CN106448149B - Road traffic accident method for early warning - Google Patents
Road traffic accident method for early warning Download PDFInfo
- Publication number
- CN106448149B CN106448149B CN201610324213.9A CN201610324213A CN106448149B CN 106448149 B CN106448149 B CN 106448149B CN 201610324213 A CN201610324213 A CN 201610324213A CN 106448149 B CN106448149 B CN 106448149B
- Authority
- CN
- China
- Prior art keywords
- accident
- traffic
- driver
- type
- traffic accident
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 230000007613 environmental effect Effects 0.000 claims abstract description 18
- 238000003066 decision tree Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 10
- 208000027418 Wounds and injury Diseases 0.000 claims description 9
- 230000006378 damage Effects 0.000 claims description 9
- 208000014674 injury Diseases 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004040 coloring Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000011002 quantification Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000000540 analysis of variance Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000000750 progressive effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 3
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 229910052709 silver Inorganic materials 0.000 description 2
- 239000004332 silver Substances 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 208000019300 CLIPPERS Diseases 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 208000021930 chronic lymphocytic inflammation with pontine perivascular enhancement responsive to steroids Diseases 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012252 genetic analysis Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003694 hair properties Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003455 independent Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000010200 validation analysis Methods 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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Chemical & Material Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of road traffic accident method for early warning, passes through driver identification informational linkage traffic accident data and traffic violation data;By traffic accident, personnel characteristics are analyzed;The high-incidence personnel decision tree judgement of traffic accident is carried out, the accident pattern of the high-incidence personnel of accident and its generation is obtained;Environmental variance signature analysis is carried out, road type and processing table of grading are obtained, obtains accident high-incidence time, weather, vehicle color rule;By the high-incidence personnel of obtained accident and its accident pattern of generation, the high-incidence environmental variance of accident is corresponded to, the driving being directed in conjunction with driver's own characteristic and environmental aspect is reminded, while carrying out accident early warning.This method combines the high-risk driver of accident and the high-incidence section of accident, the influence of the environmental factors such as time, weather is added, to reach, the high-incidence driver's judgement of accident, accident pattern judgement occurs for driver, multiple accident section corresponds to specific driver's type, the purpose that accident personnel, accident pattern, accident section are organically combined.
Description
Technical field
The present invention relates to a kind of road traffic accident method for early warning.
Background technique
Traffic is the basis of urban economy development, is most active factor in economic society activity, and the life with resident ceases
Manner of breathing closes;Along with the rapid development of economic society, urbanization quickly propel and the rapid development of motorization degree, road
Transport need dramatically increases, and traffic safety problem is increasingly prominent;Therefore, the friendship that there is an urgent need to be excavated based on traffic big data
Interpreter's event genetic analysis, estimates accident group of people at high risk, place where the accident occurred point, the anticipation of time, weather;Realize traffic accident not
Hair is first prevented, locates fastly after hair, handles objective target;
Currently, viewing angle where in terms of research traffic accidents reason analysis, stressing object, respectively having not in research method
Together, but generally speaking all it is from driver, drives vehicle, road conditions, environmental factor in terms of these and analyze the accident origin cause of formation.
It is similar in content, most of result of study all lay particular emphasis in accident driver's age, the driving age, gender and injury system
Meter analysis, and for how the environmental factors such as place where the accident occurred point, time to be combined to carry out driver driving various dimensions, differentiation minute
Analysis, to accomplish targetedly to take measures to be not directed to.
Summary of the invention
The object of the present invention is to provide a kind of road traffic accident method for early warning, from traffic violation data and traffic accident number
Traffic Accidents Reasons Analyzed is obtained accordingly and in environmental variance and is applied in actual conditions;Traffic accident group of people at high risk is estimated, is handed over
Interpreter thus occurrence type anticipation, judge accident-prone road section improvement emphasis and and its priority level, when high-incidence to traffic accident
Between, the statistical law of weather etc..It realizes that traffic accident is not sent out and first prevents, locates fastly after hair, handling objective target solve how to combine
The environmental factors such as place where the accident occurred point, time carry out driver driving various dimensions, difference analysis, to accomplish targetedly to adopt
The problem of taking measure.
The technical solution of the invention is as follows:
A kind of road traffic accident method for early warning, comprising the following steps:
S1, pass through driver identification information association traffic accident data information table and traffic violation data information table;
S2, it is analyzed by traffic accident personnel characteristics, the traffic accident for obtaining driver and traffic offence are in quantity, type
Connection, obtain driver and possess influence of the different vehicle number to accident rate, obtain driver's age, driving age and accident rate
Relationship, obtain gender differences of the driver in accident responsibility side;
S3, judged by what S2 was obtained as a result, carrying out the high-incidence personnel decision tree of traffic accident, obtain the high-incidence personnel of accident and its
The accident pattern of generation;
S4, environmental variance signature analysis are occurred accident pattern ratio according to section, are obtained using the method for K central cluster
City road cluster result;Using the method for statistics, traffic injury time, weather, vehicle color are obtained on accident rate
Distribution situation;
S5, foundation S4 acquired results judge that section accident kind is multiple according to the cluster centre of each road segment classification after cluster
Miscellaneous degree, as the first sort by;Using section accident quantity as the second sort by, road type and processing grade are obtained
Table obtains accident high-incidence time, weather, vehicle color rule;
It is that S6, combining step S3, S5 are obtained as a result, by the high-incidence personnel of accident obtained in S3 and its accident class of generation
Type corresponds to the high-incidence environmental variance of the accident of step S5, the driving being directed in conjunction with driver's own characteristic and environmental aspect
It reminds, while carrying out accident early warning.
Further, step S1 specifically: the feature vector of the traffic violation data in traffic violation data information table is
As=[A, H], wherein A is lawbreaker's identity information, and H is the illicit content of lawbreaker;In traffic accident data information table
Traffic accident data feature vector be CS=[C, K, V], wherein C be accident information, including accident occurrence type, the time,
Place, weather, K are personal information, and including driver's age, gender, attribution of liability, driving age, the different vehicle number possessed, V is vehicle
Colouring information.
Further, step S2 specifically:
S21, using the method for Sperman rank correlation, examine driver occur traffic accident and traffic offence quantity,
Correlation in type;
S22, driver possess influence of the different vehicle number to accident rate and test, specifically: from driver's traffic thing
Therefore extract it in data and vehicle number different used in a lot of accidents occurs, utilize both Sperman rank correlation tests
Correlation and its coefficient magnitude;
S23, it tests for gender differences of the driver on accident responsibility, specifically: from driver's traffic accident data
After middle extraction driver generation accident, the ownership of responsible party and its gender information utilize χ2The method of inspection examines gender in accident
Otherness on responsible party is horizontal;
S24, the method using statistics obtain the rule of driver's age, driving age on accident rate.
Further, in step S21, the relational checking of traffic accident and traffic offence in quantity, type occurs for driver
Method are as follows:
S211, from traffic accident data information table and traffic violation data information table, it is corresponding simultaneously to count every driver's hair
The number of the number of raw traffic accident, traffic offence, using the quantitative correlation of both Sperman rank correlation tests and
Its coefficient magnitude;
S212, according to traffic accident type, classify accident personnel;
S213, the corresponding illegal information for haveing these accidents personnel in traffic violation data, count each accident pattern department
All kinds of illegal numbers of machine;
S214, according to all kinds of illegal quantity after statistics, give up the Criminal type that illegal quantity is less than p times;Obtain driver
Traffic accident type-driver's traffic offence type table occurs;
S215, each type traffic in traffic accident type-driver's traffic offence type table is occurred into for gained driver
The number of the corresponding various traffic offences of accident obtains driver and traffic thing occurs than the total degree of upper each type traffic offence
Therefore type-driver's traffic offence type ratio table;Calculation formula is as follows:
Traffic accident A={ a1, a2, a3…am, amFor traffic accident type;
Accident number K={ k1, k2, k3…km, kmFor traffic accident type a occursmNumber;
Criminal type B={ b1, b2, b3…bn, bnFor traffic offence type;
Illegal numberkmbnIt is a for driver's traffic accident typem, occur illegal
Type is bnNumber;
The illegal total degree of driver
Driver's Criminal type scaling matrices
S216, using the ratio of driver's traffic offence as ordinate, driver's traffic offence type be abscissa, by all types of friendships
The ratio for all kinds of traffic offences that the driver of interpreter's event is occurred is drawn in this coordinate system, all kinds of illegal by observation driver
Ratio, and then judge the type for the accident that it occurs.
Further, the rule of driver's age, driving age on accident rate is examined in the step S24, specifically:
S241, the age and driving age that accident responsibility side driver is extracted from driver's traffic accident data, count accident responsibility
Driver's age, the driving age of side are distributed the frequency, obtain responsible party driver and the frequency-driver's age of traffic accident, driving age frequency occurs
Table;
S242, the frequency is occurred using accident as ordinate, driver's age and driving age are abscissa, by each age, driving age section
The traffic accident frequency that driver occurs is plotted on the coordinate system, judges accident its driving age of high-incidence driver, age distribution section.
Further, the high-incidence personnel decision tree judgement of accident in step S3 specifically: according to conclusion in step S2, by traffic
The accident quantity of accident personnel, possesses different vehicle numbers, driving age, age information at illegal number, uses decision-tree model
CHAID algorithm carries out accident people at highest risk classification judgement, obtains the accident pattern of the high-incidence personnel of accident and its generation.
Further, in step S4, accident pattern ratio occurs according to section, obtains city road cluster result, step
Are as follows:
S411, in traffic accident data extract accident spot, accident pattern, accident quantity, screening accidents happened number be greater than
Equal to the high-incidence place of the accident of n times;
S412, ratio of the every a kind of traffic accident type of accident spot generation in all traffic accident types is calculated
Example, obtains the percentage table of all kinds of accident pattern quantity of accident spot-generation;
S413, using the method for K central cluster, city road is divided into 3 classes, obtain city road accident pattern cluster
Table.
Further, the step of traffic injury time is analyzed in step S4 are as follows:
S421, accident date of occurrence, time are extracted from casualty data, wherein the date is divided into working day, day off;
S422, with one hour for the period, count the time it is short in traffic accident number, obtain every day 24 hours
It is interior, accident ratio table hourly;
S423, using accident quantitative proportion as ordinate, using traffic injury time as abscissa, establish coordinate system, draw system
It counts in the period, the quantitative proportion that 24 hours accidents of different date types occur;It is compared by chart, obtains traffic accident
The relationship with date, time occurs.
Further, synoptic analysis step occurs for accident in step S4 are as follows:
S431, from traffic accident data extract incident when weather pattern;
S432, ratio distribution of all types of weather generation accident numbers in all accident numbers when incident is calculated;
S433, control group data, all types of weather when using incident, point in statistical time range, on all incident weather
Cloth ratio;
S434, the difference for calculating step S432 and step S433;Calculation formula is as follows:
In statistical time range, the number of all kinds of traffic accident weather appearancewmFor weather class
Type
Under all kinds of traffic accident weather, the traffic accident quantity of generationunFor traffic accident
Weather pattern;
S435, using percentage as ordinate, weather pattern be abscissa establish coordinate system, by step S432 and step S433
Difference draw in the coordinate system, intuitively show that accidents happened easy hair weather pattern.
Further, accident vehicle color analyzing step in step S4 are as follows:
S441, from casualty data extract accident vehicle colouring information, whether be vehicle information;
S442, ratio distribution of the vehicle color in all vehicle colors is calculated;
S443, ratio distribution of the non-vehicle color in all vehicle colors is calculated;
The percentage difference of S444, the percentage for calculating non-vehicle and vehicle;
S445, using vehicle color as abscissa, percentage is ordinate, establishes coordinate system, draws non-vehicle color
The differential chart of percentage and vehicle color percentage;Obtain rule of the vehicle color in traffic accident incidence.
Further, the high-incidence weather of accident, time, vehicle color rule are obtained in step S5, specifically: foundation S423,
The statistical graph that S435, S445 are obtained, quantification determine the high-incidence weather of accident, time, section and vehicle color rule.
The beneficial effects of the present invention are: this kind of road traffic accident method for early warning, high-incidence by the high-risk driver of accident and accident
Section combines, and the influence of the environmental factors such as time, weather is added, and to reach the high-incidence driver's judgement of accident, accident class occurs for driver
Type judgement, multiple accident section correspond to specific driver's type, the mesh that accident personnel, accident pattern, accident section are organically combined
, it is reminded to realize and have for the driving changed, while can be realized and traffic management department is allowed to carry out accident early warning;It being capable of conduct
Municipal administration department carries out the feeding reference of road pipe.
Detailed description of the invention
Fig. 1 is the flow diagram of road traffic accident of embodiment of the present invention method for early warning.
Fig. 2 is the schematic diagram of accident pattern and its corresponding Criminal type in embodiment.
Fig. 3 is the different types of vehicle (different vehicle rate) that possesses of driver showing to itself therefore the influence of frequency in embodiment
It is intended to.
Fig. 4 is accident responsibility side driver driving age distribution histogram in embodiment.
Fig. 5 is accident responsibility side driver age distribution histogram in embodiment.
Fig. 6 is that accident people at highest risk judges arborescence in embodiment.
Fig. 7 be embodiment in accident quantity the intraday distribution of different date types schematic diagram.
Fig. 8 is the schematic diagram of accident weather and normal weather Species distributing proportional difference in embodiment.
Fig. 9 is in embodiment by the schematic diagram of vehicle color percentage and vehicle color percentage difference.
Specific embodiment
The preferred embodiment that the invention will now be described in detail with reference to the accompanying drawings.
Embodiment
Data Analysis Services done in the method for embodiment mainly use EXCEL and IBM SPSS Statistics
22.0 statistical analysis softwares.It is related in the based process means such as the screening, comparison, PivotTables of EXCEL and SPSS
χ2The data statistical analysis methods such as inspection, clustering, Spearman rank correlation inspection, curve estimation, decision-tree model;
As shown in Figure 1, a kind of road traffic accident method for early warning, this method comprises the following steps.
S1, pass through driver identification information association traffic accident data information table and traffic violation data information table, traffic is disobeyed
The feature vector of method data is As=[A, H], and wherein A is lawbreaker's identity information, and H is the illicit content of lawbreaker.It hands over
The feature vector of logical casualty data is CS=[C, K, V], and wherein C is accident information, including accident occurrence type, the time, place,
Weather, K are personal information, and including driver's age, gender, attribution of liability, driving age, the different vehicle number possessed, V is vehicle color
Information.
Wherein, traffic violation data includes the illicit content of lawbreaker's identity information, lawbreaker;Traffic accident data
It include: accident occurrence type, time, place, weather, driver identification information, gender, attribution of liability, the driving age, possesses the age
Different vehicle number, vehicle color information.
Embodiment case data contains 18042 traffic accident data and 2014-in certain city first half of the year in 2015
61473 traffic violation datas between 2016.It is related to 70324 people of personnel, wherein belonging to accident responsibility side and 2014-2016
During illegal total 14436 people.Wherein casualty data mainly includes being related to accident personnel identity information, i.e., identification card number,
Weather conditions, accident hair on the day of gender, date of birth, first neck card date, place where the accident occurred point, traffic injury time, incident
Raw type, accident responsibility belong to situation, accident vehicle licence plate.Unlawful data include driver license number (identification card number), illegal activities,
Illicit content.By data secondary treatment by casualty data and unlawful data compare to obtain the illegal number of accident personnel and type,
Vehicle number different used in accident number and type, accident occurs for accident personnel.
S2, traffic accident personnel characteristics analysis examine driver's traffic accident using the method for Sperman rank correlation
With traffic offence quantitatively correlation, its correlation size is determined;Using the method for statistics, obtains driver's traffic accident and hand over
Lead to the illegal correlation in type;Using the method for Sperman rank correlation, driver is examined to possess different vehicle number to thing
Therefore the interdependence effects of incidence and its size;Use χ2The method of inspection obtains gender gap of the driver in accident responsibility side
It is different;Using the method for statistics, the rule of driver's age, driving age on accident rate is obtained.
In step s 2, information is demonstrate,proved by driver identification, is associated with traffic accident data information table and traffic violation data letter
After ceasing table, the accident frequency of accident responsibility side whithin a period of time and its illegal number for a longer period of time are obtained.?
Excel first row inputs driver identity card number, and secondary series inputs pilot accident's number, and third column input the driver and disobey
Method number imports table into IBM SPSS Statistics 22.0, using sperman rank correlation test, examines knot
Fruit is as shown in table 1:
1. accident frequency of table and illegal number Spearman rank correlation check table
In table 1, * * correlation is significant (double tails) in 0.01 rank.
As the result is shown: frequency and traffic offence number occur for traffic accident in the case where significance is 0.01 standard, progressive
Significance is 0, has rank correlation.
Being handled by Microsoft Excel by accident occurrence type is that of a sort driver and its merging of Criminal type data mention
It takes, obtains that its normal hair property Criminal type situation of the driver of certain class accident occurs;Generation quantity according to certain Criminal type is by 200
Kind unlawful data screens 20 kinds, and specific distribution situation is as shown in Figure 2.
Responsible driver and its violation of law discovery in two years in comparison accident, Criminal type concentrates on a few
Class;And it was found that different accident patterns corresponds to different illegal high-incidence types, that is, people's warp of certain a kind of traffic accident occurs
The illegal a certain seed type of perseverance;Fig. 2 shows the corresponding generation high-incidence traffic of 20 classes of driver that 9 class traffic accident types occur
Ratio shared by Criminal type;Such as its generation of the people of rear-end collision occurs " enter guided vehicle road, not by prescribed direction traveling
" this Criminal type just will be high (accounting 22.29%) than other Criminal types;Accident occurrence type is traffic signal violation
Driver, occur " operating motor vehicles on the road other than highway, city expressway not by provide lanes "
This accident pattern accounting is up to whether 60.66% can prejudge the accident class that may occur by driver's illegal activities
Type, targetedly to take precautions against traffic accident;In summary two kinds of research methods we can accomplish to prejudge in advance
The high-incidence accident pattern of accident group of people at high risk.
The different vehicle number that driver is driven in a lot of accidents also will affect traffic accident incidence.Utilize this Pierre
Graceful rank correlation test is as shown in table 2: frequency and traffic offence number, which occur, for traffic accident has significant correlation (sig=
0), and related coefficient=0.620, there is stronger correlation;
The different vehicle rate of table 2. and accident frequency Spearman rank correlation check table
In table 2, * * correlation is in significant (double tails) of 0.01 rank
Be according to the conclusion that table 2 obtains: occur traffic accident quantity >=2 time, accident vehicle owning rate substantially with
Accident number and increase.I.e. the different types of vehicle number of driver's driving is more, and traffic accident frequency is also higher;Specifically
Distribution is as shown in Figure 3: with the increase of traffic accident rate, everyone average different vehicle number (different vehicle rate) possessed is also increasing.
It is as follows to the inspection of accident responsibility side driver gender differences in step 2, people is related to 36082 traffic accidents first
The accident responsibility ownership of member is first simply counted with EXCEL, later with χ in spss2The method of inspection has been determined in accident
On responsible party, there is significant gender differences, obtain table 3, table 4;It is as shown in table 3: the progressive conspicuousness in Pearson came card side <
0.05;Therefore, there are significant gender differences in accident responsibility side;Specific difference condition is shown in Table 4.
3. gender * accident responsibility situation Chi-square Test table of table
In table 3, expected count that a.0 a cell (0.0%) has is less than 5.Minimum expected is counted as 1171.84.b.
Only 2x2 table calculates.
Table 4 is it can be seen that in traffic accident, and there are significant gender gap in accident responsibility side, progressive conspicuousness is 0;
Show as male in accident be responsible party probability it is bigger;And women is smaller for the probability of responsible party.
4. gender * accident responsibility situation crosstab of table
To age, driving age Excel statistical result such as Fig. 4 of accident responsibility side in step S2.
Can obtain from Fig. 4: the driving age, accident frequency increased with the growth of driving age in 1-12 years, reached by 12 years
To maximum value, thereafter, with the increase of driving age, accident frequency is constantly reduced;The high-incidence driving age section of accident be 8-15 years and
3-5 years.
From the point of view of accident responsible party's age distribution histogram 5, because the vehicle radix that different age group possesses is different,
Without important statistical significance.
S3, by S2 obtain as a result, using decision tree to the high-incidence personnel of traffic accident judge, obtain the high-incidence personnel of accident and
Its accident pattern occurred.
Decision tree analysis is carried out about the feature of accident group of people at high risk in above-mentioned steps S3, utilizes classification-tree in SPSS
Model, analysis result are as follows:
5. model of table abstract
Use CHAID (chi-squared automatic interaction detection, the inspection of card side's automatic interaction
Survey) decision Tree algorithms carry out tree growth, because CHAID can prevent data from excessively being applied and decision tree is allowed to stop segmentation, foundation
Measurement standard be classification in calculate node P value size, determine to determine whether to continue to divide with this, so not needing to do hedge clipper
Branch.Dependent variable is accident frequency in model, and assignment is as shown above;Independent variable is driver's age, the driving age, gender, disobeys
The vehicle number (different vehicle rate) of method number, driver under one's name.Using the method for cross validation to risk assessment validation verification;Model knot
Fruit shows: driver under one's name three vehicle number (different vehicle rate), illegal number, driver's driving age independents variable be selected into and by importance successively
Successively decrease;Remaining independent variable does not have notable contribution to model, is discharged from model automatically;
6. risk assessment of table and classification
In table 6, growth method: CHAID.Dependent variable: accident frequency: 0=is irresponsible, 1=accident responsibility 1-2
It is secondary;2=accident responsibility 3-5 times.
As can be seen that 0.283 evaluation of risk is indicated according to model (zero defects responsibility, accident from the risk assessment table of table 6
Responsibility 1-2 times, accident responsibility 3-5 times), prediction classification error rate is 28.3%;The result and evaluation of risk provided in classification chart
Unanimously;It is about 72% that classification chart, which shows that driver correctly classifies,;
Fig. 6 is the specific tree table of this decision-tree model, mainly the quantity and percentage of dependent variable case in each classification
Than;The prediction classification of available dependent variable from Fig. 6.It can see the vehicle number of driver under one's name, significantly affect traffic accident
The percentage of frequency;Therefore, first time classification indicators are exactly driver's vehicle number under one's name, in two different classifications, department
Machine accident proportion has apparent difference, and so on.Finally obtained result necessarily driver's accident after Complete Classification
Number differentiation is most obvious.
S4, environmental variance signature analysis are occurred accident pattern ratio according to section, are obtained using the method for K central cluster
City road cluster result;Using the method for statistics, traffic injury time, weather, vehicle color are obtained on accident rate
Distribution situation.Wherein, environmental variance includes the weather data for studying place where the accident occurred in the period.
S5, using S4's as a result, cluster centre according to each road segment classification after cluster, judges that section accident kind is complicated
Degree, as the first sort by;Using section accident quantity as the second sort by;Obtain road type and processing table of grading;
Obtain accident high-incidence time, weather, vehicle color rule.
For the accident spot clustering in step S4, the accident pattern that accident is occurred high-incidencely carries out EXCEL system
After meter, screening accidents happened occur quantity >=20 time place;According to the place accident occurrence type ratio, clustering is carried out,
As a result such as table 7.
Accident pattern cluster ANOVA analysis of variance table occurs high-incidencely for 7. accident of table
Can be obtained according to ANOVA analytical table: accident factor is " retrograde ", " close door ", " traffic signal violation "
These three types do not have a significant impact for accident spot cluster result.
The final cluster centre of accident pattern and cluster numbers occur high-incidencely for 8. accident of table
Can be obtained according to final cluster centre table 8: for all sections, accident pattern " knocking into the back " and " not by rule
Surely give way " it is its major accident occurrence type;The ratio of the accident pattern " knocking into the back " in section 1,2,3 is incremented by successively, with
The ratio of this while accident pattern " not giving way in regulation " is successively successively decreased;Main class occurs for accident for section 1 and 2
Type is " not giving way by regulation ";For section 3, it is " knocking into the back " that main Types, which occur, for accident;Therefore essence can be concentrated
Power solves the major accident occurrence type of certain a road section.
For comparing, the accident occurrence type in section 2 is more comprehensive available with respect to section 1 and 3;Therefore speculate the road in section 2
Road situation is more complicated, and difficulty of governance is relatively large, and the accident occurrence type in section 1 and section 3 is more single, so administering
Difficulty is relatively small;
According to accident pattern complexity, it is incremented by successively that section difficulty of governance is ordered as 1,3,2.It is sent out according still further to each place accident
City's part way traffic accident priority level that takes preventive measures is listed table 9 for traffic administration personnel reference by raw number.
The often property the sent out section classification of 9 Guiyang accident of table and priority level
Analysis to traffic injury time in step S4 counts on May 30,2 days to 2015 January in 2015 in embodiment
The intraday accident quantity of interior different date types, from figure 7 it can be seen that the distribution of the time of casualty on working day and day off is deposited
In significant difference, workaday accident occurrence in peak period between 8 points to 9 points, corresponds to working peak period in the morning;It is secondary
Peak appears in 17 points to 18 points or so, corresponds to next peak period;And accident period of right time festivals or holidays relatively disperses, and concentrates on 9
O'clock between 18 points.
Amounted to 151 days during this, accident 18151 occur and rises, International Labour Day, the Ching Ming Festival it is 6 days total, accident 858 occurs and rises;
Wherein time holiday accounts for total time 3.97%, and holiday accident quantity accounts for total quantity 4.73%;It therefore, is that accident is high-incidence during holiday
Time.
The analysis of weather occurs for accident in step S4, counts on May 30,2 days to 2015 January in 2015 in this example
Weather distribution situation when 18151 interior accidents occur, the weather profiles versus with during, the weather point when being occurred with accident
Cloth ratio subtracts practical weather distribution proportion, then is ranked up by size, obtains Fig. 8;Fig. 8 is shown, under preceding ten kinds of weather patterns,
Accident proportion is higher than the ratio that accident does not occur, and is gradually decremented to cloudy/shower, after such weather backward
Under weather, the ratio that accident does not occur is higher than the ratio that accident occurs and be gradually incremented to shower and turn the weather of shower and reach
Maximum value.
The analysis of vehicle color occurs for accident in step S4, counts May 2 days to 2015 January in 2015 in this example
36302 vehicles of 18151 accidents in 30 days reject bad data, are finally left 36060 vehicles, start including 18873
Thing vehicle and 17187 are related to 9 kinds of vehicle color by vehicle;We are subtracted with by the percent profile of vehicle color
Go the percent profile of vehicle color;It is as shown in Figure 9: in accident, white, silver color, red vehicle more start
Thing vehicle, less is by vehicle.And in reality, driver occur traffic accident whether with itself drive vehicle color without
It closes, and has some relationships with the color of opponent vehicle;So body color is white, the vehicle of silver color, red is relatively pacified
Entirely, it is not easy to be caused trouble.
The conclusion that S6, combining step S3, S5 are obtained is directed in conjunction with driver's own characteristic and its locating environmental aspect
The driving of change is reminded, while traffic management department being allowed to carry out accident early warning;The feeding ginseng of road pipe is carried out as municipal administration department
It examines.
Claims (9)
1. a kind of road traffic accident method for early warning, which comprises the following steps:
S1, pass through driver identification information association traffic accident data information table and traffic violation data information table;
S2, it is analyzed by traffic accident personnel characteristics, obtains the connection of the traffic accident and traffic offence of driver in quantity, type
System, obtains driver and possesses influence of the different vehicle number to accident rate, obtain the pass of driver's age, driving age and accident rate
System, obtains gender differences of the driver in accident responsibility side;Step S2 specifically:
S21, using the method for Sperman rank correlation, examine driver that traffic accident and traffic offence occurs in the phase of quantity
Guan Xing, using the method for simple statistics, inspection driver generation traffic accident type is contacted with driver's traffic offence type;Step
In S21, the relational checking method of traffic accident and traffic offence in quantity, type occurs for driver are as follows:
S211, from traffic accident data information table and traffic violation data information table, it is corresponding and count every driver and hand over
Interpreter thus number, traffic offence number, using the quantitative correlation of both Sperman rank correlation tests and its be
Number size;
S212, according to traffic accident type, classify accident personnel;
S213, the corresponding illegal information for haveing these accidents personnel in traffic violation data, it is each to count each accident pattern driver
The illegal number of class;
S214, according to all kinds of illegal quantity after statistics, give up the Criminal type that illegal quantity is less than p times;Obtain driver
Traffic accident type-driver's traffic offence type table;
S215, each type traffic accident in traffic accident type-driver's traffic offence type table is occurred into for gained driver
The number of corresponding various traffic offences obtains driver and traffic accident class occurs than the total degree of upper each type traffic offence
Type-driver's traffic offence type ratio table;Calculation formula is as follows:
Traffic accident A={ a1, a2, a3…am, amFor traffic accident type;
Accident number K={ k1, k2, k3…km, kmFor traffic accident type a occursmNumber;
Criminal type B={ b1, b2, b3…bn, bnFor traffic offence type;
Illegal numberkmbnIt is a for driver's traffic accident typem, Criminal type occurs
For bnNumber;
The illegal total degree of driver
Driver's Criminal type scaling matrices
S216, using the ratio of driver's traffic offence as ordinate, driver's traffic offence type be abscissa, by all types of traffic things
Therefore the ratio of all kinds of traffic offences that is occurred of driver draw in this coordinate system, pass through observation all kinds of illegal ratios of driver
Example, and then judge the type for the accident that it occurs;
S22, driver possess influence of the different vehicle number to accident rate and test, specifically: from driver's traffic accident number
According to middle extraction, vehicle number different used in a lot of accidents occurs in it, utilizes the phase of both Sperman rank correlation tests
Closing property and its coefficient magnitude;
S23, it tests for gender differences of the driver on accident responsibility, specifically: it is mentioned from driver's traffic accident data
After taking driver's generation accident, the ownership of responsible party and its gender information utilize x2The method of inspection examines gender in accident responsibility
Otherness in side is horizontal;
S24, the method using statistics obtain the rule of driver's age, driving age on accident rate;
S3, judged by what S2 was obtained as a result, carrying out the high-incidence personnel decision tree of traffic accident, obtain the high-incidence personnel of accident and its generation
Accident pattern;
S4, environmental variance signature analysis are occurred accident pattern ratio according to section, are obtained city using the method for K central cluster
Section cluster result;Using the method for statistics, obtains traffic injury time, weather, vehicle color and be distributed on accident rate
Situation;
S5, section accident kind complexity is judged according to the cluster centre of each road segment classification after cluster according to S4 acquired results
Degree, as the first sort by;Using section accident quantity as the second sort by, road type and processing table of grading are obtained,
Obtain accident high-incidence time, weather, vehicle color rule;
It is that S6, combining step S3, S5 are obtained as a result, by the high-incidence personnel of accident obtained in S3 and its accident pattern of generation, it is right
The high-incidence environmental variance of the accident of step S5 should be arrived, the driving being directed in conjunction with driver's own characteristic and environmental aspect is reminded,
Accident early warning is carried out simultaneously.
2. road traffic accident method for early warning as described in claim 1, which is characterized in that step S1 specifically: traffic offence
The feature vector of traffic violation data in data information table is As=[A, H], and wherein A is lawbreaker's identity information, and H is separated
The illicit content of method personnel;The feature vector of traffic accident data in traffic accident data information table is CS=[C, K, V],
Middle C is accident information, including accident occurrence type, time, place, weather, K are personal information, including driver identification information, year
Age, gender, attribution of liability, driving age, the different vehicle number possessed, V are vehicle color information.
3. road traffic accident method for early warning as described in claim 1, which is characterized in that examine driver in the step S24
The rule of age, driving age on accident rate, specifically:
S241, the age and driving age that accident responsibility side driver is extracted from driver's traffic accident data, statistics accident responsibility side
Driver's age, driving age are distributed the frequency, obtain responsible party driver and the frequency-driver's age of traffic accident, driving age frequency table occurs;
S242, the frequency is occurred using accident as ordinate, driver's age and driving age are abscissa, by each age, the driver of driving age section
The traffic accident frequency of generation is plotted on the coordinate system, judges accident its driving age of high-incidence driver, age distribution section.
4. road traffic accident method for early warning as described in any one of claims 1-3, it is characterised in that: accident is high in step S3
Hair personnel decision tree judgement specifically: according to conclusion in step S2, by the accident quantity of traffic accident personnel, illegal number, gather around
There are different vehicle numbers, driving age, age information, carries out accident people at highest risk classification using the CHAID algorithm of decision-tree model and sentence
It is disconnected, obtain the accident pattern of the high-incidence personnel of accident and its generation.
5. road traffic accident method for early warning as described in any one of claims 1-3, it is characterised in that: in step S4, foundation
Accident pattern ratio occurs for section, obtains city road cluster result, step are as follows:
S411, in traffic accident data extract accident spot, accident pattern, accident quantity, screening accidents happened number be more than or equal to n
The high-incidence place of secondary accident;
S412, ratio of the every a kind of traffic accident type of accident spot generation in all traffic accident types is calculated, obtained
To the percentage table of all kinds of accident pattern quantity of accident spot-generation;
S413, using the method for K central cluster, city road is divided into 3 classes, obtains city road accident pattern cluster table.
6. road traffic accident method for early warning as described in any one of claims 1-3, which is characterized in that accident is sent out in step S4
The step of raw time analysis are as follows:
S421, accident date of occurrence, time are extracted from casualty data, wherein the date is divided into working day, day off;
S422, with one hour for the period, count the time it is short in traffic accident number, obtain in 24 hours every day, often
The accident ratio table of hour;
S423, using accident quantitative proportion as ordinate, using traffic injury time as abscissa, coordinate system is established, when drawing statistics
Between in section, quantitative proportion that 24 hours accidents of different date types occur;It is compared by chart, obtains traffic accident
With the relationship on date, time.
7. road traffic accident method for early warning as claimed in claim 6, which is characterized in that weather point occurs for accident in step S4
Analyse step are as follows:
S431, from traffic accident data extract incident when weather pattern;
S432, ratio distribution of all types of weather generation accident numbers in all accident numbers when incident is calculated;
S433, control group data, all types of weather when using incident, the distribution ratio in statistical time range, on all incident weather
Example;
S434, the difference for calculating step S432 and step S433;Calculation formula is as follows:
In statistical time range, the number of all kinds of traffic accident weather appearancewmFor weather pattern
Under all kinds of traffic accident weather, the traffic accident quantity of generationunFor traffic accident weather
Type;
S435, using percentage as ordinate, weather pattern be abscissa establish coordinate system, by the difference of step S432 and step S433
Value is drawn in the coordinate system, intuitively show that accidents happened easy hair weather pattern.
8. road traffic accident method for early warning as claimed in claim 7, which is characterized in that accident vehicle color point in step S4
Analyse step are as follows:
S441, from traffic accident data extract accident vehicle colouring information, whether be vehicle information;
S442, ratio distribution of the vehicle color in all vehicle colors is calculated;
S443, ratio distribution of the non-vehicle color in all vehicle colors is calculated;
The percentage difference of S444, the percentage for calculating non-vehicle and vehicle;
S445, using vehicle color as abscissa, percentage is ordinate, establishes coordinate system, draws non-vehicle color percentage
Than the differential chart with vehicle color percentage;Obtain rule of the vehicle color in traffic accident incidence.
9. road traffic accident method for early warning as claimed in claim 8, it is characterised in that: obtain the high-incidence day of accident in step S5
Gas, time, vehicle color rule, specifically: according to the statistical graph that S423, S435, S445 are obtained, quantification determines accident height
Send out weather, time, section and vehicle color rule.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610324213.9A CN106448149B (en) | 2016-05-16 | 2016-05-16 | Road traffic accident method for early warning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610324213.9A CN106448149B (en) | 2016-05-16 | 2016-05-16 | Road traffic accident method for early warning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106448149A CN106448149A (en) | 2017-02-22 |
CN106448149B true CN106448149B (en) | 2019-08-09 |
Family
ID=58183873
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610324213.9A Active CN106448149B (en) | 2016-05-16 | 2016-05-16 | Road traffic accident method for early warning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106448149B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111009127A (en) * | 2019-12-24 | 2020-04-14 | 安徽虹湾信息技术有限公司 | Urban dynamic early warning system and method based on accident risk |
Families Citing this family (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122480A (en) * | 2017-05-04 | 2017-09-01 | 山东浪潮云服务信息科技有限公司 | A kind of cloud analysis method and system based on traffic violation data |
CN107798619A (en) * | 2017-05-05 | 2018-03-13 | 平安科技(深圳)有限公司 | Survey method for allocating tasks, system, server and medium |
CN108399739A (en) * | 2017-05-26 | 2018-08-14 | 中山大学 | A kind of emphasis supervision section choosing method |
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 |
CN108346317B (en) * | 2018-04-11 | 2020-07-14 | 北京汽车研究总院有限公司 | Road risk early warning method and device |
CN108647743B (en) * | 2018-06-25 | 2021-08-10 | 江苏智通交通科技有限公司 | Driver safety portrait system |
CN109285344B (en) * | 2018-06-25 | 2021-05-28 | 江苏智通交通科技有限公司 | Identification method and intelligent decision-making system for key monitoring objects of high-risk traffic personnel |
CN109063751B (en) * | 2018-07-16 | 2021-09-17 | 江苏智通交通科技有限公司 | Traffic high-risk personnel identification method based on gradient lifting decision tree algorithm |
CN109086808B (en) * | 2018-07-16 | 2021-09-17 | 江苏智通交通科技有限公司 | Traffic high-risk personnel identification method based on random forest algorithm |
CN109003450A (en) * | 2018-08-06 | 2018-12-14 | 江苏师范大学 | A kind of vehicle early warning method identified based on driver's age and gender |
CN109461302A (en) * | 2018-09-17 | 2019-03-12 | 北京交通大学 | A kind of data segmentation method based on Chi-square Test |
CN111656140B (en) | 2018-09-18 | 2023-08-18 | 北京嘀嘀无限科技发展有限公司 | Artificial intelligence system and method for predicting traffic accident place |
CN109598929B (en) * | 2018-11-26 | 2020-06-16 | 北京交通大学 | Multi-class traffic accident starting number prediction method |
CN109767597B (en) * | 2019-01-19 | 2021-05-11 | 跨越速运集团有限公司 | Vehicle accident early warning method and system |
CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
CN110322682A (en) * | 2019-04-30 | 2019-10-11 | 四川省气象服务中心 | Position calculating method, analysis method, method for early warning and its system of traffic accident |
CN110134715B (en) * | 2019-05-29 | 2021-07-06 | 精英数智科技股份有限公司 | Analysis method for coal mine accident concealed report |
CN110706517B (en) * | 2019-11-07 | 2020-08-28 | 深圳鼎然信息科技有限公司 | Intelligent safety early warning method, device and system for vehicle and storage medium |
CN110853357B (en) * | 2019-12-02 | 2022-02-11 | 华东交通大学 | Early warning control system and method for dangerous highway sections and construction areas |
CN112598905B (en) * | 2020-12-14 | 2021-10-26 | 苏州智能交通信息科技股份有限公司 | Passenger flow dynamic analysis early warning method, system and storage medium |
CN112732452B (en) * | 2021-03-30 | 2021-06-22 | 广州赛瑞科技股份有限公司 | Electric vehicle internet of things management and control method and system based on edge calculation |
CN113033110B (en) * | 2021-05-27 | 2021-10-29 | 深圳市城市交通规划设计研究中心股份有限公司 | Important area personnel emergency evacuation system and method based on traffic flow model |
CN113591824B (en) * | 2021-10-08 | 2022-02-01 | 浙江力嘉电子科技有限公司 | Traffic violation data entry anomaly detection method and device |
CN113920732B (en) * | 2021-10-11 | 2023-02-28 | 长安大学 | Road traffic accident risk early warning method for specific driving crowd |
CN114283581A (en) * | 2021-12-27 | 2022-04-05 | 安徽达尔智能控制系统股份有限公司 | Rural road safety comprehensive management method and system |
CN114582132B (en) * | 2022-05-05 | 2022-08-09 | 四川九通智路科技有限公司 | Vehicle collision detection early warning system and method based on machine vision |
CN117350537A (en) * | 2023-09-15 | 2024-01-05 | 国投曹妃甸港口有限公司 | Production safety emergency command method and system based on risk prediction |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008129817A (en) * | 2006-11-20 | 2008-06-05 | Aisin Aw Co Ltd | Running condition determination method and running condition determination device |
CN103366551A (en) * | 2012-04-05 | 2013-10-23 | 郭海锋 | Road traffic safety evaluation method |
CN104680841A (en) * | 2015-03-12 | 2015-06-03 | 厦门奥声科技有限公司 | Driving early warning method |
CN104809916A (en) * | 2015-04-21 | 2015-07-29 | 重庆大学 | Mountain road curve vehicle crossing early warning method based on videos |
CN104978853A (en) * | 2014-04-01 | 2015-10-14 | 中国移动通信集团公司 | Road traffic safety evaluating method and system |
-
2016
- 2016-05-16 CN CN201610324213.9A patent/CN106448149B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008129817A (en) * | 2006-11-20 | 2008-06-05 | Aisin Aw Co Ltd | Running condition determination method and running condition determination device |
CN103366551A (en) * | 2012-04-05 | 2013-10-23 | 郭海锋 | Road traffic safety evaluation method |
CN104978853A (en) * | 2014-04-01 | 2015-10-14 | 中国移动通信集团公司 | Road traffic safety evaluating method and system |
CN104680841A (en) * | 2015-03-12 | 2015-06-03 | 厦门奥声科技有限公司 | Driving early warning method |
CN104809916A (en) * | 2015-04-21 | 2015-07-29 | 重庆大学 | Mountain road curve vehicle crossing early warning method based on videos |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111009127A (en) * | 2019-12-24 | 2020-04-14 | 安徽虹湾信息技术有限公司 | Urban dynamic early warning system and method based on accident risk |
Also Published As
Publication number | Publication date |
---|---|
CN106448149A (en) | 2017-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106448149B (en) | Road traffic accident method for early warning | |
CN111462488B (en) | Intersection safety risk assessment method based on deep convolutional neural network and intersection behavior characteristic model | |
Basso et al. | Real-time crash prediction in an urban expressway using disaggregated data | |
CN105303197B (en) | A kind of vehicle follow the bus safety automation appraisal procedure based on machine learning | |
CN103049740B (en) | Fatigue state detection method based on video image and device | |
CN108427757A (en) | Emphasis vehicle pass-through method for early warning based on correlation rule and supervisory systems | |
CN110866677A (en) | Driver relative risk evaluation method based on benchmark analysis | |
CN111242484B (en) | Vehicle risk comprehensive evaluation method based on transition probability | |
CN108596409A (en) | The method for promoting traffic hazard personnel's accident risk prediction precision | |
CN106157135A (en) | Antifraud system and method based on Application on Voiceprint Recognition Sex, Age | |
CN109598931A (en) | Group based on traffic safety risk divides and difference analysis method and system | |
CN103065121A (en) | Engine driver state monitoring method and device based on video face analysis | |
CN109191828B (en) | Traffic participant accident risk prediction method based on ensemble learning | |
CN111401414B (en) | Natural driving data-based dangerous scene extraction and classification method | |
CN109086808A (en) | Traffic high-risk personnel recognition methods based on random forests algorithm | |
Simončič | Road accidents in Slovenia involving a pedestrian, cyclist or motorcyclist and a car | |
CN114168646A (en) | Multi-data fusion-based commercial vehicle transportation monitoring method and system | |
CN110901385A (en) | Active speed limiting method based on fatigue state of driver | |
CN115713858A (en) | Intelligent traffic operation management and control system based on traffic big data | |
Wang et al. | Vision-based highway traffic accident detection | |
Ncube et al. | Road accidents fatalities trends and safety management in South Africa | |
CN116153063A (en) | Traffic safety hidden danger early warning method and system | |
CN109272412A (en) | A kind of vehicle insurance Claims Resolution air control maintenance system | |
CN110263074A (en) | A method of illegal accident corresponding relationship is excavated based on LLE and K averaging method | |
Hossain et al. | Data mining approach to explore emergency vehicle crash patterns: A comparative study of crash severity in emergency and non-emergency response modes |
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 | ||
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. |