CN111563555A - Driver driving behavior analysis method and system - Google Patents
Driver driving behavior analysis method and system Download PDFInfo
- Publication number
- CN111563555A CN111563555A CN202010391470.0A CN202010391470A CN111563555A CN 111563555 A CN111563555 A CN 111563555A CN 202010391470 A CN202010391470 A CN 202010391470A CN 111563555 A CN111563555 A CN 111563555A
- Authority
- CN
- China
- Prior art keywords
- driver
- driving
- data
- driving behavior
- index
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Automation & Control Theory (AREA)
- Probability & Statistics with Applications (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a driver driving behavior analysis system, which is characterized in that an additionally-installed measuring module is used for collecting vehicle driving data, the measured data are sent to a cloud platform of a vehicle network for calculation, the data are preprocessed, the driver driving behavior is scored, an entropy weight method is used for calculating each index weight and calculating the comprehensive score of a driver, a fuzzy C mean algorithm is used for carrying out cluster analysis on the scores, a cluster result is input into a BP neural network for training, vehicle real-time data are led into the trained BP neural network, a BP neural network classifier classifies the driving behavior, the classification result is processed and converted into an audio signal, the audio signal is sent to a voice device of a vehicle, and the voice device reminds the driver.
Description
Technical Field
The invention belongs to the field of analysis of driving behaviors of drivers, and particularly relates to a method and a system for analyzing driving behaviors of drivers.
Background
Driver driving behavior analysis is an indispensable part in the field of vehicle driving, and by analyzing driver driving behavior, we can classify driver driving behavior into several categories, for example, driver driving behavior can be classified into aggressive driving behavior, general driving behavior, cautious driving behavior, and the like. The vehicle driving system can evaluate the behavior of the driver according to the divided behavior categories and analyze whether the behavior of the driver has potential safety hazards and other problems. Thereby effectively preventing unnecessary traffic accidents.
The existing driver driving behavior analysis method also comprises preprocessing methods such as a hierarchical analysis method and a factor analysis method based on questionnaire survey, clustering algorithms such as kmeans and spectral clustering, and a classifier mainly comprises Bayes, KNN and a support vector machine. However, these methods have the following disadvantages: the subjectivity of the analytic hierarchy process is too strong, and the factor analytic process is easy to cause information loss; kmeans and spectral clustering have high requirements on initial clustering centers and are easy to fall into local optimal solutions; if the parameters do not meet normal distribution, the Bayesian classifier is difficult to establish, the KNN calculation is too large, the efficiency is not high, and the multi-classification problem is difficult to solve by a support vector machine.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a driver driving behavior analysis method which is strong in objective information, high in efficiency and suitable for solving the multi-classification problem.
The invention also provides a system based on the driver driving behavior analysis method.
In order to achieve the purpose, the invention adopts the following technical scheme.
A driver driving behavior analysis method is characterized by comprising the following steps: 1) collecting vehicle running data through a vehicle-mounted terminal and a road side system; 2) preprocessing the acquired vehicle running data by using a controller; 3) grading the driving behavior of the driver according to the preprocessing result; 4) calculating the weight of each index of the vehicle driving data by using an entropy weight method; 5) calculating the comprehensive score of the driver according to the weight of each index; 6) carrying out cluster analysis on the driver comprehensive score by using a fuzzy C-means algorithm; 7) inputting the clustering result into a BP neural network for training; 8) and importing the real-time data of the vehicle into the trained BP neural network, and classifying the driving behavior of the driver by using a BP neural network classifier.
More preferably, in step 1), the vehicle travel data includes: one or more of time, longitude, latitude, direction, throttle signal, left turn signal, right turn signal, hand brake signal, foot brake signal, speed and mileage.
More preferably, in step 2), the specific process of the pretreatment is as follows: and forming a matrix by the vehicle running data, wherein the rows of the matrix represent the same vehicle, and the columns of the matrix represent the same index.
More preferably, in step 3), the scoring method is as follows: 3.1) defining the secondary indexes of the driving behavior of the driver as follows: driving speed, daily trip condition, fatigue driving, night driving and four-urgency behaviors; 3.2) setting a third-level index under each second-level index: the driving speed comprises average driving speed and overspeed times, the daily trip comprises driving mileage and driving time, the fatigue driving comprises continuous driving time and fatigue driving times, the night driving comprises night driving time and night average speed, and the four-rush behaviors comprise quick acceleration, quick deceleration, quick turning and quick braking; 3.3) determining specific scoring criteria under each tertiary index.
More preferably, in step 4), the method for calculating the weight includes: 4.1) carrying out standardization processing on the data, wherein if m three-level indexes exist, n data exist under each three-level index, and after the three-level indexes are standardized, the data are as follows:in the above formula, YijRepresenting the normalized value, X, of each of the three levels of the indexijRepresenting individual data under each tertiary index, XiA data set representing some tertiary index; 4.2) solving the information entropy of each index:in the formula4.3) calculating the weight of each index:
more preferably, in step 5), the driver composite score is calculated as a weighted average of the indexes.
More preferably, in step 6), the cluster analysis step is as follows: 6.1) setting the clustering number and the weighting index; 6.2) initializing each clustering center; 6.3) calculating a membership function by using the current clustering center; 6.4) calculating and updating the clustering center by using the current membership function; 6.5) repeating the step 6.3) and the step 6.4) until the membership value of each sample is stable, thereby completing fuzzy C-means clustering.
More preferably, in step 7), the step of training the BP neural network with the clustering result is as follows: 7.1) reading training data and normalizing the characteristic values; 7.2) creating a BP neural network, and setting the neuron number, the neuron transfer function and the training method of a hidden layer and an output layer; 7.3) setting training parameters such as learning rate, maximum training times and training required precision; 7.4) begin training.
A driver driving behavior analysis system, comprising: the measuring module and the voice device are connected with a cloud platform of the Internet of vehicles, the driver driving behavior analysis method is arranged on the cloud platform of the Internet of vehicles, data measured by the measuring module are sent to the cloud platform of the Internet of vehicles for calculation and classification of the driver driving behaviors, and after the classification result is processed, the data are converted into audio signals which are sent to the voice device to give voice prompt to the driver.
The invention has the beneficial effects that:
the preprocessing adopts an entropy weight method, the objectivity is strong, and the information integrity is high; the clustering algorithm adopts KFCM (Kenerl fuzzy means, fuzzy c-means algorithm based on kernel function), establishes uncertain description of the sample to the category, and is more objective and higher in efficiency; the classifier adopts a BP neural network, has nonlinear fitting capacity and can solve the problem of multi-classification.
Drawings
Fig. 1 is a flowchart of a method for analyzing driving behavior of a driver according to the present invention.
Detailed Description
The following describes the embodiments of the present invention with reference to the drawings of the specification, so that the technical solutions and the advantages thereof are more clear and clear. The embodiments described below are exemplary and are intended to be illustrative of the invention, but are not to be construed as limiting the invention.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
As shown in fig. 1, a method for analyzing driving behavior of a driver includes the following steps: 1) collecting vehicle running data through a vehicle-mounted terminal and a road side system; 2) preprocessing the acquired vehicle running data by using a controller; 3) grading the driving behavior of the driver according to the preprocessing result; 4) calculating the weight of each index of the vehicle driving data by using an entropy weight method; 5) calculating the comprehensive score of the driver according to the weight of each index; 6) carrying out cluster analysis on the driver comprehensive score by using a fuzzy C-means algorithm; 7) inputting the clustering result into a BP neural network for training; 8) and importing the real-time data of the vehicle into the trained BP neural network, and classifying the driving behavior of the driver by using a BP neural network classifier.
Wherein, in the step 1), the collected vehicle driving data comprises time, longitude, latitude, direction, throttle signal, left turn signal, right turn signal, hand brake signal, foot brake signal, speed and driving mileage.
In the step 2), the pretreatment specifically comprises the following steps: the data are formed into a matrix N, the rows of the matrix N represent the same vehicle, and the columns of the matrix N represent the same attributes.
In step 3), the scoring method of the driver driving line comprises the following steps:
and 3.1) setting secondary indexes of the driving behaviors of the driver as the driving speed, the daily travel condition, the fatigue driving, the night driving and the four-urgency behaviors.
3.2) setting a third-level index under each second-level index: the driving speed comprises average driving speed and overspeed times, the daily trip comprises driving mileage and driving time, the fatigue driving comprises continuous driving time and fatigue driving times, the night driving comprises night driving time and night average speed, and the four-rush behaviors comprise quick acceleration, quick deceleration, quick turning and quick braking;
3.3) determining specific scoring criteria under each tertiary index, wherein the scoring criteria are as follows:
average running vehicle speed (unit: km/h): 100 points are obtained from 0 to 35, 90 points are obtained from 35 to 50, 75 points are obtained from 45 to 60, 50 points are obtained from 60 to 80, and 20 points are obtained above 80.
Number of overspeed times: 100 points are obtained after 0 time, 85 points are obtained after 1-2 times, 70 points are obtained after 3-4 times, 50 points are obtained after 5-6 times, and 10 points are obtained after more than 6 times.
Total mileage traveled per day (unit: km): 100 points are obtained from 0 to 30, 90 points are obtained from 30 to 40, 80 points are obtained from 40 to 70, 65 points are obtained from 70 to 90, 50 points are obtained from 90 to 120, 30 points are obtained from 120 to 200, and 10 points are obtained from more than 200.
Total driving time per day (unit: h): 100 points are obtained from 0 to 2, 85 points are obtained from 2 to 3, 70 points are obtained from 3 to 4, 50 points are obtained from 4 to 6, 25 points are obtained from 6 to 7, and 10 points are obtained above 7.
Continuous driving time (unit: h): 100 points are obtained from 0 to 2, 80 points are obtained from 2 to 3, 70 points are obtained from 3 to 4, 50 points are obtained from 4 to 5, and 10 points are obtained above 5.
Number of fatigue drives (1 time without rest for more than 15 minutes for 2 consecutive hours): 100 points for 0 time, 80 points for 1 time, 50 points for 2 times, and 10 points for 3 times or more.
Night driving time (20: 00-second day 6:00, unit h): 100 points are obtained from 0 to 1, 85 points are obtained from 1 to 2, 60 points are obtained from 2 to 3, 40 points are obtained from 3 to 5, and 10 points are obtained above 5.
Night average vehicle speed (unit km/h): 100 points are obtained from 0 to 30, 90 points are obtained from 30 to 40, 75 points are obtained from 40 to 50, 50 to 60 and 10 points are obtained above 60.
Rapid acceleration, rapid deceleration and rapid turning: 100 points are obtained for 0 time, 95 points are obtained for 1 time, 85 points are obtained for 2-3 times, 65 points are obtained for 4-5 times, 40 points are obtained for 6-9 times, and 20 points are obtained for 10 times or more.
Emergency braking: 100 points for 0 time, 85 points for 1 time, 70 points for 2 times, 50 points for 3-4 times, and 20 points for 5 times or more.
In step 4), the entropy weight method determines the weights of the indexes, and the specific steps are as follows:
step 4.1, carrying out standardization processing on the data, wherein if m three-level indexes exist, n data exist under each three-level index, and after the three-level indexes are standardized, the data are as follows:
in the above formula, YijRepresenting the normalized value, X, of each of the three levels of the indexijRepresenting individual data under each tertiary index, XiA data set representing some tertiary index.
Step 4.2, the information entropy of each three-level index is obtained, and according to the definition of the information entropy, the information entropy of a group of data is expressed as follows:
Step 4.3, calculating the weight of each index:
in step 5), the method for calculating the driver comprehensive score includes:
In step 6), the specific steps of the cluster analysis are as follows:
step 6.1, setting the clustering number c to be 3 and the weighting index b to be 2;
step 6.2, initializing each clustering center Mi,
wherein Ni is the number of driver score samples in the ith class;
6.3, calculating a membership function by using the current clustering center:
and 6.4, calculating and updating the clustering center by using the current membership function according to the following formula:
and 6.5, repeating the steps 6.3 and 6.4 until the membership value of each sample is stable, thereby completing fuzzy C-means clustering division.
In step 7), the training of the BP neural network by using the clustering result specifically comprises the following steps:
step 7.1, reading training data and normalizing the characteristic values;
7.2, creating a BP neural network, wherein the number of neurons of a hidden layer and an output layer is respectively 20 and 3, the neuron transfer function sequentially adopts a logarithmic S-shaped transfer function logsig and a linear transfer function purelin, and the training method adopts a self-adaptive Ir momentum gradient descent method;
7.3, setting training parameters, wherein the learning rate is 0.01, the maximum training frequency is 5000, and the training required precision is 0.001;
and 7.4, starting training.
During actual work, vehicle driving data are collected through the vehicle-mounted terminal and the road side system, the collected vehicle driving data are sent to a cloud platform of the Internet of vehicles for calculation, classification results are processed and then converted into audio signals, and the audio signals are sent to a voice device of the vehicle, and the voice device reminds a driver.
It will be appreciated by those skilled in the art from the foregoing description of construction and principles that the invention is not limited to the specific embodiments described above, and that modifications and substitutions based on the teachings of the art may be made without departing from the scope of the invention as defined by the appended claims and their equivalents. The details not described in the detailed description are prior art or common general knowledge.
Claims (9)
1. A driver driving behavior analysis method is characterized by comprising the following steps:
1) collecting vehicle running data through a vehicle-mounted terminal and a road side system;
2) preprocessing the acquired vehicle running data by using a controller;
3) grading the driving behavior of the driver according to the preprocessing result;
4) calculating the weight of each index of the vehicle driving data by using an entropy weight method;
5) calculating the comprehensive score of the driver according to the weight of each index;
6) carrying out cluster analysis on the driver comprehensive score by using a fuzzy C-means algorithm;
7) inputting the clustering result into a BP neural network for training;
8) and importing the real-time data of the vehicle into the trained BP neural network, and classifying the driving behavior of the driver by using a BP neural network classifier.
2. The driver's driving behavior analysis method according to claim 1, wherein in step 1), the vehicle travel data includes: one or more of time, longitude, latitude, direction, throttle signal, left turn signal, right turn signal, hand brake signal, foot brake signal, speed and mileage.
3. The driver driving behavior analysis method according to claim 1, wherein in step 2), the specific process of the preprocessing is: and forming a matrix by the vehicle running data, wherein the rows of the matrix represent the same vehicle, and the columns of the matrix represent the same index.
4. The driver driving behavior analysis method according to claim 1, wherein in step 3), the scoring method is as follows:
3.1) defining the secondary indexes of the driving behavior of the driver as follows: driving speed, daily trip condition, fatigue driving, night driving and four-urgency behaviors;
3.2) setting a third-level index under each second-level index: the driving speed comprises average driving speed and overspeed times, the daily trip comprises driving mileage and driving time, the fatigue driving comprises continuous driving time and fatigue driving times, the night driving comprises night driving time and night average speed, and the four-rush behaviors comprise quick acceleration, quick deceleration, quick turning and quick braking;
3.3) determining specific scoring criteria under each tertiary index.
5. The driver driving behavior analysis method according to claim 4, wherein in step 4), the weight is calculated by:
4.1) carrying out standardization processing on the data, wherein if m three-level indexes exist, n data exist under each three-level index, and after the three-level indexes are standardized, the data are as follows:
in the above formula, YijRepresenting the normalized value, X, of each of the three levels of the indexijRepresenting individual data under each tertiary index, XiA data set representing some tertiary index;
4.2) solving the information entropy of each index;
6. the driver driving behavior analysis method according to claim 1, wherein in step 5), the driver composite score is calculated as a weighted average of the indicators.
7. The driver driving behavior analysis method according to claim 1, wherein in step 6), the cluster analysis step is as follows:
6.1) setting the clustering number and the weighting index;
6.2) initializing each clustering center;
6.3) calculating a membership function by using the current clustering center;
6.4) calculating and updating the clustering center by using the current membership function;
6.5) repeating the step 6.3) and the step 6.4) until the membership value of each sample is stable, thereby completing fuzzy C-means clustering.
8. The driver driving behavior analysis method according to claim 1, wherein in step 7), the step of training the BP neural network with the clustering result is as follows:
7.1) reading training data and normalizing the characteristic values;
7.2) creating a BP neural network, and setting the neuron number, the neuron transfer function and the training method of a hidden layer and an output layer;
7.3) setting training parameters such as learning rate, maximum training times and training required precision;
7.4) begin training.
9. A driver driving behavior analysis system, comprising: the driver driving behavior analysis method comprises a measuring module and a voice device, wherein the measuring module and the voice device are both connected with a cloud platform of the Internet of vehicles, the cloud platform of the Internet of vehicles is provided with the driver driving behavior analysis method according to any one of claims 1-8, data measured by the measuring module are sent to the cloud platform of the Internet of vehicles for calculation and classification of driving behaviors of drivers, and after a classification result is processed, the data are converted into audio signals which are sent to the voice device to give voice prompt to the driver.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010391470.0A CN111563555A (en) | 2020-05-11 | 2020-05-11 | Driver driving behavior analysis method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010391470.0A CN111563555A (en) | 2020-05-11 | 2020-05-11 | Driver driving behavior analysis method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111563555A true CN111563555A (en) | 2020-08-21 |
Family
ID=72070876
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010391470.0A Pending CN111563555A (en) | 2020-05-11 | 2020-05-11 | Driver driving behavior analysis method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111563555A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112216066A (en) * | 2020-08-25 | 2021-01-12 | 南京市德赛西威汽车电子有限公司 | Fatigue driving traffic guiding method based on V2X |
CN112706777A (en) * | 2020-12-28 | 2021-04-27 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for adjusting driving behaviors of user under vehicle working conditions |
CN113159651A (en) * | 2021-05-21 | 2021-07-23 | 河南科技大学 | Service quality evaluation method for taxi |
CN113657716A (en) * | 2021-07-16 | 2021-11-16 | 长安大学 | Comprehensive evaluation method for safety of driver driving behavior based on entropy weight method |
CN113867536A (en) * | 2021-10-12 | 2021-12-31 | 浙江数智交院科技股份有限公司 | Interaction mode determination method, data acquisition method and device and electronic equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106202872A (en) * | 2016-06-27 | 2016-12-07 | 江苏迪纳数字科技股份有限公司 | Vehicle driving behavior scoring method |
CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
CN108711016A (en) * | 2018-06-05 | 2018-10-26 | 合肥湛达智能科技有限公司 | A kind of driving behavior methods of marking based on BP neural network |
CN108717536A (en) * | 2018-05-28 | 2018-10-30 | 深圳市易成自动驾驶技术有限公司 | Driving instruction and methods of marking, equipment and computer readable storage medium |
CN109572706A (en) * | 2018-12-12 | 2019-04-05 | 西北工业大学 | A kind of driving safety evaluation method and device |
CN110276954A (en) * | 2019-06-28 | 2019-09-24 | 青岛无车承运服务中心有限公司 | Vehicle driving behavior integration methods of marking based on BEI-DOU position system |
CN110682865A (en) * | 2019-11-06 | 2020-01-14 | 复变时空(武汉)数据科技有限公司 | Driver driving behavior monitoring method |
CN110979341A (en) * | 2019-10-08 | 2020-04-10 | 复变时空(武汉)数据科技有限公司 | Driver driving behavior analysis method and analysis system |
-
2020
- 2020-05-11 CN CN202010391470.0A patent/CN111563555A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106202872A (en) * | 2016-06-27 | 2016-12-07 | 江苏迪纳数字科技股份有限公司 | Vehicle driving behavior scoring method |
CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
CN108717536A (en) * | 2018-05-28 | 2018-10-30 | 深圳市易成自动驾驶技术有限公司 | Driving instruction and methods of marking, equipment and computer readable storage medium |
CN108711016A (en) * | 2018-06-05 | 2018-10-26 | 合肥湛达智能科技有限公司 | A kind of driving behavior methods of marking based on BP neural network |
CN109572706A (en) * | 2018-12-12 | 2019-04-05 | 西北工业大学 | A kind of driving safety evaluation method and device |
CN110276954A (en) * | 2019-06-28 | 2019-09-24 | 青岛无车承运服务中心有限公司 | Vehicle driving behavior integration methods of marking based on BEI-DOU position system |
CN110979341A (en) * | 2019-10-08 | 2020-04-10 | 复变时空(武汉)数据科技有限公司 | Driver driving behavior analysis method and analysis system |
CN110682865A (en) * | 2019-11-06 | 2020-01-14 | 复变时空(武汉)数据科技有限公司 | Driver driving behavior monitoring method |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112216066A (en) * | 2020-08-25 | 2021-01-12 | 南京市德赛西威汽车电子有限公司 | Fatigue driving traffic guiding method based on V2X |
CN112706777A (en) * | 2020-12-28 | 2021-04-27 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for adjusting driving behaviors of user under vehicle working conditions |
CN112706777B (en) * | 2020-12-28 | 2022-05-10 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for adjusting driving behaviors of user under vehicle working conditions |
CN113159651A (en) * | 2021-05-21 | 2021-07-23 | 河南科技大学 | Service quality evaluation method for taxi |
CN113657716A (en) * | 2021-07-16 | 2021-11-16 | 长安大学 | Comprehensive evaluation method for safety of driver driving behavior based on entropy weight method |
CN113657716B (en) * | 2021-07-16 | 2024-03-05 | 长安大学 | Comprehensive evaluation method for driving behavior safety of driver based on entropy weight method |
CN113867536A (en) * | 2021-10-12 | 2021-12-31 | 浙江数智交院科技股份有限公司 | Interaction mode determination method, data acquisition method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111563555A (en) | Driver driving behavior analysis method and system | |
CN112508392B (en) | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway | |
CN109448369B (en) | Real-time operation risk calculation method for expressway | |
CN112201038B (en) | Road network risk assessment method based on risk of bad driving behavior of single vehicle | |
Ma et al. | Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry | |
CN108596409B (en) | Method for improving accident risk prediction precision of traffic hazard personnel | |
CN110866677B (en) | Driver relative risk evaluation method based on benchmark analysis | |
CN111461185A (en) | Driving behavior analysis method based on improved K-means | |
CN107742193A (en) | A kind of driving Risk Forecast Method based on time-varying state transition probability Markov chain | |
CN111242484B (en) | Vehicle risk comprehensive evaluation method based on transition probability | |
CN110796859A (en) | Real-time traffic state identification and accident risk early warning method based on traffic flow | |
CN108769104B (en) | Road condition analysis and early warning method based on vehicle-mounted diagnosis system data | |
CN110562261B (en) | Method for detecting risk level of driver based on Markov model | |
CN108876165B (en) | Driver safety monitoring learning system | |
CN113222385B (en) | Method for constructing and evaluating driving condition of electric automobile | |
CN109191828B (en) | Traffic participant accident risk prediction method based on ensemble learning | |
CN105809193A (en) | Illegal operation vehicle recognition method based on Kmeans algorithm | |
CN113920732B (en) | Road traffic accident risk early warning method for specific driving crowd | |
CN116957345B (en) | Data processing method for unmanned system | |
CN110858312A (en) | Driver driving style classification method based on fuzzy C-means clustering algorithm | |
Agrawal et al. | Towards real-time heavy goods vehicle driving behaviour classification in the united kingdom | |
CN113581188A (en) | Commercial vehicle driver driving style identification method based on Internet of vehicles data | |
CN110610326A (en) | Driving management system based on driving data | |
CN113657432A (en) | Commercial vehicle driving behavior risk level identification method based on Internet of vehicles data | |
CN112308136A (en) | SVM-Adaboost-based driving distraction detection method |
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 |