CN107644532A - A kind of traffic violation menace level Forecasting Methodology based on Bayesian network - Google Patents
A kind of traffic violation menace level Forecasting Methodology based on Bayesian network Download PDFInfo
- Publication number
- CN107644532A CN107644532A CN201710855633.4A CN201710855633A CN107644532A CN 107644532 A CN107644532 A CN 107644532A CN 201710855633 A CN201710855633 A CN 201710855633A CN 107644532 A CN107644532 A CN 107644532A
- Authority
- CN
- China
- Prior art keywords
- represent
- mrow
- traffic violation
- menace level
- year
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 6
- 206010039203 Road traffic accident Diseases 0.000 abstract description 17
- 230000002265 prevention Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 abstract description 2
- 230000014509 gene expression Effects 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 125000002015 acyclic group Chemical group 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Cosmetics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of traffic violation menace level Forecasting Methodology based on Bayesian network, this method carries out the oriented diagram description based on network structure, the incidence relation and influence degree between each key element are portrayed using with the directed acyclic graph in network structure, its each key element is expressed with node variable, the incidence relation between each key element is expressed with the directed edge between node, the influence degree between each key element is described with conditional probability table;The Bayesian network model that the inventive method is established can preferably predict the menace level of traffic violation, and its prediction result can be applicable in traffic violation management and traffic accident prevention.
Description
Technical field
The present invention relates to traffic psychology field, more particularly, to a kind of traffic violation based on Bayesian network
Menace level Forecasting Methodology.
Background technology
In the last few years, China's car ownership rapidly increased, and car ownership in 2015 is up to 2.79 hundred million.Meanwhile machine
The illegal phenomenon of motor-car driver is universal, according to statistics, national investigation traffic violation 4.42 hundred million altogether in 2015, nearly 90%
Personal injury traffic accident is caused by illegal activities.
Domestic and foreign scholars have carried out some researchs for traffic accident:Ma Zhuanlin et al. returns mould with accumulation Logistic
Type is studied the influence factor of the traffic accident order of severity;Li Juan et al. have studied based on improved BP neural network mould
The method that number, death toll and the number of injured people that traffic accident occurs type are predicted;Qin little Hu etc. uses Bayesian network
The influence that traffic accident occurs the factors such as network scale-model investigation weather, period, speed;Abroad, Karacasu et al. is transported
The reason for traffic accident occurs is analyzed with logistics models;Hu S R et al. are with cumulative logistic regression model to railway crossing
The seriousness that traffic accident occurs is studied;FU H et al. are by studying the pass of people, car, road and environment and traffic accident
System, the generation of traffic accident is predicted with BP neural network model;Mehmet et al. is to BP neural network and some other side
Method prediction traffic accident compares;De OJ et al. pass through to road information, weather with Bayesian network model
The reason for traffic accident occurs is studied in the analysis of information and driver information etc.;Mujalli et al. is by studying thing
Therefore the factor such as type, age, weather conditions, sex, illumination, number of injured people and involved occupant builds Bayesian network,
Predict the order of severity of traffic accident;Davis etc. have studied application of the Bayesian network in terms of traffic accident reproduction.So
And traffic violation is used as one of the main reason for causing traffic accident, but few people go to study.
Traffic violation is influenceed by many factors.Guangzhou annual traffic violation data in 2015 is chosen, is obtained
Data 4775690, valid data 4623665 are obtained by processing.Based on data to driver's sex, the age, the driving age, when
Between, the factor such as type of vehicle and car plate ownership place and traffic violation menace level analyzed, find these factors with
Traffic violation menace level has certain correlation.A traffic violation menace level forecast model is established, can be with
Reference is provided for traffic violation management and traffic accident prevention.
The content of the invention
The present invention provides a kind of friendship of the menace level based on Bayesian network that can preferably predict traffic violation
Logical illegal activities menace level Forecasting Methodology.
In order to reach above-mentioned technique effect, technical scheme is as follows:
A kind of traffic violation menace level Forecasting Methodology based on Bayesian network, comprises the following steps:
S1:Determine the variable of Bayesian model;
S2:Establish Bayesian model and train the model.
Further, the detailed process of the step S1 is:
Return according to driver's sex, age, driving age, illegal incidents time of origin section, illegal vehicle type and vehicle
The analysis of possession and traffic offence menace level, determines variable of these factors as Bayesian model, a training set and
Parameter in training set is represented by:
X={ G, A, D, T, W, V, O, L } (1)
Wherein:
G={ 0,1 } represents sex, and 0 represents women, and 1 represents male;
A={ 0,1,2,3,4,5 } represents the age, wherein 0 expression 18-20 year, 1 expression 21-30 year, 2 expressions 31-40 year, 3
Represent 41-50 year, 4 represent 51-60 year, 5 represent 61 years old and more than;
D={ 0,1,2,3,4,5 } represents the driving age, wherein 0 represents 0-3,1 represents 4-6, and 2 represent 7-10, and 3 represent
10-15,4 represent 16-20,5 represent 21 years and more than;
T={ 0,1,2 } represents illegal incidents time of origin section, wherein { 0,1,2, } represent that low frequency, intermediate frequency, height occurs respectively
The period of the traffic offence event of frequency;
V={ 0,1,2 } represents type of vehicle, wherein { 0,1,2,3 } represents other vehicles, large car, car respectively;
O={ 0,1 } represents car plate ownership place, wherein 0 represents local, 1 represents non-local;
L={ 1,2,3 } represents illegal activities grade, wherein 1 represents slight, 2 represent general, and 3 represent great.
Further, the detailed process of the step S2 is:
According to dependency relation between each model variable, it is pre- to establish the traffic violation menace level based on Bayesian network
Survey model:
P (L | G, A, D, T, V, O)=P (L | h)=P (h | L) * P (L)/P (h) P (L | h) (2)
Assume to obtain using maximum posteriori:
P (L | h)=P (h | L) * P (L) (3)
Make 6 conditions separate, (3) formula can be write as:
Compared with prior art, the beneficial effect of technical solution of the present invention is:
The inventive method carries out the oriented diagram description based on network structure, using with the directed acyclic in network structure
Figure portrays the incidence relation and influence degree between each key element, with node variable expresses its each key element, with node it
Between directed edge express the incidence relation between each key element, the influence degree between each key element described with conditional probability table;
The Bayesian network model that the inventive method is established can preferably predict the menace level of traffic violation, its prediction result
It can be applicable in traffic violation management and traffic accident prevention.
Brief description of the drawings
Fig. 1 is the traffic violation menace level forecast model structural representation of the present invention.
Embodiment
Accompanying drawing being given for example only property explanation, it is impossible to be interpreted as the limitation to this patent;
In order to more preferably illustrate the present embodiment, some parts of accompanying drawing have omission, zoomed in or out, and do not represent actual product
Size;
To those skilled in the art, it is to be appreciated that some known features and its explanation, which may be omitted, in accompanying drawing
's.
Technical scheme is described further with reference to the accompanying drawings and examples.
Embodiment 1
A kind of traffic violation menace level Forecasting Methodology based on Bayesian network, comprises the following steps:
S1:Determine the variable of Bayesian model;
S2:Establish Bayesian model and train the model.
Further, the detailed process of the step S1 is:
Return according to driver's sex, age, driving age, illegal incidents time of origin section, illegal vehicle type and vehicle
The analysis of possession and traffic offence menace level, determines variable of these factors as Bayesian model, a training set and
Parameter in training set is represented by, as shown in Figure 1:
X={ G, A, D, T, W, V, O, L } (1)
Wherein:
G={ 0,1 } represents sex, and 0 represents women, and 1 represents male;
A={ 0,1,2,3,4,5 } represents the age, wherein 0 expression 18-20 year, 1 expression 21-30 year, 2 expressions 31-40 year, 3
Represent 41-50 year, 4 represent 51-60 year, 5 represent 61 years old and more than;
D={ 0,1,2,3,4,5 } represents the driving age, wherein 0 represents 0-3,1 represents 4-6, and 2 represent 7-10, and 3 represent
10-15,4 represent 16-20,5 represent 21 years and more than;
T={ 0,1,2 } represents illegal incidents time of origin section, wherein { 0,1,2, } represent that low frequency, intermediate frequency, height occurs respectively
The period of the traffic offence event of frequency;
V={ 0,1,2 } represents type of vehicle, wherein { 0,1,2,3 } represents other vehicles, large car, car respectively;
O={ 0,1 } represents car plate ownership place, wherein 0 represents local, 1 represents non-local;
L={ 1,2,3 } represents illegal activities grade, wherein 1 represents slight, 2 represent general, and 3 represent great.
Further, the detailed process of the step S2 is:
According to dependency relation between each model variable, it is pre- to establish the traffic violation menace level based on Bayesian network
Survey model:
P (L | G, A, D, T, V, O)=P (L | h)=P (h | L) * P (L)/P (h) P (L | h) (2)
Assume to obtain using maximum posteriori:
P (L | h)=P (h | L) * P (L) (3)
Make 6 conditions separate, (3) formula can be write as:
From formula (4), each grade prior probability P (h | L) is calculated, it should be understood that the prior probability of each factor in road.Selection has
Training set of 1,000,000 datas in data as Bayesian network model is imitated, the traffic violation order of severity is calculated in advance
Method is trained.By being trained to obtain required dependent probability distribution as shown in table 1 to the data set.
The traffic offence factor prior probability of table 1
After known prior probability, the basic think of of traffic violation order of severity prediction is carried out with Bayesian network model
Road:
For an any given group observations G=G1, A=A1, D=D1, T=T1, V=V1, O=O1, can calculate respectively
Go out L=L1, L=L2, L=L3Posterior probability, i.e.,:
P(L1|G1,A1,D1,T1,V1,O1);
P(L2|G1,A1,D1,T1,V1,O1);
P(L3|G1,A1,D1,T1,V1,O1)。
The respective posterior probability values of Three Estate can be calculated according to formula (4), compare its size, wherein posterior probability is maximum
A grade be predict traffic violation menace level.
The present invention and the precision of prediction contrast experiment of accumulation Logistics models and neural network model:
1,000,000 datas used in utilization example 1 are demarcated to accumulation Logistics models and neural network model and (used
SPSS statistical analysis softwares).In Guangzhou 2012-2016 traffic violation data, 10,000 are employed at random every year
(being taken outside training set data for 2015) traffic violation data is come to Bayesian network model, accumulation as test set
The precision of prediction of Logistics models and neural network model is tested and compared.
The precision of prediction of table 2 contrasts
As shown in Table 2, the accuracy rate that the traffic violation order of severity is predicted is reached with Bayesian network model
More than 0.7, generally higher than accumulate Logistics models and neural network model, this absolutely proved Bayesian network model with
The prediction of traffic violation menace level has higher compatible degree.
It is if the factors such as the psychology of driver, physiological status, weather and condition of road surface is serious to traffic violation
The influence of grade is taken into account, and the precision of Bayesian model will further improve.On the whole, predicted with Bayesian network model
The order of severity of traffic violation is feasible.
Same or analogous label corresponds to same or analogous part;
Position relationship is used for being given for example only property explanation described in accompanying drawing, it is impossible to is interpreted as the limitation to this patent;
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not pair
The restriction of embodiments of the present invention.For those of ordinary skill in the field, may be used also on the basis of the above description
To make other changes in different forms.There is no necessity and possibility to exhaust all the enbodiments.It is all this
All any modification, equivalent and improvement made within the spirit and principle of invention etc., should be included in the claims in the present invention
Protection domain within.
Claims (3)
1. a kind of traffic violation menace level Forecasting Methodology based on Bayesian network, it is characterised in that including following step
Suddenly:
S1:Determine the variable of Bayesian model;
S2:Establish Bayesian model and train the model.
2. the traffic violation menace level Forecasting Methodology according to claim 1 based on Bayesian network, its feature
It is, the detailed process of the step S1 is:
According to driver's sex, age, driving age, illegal incidents time of origin section, illegal vehicle type and vehicle ownership place
With the analysis of traffic offence menace level, variable of these factors as Bayesian model, a training set and training are determined
The parameter of concentration is represented by:
X={ G, A, D, T, W, V, O, L } (1)
Wherein:
G={ 0,1 } represents sex, and 0 represents women, and 1 represents male;
A={ 0,1,2,3,4,5 } represents the age, wherein 0 represents 18-20 year, 1 represents 21-30 year, and 2 represent 31-40 year, and 3 represent
41-50 year, 4 represent 51-60 year, 5 represent 61 years old and more than;
D={ 0,1,2,3,4,5 } represents the driving age, wherein 0 represents 0-3,1 represents 4-6, and 2 represent 7-10, and 3 represent 10-15
Year, 4 represent 16-20,5 represent 21 years and more than;
T={ 0,1,2 } represents illegal incidents time of origin section, wherein { 0,1,2, } represent that low frequency, intermediate frequency, high frequency occurs respectively
The period of traffic offence event;
V={ 0,1,2 } represents type of vehicle, wherein { 0,1,2,3 } represents other vehicles, large car, car respectively;
O={ 0,1 } represents car plate ownership place, wherein 0 represents local, 1 represents non-local;
L={ 1,2,3 } represents illegal activities grade, wherein 1 represents slight, 2 represent general, and 3 represent great.
3. the traffic violation menace level Forecasting Methodology according to claim 1 based on Bayesian network, its feature
It is, the detailed process of the step S2 is:
According to dependency relation between each model variable, the traffic violation menace level prediction mould based on Bayesian network is established
Type:
P (L | G, A, D, T, V, O)=P (L | h)=P (h | L) * P (L)/P (h) P (L | h) (2)
Assume to obtain using maximum posteriori:
P (L | h)=P (h | L) * P (L) (3)
Make 6 conditions separate, (3) formula can be write as:
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>L</mi>
<mo>|</mo>
<mi>h</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>L</mi>
<mo>)</mo>
</mrow>
<msubsup>
<mo>&Pi;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>6</mn>
</msubsup>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>h</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mi>L</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710855633.4A CN107644532A (en) | 2017-09-20 | 2017-09-20 | A kind of traffic violation menace level Forecasting Methodology based on Bayesian network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710855633.4A CN107644532A (en) | 2017-09-20 | 2017-09-20 | A kind of traffic violation menace level Forecasting Methodology based on Bayesian network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107644532A true CN107644532A (en) | 2018-01-30 |
Family
ID=61113859
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710855633.4A Pending CN107644532A (en) | 2017-09-20 | 2017-09-20 | A kind of traffic violation menace level Forecasting Methodology based on Bayesian network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107644532A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108417033A (en) * | 2018-03-23 | 2018-08-17 | 四川高路交通信息工程有限公司 | Expressway traffic accident analysis prediction technique based on multi-dimensional factors |
CN109344896A (en) * | 2018-09-29 | 2019-02-15 | 江苏大学 | A kind of driver's condition of the injury grade forecast algorithm |
CN109697512A (en) * | 2018-12-26 | 2019-04-30 | 东南大学 | Personal data analysis method and computer storage medium based on Bayesian network |
CN109816985A (en) * | 2019-03-27 | 2019-05-28 | 常州璨禾辰信息科技有限公司 | A kind of urban traffic conditions method for early warning based on bayes algorithm |
CN110689642A (en) * | 2019-09-18 | 2020-01-14 | 山东大学 | Abnormal driving distinguishing method and system based on vehicle-mounted OBD data and probability statistics |
CN112016735A (en) * | 2020-07-17 | 2020-12-01 | 厦门大学 | Patrol route planning method and system based on traffic violation hotspot prediction and readable storage medium |
CN113591824A (en) * | 2021-10-08 | 2021-11-02 | 浙江力嘉电子科技有限公司 | Traffic violation data entry anomaly detection method and device |
CN114446045A (en) * | 2021-09-14 | 2022-05-06 | 武汉长江通信智联技术有限公司 | Method for studying and judging illegal transportation behaviors of vehicles on highway in epidemic situation period |
CN114595997A (en) * | 2022-03-21 | 2022-06-07 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
CN115830873A (en) * | 2023-01-10 | 2023-03-21 | 西南交通大学 | Urban road traffic event classification method, device, equipment and readable storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101236695A (en) * | 2008-03-05 | 2008-08-06 | 中科院嘉兴中心微系统所分中心 | Driver status estimation system based on vehicle mounted sensor network |
CN101976501A (en) * | 2010-10-29 | 2011-02-16 | 天津市市政工程设计研究院 | Principal component analysis and neural network based port road safety prediction method |
CN102231231A (en) * | 2011-06-16 | 2011-11-02 | 同济大学 | Area road network traffic safety situation early warning system and method thereof |
CN104751642A (en) * | 2015-03-11 | 2015-07-01 | 同济大学 | Real-time estimating method for high-grade road traffic flow running risks |
CN104809879A (en) * | 2015-05-14 | 2015-07-29 | 重庆大学 | Expressway road traffic state estimation method based on dynamic Bayesian network |
CN105045975A (en) * | 2015-06-30 | 2015-11-11 | 北京师范大学 | Bayesian network model based risk evaluation method for road transportation accident |
US9424745B1 (en) * | 2013-11-11 | 2016-08-23 | Emc Corporation | Predicting traffic patterns |
US20160364983A1 (en) * | 2015-06-11 | 2016-12-15 | Here Global B.V. | Traffic Speed Modeling |
-
2017
- 2017-09-20 CN CN201710855633.4A patent/CN107644532A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101236695A (en) * | 2008-03-05 | 2008-08-06 | 中科院嘉兴中心微系统所分中心 | Driver status estimation system based on vehicle mounted sensor network |
CN101976501A (en) * | 2010-10-29 | 2011-02-16 | 天津市市政工程设计研究院 | Principal component analysis and neural network based port road safety prediction method |
CN102231231A (en) * | 2011-06-16 | 2011-11-02 | 同济大学 | Area road network traffic safety situation early warning system and method thereof |
US9424745B1 (en) * | 2013-11-11 | 2016-08-23 | Emc Corporation | Predicting traffic patterns |
CN104751642A (en) * | 2015-03-11 | 2015-07-01 | 同济大学 | Real-time estimating method for high-grade road traffic flow running risks |
CN104809879A (en) * | 2015-05-14 | 2015-07-29 | 重庆大学 | Expressway road traffic state estimation method based on dynamic Bayesian network |
US20160364983A1 (en) * | 2015-06-11 | 2016-12-15 | Here Global B.V. | Traffic Speed Modeling |
CN105045975A (en) * | 2015-06-30 | 2015-11-11 | 北京师范大学 | Bayesian network model based risk evaluation method for road transportation accident |
Non-Patent Citations (3)
Title |
---|
王冲主编: "《现代信息检索技术基本原理教程》", 30 November 2013, 西安:西安电子科技大学出版社 * |
胡可云,田凤占,黄厚宽编著: "《数据挖掘理论与应用》", 30 April 2008, 北京:北京交通大学出版社 * |
蒋良孝,李超群编: "《贝叶斯网络分类器 算法与应用》", 31 December 2015, 武汉:中国地质大学出版社 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108417033A (en) * | 2018-03-23 | 2018-08-17 | 四川高路交通信息工程有限公司 | Expressway traffic accident analysis prediction technique based on multi-dimensional factors |
CN109344896A (en) * | 2018-09-29 | 2019-02-15 | 江苏大学 | A kind of driver's condition of the injury grade forecast algorithm |
CN109697512B (en) * | 2018-12-26 | 2023-10-27 | 东南大学 | Personal data analysis method based on Bayesian network and computer storage medium |
CN109697512A (en) * | 2018-12-26 | 2019-04-30 | 东南大学 | Personal data analysis method and computer storage medium based on Bayesian network |
CN109816985A (en) * | 2019-03-27 | 2019-05-28 | 常州璨禾辰信息科技有限公司 | A kind of urban traffic conditions method for early warning based on bayes algorithm |
CN110689642A (en) * | 2019-09-18 | 2020-01-14 | 山东大学 | Abnormal driving distinguishing method and system based on vehicle-mounted OBD data and probability statistics |
CN110689642B (en) * | 2019-09-18 | 2020-10-09 | 山东大学 | Abnormal driving distinguishing method and system based on vehicle-mounted OBD data and probability statistics |
CN112016735A (en) * | 2020-07-17 | 2020-12-01 | 厦门大学 | Patrol route planning method and system based on traffic violation hotspot prediction and readable storage medium |
CN112016735B (en) * | 2020-07-17 | 2023-03-28 | 厦门大学 | Patrol route planning method and system based on traffic violation hotspot prediction and readable storage medium |
CN114446045A (en) * | 2021-09-14 | 2022-05-06 | 武汉长江通信智联技术有限公司 | Method for studying and judging illegal transportation behaviors of vehicles on highway in epidemic situation period |
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 |
CN113591824A (en) * | 2021-10-08 | 2021-11-02 | 浙江力嘉电子科技有限公司 | Traffic violation data entry anomaly detection method and device |
CN114595997A (en) * | 2022-03-21 | 2022-06-07 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
CN115830873A (en) * | 2023-01-10 | 2023-03-21 | 西南交通大学 | Urban road traffic event classification method, device, equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107644532A (en) | A kind of traffic violation menace level Forecasting Methodology based on Bayesian network | |
Ahmed et al. | Effects of truck traffic on crash injury severity on rural highways in Wyoming using Bayesian binary logit models | |
Zheng et al. | Commercial truck crash injury severity analysis using gradient boosting data mining model | |
Cafiso et al. | Using the Delphi method to evaluate opinions of public transport managers on bus safety | |
Mirabadi et al. | Application of association rules in Iranian Railways (RAI) accident data analysis | |
Hong et al. | Discovering insightful rules among truck crash characteristics using apriori algorithm | |
Mooradian et al. | Analysis of driver and passenger crash injury severity using partial proportional odds models | |
Dai et al. | Driving cycles: a new cycle-building method that better represents real-world emissions | |
Kuşkapan et al. | Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms | |
Wen et al. | The effects of traffic composition on freeway crash frequency by injury severity: A Bayesian multivariate spatial modeling approach | |
Channamallu et al. | Impact of Autonomous Vehicles on Traffic Crashes in Comparison with Conventional Vehicles | |
Zhao et al. | Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots | |
Liu et al. | Predicting interstate motor carrier crash rate level using classification models | |
Das et al. | Fatal crashes at highway rail grade crossings: A US based study | |
Biggi et al. | Artificial intelligence in self-driving cars research and innovation: A scientometric and bibliometric analysis | |
CN103714695A (en) | Method for analyzing vehicle operation state based on vehicle running data | |
Nai et al. | Fuzzy risk mode and effect analyasis based on raw driving data for pay-how-you-drive vehicle insurance | |
Huang et al. | Jointly analyzing freeway primary and secondary crash severity using a copula-based approach | |
Wang et al. | Effects of speed difference on injury severity of freeway rear-end crashes: Insights from correlated joint random parameters bivariate probit models and temporal instability | |
Basso et al. | Assessing factors influencing the occurrence of traffic conflicts: a vehicle-by-vehicle approach | |
Samerei et al. | Analyzing the transition from two-vehicle collisions to chain reaction crashes: A hybrid approach using random parameters logit model, interpretable machine learning, and clustering | |
Ahmed et al. | PARATRANSIT SAFETY AS A KEY RESOURCE FOR SUSTAINABLE MOBILITY IN DEVELOPING COUNTRIES. | |
Boylan et al. | A systematic review of the use of in-vehicle telematics in monitoring driving behaviours | |
YANG et al. | Examining Drivers’ Injury Severity of Two-Vehicle Crashes between Passenger Cars and Trucks Considering Vehicle Types | |
Moghaddam et al. | Crash severity modeling in urban highways using backward regression method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180130 |