CN106448158A - Corresponding analysis based traffic accident cause analyzing method - Google Patents
Corresponding analysis based traffic accident cause analyzing method Download PDFInfo
- Publication number
- CN106448158A CN106448158A CN201610807054.8A CN201610807054A CN106448158A CN 106448158 A CN106448158 A CN 106448158A CN 201610807054 A CN201610807054 A CN 201610807054A CN 106448158 A CN106448158 A CN 106448158A
- Authority
- CN
- China
- Prior art keywords
- accident
- type
- traffic
- violation
- types
- 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
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 90
- 238000004458 analytical method Methods 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000012216 screening Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000011985 exploratory data analysis Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 abstract 4
- 230000002596 correlated effect Effects 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 9
- 238000002474 experimental method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a corresponding analysis based traffic accident cause analyzing method, comprising the following steps: inputting traffic accident data and traffic violation data wherein both are correlated through the identity information of a driver; conducting corresponding analysis on the type of traffic accident and the type of traffic violation by the driver; and conducting multiple corresponding analysis on the type of the traffic accident by the driver, the driver's age and gender as well as the car family. The corresponding analysis based traffic accident cause analyzing method of the invention is capable of analyzing the driver's driving actions and the influencing factors on the driving actions through the recorded violations, driving age, gender, car brand of the driver as well as the type of traffic accident so as to make targeted precautions to traffic accident and increase the safety on the road.
Description
Technical Field
The invention relates to a traffic accident cause analysis method based on a corresponding analysis model.
Background
With the gradual rise of the automobile holding quantity in China, the problem of traffic accidents is more prominent; various types of traffic accidents emerge endlessly; behind these accident types there must be a variety of accident causes, driver-based, road environment-based, etc.; therefore, a large amount of data is needed to be analyzed and explored to find out the difference and the relation among various accident type factors; therefore, traffic accidents are prevented pertinently, and the safety of roads is improved.
At present, a traffic accident cause analysis method lacks detailed classification, and most of researches focus on the number of times of traffic accidents and influence relations of the times; corresponding research is lacked for the analysis of the driving behavior of the driver and the analysis of the accident type of the driver; in reality, the violation is a fuse which causes the final traffic accident, and how to explore the type of traffic accident caused by the violation behavior of a driver in the driving process from the historical violation record of the driver; secondly, the driving behavior of the driver is irrelevant to the driving age and the sex of the driver; the solution of the above problems has a positive effect on the analysis of the cause of the traffic accident.
Disclosure of Invention
The invention aims to provide a traffic accident cause analysis method based on a corresponding analysis model, aiming at different traffic accident types, and performing multi-dimensional analysis and exploration on causes influencing the accident types by using a corresponding analysis and clustering method, so as to solve the problems in the prior art.
The technical solution of the invention is as follows:
a traffic accident cause analysis method based on a corresponding analysis model comprises the following steps,
s1, inputting traffic violation data and traffic accident data, and associating the traffic violation data with the traffic accident data through driver identity information;
s2, correspondingly analyzing the traffic accident type and the traffic violation type, firstly, carrying out exploratory analysis, counting violation data by using a data perspective view, and screening violation sample data for subsequent analysis by a threshold value method; finding out accident crowds corresponding to each violation type and accident types generated by the accident crowds, and counting the proportion of each accident type in all accident types; secondly, selecting representative accident categories and accident types thereof for simple corresponding analysis;
s3, analyzing the traffic accident type, the driving age and sex of the driver and the multivariate correspondence of the driving vehicle; extracting the identity information of accident responsible parties from the accident data, and the corresponding four types of information of the accident type, the brand type of the hit-and-accident vehicle, the driving age of a driver and the gender of the driver; the method comprises the steps that t types of accidents, y types of driving vehicles, j types of driving ages and genders are in one-to-one correspondence, and x-t-y-j combinations are generated in total; and counting the number of people corresponding to each type of combination, and obtaining multiple corresponding relations by utilizing a multivariate corresponding analysis method in statistics.
Further, in step S1, the feature vector of the traffic accident data is CS ═ C, K, V ], where C is the accident occurrence type; k is personnel information including sex, driving age and accident liability attribution of a driver; v is vehicle brand information; the feature vector of the traffic violation data is WS ═ A, H, wherein A is the identity information of the violator, and H is the violation content of the violator.
Further, in step S2, the exploratory analysis specifically includes:
s21, classifying accident drivers according to the types of the traffic accidents;
s22, screening the violation records of the accident driver from the traffic violation data sheet according to the accident driver information, and counting the number of various violations of each accident type driver;
s23, reserving the violation types with the violation times more than or equal to p according to the counted number of the violations, wherein p is a violation sample screening threshold value;
s24, calculating the ratio of the number of the various traffic violations corresponding to each type of traffic accident to the total number of the traffic violations of each type;
s25, the proportion of the drivers violating the traffic regulations is used as a vertical coordinate, the types of the drivers violating the traffic regulations are used as a horizontal coordinate, the proportion of various traffic regulations of the drivers of various traffic accidents is drawn in the coordinate system, the proportion of various traffic regulations of the drivers of various accident types is observed, and the accident and violation relation is initially explored.
Further, in step S24, the calculation formula is as follows:
traffic accident a ═ a1，a2，…ai，…amIn which a isiThe traffic accident type is adopted, and m is the accident type sequence;
number of accident people K ═ K1，k2，…k3，…，kmIn which k isiFor the traffic accident type aiThe number of people;
violation type B ═ B1，b2，…bi，…，bn}，biIs a traffic violation type, and n is a violation type sequence;
number of persons violating the regulationskmbnThe traffic accident type is amOf the type bnThe number of times of (c);
total number of drivers with violation type m
Total number of violations of driver
Driver violation type proportion matrix
Further, in step S2, a representative accident category and an accident type thereof are selected for simple correspondence analysis, and the selected criteria are:
wherein,nthe difference value of the distribution proportion of drivers of various accident types in each type of violation type and the total accident type people number distribution proportion is 2 times; lambda is an abnormal threshold value corresponding to the accident category and the violation category; μ is the threshold number of people for each type of violation.
The practical meaning of the selection standard is to find out the difference value between the distribution proportion of drivers of various accident types in each violation type and the total accident type number distribution proportion so as to obtain the value with abnormal violation type and accident type number distribution proportion;
further, the multivariate corresponding analysis of the driving age, the sex, the type of the driving vehicle and the type of the traffic accident in the step S3 includes the following steps:
s31, classifying drivers of accident liability parties according to the types of the traffic accidents;
s32, simply counting the driving ages of the drivers to obtain the variation trend of the number of accidents of the drivers on the driving ages of the drivers;
s33, classifying the driving ages of the drivers of the accident liability parties in sections according to the change trend obtained in the step S32;
s34, classifying the vehicles according to the brand series of the vehicles;
s35, counting the driving ages, the sexes and the types of the driven vehicles of all drivers under each type of accident, and carrying out merged similar counting to obtain the total generated x-type (2 x t y j) combinations and the corresponding number of people under each type of combinations;
and S36, obtaining multiple corresponding relations by using a corresponding analysis method according to the result obtained in the step S35, and intuitively reflecting the relation between the variables in a form of the distance between the points in a two-dimensional space coordinate.
The invention has the beneficial effects that: the traffic accident cause analysis method based on the corresponding analysis model is characterized in that the corresponding analysis method is used for carrying out multi-dimensional exploration on accident causes causing different types, and the driving behaviors and the influence factors of a driver are analyzed through the history violation record, the driving age, the gender, the vehicle brand and the type of a traffic accident to obtain multiple corresponding relations; therefore, the pertinence prevention of traffic accidents is realized, and the safety of roads is improved.
Drawings
Fig. 1 is a schematic flow chart of a traffic accident cause analysis method based on a corresponding analysis model according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of the accident type and the corresponding violation type obtained in the embodiment.
FIG. 3 is a scatter plot showing the simple correspondence between the type of accident and its violation type in the example.
FIG. 4 is a category point join graph of the multivariate correspondence analysis in an embodiment.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Examples
Embodiments apply corresponding analysis methods in statistics for multi-dimensional exploration of causes of accidents that cause different types. The embodiment explores what kind of traffic accidents can be caused by the violation behaviors of the driver in the driving process through the history violation records of the driver; and secondly, analyzing and obtaining the relation between the driving behavior of the driver and the vehicle driven by the driver according to the driving age and the sex.
The traffic accident cause analysis method based on the corresponding analysis model comprises the following steps: inputting traffic accident data and traffic violation data, wherein the traffic accident data and the traffic violation data are related through driver identity information; correspondingly analyzing the traffic accident type and the traffic violation type of a driver; and carrying out multiple corresponding analysis on the type of the traffic accident of the driver, the driving age, the sex and the train of the driver.
According to the traffic accident cause analysis method based on the corresponding analysis model, the driving behavior and the influence factors of the driver are analyzed through the history violation record, the driving age, the gender, the vehicle brand and the type of the traffic accident; therefore, the pertinence prevention of traffic accidents is realized, and the safety of roads is improved.
The traffic violation data includes: identity information of the offender and the contents of the offender violation.
The traffic accident data includes: accident occurrence type, sex of driver, responsibility, driving age, and vehicle brand information.
The traffic accident cause analysis method based on the corresponding analysis model, as shown in fig. 1, comprises the following steps,
s1, inputting traffic violation data and traffic accident data, and associating the traffic violation data with the traffic accident data through driver identity information; the characteristic vector of the traffic accident data is CS ═ C, K, V ], wherein C is an accident occurrence type; k is personnel information including sex, driving age and accident liability attribution of a driver; v is vehicle brand information; the feature vector of the traffic violation data is WS ═ A, H, wherein A is the identity information of the violator, and H is the violation content of the violator.
S2, correspondingly analyzing the traffic accident type and the traffic violation type, firstly, carrying out exploratory analysis, counting violation data by using a data perspective view, and screening violation sample data for subsequent analysis by a threshold value method; finding out accident crowds corresponding to each violation type and accident types generated by the accident crowds, and counting the proportion of each accident type in all accident types; secondly, selecting representative accident categories and accident types thereof for simple corresponding analysis.
In step S2, the exploratory analysis specifically includes:
s21, classifying accident drivers according to the types of the traffic accidents;
s22, screening the violation records of the accident driver from the traffic violation data sheet according to the accident driver information, and counting the number of various violations of each accident type driver;
s23, reserving the violation types with the violation times more than or equal to p according to the counted number of the violations, wherein p is a violation sample screening threshold value;
s24, calculating the ratio of the number of the various traffic violations corresponding to each type of traffic accident to the total number of the traffic violations of each type, wherein the calculation formula is as follows:
traffic accident a ═ a1，a2，…ai，…amIn which a isiThe traffic accident type is adopted, and m is the accident type sequence;
number of accident people K ═ K1，k2，…k3，…，kmIn which k isiFor the traffic accident type aiThe number of people;
violation type B ═ B1，b2，…bi，…，bn}，biIs a traffic violation type, and n is a violation type sequence;
number of persons violating the regulationskmbnThe traffic accident type is amOf the type bnThe number of times of (c);
total number of drivers with violation type m
Total number of violations of driver
Driver violation type proportion matrix
S25, the proportion of the drivers violating the traffic regulations is used as a vertical coordinate, the types of the drivers violating the traffic regulations are used as a horizontal coordinate, the proportion of various traffic regulations of the drivers of various traffic accidents is drawn in the coordinate system, the proportion of various traffic regulations of the drivers of various accident types is observed, and the accident and violation relation is initially explored.
S26, selecting representative accident categories and accident types thereof for simple corresponding analysis, wherein the selected criteria are as follows:
wherein,nthe difference value of the distribution proportion of drivers of various accident types in each type of violation type and the total accident type people number distribution proportion is 2 times; lambda is an abnormal threshold value corresponding to the accident category and the violation category; μ is the threshold number of people for each type of violation.
The practical meaning of the selection standard is to find out the difference value between the distribution proportion of drivers of various accident types in each violation type and the total accident type number distribution proportion so as to obtain the value with abnormal violation type and accident type number distribution proportion;
s3, analyzing the traffic accident type, the driving age and sex of the driver and the multivariate correspondence of the driving vehicle; extracting the identity information of accident responsible parties from the accident data, and the corresponding four types of information of the accident type, the brand type of the hit-and-accident vehicle, the driving age of a driver and the gender of the driver; the method comprises the steps that t types of accidents, y types of driving vehicles, j types of driving ages and genders are in one-to-one correspondence, and x-t-y-j combinations are generated in total; and counting the number of people corresponding to each type of combination, and obtaining multiple corresponding relations by utilizing a multivariate corresponding analysis method in statistics.
The multivariate corresponding analysis of the driving age, the sex, the type of the driving vehicle and the type of the traffic accident in the step S3 comprises the following steps:
s31, classifying drivers of accident liability parties according to the types of the traffic accidents;
s32, simply counting the driving ages of the drivers to obtain the variation trend of the number of accidents of the drivers on the driving ages of the drivers;
s33, classifying the driving ages of the drivers of the accident liability parties in sections according to the change trend obtained in the step S32;
s34, classifying the vehicles according to the brand series of the vehicles;
s35, counting the driving ages, the sexes and the types of the driven vehicles of all drivers under each type of accident, and carrying out merged similar counting to obtain the total generated x-type (2 x t y j) combinations and the corresponding number of people under each type of combinations;
and S36, obtaining multiple corresponding relations by using a corresponding analysis method according to the result obtained in the step S35, and intuitively reflecting the relation between the variables in a form of the distance between the points in a two-dimensional space coordinate.
Experimental verification
The data analysis processing in the embodiment method mainly uses EXCEL and IBM SPSS statistics22.0 statistical analysis software; relates to basic processing means such as EXCEL screening, comparison and data perspective table and a corresponding analysis method in SPSS.
Referring to fig. 1, a traffic accident cause analysis method based on a corresponding analysis model includes the following steps:
inputting the violation data and accident data of the driver, wherein the violation data and the accident data correspond to each other through the identity information of the driver.
The case data comprises 56651 traffic accident data of 2015 year all year round of a certain city and 61473 traffic violation data of 2014-2016 two years, and relates to 113302 rest persons; the accident data comprises a driver identity card number, an accident category, responsibility information, a driver driving age, a gender and a hit-and-run vehicle brand; the violation data comprises a driver identity number, a violation code and violation content.
Through EXCEL form processing, merging and extracting drivers with the same accident occurrence type and violation type data thereof to obtain the frequent violation type condition of the drivers with certain accidents; the results of screening 200 kinds of violation data to 20 kinds according to the occurrence number of a certain violation type are shown in fig. 2.
Comparing drivers responsible in the accident with the violation conditions of the drivers within two years, and finding out the violation conditions, wherein the violation types are concentrated in a certain category; and the different accident types are found to correspond to different violation high-incidence types, namely, a certain type of violation is frequently violated by a person who has a certain type of traffic accident; FIG. 2 shows the proportion of the driver who has 9 types of traffic accidents corresponding to 20 types of high-speed traffic violation; for example, the violation type of the person who has rear-end collision, who enters the guide lane and does not drive in the specified direction, is higher than other violation types (22.29 percent); the accident type is a driver who violates a traffic signal, and the accident type accounting for the fact that the vehicle is driven to drive on the road other than the expressway and the urban expressway without a specified lane is up to 60.66%; therefore, guess that the accident type which may happen can be judged in advance through the historical violation behaviors of the driver, so that the driver can be convenient to prevent the traffic accidents in a targeted manner;
selecting representative accident categories and accident types thereof for corresponding analysis according to the exploration thought; selectingn>0，cnIf the number is more than 50, the rule-breaking type of the experiment is selected, and the accident type serial number is 1-7 according to the obtained matrix; the practical meaning of the selection standard is to find out the difference value between the distribution proportion of drivers of various accident types in each violation type and the total accident type number distribution proportion so as to obtain the value with abnormal violation type and accident type number distribution proportion; experimental subject and results table 1
TABLE 1 Accident class and violation class of experiment
And correspondingly analyzing the 7 types of accident types and the number of 13 types of violation high-incidence types respectively corresponding to the 7 types of accident types.
Table 2 statistical summary table for corresponding analysis
a. Degree of freedom 72
Table 2 is a statistical summary table of corresponding analysis, in this experiment, 1 is subtracted according to the accident category (7 categories), that is, 6 dimensions; the inertia proportion represents a characteristic value and is an index for measuring the capability of explaining the variation of data; the first dimension of the table shows 42.8% variation and the second dimension shows the remaining 28.4% variation; the two-dimensional standard deviation is 0.22-0.30, which shows that the point estimation value is more accurate, and the correlation coefficient of the factor is-0.024, which shows that the factor decomposition is very stable; therefore, the reliability of the corresponding analysis experiment is high.
FIG. 3 is a scatter plot of the corresponding analysis, and it is evident from FIG. 3 that the driver with the accident category "1" and the category "7" has a high correlation with the violation types "g", "b", and "d"; the correlation between the driver with the accident category of 3 and the violation types of a and f is high; the correlation between the driver with the accident category of 2 and the violation type of e is high; the correlation between the driver with the accident category of 4 and the violation type of c is high; drivers with accident categories "5" and "6" appeared with no obvious difference in violation categories.
Secondly, according to the violation types and the corresponding quantity, drivers with the accident types of 1, 3, 6 and 7 can be approximately divided into one type; it can be inferred that the driving behavior of such accident drivers is largely similar.
Extracting the identity information of accident responsible parties from the accident data, and four types of information of corresponding accident types, the brand types of the hit-and-miss vehicles, the driving ages of drivers and the sexes, as shown in a table 3; accident types are classified into nine types according to original data, and specific classification conditions and weight frequency are shown in a classification table 1 in a table 3; the brand types of the vehicles causing the trouble are classified into six types according to the vehicle series, and the specific classification conditions and the weight frequency are shown in a sub-table 2 in a table 3; the driving age categories are divided into 4 categories according to the driving age distribution condition of drivers of responsible parties; the specific classification conditions and the weight frequencies are shown in sub-table 3 in table 3; the accident responsible party gender classification and its weighting frequency are shown in sub-table 4 of table 3.
29098 accident types, driving vehicle types, driving age types and genders of accident responsible parties in accidents are in one-to-one correspondence to generate 356 effective combination types in total, and the relationship between two classification variables is reflected more intuitively through distance in a two-dimensional space in a point form by utilizing a method for analyzing multivariate correspondence in statistics.
TABLE 3 descriptive statistics summary sheet
Normalizing a variable main body;
model summary table display of processing results: the Cronbach's Alpha average is equal to 0.572, which is within an acceptable range on exploratory studies; the variable interpretations of the model by the dimension 1 and the dimension 2 are up to 87.6% in total, and most characteristics of the model are considered to be reflected; it is therefore appropriate to choose a statistical tool for multiple correspondence analysis in this case.
Table 4 abstract of model
The cronbach's Alpha mean is based on the mean eigenvalue;
FIG. 4 is a scatter diagram of multivariate correspondence analysis, which shows potential relationships between categories and samples in a graphical manner, and the closer the distance between a column point and a row point is, the more closely the relationships are represented; the final result is more intuitive:
the type of rear-end collision is more likely to occur for drivers with the driving age of 0-2 years; the type of accidents that the drivers with the driving ages of 3-7 years are easy to violate the traffic signals; drivers with the driving age of 8-12 years are more prone to accidents of vehicle sliding caused by the fact that low gears are not hung and parking brakes are not pulled when the vehicles are parked; older drivers over 12 years do not have a particular type of accident.
The male driver is more likely to have the accident type of vehicle sliding caused by the fact that a low gear is not hung and the parking brake is not pulled when the vehicle is parked; the accident type that the female driver does not give way according to the regulation is more easily generated; the drivers of both men and women are prone to the type of retrograde accidents.
Data analysis shows that: the accident type that the vehicle slides due to the fact that a low-speed gear is not hung and the parking brake is not pulled when the vehicle is parked is more prone to happen to owners of domestic vehicles; the car owner of the American series car is more likely to have the accident type of backing; the car owner of the Korean car is more likely to have rear-end collision accident type; the accident type of the owner of the daily automobile is mostly other types which are responsible by law; domestic vehicles are relatively easy to have traffic accidents and the types of the accidents are more complicated; while the German series vehicle is safer than other types of vehicles.
In summary: compared with the category, the male driver who drives a domestic vehicle and has the driving age of 8-12 years is more prone to accidents of vehicle sliding caused by the fact that a low-speed gear is not hung and a parking brake is not pulled during parking.
Claims (6)
1. A traffic accident cause analysis method based on a corresponding analysis model is characterized in that: comprises the following steps of (a) carrying out,
s1, inputting traffic violation data and traffic accident data, and associating the traffic violation data with the traffic accident data through driver identity information;
s2, correspondingly analyzing the traffic accident type and the traffic violation type, firstly, carrying out exploratory analysis, counting violation data by using a data perspective view, and screening violation sample data for subsequent analysis by a threshold value method; finding out accident crowds corresponding to each violation type and accident types generated by the accident crowds, and counting the proportion of each accident type in all accident types; secondly, selecting representative accident categories and accident types thereof for simple corresponding analysis;
s3, analyzing the traffic accident type, the driving age and sex of the driver and the multivariate correspondence of the driving vehicle; extracting the identity information of accident responsible parties from the accident data, and the corresponding four types of information of the accident type, the brand type of the hit-and-accident vehicle, the driving age of a driver and the gender of the driver; the method comprises the steps that t types of accidents, y types of driving vehicles, j types of driving ages and genders are in one-to-one correspondence, and x-t-y-j combinations are generated in total; and counting the number of people corresponding to each type of combination, and obtaining multiple corresponding relations by utilizing a multivariate corresponding analysis method in statistics.
2. The traffic accident cause analysis method based on the correspondence analysis model according to claim 1, wherein: in step S1, the traffic accident data has a feature vector CS ═ C, K, V ], where C is the accident occurrence type; k is personnel information including sex, driving age and accident liability attribution of a driver; v is vehicle brand information; the feature vector of the traffic violation data is WS ═ A, H, wherein A is the identity information of the violator, and H is the violation content of the violator.
3. The traffic accident cause analysis method based on the correspondence analysis model according to claim 1, wherein: in step S2, the exploratory analysis specifically includes:
s21, classifying accident drivers according to the types of the traffic accidents;
s22, screening the violation records of the accident driver from the traffic violation data sheet according to the accident driver information, and counting the number of various violations of each accident type driver;
s23, reserving the violation types with the violation times more than or equal to p according to the counted number of the violations, wherein p is a violation sample screening threshold value;
s24, calculating the ratio of the number of the various traffic violations corresponding to each type of traffic accident to the total number of the traffic violations of each type;
s25, the proportion of the drivers violating the traffic regulations is used as a vertical coordinate, the types of the drivers violating the traffic regulations are used as a horizontal coordinate, the proportion of various traffic regulations of the drivers of various traffic accidents is drawn in the coordinate system, the proportion of various traffic regulations of the drivers of various accident types is observed, and the accident and violation relation is initially explored.
4. A traffic accident cause analysis method based on a correspondence analysis model according to claim 3, characterized in that: specifically, in step S24, the calculation formula is as follows:
traffic accident a ═ a1，a2，…ai，…amIn which a isiThe traffic accident type is adopted, and m is the accident type sequence;
number of accident people K ═ K1，k2，…k3，…，kmIn which k isiFor the traffic accident type aiThe number of people;
violation type B ═ B1，b2，…bi，…，bn}，biIs a traffic violation type, and n is a violation type sequence;
number of persons violating the regulationskmbnThe traffic accident type is amOf the type bnThe number of times of (c);
total number of drivers with violation type m
Total number of violations of driver
Driver violation type proportion matrix
5. A traffic accident cause analysis method based on a correspondence analysis model according to claim 3, characterized in that: in the step S2, a representative accident category and an accident type thereof are selected for simple correspondence analysis, and the selected criteria are:
wherein,nthe difference value of the distribution proportion of drivers of various accident types in each type of violation type and the total accident type people number distribution proportion is 2 times; lambda is an abnormal threshold value corresponding to the accident category and the violation category; μ is the threshold number of people for each type of violation.
6. The traffic accident cause analysis method based on the correspondence analysis model according to any one of claims 1 to 5, wherein: the multivariate corresponding analysis of the driving age, the sex, the type of the driving vehicle and the type of the traffic accident in the step S3 comprises the following steps:
s31, classifying drivers of accident liability parties according to the types of the traffic accidents;
s32, simply counting the driving ages of the drivers to obtain the variation trend of the number of accidents of the drivers on the driving ages of the drivers;
s33, classifying the driving ages of the drivers of the accident liability parties in sections according to the change trend obtained in the step S32;
s34, classifying the vehicles according to the brand series of the vehicles;
s35, counting the driving ages, the sexes and the types of the driven vehicles of all drivers under each type of accident, and carrying out merged similar counting to obtain the total generated x-type (2 x t y j) combinations and the corresponding number of people under each type of combinations;
and S36, obtaining multiple corresponding relations by using a corresponding analysis method according to the result obtained in the step S35, and intuitively reflecting the relation between the variables in a form of the distance between the points in a two-dimensional space coordinate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610807054.8A CN106448158B (en) | 2016-09-06 | Traffic accidents reason analysis method based on correspondence analysis model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610807054.8A CN106448158B (en) | 2016-09-06 | Traffic accidents reason analysis method based on correspondence analysis model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106448158A true CN106448158A (en) | 2017-02-22 |
| CN106448158B CN106448158B (en) | 2019-07-16 |
Family
ID=
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107845262A (en) * | 2017-11-09 | 2018-03-27 | 山东浪潮云服务信息科技有限公司 | A kind of Predictive Methods of Road Accidents and device |
| CN108922170A (en) * | 2018-06-13 | 2018-11-30 | 同济大学 | A kind of Intersection Safety Evaluation Method based on electric police grasp shoot data |
| CN108986468A (en) * | 2018-08-01 | 2018-12-11 | 平安科技（深圳）有限公司 | Processing method, device, computer equipment and the computer storage medium of traffic accident |
| CN110717035A (en) * | 2018-07-11 | 2020-01-21 | 北京嘀嘀无限科技发展有限公司 | Accident rapid processing method, system and computer readable medium |
| CN111063056A (en) * | 2019-11-21 | 2020-04-24 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Aviation accident analysis method and device, computer equipment and storage medium |
| CN112989069A (en) * | 2021-05-10 | 2021-06-18 | 苏州博宇鑫交通科技有限公司 | Traffic violation analysis method based on knowledge graph and block chain |
| CN113256993A (en) * | 2021-07-15 | 2021-08-13 | 杭州华鲤智能科技有限公司 | Method for training and analyzing vehicle driving risk by model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662141B2 (en) * | 1995-01-13 | 2003-12-09 | Alan R. Kaub | Traffic safety prediction model |
| CN1889144A (en) * | 2006-07-24 | 2007-01-03 | 王成利 | Electronic detecting device for carrying out management to motor vehicles and drivers |
| CN102779430A (en) * | 2011-05-12 | 2012-11-14 | 德尔福技术有限公司 | Vision based night-time rear collision warning system, controller, and method of operating the same |
| CN103914945A (en) * | 2014-03-25 | 2014-07-09 | 刘业兴 | Monitoring and managing system and method for driver of motor vehicle |
| CN104331740A (en) * | 2013-07-22 | 2015-02-04 | 李娟� | Management device for motor vehicles and drivers |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662141B2 (en) * | 1995-01-13 | 2003-12-09 | Alan R. Kaub | Traffic safety prediction model |
| CN1889144A (en) * | 2006-07-24 | 2007-01-03 | 王成利 | Electronic detecting device for carrying out management to motor vehicles and drivers |
| CN102779430A (en) * | 2011-05-12 | 2012-11-14 | 德尔福技术有限公司 | Vision based night-time rear collision warning system, controller, and method of operating the same |
| CN104331740A (en) * | 2013-07-22 | 2015-02-04 | 李娟� | Management device for motor vehicles and drivers |
| CN103914945A (en) * | 2014-03-25 | 2014-07-09 | 刘业兴 | Monitoring and managing system and method for driver of motor vehicle |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107845262A (en) * | 2017-11-09 | 2018-03-27 | 山东浪潮云服务信息科技有限公司 | A kind of Predictive Methods of Road Accidents and device |
| CN108922170A (en) * | 2018-06-13 | 2018-11-30 | 同济大学 | A kind of Intersection Safety Evaluation Method based on electric police grasp shoot data |
| CN108922170B (en) * | 2018-06-13 | 2020-11-27 | 同济大学 | Intersection safety evaluation method based on electronic police snapshot data |
| CN110717035A (en) * | 2018-07-11 | 2020-01-21 | 北京嘀嘀无限科技发展有限公司 | Accident rapid processing method, system and computer readable medium |
| CN108986468A (en) * | 2018-08-01 | 2018-12-11 | 平安科技（深圳）有限公司 | Processing method, device, computer equipment and the computer storage medium of traffic accident |
| CN111063056A (en) * | 2019-11-21 | 2020-04-24 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Aviation accident analysis method and device, computer equipment and storage medium |
| CN111063056B (en) * | 2019-11-21 | 2021-09-07 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Aviation accident analysis method and device, computer equipment and storage medium |
| CN112989069A (en) * | 2021-05-10 | 2021-06-18 | 苏州博宇鑫交通科技有限公司 | Traffic violation analysis method based on knowledge graph and block chain |
| CN113256993A (en) * | 2021-07-15 | 2021-08-13 | 杭州华鲤智能科技有限公司 | Method for training and analyzing vehicle driving risk by model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Analysis of commercial truck drivers’ potentially dangerous driving behaviors based on 11-month digital tachograph data and multilevel modeling approach | |
| Feng et al. | Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data | |
| Yu et al. | A latent class approach for driver injury severity analysis in highway single vehicle crash considering unobserved heterogeneity and temporal influence | |
| Abdel-Aty et al. | Modeling rear-end collisions including the role of driver’s visibility and light truck vehicles using a nested logit structure | |
| Kweon et al. | Overall injury risk to different drivers: combining exposure, frequency, and severity models | |
| Quimby et al. | The Factors the Influence a Driver's Choice of Speed: A Questionnaire Study | |
| Abdel-Aty et al. | Exploring the overall and specific crash severity levels at signalized intersections | |
| Kovaceva et al. | Identification of aggressive driving from naturalistic data in car-following situations | |
| Cheng et al. | Development of a Chinese motorcycle rider driving violation questionnaire | |
| Rezapour Mashhadi et al. | Impact of traffic enforcement on traffic safety | |
| Ghazizadeh et al. | Text mining to decipher free-response consumer complaints: Insights from the NHTSA vehicle owner’s complaint database | |
| Li et al. | Crash Risk Prediction Model of Lane‐Change Behavior on Approaching Intersections | |
| Wilde | Accident countermeasures and behavioural compensation: The position of risk homeostasis theory | |
| Balkin et al. | Assessing the impact of speed-limit increases on fatal interstate crashes | |
| Wilson et al. | Young driver risk in relation to parents' retrospective driving record | |
| Lv et al. | The influence of different factors on right-turn distracted driving behavior at intersections using naturalistic driving study data | |
| Kwigizile et al. | Inconsistencies of ordered and unordered probability models for pedestrian injury severity | |
| Austin et al. | Effect of vehicle and crash factors on older occupants | |
| Joksch et al. | Vehicle aggressivity: Fleet characterization using traffic collision data | |
| Ramezani-Khansari et al. | Comparing the Effect of Age, Gender, and Desired Speed on Car‐Following Behavior by Using Driving Simulator | |
| Mekonnen | Risk factors of road traffic accidents and its severity in North Shewa Zone, Amhara Region, Ethiopia | |
| Abdel-Aty et al. | Configuration analysis of two-vehicle rear-end crashes | |
| Chen et al. | Initial Indications of Safety of Driverless Automated Driving Systems | |
| CN106448158A (en) | Corresponding analysis based traffic accident cause analyzing method | |
| Yuan et al. | Study of correlation between driver emergency measures and pedestrian injury based on combined driving simulator and computer simulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder |
Address after: 211100 No. 19 Suyuan Avenue, Jiangning Economic and Technological Development Zone, Nanjing City, Jiangsu Province Patentee after: JIANGSU ZHITONG TRAFFIC TECHNOLOGY Co.,Ltd. Address before: 210006, Qinhuai District, Jiangsu, Nanjing should be 388 days street, Chenguang 1865 Technology Creative Industry Park E10 building on the third floor Patentee before: JIANGSU ZHITONG TRAFFIC TECHNOLOGY Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder |