CN109993356A - A kind of traffic optimization system and method based on XGBOOST - Google Patents
A kind of traffic optimization system and method based on XGBOOST Download PDFInfo
- Publication number
- CN109993356A CN109993356A CN201910229274.0A CN201910229274A CN109993356A CN 109993356 A CN109993356 A CN 109993356A CN 201910229274 A CN201910229274 A CN 201910229274A CN 109993356 A CN109993356 A CN 109993356A
- Authority
- CN
- China
- Prior art keywords
- xgboost
- lane
- real
- traffic optimization
- intelligent guardrail
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000011084 recovery Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 230000004913 activation Effects 0.000 claims abstract description 11
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 230000001427 coherent effect Effects 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006698 induction Effects 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- 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
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to machine learning techniques fields, more particularly to a kind of traffic optimization system and method based on XGBOOST, the present invention first will carry out pre-training to XGBOOST model, after startup program activation, Intelligent guardrail can receive the signal from control centre, the lane of congestion side is widened, the lane of unobstructed side is carried out narrowed.Here for prevent because Intelligent guardrail change frequently due to traffic problems occur, β must not be less than by devising Intelligent guardrail transformation period.When the absolute value abs_t of the difference of the average transit time of the both sides of the road following half an hour is less than threshold values γ, and when the link change time is greater than β, activate recovery routine, Intelligent guardrail receives restore signal after, can restore to original state.The index that the present invention gets congestion using average transit time as road, when congestion occurs in two-way lane side, other side passage is smooth, then system meeting automatic starting device, widens the lane of congestion side, the lane of smooth side is narrowed, to achieve the effect that slow down congestion.
Description
Technical field
The present invention relates to machine learning techniques fields, and in particular to a kind of traffic optimization system and side based on XGBOOST
Method.
Background technique
It is shown according to related data, the whole nation and rises year by year for 1 year because losing about 170,000,000,000 yuan caused by traffic congestion.It hands over
Logical congestion also will affect physical and mental health in addition to influencing expanding economy.The reason of causing congestion is more people, Che Duo, friendship nothing but
Logical infrastructure and traffic administration are not kept pace with.
Traffic jam issue is solved, can be started in terms of two, first aspect is to prevent traffic congestion in advance, Ke Yizeng
Add public transport infrastructure construction and formulates reasonable traffic administration method.Second aspect is carried out after getting congestion
Real-time traffic scheduling for the solution of real-time congestion is obtained by urban traffic information acquisition and processing system at present
The real-time average travel speed of urban road network and real-time traffic states identify congested link, are then divided into congested link
Induction control domain and buffer-induced region, and automatically generate corresponding induction information.
Summary of the invention
In view of the deficiencies of the prior art, the invention discloses a kind of the traffic optimization system and method based on XGBOOST, sheet
Invention makes full use of road real time data, in conjunction with machine learning model, judges road traffic condition, is the broadening (narrowed) in lane
Important foundation is provided.
The present invention is achieved by the following technical programs:
A kind of traffic optimization method based on XGBOOST, which is characterized in that the described method comprises the following steps:
S1, which obtains traffic information and carries out data processing, generates XGBOOST model；
S2 cleans transit time t_real average in data, does Feature Engineering, and is input to the progress of XGBOOST model
Training；
S3 cleans real time data t_real, does Feature Engineering, is predicted；
S4 control centre decision keeps the state of Intelligent guardrail constant or activation recovery routine；
For S5 according to instruction startup program, Intelligent guardrail is moved to current smooth side, widens the lane of congestion side, narrows
The lane of smooth side；
S6 restores according to instruction recovery routine Intelligent guardrail to normal state.
Preferably, in the S1, the Data processing three parts data will be handled, and first part's data acquire road
Section two sides lane is round-the-clock using half an hour as the average transit time t_real of granularity；
Second part count both sides of the road be averaged transit time difference absolute value average value abs_t_avg, and take
Minimum threshold values γ of twice of abs_t_avg as control centre's activation startup program；
Part III determines the most short transformation period β of system according to the case where section.
Preferably, in the S3, it is small using XGBOOST model to be predicted to real time data t_real both sides of the road future half
When average transit time t_pre, real time data t_real is cleaned, Feature Engineering is then done, is finally predicted.
Preferably, in the S4, control centre's Decision Control center is small every both sides of the road future half of time β calculating
When average transit time difference absolute value abs_t, when abs_t be greater than threshold values γ when, control centre issue starting
Signal activates startup program to Intelligent guardrail.
Preferably, if after time β, if γ is still greater than in abs_t, keep the state of Intelligent guardrail constant, if
Abs_t is less than γ, then control centre activates recovery routine.
A kind of traffic optimization system based on XGBOOST, the optimization system for realizing above-mentioned any one based on
The traffic optimization method of XGBOOST, which is characterized in that the system comprises speed testing device, intelligent control center, intelligence shields
Column and warning device.
Preferably, the speed testing device is used to acquire the average transit time t_real of vehicle, the data obtained
On the one hand it is used for the training of XGBOOST model, is on the other hand predicted in real time for XGBOOST model.
Preferably, the intelligent control center accepts the training and prediction of XGBOOST model, and control centre is according to model
Prediction issues activation signal to Intelligent guardrail after making a policy or restores signal.
Preferably, when the Intelligent guardrail receives the coherent signal of control centre, Intelligent guardrail can be moved along track
To corresponding lane.
Preferably, for the warning device when catastrophic failure occurs in system, passerby can press device, relevant departments
It can be on the scene at once and system is safeguarded.
The invention has the benefit that
The present invention can carry out intelligent scheduling to traffic in the peak period of trip.The present invention is using average transit time as road
The index that road gets congestion, when congestion occurs in two-way lane side, other side passage is smooth, then system meeting automatic starting device,
The lane for widening congestion side, narrows the lane of smooth side, to achieve the effect that slow down congestion.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of the traffic optimization method based on XGBOOST of the present embodiment；
Fig. 2 is a kind of traffic optimization system diagram based on XGBOOST of the present embodiment.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Embodiment 1
In the present embodiment, pre-training first is carried out to XGBOOST model, the effect of model is that real-time prediction both sides of the road exist
Average transit time t_pre in the following half an hour, then control centre calculates the average logical of the both sides of the road following half an hour
The absolute value abs_t of the difference of row time then activates startup program when this value is more than preset threshold values γ.Starting
After program activation, Intelligent guardrail can receive the signal from control centre, widen to the lane of congestion side, to unobstructed side
Lane carry out it is narrowed.Here for prevent because Intelligent guardrail change frequently due to traffic problems occur, devise Intelligent guardrail change
Change the time must not less than β (i.e. lane widened after at least through time β could start recovery routine, vice versa).Work as road
When the absolute value abs_t of the difference of the average transit time of two sides half an hour in future is less than threshold values γ, and the link change time
When greater than β, after activating recovery routine, Intelligent guardrail to receive recovery signal, it can restore to original state.
The present embodiment can be divided into data processing, model pre-training, model are predicted in real time, control centre's decision, startup program,
This 5 processes of recovery routine, specific as follows:
(1) data processing stage: this stage has three parts data to be handled, and first part's data are sections to be acquired
Two sides lane is round-the-clock using half an hour as the average transit time t_real of granularity.Second part is to count both sides of the road to put down
The average value abs_t_avg of the absolute value of equal transit time difference, and take twice of abs_t_avg and opened as control centre's activation
The minimum threshold values γ of dynamic program.Part III is that the most short transformation period β of system is determined according to the case where section.
(2) model pre-training: this stage mainly training XGBOOST model first does clearly average transit time t_real
It washes, then does Feature Engineering, recently enter model and be trained.
(3) model is predicted in real time: this stage is that XGBOOST model to be utilized predicts road two to real time data t_real
The average transit time t_pre of side half an hour in future.With (2), real time data t_real need to be cleaned, then do feature work
Journey is finally predicted.
(4) control centre's decision: control centre calculates a both sides of the road not every time β (the most short transformation period of system)
The absolute value abs_t for carrying out the difference of the average transit time of half an hour, when abs_t is greater than threshold values γ, control centre's hair
Enabling signal activates startup program to Intelligent guardrail out.If, if γ is still greater than in abs_t, keeping intelligence after time β
The state of energy guardrail is constant, if abs_t is less than γ, control centre activates recovery routine.
(5) startup program: Intelligent guardrail is moved to current smooth side, widens the lane of congestion side, narrows smooth one
The lane of side.
(6) recovery routine: Intelligent guardrail restores to normal state.The flow diagram of whole system is as shown in Figure 1.
The present embodiment can carry out intelligent scheduling to traffic in the peak period of trip.The present invention using average transit time as
The index that road gets congestion, when congestion occurs in two-way lane side, other side passage is smooth, then system can start dress automatically
It sets, widens the lane of congestion side, the lane of smooth side is narrowed, to achieve the effect that slow down congestion.
Embodiment 2
In the present embodiment, a kind of traffic optimization system based on XGBOOST is disclosed as shown in Figure 2, entire whole main packet
Following components are included, first is that speed testing device, second is that intelligent control center, third is that Intelligent guardrail, fourth is that warning device.
(1) speed testing device: it is mainly used for acquiring the average transit time t_real of vehicle.The data one obtained
Aspect is used for the training of XGBOOST model, is on the other hand predicted in real time for XGBOOST model.
(2) intelligent control center: the training and prediction of XGBOOST model are carried out in intelligent control center.Control centre's root
Activation signal is issued to Intelligent guardrail after making a policy according to the prediction of model or restores signal.
(3) Intelligent guardrail: when receiving the coherent signal of control centre, Intelligent guardrail can be moved to correspondence along track
Lane.
(4) warning device: when catastrophic failure occurs in system, passerby can press device, and relevant departments can horse
On be on the scene system safeguarded.
The present invention mainly utilizes machine learning techniques prediction road to be averaged transit time, using average transit time as index,
When both sides of the road lane, the following half an hour is averaged transit time absolute value of the difference abs_t greater than threshold values β, journey is widened in starting lane
Sequence；Otherwise, restore lane to state.The advantages of this programme, is as follows:
(1) from the utilization rate of road itself: in the case where getting congestion, the present invention can make full use of road to provide
The traffic capacity of road is improved in source.
(2) from driver's personal efficiency: driver haves no need to change original route and arrives at the destination, and effectively saves in this way
Transportation cost.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of traffic optimization method based on XGBOOST, which is characterized in that the described method comprises the following steps:
S1, which obtains traffic information and carries out data processing, generates XGBOOST model；
S2 cleans transit time t_real average in data, does Feature Engineering, and be input to XGBOOST model and instructed
Practice；
S3 cleans real time data t_real, does Feature Engineering, is predicted；
S4 control centre decision keeps the state of Intelligent guardrail constant or activation recovery routine；
For S5 according to instruction startup program, Intelligent guardrail is moved to current smooth side, widens the lane of congestion side, narrows smooth
The lane of side；
S6 restores according to instruction recovery routine Intelligent guardrail to normal state.
2. the traffic optimization method according to claim 1 based on XGBOOST, which is characterized in that in the S1, the number
It to be handled according to three parts data in processing, it is round-the-clock using half an hour as particle that first part's data acquire section two sides lane
The average transit time t_real of degree；
Second part count both sides of the road be averaged transit time difference absolute value average value abs_t_avg, and take abs_
Minimum threshold values γ of twice of t_avg as control centre's activation startup program；
Part III determines the most short transformation period β of system according to the case where section.
3. the traffic optimization method according to claim 1 based on XGBOOST, which is characterized in that in the S3, utilize
XGBOOST model predicts the average transit time t_pre of the both sides of the road following half an hour to real time data t_real, to real-time
Data t_real is cleaned, and is then done Feature Engineering, is finally predicted.
4. the traffic optimization method according to claim 1 based on XGBOOST, which is characterized in that in the S4, in control
Heart Decision Control center calculates the absolute value of the difference of the average transit time of a both sides of the road following half an hour every time β
Abs_t, when abs_t is greater than threshold values γ, control centre issues enabling signal to Intelligent guardrail, activates startup program.
5. the traffic optimization method according to claim 4 based on XGBOOST, which is characterized in that if by time β
Afterwards, if γ is still greater than in abs_t, keep the state of Intelligent guardrail constant, if abs_t is less than γ, control centre's activation is extensive
Multiple program.
6. a kind of traffic optimization system based on XGBOOST, the optimization system is for realizing appointing as described in claim 2-5
The traffic optimization method based on XGBOOST of meaning one, which is characterized in that the system comprises speed testing devices, intelligence control
Center, Intelligent guardrail and warning device processed.
7. the traffic optimization system according to claim 6 based on XGBOOST, which is characterized in that the velocity test dress
The average transit time t_real for acquiring vehicle is set, on the one hand the data obtained are used for the training of XGBOOST model, separately
On the one hand it is predicted in real time for XGBOOST model.
8. the traffic optimization system according to claim 6 based on XGBOOST, which is characterized in that in the intelligent control
The heart accepts the training and prediction of XGBOOST model, and control centre issues after being made a policy according to the prediction of model to Intelligent guardrail
Activation signal restores signal.
9. the traffic optimization system according to claim 6 based on XGBOOST, which is characterized in that the Intelligent guardrail connects
When receiving the coherent signal of control centre, Intelligent guardrail can be moved to corresponding lane along track.
10. the traffic optimization system according to claim 6 based on XGBOOST, which is characterized in that the warning device exists
When catastrophic failure occurs in system, passerby can press device, and relevant departments can be on the scene at once and tie up to system
Shield.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910229274.0A CN109993356A (en) | 2019-03-25 | 2019-03-25 | A kind of traffic optimization system and method based on XGBOOST |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910229274.0A CN109993356A (en) | 2019-03-25 | 2019-03-25 | A kind of traffic optimization system and method based on XGBOOST |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109993356A true CN109993356A (en) | 2019-07-09 |
Family
ID=67131528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910229274.0A Pending CN109993356A (en) | 2019-03-25 | 2019-03-25 | A kind of traffic optimization system and method based on XGBOOST |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993356A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570862A (en) * | 2021-07-28 | 2021-10-29 | 太原理工大学 | XGboost algorithm-based large traffic jam early warning method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635089A (en) * | 2009-05-22 | 2010-01-27 | 上海宝康电子控制工程有限公司 | System and method for coordinating traffic control and traffic guidance |
| US20170185904A1 (en) * | 2015-12-29 | 2017-06-29 | 24/7 Customer, Inc. | Method and apparatus for facilitating on-demand building of predictive models |
| CN107871167A (en) * | 2017-10-20 | 2018-04-03 | 广东工业大学 | A kind of causal structure learning method based on likelihood score |
| CN108629985A (en) * | 2018-04-25 | 2018-10-09 | 梧州井儿铺贸易有限公司 | A kind of zebra stripes guardrail that intelligence degree is high |
| CN109191849A (en) * | 2018-10-22 | 2019-01-11 | 北京航空航天大学 | A kind of traffic congestion Duration Prediction method based on multi-source data feature extraction |
| CN109191840A (en) * | 2018-09-13 | 2019-01-11 | 电子科技大学 | A kind of real-time traffic condition determination method based on intelligent terminal |
| CN109240090A (en) * | 2018-11-08 | 2019-01-18 | 浙江大学 | A kind of adaptive soft-sensor modeling method of the incremental learning XGBOOST model based on time difference |
| US20190036816A1 (en) * | 2017-07-31 | 2019-01-31 | Cisco Technology, Inc. | Controlling a software-defined network |
| CN109359788A (en) * | 2018-12-06 | 2019-02-19 | 西南交通大学 | A kind of initial late method for building up for influencing prediction model of bullet train |
-
2019
- 2019-03-25 CN CN201910229274.0A patent/CN109993356A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635089A (en) * | 2009-05-22 | 2010-01-27 | 上海宝康电子控制工程有限公司 | System and method for coordinating traffic control and traffic guidance |
| US20170185904A1 (en) * | 2015-12-29 | 2017-06-29 | 24/7 Customer, Inc. | Method and apparatus for facilitating on-demand building of predictive models |
| US20190036816A1 (en) * | 2017-07-31 | 2019-01-31 | Cisco Technology, Inc. | Controlling a software-defined network |
| CN107871167A (en) * | 2017-10-20 | 2018-04-03 | 广东工业大学 | A kind of causal structure learning method based on likelihood score |
| CN108629985A (en) * | 2018-04-25 | 2018-10-09 | 梧州井儿铺贸易有限公司 | A kind of zebra stripes guardrail that intelligence degree is high |
| CN109191840A (en) * | 2018-09-13 | 2019-01-11 | 电子科技大学 | A kind of real-time traffic condition determination method based on intelligent terminal |
| CN109191849A (en) * | 2018-10-22 | 2019-01-11 | 北京航空航天大学 | A kind of traffic congestion Duration Prediction method based on multi-source data feature extraction |
| CN109240090A (en) * | 2018-11-08 | 2019-01-18 | 浙江大学 | A kind of adaptive soft-sensor modeling method of the incremental learning XGBOOST model based on time difference |
| CN109359788A (en) * | 2018-12-06 | 2019-02-19 | 西南交通大学 | A kind of initial late method for building up for influencing prediction model of bullet train |
Non-Patent Citations (2)
| Title |
|---|
| 刘振辉: "基于多模型融合的短时交通流量预测", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 范有明 等: "智能道路机非分隔护栏控制***的研究", 《中国战略新兴产业》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570862A (en) * | 2021-07-28 | 2021-10-29 | 太原理工大学 | XGboost algorithm-based large traffic jam early warning method |
| CN113570862B (en) * | 2021-07-28 | 2022-05-10 | 太原理工大学 | XGboost algorithm-based large traffic jam early warning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gu et al. | Utilizing UAV video data for in-depth analysis of drivers’ crash risk at interchange merging areas | |
| Wang et al. | Multi-train trajectory optimization for energy efficiency and delay recovery on single-track railway lines | |
| Zhao et al. | Gap acceptance probability model for pedestrians at unsignalized mid-block crosswalks based on logistic regression | |
| Zhang et al. | The effects of sunshields on red light running behavior of cyclists and electric bike riders | |
| Brosseau et al. | The impact of waiting time and other factors on dangerous pedestrian crossings and violations at signalized intersections: A case study in Montreal | |
| Bartholdi III et al. | A self-coördinating bus route to resist bus bunching | |
| CN105046956B (en) | Traffic flow simulating and predicting method based on turning probability | |
| CN104715610B (en) | A kind of traffic index computational methods towards urban transportation | |
| Yang et al. | An accelerated failure time model for investigating pedestrian crossing behavior and waiting times at signalized intersections | |
| CN111681433B (en) | Intersection traffic signal lamp timing optimization method and device | |
| CN106997689B (en) | V2P based on crossing avoids collision method | |
| Wey | Model formulation and solution algorithm of traffic signal control in an urban network | |
| CN109754597A (en) | A kind of urban road area congestion regulating strategy recommender system and method | |
| Zhou et al. | Active signal priority control method for bus rapid transit based on Vehicle Infrastructure Integration | |
| Jin et al. | Observational characteristics of pedestrian flows under high-density conditions based on controlled experiments | |
| Yao et al. | Emergency vehicle route oriented signal coordinated control model with two-level programming | |
| Chandra et al. | Accessibility evaluations for nighttime walking and bicycling for low-income shift workers | |
| CN110009257A (en) | Multiple dimensioned variable window cellular Automation Model based on urban traffic blocking sprawling analysis | |
| CN110491125A (en) | A kind of traffic prewarning guidance information generation method | |
| Ding et al. | Strategy for multiobjective transit signal priority with prediction of bus dwell time at stops | |
| Mirhashemi et al. | Macro-level literature analysis on pedestrian safety: Bibliometric overview, conceptual frames, and trends | |
| Goñi-Ros et al. | Empirical analysis of the macroscopic characteristics of bicycle flow during the queue discharge process at a signalized intersection | |
| CN104882005B (en) | A kind of method and device for detecting lane flow amount | |
| CN103927901B (en) | A kind of accurate recording viewing area congestion in road causes the method and system of point | |
| Davis | Realizing Wardrop equilibria with real-time traffic information |
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: 20190709 |