CN103646533A - A traffic accident modeling and control method based on sparse multi-output regression - Google Patents
A traffic accident modeling and control method based on sparse multi-output regression Download PDFInfo
- Publication number
- CN103646533A CN103646533A CN201310596073.7A CN201310596073A CN103646533A CN 103646533 A CN103646533 A CN 103646533A CN 201310596073 A CN201310596073 A CN 201310596073A CN 103646533 A CN103646533 A CN 103646533A
- Authority
- CN
- China
- Prior art keywords
- traffic
- traffic accident
- accident
- modeling
- control method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a traffic accident modeling and control method based on sparse multi-output regression, and can be used to carry out modeling on conditions of traffic accidents of a certain selected region. A multi-output regression accident model is established for a certain region. Characteristic parameters irrelevant to the accidents can be automatically detected and the influence of each parameter is distinguished. The characteristic parameters relevant to the traffic are brought into the model, and conditions of traffic accidents occurring in the future in the region can be predicted. According to the invention, historical and current situation data are utilized to carry out modeling on the severe degree of the traffic accidents; the characteristic parameters irrelevant to the accidents can be automatically removed and key factors which influence road traffic safety can be discriminated, so that the adoption of more targeted measures in road programming is facilitated. The traffic accident modeling and control method has practical engineering application values in traffic accident prediction, accident reason analysis and road construction improvement guidance.
Description
Technical field
The invention belongs to traffic intelligent management and control technology field, with the sparse multi-output regression model of proposition, set up a kind of road traffic accident method, and can automatic detection influence the key factor of traffic safety, in prediction traffic accident, analyze cause of accident, instruct road construction to improve with actual engineering application value.
Background technology
With developing rapidly for China's road traffic cause, traffic accident surges as one of serious problem of society today received much concern now.Just because of the serious consequence that traffic accident is caused, a large amount of human and material resources and financial resources have poured into accident prevention and countermeasure in China, more perfect control of traffic and road law, regulation and relevant policies are formulated, but the Factual Damage caused by the road traffic accident of China is still serious, and the trend of rising is constantly in, annual toll on traffic occupy first place in the world.Therefore, in order to ensure economic development and social stability, people's safety and cargo transportation security are ensured, the traffic safety situation to China makes the prediction of science, becomes very necessary and extremely urgent.
At present, a variety of methods are modeled applied to accident both at home and abroad.Existing research, which establishes accident, to be occurred and traffic stream characteristics, road environment condition, the size of population, relation between the data such as vehicle guaranteeding organic quantity, but most of analyzed from the angle of macroscopic view, the analysis result drawn is the prediction of the traffic accident number of times in a region, and this does not have too big effect for preventing and reducing traffic accident.Although also there is influence of factor of the part research from microcosmic angle analysis road to traffic accident, but, the factor that have ignored influence traffic accident is a lot, and some of which factor exists as noise factor, if not rejecting these characteristic parameters and carrying out traffic accident modeling, this may hide the real feature and inherent law of traffic accident.
Traffic accident is the complicated system produced by many factors collective effect, and the relation between these factors is difficult to be described with the method for parsing, and the model of traffic accident can be set up with degree of precision by the study to historical data based on sparse multi-output regression model.
For the accuracy of modeling, do not omit important information, we can consider as far as possible many factors, while must also reject the characteristic parameter unrelated with accident, therefore, invention introduces sparse analytic approach, sparse analysis is carried out to initial data, so that the key factor of influence traffic safety is distinguished, so that effectively utilizing a large amount of statistics carries out quantitative analysis, the internal relation between variable is disclosed, and can provide and targetedly instruct for the improvement of road construction.
The content of the invention
The problem to be solved in the present invention is overcome prior art above-mentioned not enough there is provided one kind is simple to operate, and accuracy is high, it is adaptable to road safety check in the method that models of traffic accident.
The technical scheme is that：
A）Obtain the historical traffic casualty data sample N groups { X in somewhere1,X2,...,XN, each XI（I=1,2,3,...,N）Including following populations, vehicle, road and environmental information：Total number of people x1, schooling x2, income level x3, driver's quantity x4, truck conspicuity marking quantity x5, cyclecar quantity x6, non-motor vehicle quantity x7, main section total length x8, main road section traffic volume lamp quantity x9, average weather conditions x10。
B）Obtain corresponding traffic accident result sample { Y1,Y2,...,YN, each YI（I=1,2,3,...,N）Including accident frequency y1, death toll y2, number of injured people y3And direct economic loss y4。
C) traffic accident data prediction.By above-mentioned N groups traffic accident data sample { X1,X2,...,XNNormalization, and be stored in matrix X.By the corresponding traffic accident result sample { Y of above-mentioned N groups1,Y2,...,YNBe stored in matrix Y.
D X) is assumedIWith YI（I=1,2,3,...,N）Meet relation YI=XIW+ ε, W are coefficient, and ε is Gaussian noise.If λ is balance parameters, 0.01≤λ≤100 are can be taken as, then W can be obtained by solving following sparse multi-output regression model
E coefficient matrix W) is chosen so that J (W) reaches minimum value, if D is unit matrix.
F) by J (W) to W differentiations, and make result be equal to 0, obtain
XT(XW-Y)+λDW=0
G) solve above formula and obtain W=(XTX+λD)-1XTY。
If D' is diagonal matrix, diagonal element is the inverse of the L2 norms of W correspondence rows.
H) whether evaluation algorithm restrains, i.e., | | D-D'| | whether less than given number ε（Such as ε=0.001）, if it is, output W, otherwise D' is copied in D, go to step F).
I）Row according to being all zero in W is identified models unrelated factor to traffic accident, the influence according to the different factors of the positive and negative and size discrimination of the value of non-zero row in W to traffic accident.Such as driver's quantity x4Coefficient be negative, then in traffic planninng that should be afterwards increase driver quantity with reduce future traffic accident.
J) according to the above-mentioned regional traffic accident characteristic parameter X'=(x gathered later1,x2,...,x10), it is WX' to predict above-mentioned regional accident frequency, death toll, number of injured people and direct economic loss.
The technique effect of the present invention is as follows：
Based on sparse multi-output regression model.Some existing research methods are directly trained by the use of initial data as input variable, but there is both sides in these initial data, one is that data volume is big, dimension is more, one is there is correlation between data, information has redundancy, and this precision that will result in result is high and reduction of training speed.Sparse analysis, the automatic rejection characteristic parameter unrelated with accident are carried out to initial data, so that effectively utilizing a large amount of statistics carries out quantitative analysis, the internal relation between variable is disclosed.
Influence factor is chosen from microcosmic angle to be modeled.Traditional Predictive Methods of Road Accidents is all to be analyzed using some macroscopical influence factors as input variable, and what is obtained is the data of the traffic accident of an entirety.The present invention is to regard the microcosmic influence factors of road as input data, analyze these factors and the relation of traffic accident, so as to obtain respective influence of these factors on traffic accident, this conclusion may apply in Highway traffic safety assessment, and the design and trimming for road and surrounding enviroment provide foundation.
Brief description of the drawings
Fig. 1 is the traffic accident model flow block diagram based on sparse multi-output regression of the present invention.
Embodiment
In today's society, traffic safety gets more and more people's extensive concerning, and the research of road safety assessment plays the role of very big for the reduction of traffic accident.The present invention is analyzed and researched from microcosmic angle using the modeling method based on sparse multi-output regression to the relation of a variety of variables such as a certain area and traffic accident.
The workflow of the present invention is described in detail below：
First, the selection of data
Road traffic is the dynamical system being made up of key elements such as people, car, road, environment.During traffic accident is road traffic system, due to people, car, road, the cooperation imbalance of all key elements of environment and the event accidentally happened suddenly.Therefore, when choosing the factor of influence of traffic accident, to be analyzed from the above.
1. human factor:According to the statistics of traffic accidents result of 2002, the death toll caused due to people accounts for the 88.98% of the dead sum of traffic accident then, wherein automobile driver accounts for 78.56% for main cause, and non-motor vehicle driver accounts for 4.20%, and pedestrian and rider account for 6.22%.It can be seen that, in general, the key of traffic accident is automobile driver.Therefore have chosen a certain regional periphery total number of people and its average schooling and income, four indexs of driver's quantity.
2. the factor of car：The second largest key element for causing traffic accident is vehicle.The vehicle travelled on road, existing motor vehicle also has non-motor vehicle, wherein motor vehicle（Especially truck conspicuity marking）It is a kind of quick vehicles, energy is maximum, and protective is preferably also.But this protective only protects driver and occupant, accordingly, with respect to bicycle and other non-motor vehicles, motor vehicle is traffic powerhouse.But increasing for non-motor vehicle quantity can also influence on how much generations of traffic accident, therefore have chosen truck conspicuity marking quantity, cyclecar quantity, three indexs of non-motor vehicle quantity.
3. road and environmental factor：The environmental factor of influence traffic safety can be divided into natural environment and artificial environment, and natural environment mainly includes geographical position, meteorological condition, and time etc., artificial environment includes situation of land use, trackside interference, road barrier etc..The present invention have chosen above-mentioned regional main section total length, main road section traffic volume lamp quantity and averagely these three indexs of weather conditions as factor of influence.
2nd, road accident risk model is set up：
A the historical traffic casualty data sample N groups { X in somewhere) is obtained1,X2,...,XN, each XI（I=1,2,3,...,N）Including population, vehicle, road and environmental information：Total number of people x1, schooling x2, income level x3, driver's quantity x4, truck conspicuity marking quantity x5, cyclecar quantity x6, non-motor vehicle quantity x7, main section total length x8, main road section traffic volume lamp quantity x9, average weather conditions x10。
B corresponding traffic accident result sample { Y) is obtained1,Y2,...,YN, each YI（I=1,2,3,...,N）Including accident frequency y1, death toll y2, number of injured people y3And direct economic loss y4。
C) traffic accident data prediction.By above-mentioned N groups traffic accident data sample { X1,X2,...,XNNormalization, and be stored in matrix X.By the corresponding traffic accident result sample { Y of above-mentioned N groups1,Y2,...,YNBe stored in matrix Y.
D X) is assumedIWith YI（I=1,2,3,...,N）Meet relation YI=XIW+ ε, W are coefficient, and ε is Gaussian noise.If λ is balance parameters, 0.01≤λ≤100 are can be taken as, then W can be obtained by solving following sparse multi-output regression model
E coefficient matrix W) is chosen so that J (W) reaches minimum value, if D is unit matrix.
F) by J (W) to W differentiations, and make result be equal to 0, obtain
XT(XW-Y)+λDW=0
G) solve above formula and obtain W=(XTX+λD)-1XTY。
If D' is diagonal matrix, diagonal element is the inverse of the L2 norms of W correspondence rows.
H) whether evaluation algorithm restrains, i.e., | | D-D'| | whether less than given number ε（Such as ε=0.001）, if it is, output W, otherwise D' is copied in D, go to step F).
I）Row according to being all zero in W is identified models unrelated factor to traffic accident, the influence according to the different factors of the positive and negative and size discrimination of the value of non-zero row in W to traffic accident.Such as driver's quantity x4Coefficient be negative, then in traffic planninng that should be afterwards increase driver quantity with reduce future traffic accident.
J) according to the above-mentioned regional traffic accident characteristic parameter X'=(x gathered later1,x2,...,x10), it is WX' to predict above-mentioned regional accident frequency, death toll, number of injured people and direct economic loss.
Practice process is divided into model learning and model and uses two processes.
Model learning：Such as Fig. 1, the traffic accident data and corresponding traffic accident result data in a certain regional certain time are collected.The traffic accident function of sparse multi-output regression is set up according to foregoing modeling procedure, that is, calculates YI=XIW+ ε sparse matrix W.
Model is used：Row according to being all zero in W is identified models unrelated factor to traffic accident, the influence according to the different factors of the positive and negative and size discrimination of the value of non-zero row in W to traffic accident.Such as driver's quantity x4Coefficient be negative, then in traffic planninng that should be afterwards increase driver quantity with reduce future traffic accident.Also, according to the traffic accident feature X'=(x gathered in some time of areal1,x2,...,x10), using accident frequencies of the W to this area, death toll, number of injured people and direct economic loss are predicted X'W.
Claims (4)
1. traffic accident modeling and control method based on sparse multi-output regression, it is characterised in that concretely comprise the following steps：
A）Obtain the historical traffic casualty data sample N groups { X in somewhere1,X2,...,XN, each XI（I=1,2,3,...,N）Including following populations, vehicle, road and environmental information：Total number of people x1, schooling x2, income level x3, driver's quantity x4, truck conspicuity marking quantity x5, cyclecar quantity x6, non-motor vehicle quantity x7, main section total length x8, main road section traffic volume lamp quantity x9, average weather conditions x10；
B）Obtain corresponding traffic accident result sample { Y1,Y2,...,YN, each YI（I=1,2,3,...,N）Including accident frequency y1, death toll y2, number of injured people y3And direct economic loss y4；
C) traffic accident data prediction；By above-mentioned N groups traffic accident data sample { X1,X2,...,XNNormalization, and be stored in matrix X.By the corresponding traffic accident result sample { Y of above-mentioned N groups1,Y2,...,YNBe stored in matrix Y；
D X) is assumedIWith YI（I=1,2,3,...,N）Meet relation YI=XIW+ ε, W are coefficient, and ε is Gaussian noise.If λ is balance parameters, 0.01≤λ≤100 are can be taken as, then W can be obtained by solving following sparse multi-output regression model
E coefficient matrix W) is chosen so that J (W) reaches minimum value, if D is unit matrix；
F) by J (W) to W differentiations, and make result be equal to 0, obtain
XT(XW-Y)+λDW=0；
G) solve above formula and obtain W=(XTX+λD)-1XTY；
If D' is diagonal matrix, diagonal element is the inverse of the L2 norms of W correspondence rows；
H) whether evaluation algorithm restrains, i.e., | | D-D'| | whether less than given number ε（Such as ε=0.001）, if it is, output W, otherwise D' is copied in D, go to step F)；
I）Row according to being all zero in W is identified models unrelated factor to traffic accident, the influence according to the different factors of the positive and negative and size discrimination of the value of non-zero row in W to traffic accident;
J) according to the above-mentioned regional traffic accident characteristic parameter X'=(x gathered later1,x2,...,x10), it is WX' to predict above-mentioned regional accident frequency, death toll, number of injured people and direct economic loss.
2. traffic accident modeling and control method according to claim 1 based on sparse multi-output regression, it is characterised in that the step D）In, the balance parameters λ：0.01≤λ≤100.
3. traffic accident modeling and control method according to claim 1 based on sparse multi-output regression, it is characterised in that the step H）In, given number ε：0.001≤ε≤0.1.
4. traffic accident modeling and control method according to claim 1 based on sparse multi-output regression, it is characterised in that the step I）In, it is to the method that accident is controlled according to modeling result：If the value of non-zero row is just, the correspondence factor has negative effect to accident forecast in W, it should consider to reduce the factor in roading；If the value of non-zero row is negative in W, the correspondence factor has positive influences to accident forecast, should consider to increase the factor in roading；Such as driver's quantity x4Coefficient be negative, then in traffic planninng that should be afterwards increase driver quantity with reduce future traffic accident.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310596073.7A CN103646533B (en) | 2013-11-22 | 2013-11-22 | Traffic accident modeling and control method based on sparse multi-output regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310596073.7A CN103646533B (en) | 2013-11-22 | 2013-11-22 | Traffic accident modeling and control method based on sparse multi-output regression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103646533A true CN103646533A (en) | 2014-03-19 |
| CN103646533B CN103646533B (en) | 2016-05-25 |
Family
ID=50251740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310596073.7A Expired - Fee Related CN103646533B (en) | 2013-11-22 | 2013-11-22 | Traffic accident modeling and control method based on sparse multi-output regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103646533B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485919A (en) * | 2016-10-11 | 2017-03-08 | 东南大学 | A kind of method for judging that through street fixed point tachymeter is affected on traffic accident quantity |
| CN106530712A (en) * | 2016-12-16 | 2017-03-22 | 上海斐讯数据通信技术有限公司 | Big data-based system and method for pre-estimation of traffic casualty accident rates |
| CN106816020A (en) * | 2015-12-02 | 2017-06-09 | 大陆汽车投资（上海）有限公司 | Traffic accident information processing method based on data analysis |
| CN108776650A (en) * | 2018-06-05 | 2018-11-09 | 浙江大学 | A kind of non-motorized lane service level evaluation method based on mixed Gauss model |
| CN109087505A (en) * | 2018-07-11 | 2018-12-25 | 北京交通大学 | A kind of traffic safety code efficiency analysis method for motorcycle |
| CN113887604A (en) * | 2021-09-27 | 2022-01-04 | 同济大学 | Key management area identification method for safety education improvement |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004126757A (en) * | 2002-09-30 | 2004-04-22 | Toshiba Corp | Data predicting device, data predicting method and data prediction program |
| DE102006044086A1 (en) * | 2006-09-20 | 2008-04-10 | Audi Ag | Traffic situation e.g. accident-critical driving situation, simulating system, has reference vehicle, where behavior of vehicle temporally takes place based on information detected by detection unit during simulated traffic situation |
| CN102103715A (en) * | 2010-11-18 | 2011-06-22 | 上海海事大学 | Negative binomial regression-based maritime traffic accident investigation analysis and prediction method |
| CN102306450A (en) * | 2011-08-30 | 2012-01-04 | 同济大学 | Layout method for traffic detectors of sparse road network |
| CN102360525A (en) * | 2011-09-28 | 2012-02-22 | 东南大学 | Discriminant analysis-based high road real-time traffic accident risk forecasting method |
| CN102855395A (en) * | 2012-08-16 | 2013-01-02 | 长安大学 | Method for distinguishing road black spot |
| CN103226818A (en) * | 2013-04-25 | 2013-07-31 | 武汉大学 | Single-frame image super-resolution reconstruction method based on manifold regularized sparse support regression |
| CN103400346A (en) * | 2013-07-18 | 2013-11-20 | 天津大学 | Video super resolution method for self-adaption-based superpixel-oriented autoregression model |
-
2013
- 2013-11-22 CN CN201310596073.7A patent/CN103646533B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004126757A (en) * | 2002-09-30 | 2004-04-22 | Toshiba Corp | Data predicting device, data predicting method and data prediction program |
| DE102006044086A1 (en) * | 2006-09-20 | 2008-04-10 | Audi Ag | Traffic situation e.g. accident-critical driving situation, simulating system, has reference vehicle, where behavior of vehicle temporally takes place based on information detected by detection unit during simulated traffic situation |
| CN102103715A (en) * | 2010-11-18 | 2011-06-22 | 上海海事大学 | Negative binomial regression-based maritime traffic accident investigation analysis and prediction method |
| CN102306450A (en) * | 2011-08-30 | 2012-01-04 | 同济大学 | Layout method for traffic detectors of sparse road network |
| CN102360525A (en) * | 2011-09-28 | 2012-02-22 | 东南大学 | Discriminant analysis-based high road real-time traffic accident risk forecasting method |
| CN102855395A (en) * | 2012-08-16 | 2013-01-02 | 长安大学 | Method for distinguishing road black spot |
| CN103226818A (en) * | 2013-04-25 | 2013-07-31 | 武汉大学 | Single-frame image super-resolution reconstruction method based on manifold regularized sparse support regression |
| CN103400346A (en) * | 2013-07-18 | 2013-11-20 | 天津大学 | Video super resolution method for self-adaption-based superpixel-oriented autoregression model |
Non-Patent Citations (3)
| Title |
|---|
| 姜华平: "道路交通事故预测模型的构建与应用", 《山东交通学院学报》, vol. 11, no. 01, 31 March 2003 (2003-03-31), pages 35 - 37 * |
| 秦小虎等: "一种基于贝叶斯网络模型的交通事故预测方法", 《计算机仿真》, vol. 22, no. 11, 30 November 2005 (2005-11-30), pages 230 - 231 * |
| 韩文涛等: "基于灰色系统的道路交通事故预测模型研究", 《西安建筑科技大学学报(自然科学版)》, vol. 37, no. 03, 30 September 2005 (2005-09-30), pages 375 - 377 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106816020A (en) * | 2015-12-02 | 2017-06-09 | 大陆汽车投资（上海）有限公司 | Traffic accident information processing method based on data analysis |
| CN106485919A (en) * | 2016-10-11 | 2017-03-08 | 东南大学 | A kind of method for judging that through street fixed point tachymeter is affected on traffic accident quantity |
| CN106530712A (en) * | 2016-12-16 | 2017-03-22 | 上海斐讯数据通信技术有限公司 | Big data-based system and method for pre-estimation of traffic casualty accident rates |
| CN106530712B (en) * | 2016-12-16 | 2019-09-13 | 上海斐讯数据通信技术有限公司 | The system and method for vehicular casualty rate is estimated by big data |
| CN108776650A (en) * | 2018-06-05 | 2018-11-09 | 浙江大学 | A kind of non-motorized lane service level evaluation method based on mixed Gauss model |
| CN109087505A (en) * | 2018-07-11 | 2018-12-25 | 北京交通大学 | A kind of traffic safety code efficiency analysis method for motorcycle |
| CN109087505B (en) * | 2018-07-11 | 2020-05-22 | 北京交通大学 | Traffic safety regulation effectiveness analysis method for motorcycle |
| CN113887604A (en) * | 2021-09-27 | 2022-01-04 | 同济大学 | Key management area identification method for safety education improvement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103646533B (en) | 2016-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103646533A (en) | A traffic accident modeling and control method based on sparse multi-output regression | |
| CN105225500B (en) | A kind of traffic control aid decision-making method and device | |
| CN108765235A (en) | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case | |
| CN106383920B (en) | A kind of particularly serious traffic accident causation recognition methods based on correlation rule | |
| CN101976501A (en) | Principal component analysis and neural network based port road safety prediction method | |
| CN104021672B (en) | A kind of method and apparatus obtaining traffic congestion index | |
| Li et al. | A fuzzy logic‐based variable speed limit controller | |
| CN103895649B (en) | A kind of driver safety driving warning method | |
| CN102568206B (en) | Video monitoring-based method for detecting cars parking against regulations | |
| CN104318757B (en) | Bus bus or train route section Forecasting Methodology working time on a kind of public transportation lane | |
| CN103646534A (en) | A road real time traffic accident risk control method | |
| CN112002112B (en) | Security and protection efficiency evaluation method and system for perimeter intrusion alarm system of high-speed railway | |
| WO2022257201A1 (en) | Urban traffic safety early-warning method and system based on human-machine hybrid-augmented intelligence | |
| CN106251661A (en) | Tunnel portal section wagon flow control method | |
| CN114463868B (en) | Traffic flow combination prediction method and system for toll station facing traffic flow control | |
| CN108510733A (en) | A kind of fusion of data depth transboundary solves the managing and control system of highway communication congestion | |
| CN105719510A (en) | Efficiency evaluation method of road traffic accident chain blocking system under IOV (Internet of Vehicles) environment | |
| Pilko et al. | Study of vehicle speed in the design of roundabouts | |
| CN101075377A (en) | Method for automatically inspecting highway traffic event based on offset minimum binary theory | |
| CN106530714A (en) | Secondary traffic accident time prediction method based on traffic flow data | |
| Tripodi et al. | A decision support system for analysis of vulnerable road users safety issues: results of the Saferbrain project | |
| Kitali et al. | Using crash modification factors to appraise the safety effects of pedestrian countdown signals for drivers | |
| CN103886762B (en) | Traffic behavior sort method in section in road network | |
| CN109191851A (en) | A kind of traffic lights redundancy time calculation method and device | |
| Al Jaman et al. | Effects of automated traffic enforcement on driver behavior at a signalized intersection in Saudi Arabia |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160525 Termination date: 20161122 |