 | Dynamic prediction system and method for operation safety situation of public transport enterprise |
| CN115862391A (en) * | 2022-11-22 | 2023-03-28 | 东南大学 | Airport runway vehicle following safety evaluation method oriented to intelligent networking environment |
| CN115862391B (en) * | 2022-11-22 | 2023-08-29 | 东南大学 | Airport road car following safety judging method oriented to intelligent networking environment |
| CN117993937A (en) * | 2024-04-07 | 2024-05-07 | 永立数智(北京)科技有限公司 | Network freight driver credibility level identification method based on large-scale freight data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113887896B (en) | 2024-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887896A (en) | Method for evaluating driving safety level of commercial truck driver | |
| US10678250B2 (en) | Method and system for risk modeling in autonomous vehicles | |
| CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| Feng et al. | Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data | |
| Das et al. | Detecting lane change maneuvers using SHRP2 naturalistic driving data: A comparative study machine learning techniques | |
| Lyu et al. | Using naturalistic driving data to identify driving style based on longitudinal driving operation conditions | |
| CN110858312A (en) | Driver driving style classification method based on fuzzy C-means clustering algorithm | |
| CN112530164B (en) | Active driving safety early warning method and system for high-altitude area road | |
| Wang et al. | SafeDrive: A new model for driving risk analysis based on crash avoidance | |
| EP4126620B1 (en) | Coachable driver risk groups | |
| Yan et al. | Automatic identification method for driving risk status based on multi-sensor data | |
| Alicioglu et al. | Assessing accident risk using ordinal regression and multinomial logistic regression data generation | |
| CN118014349A (en) | Tunnel accident risk assessment method, system and equipment | |
| Ahmed et al. | Driver Performance and Behavior in Adverse Weather Conditions: Microsimulation and Variable Speed Limit Implementation of the SHRP2 Naturalistic Driving Study Results-Phase 3 | |
| CN116597611A (en) | Method, system and device for monitoring and early warning driver state | |
| Priyadharshini et al. | A comprehensive review of various data collection approaches, features, and algorithms used for the classification of driving style | |
| Im et al. | Driver distraction detection by in-vehicle signal processing | |
| Ali et al. | Employment of instrumented vehicles to identify real-time snowy weather conditions on freeways using supervised machine learning techniques–A naturalistic driving study | |
| Mumcuoglu et al. | Driver evaluation in heavy duty vehicles based on acceleration and braking behaviors | |
| Sun et al. | A recognition model of driving risk based on belief rule-base methodology | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| Jain et al. | A computational model for driver risk evaluation and crash prediction using contextual data from on-board telematics | |
| Zhang et al. | Detecting driver distractions using a deep learning approach and multi-source naturalistic driving data | |
| Fasanmade et al. | Context-Aware Quantitative Risk Assessment Machine Learning Model for Drivers Distraction | |
| Hashmi et al. | Preventing Road Accidents by Analysing Speed, Driving Pattern and Drowsiness Using Deep Learning |
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 |