CN109712394A - A kind of congestion regions discovery method - Google Patents
A kind of congestion regions discovery method Download PDFInfo
- Publication number
- CN109712394A CN109712394A CN201910035076.0A CN201910035076A CN109712394A CN 109712394 A CN109712394 A CN 109712394A CN 201910035076 A CN201910035076 A CN 201910035076A CN 109712394 A CN109712394 A CN 109712394A
- Authority
- CN
- China
- Prior art keywords
- congestion
- index
- node
- congestion regions
- regions
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention belongs to intelligent transportation system technical fields, are related to a kind of congestion regions discovery method, urban congestion region can be accurately calculated, for the optimization of urban road system and the promotion of service level.Intersection network, networking rule and stifled point are first defined respectively, stifled point has following index auxiliary to calculate, it is Rate Index, time occupancy index and section composite index respectively, then congestion regions discovery is carried out, the definition of congestion regions clear first, congestion regions should be the set of congestion points within the scope of one here, in this region, stifled point distribution is more intensive, and stifled line all roads in region account for relatively high；Wherein congestion regions state evaluation index is as follows: congestion regions can be measured in terms of congestion index and congestion density two, and present general inventive concept is ingenious, and calculated result is accurate, and calculating process is convenient and efficient, and application environment is friendly, wide market.
Description
Technical field:
The invention belongs to intelligent transportation system technical field, it is related to the congestion regions discovery side at a kind of urban road and crossing
Method, especially a kind of congestion regions find method, urban congestion region can be accurately calculated, for the excellent of urban road system
Change the promotion with service level.
Background technique:
As Urbanization in China is accelerated, traffic jam issue becomes more and more prominent.Traffic congestion phenomenon is not only made
At the increase of city cost of investment, mass energy is wasted, increases environmental pollution, damage people's health and is brought
Psychiatric disturbance reduces social activities efficiency, will cause biggish economic loss.This also shows that the city of traffic severe congestion
Plan unreasonable, means of transportation are not perfect, manage not scientific.Potential urban congestion regional issue is found in time, is carried out in time
Planning prepares just to be particularly important.The sensing data of bulky complex provides important data for congestion discovery on road
Source, but tradition discovery algorithm realizes that the effect is unsatisfactory.
Based on this, the present invention seeks to design a kind of traffic congestion region discovery method, and this method can be based on road traffic
Sensing data, crossing, section and the region for defining, finding out congestion provide the decision-making foundation of urban traffic control optimization, into
And improve urban transportation traffic efficiency.
Summary of the invention:
It is an object of the invention to overcome defect of the existing technology, design provides a kind of congestion regions discovery method,
This method can be found urban congestion region and potential congestion regions in time, be carried out for urban planning by Modeling analysis
Screen the preparation of key area.
To achieve the goals above, a kind of congestion regions discovery method that this hair is related to specifically calculates step according to such as lower section
Formula carries out:
S1, preparation:
For the discovery work for realizing the congestion regions for giving the period, following three preconditions are needed:
(1) intersection network: when analysis congestion regions, it is necessary first to be established according to syntople of the intersection on road
Intersection, referred to as intersection network are loaded on the network of intersection according to data characteristics, further according to intersection net
Some data of network find congestion regions；
(2) networking rule: the frontier juncture system, company according to upstream and downstream syntople networking of the intersection on road, between node
It is determined according to corresponding intersection；
(3) it blocks up point: according to road data, thering is following index auxiliary to calculate
A, Rate Index: the relationship of speed and speed congestion index is in a linear relationship, is set as free stream velocity and (is defaulted as
80km/h), then differentiate that the index of traffic behavior can be calculate by the following formula:
JvFor speed congestion index,For this die rolled section speed；
B, time occupancy index: time occupancy and the relationship of time occupancy congestion index are inversely proportional, then the time accounts for
Have the calculation formula of rate traffic index as follows:
JoFor time occupancy congestion index,This die rolled section time occupancy；
C, section composite index is established: being comprehensively considered the influence of speed and time occupancy, is established urban traffic index such as
Under:
J=η Jv+(1-η)Jo
J is the comprehensive sex index of traffic behavior；Jv is speed congestion index；Jo is time occupancy congestion index；η is speed
The weight coefficient of index and time occupancy index, value 0-1, system can be defaulted as 0.5, can be according to the actual situation
It is adjusted；
S2, congestion regions discovery:
The definition of congestion regions clear first, congestion regions should be the set of congestion points within the scope of one here, at this
In a region, stifled point distribution is more intensive, and stifled line all roads in region account for relatively high；
Related definition, degree centrality is that the Measure Indexes of node center are portrayed in network analysis, the section of a node
The more big degree centrality for just meaning this node of point degree is higher, and the node is more important in a network, and directed networks are by node
Out-degree and in-degree and degree centrality as node,
Surrounding intensively blocks up point: using node a as the center of circle, distance d is radius, when the stifled point around stifled is densely distributed, is determined
Justice is that surrounding intensively blocks up point, and density index is as follows, and N is represented using a as in the circle in the center of circle, the number of node, M refers in this N number of node
There are M stifled points, define density threshold ec, as the density C of node ii≥ec, claiming node i is around intensively to block up a little,
The congestion regions discovery of given period is described as follows:
Input: intersection network G blocks up point set P, accessed node setDensity threshold eC, distance threshold eD
Output: congestion regions F
Step1: traversing stifled point set P, and all block up is pressed illumination centrality by the density index and degree centrality of the stifled point of calculating
Descending arrangement deposit queue M, congestion regions serial number m=1；
Step2: if queue M is not sky, node a is taken out from M, otherwise goes to step8；
Step3: ifAnd Ca >=eC, node a enters transient node queue R and otherwise goes to step2；
Step4: if queue R is not sky, node c is taken out from R, D=D ∪ { c }, Fm=Fm ∪ { c } are otherwise gone to
step7；
Step5: it if stifled point set P is not sky, takes out node b and otherwise goes to step4；
Step6: ifLinear distance d between calculate node cbcbIf dcb≤ ed, and Cb >=ec, node b enters
Queue R, D=D ∪ { b } otherwise goes to step5；
Step7: congestion regions Fm, F=F ∪ a Fm, m=m+1 are obtained；
Step8: the set F of congestion regions is exported；
Each of last congestion regions set F element is exactly a congestion regions；
Wherein congestion regions state evaluation index is as follows: congestion regions can be measured in terms of following two
A, congestion index defines intersection congestion index CrC:
Wherein, M is the intersection set in single congestion regions, | M | the number for representing element in set, according to calculating
Congestion index is as a result, control jam level division table obtains the whole congestion status evaluation of congestion regions；
B, congestion density, it is assumed that M is the intersection set in single congestion regions, | M | the number of element in set is represented,
A is the highest stifled point of M moderate centrality, and D is the diameter of M, and congestion density (CrD) is defined as to the border circular areas using D as diameter
Interior stifled quantity and number of nodes ratio (numerical values recited of D can according to demand, the reality factors such as urban road actual conditions into
Row adjustment), the bigger expression congestion regions of value for being apparent from CrD are more intensive,
N indicates the interstitial content in border circular areas, is stifled point with red point, and red line indicates the diameter of the congestion regions,
Intermediate point is found out as the center of circle, finds out the border circular areas, and calculates the value of CrD.
Stifled point is clustered according to the linear distance between node using clustering algorithm in the present invention, it is contemplated that congestion regions
The set of point dense distribution is blocked up in description, therefore the starting point of algorithm is determined according to the degree centrality size of node, ensure that congestion area
The intensive in domain.
Distance threshold e in the present inventiond, it is an empirical value, situations such as different periods, urban road distribution, edTake
Value is different, edValue it is bigger, it is bigger to will lead to a final congestion regions range；The wherein value of empirical value is to rely on to go through
History data experience obtains.
Transient node queue R be under the conditions of simulation code operating condition for, node be stored in temporary queue (data
Structure), it is same nature with the queue before pseudocode, first queue M is to be put into all point sequences, second queue
R is the point that filtration fraction does not meet threshold value.
Compared with prior art, the present invention what is obtained has the beneficial effect that:
1. the concept of intersection network is introduced, the concrete condition of more intuitive reaction traffic congestion, and meanwhile it is easy to operate and cut
It is real feasible.
2. according to the urban traffic index definition of speed and time occupancy, more it is succinct effectively, reduce to data according to
Rely.
3. the field of data mining clustering algorithm has been used, so that the similitude between the element in same class is than other classes
The similitude of element is stronger, makes the homogeney maximization and the heterogeneous maximization of element between class and class of element between class.It is main
Foundation is that the sample gathered in the same data set should be similar to each other, and the sample for belonging to different groups should be sufficiently dissimilar.
It can more accurately determine congestion regions and range.
4. its general plotting is ingenious, calculated result is accurate, and calculating process is convenient and efficient, and application environment is friendly, market prospects
It is wide.
Detailed description of the invention:
Fig. 1 is network model figure in intersection of the present invention.
Fig. 2 is congestion regions schematic diagram of the present invention.
Fig. 3 is jam situation schematic diagram of the present invention.
Specific embodiment:
Below by example with reference, the present invention is further described.
Embodiment 1:
The traffic congestion region discovery method that the present embodiment is related to is achieved through the following technical solutions:
S1, preparation:
For the discovery work for realizing the congestion regions for giving the period, following three preconditions are needed:
(1) intersection network: when analysis congestion regions, it is necessary first to be established according to syntople of the intersection on road
Intersection, referred to as: intersection network；It according to data characteristics, is loaded on the network of intersection, further according to intersection network
Some data, find congestion regions；
(2) networking rule: according to upstream and downstream syntople networking of the intersection on road, as shown in Figure 1, A is the upper of C
Swim intersection, B is section between AC, and when constructing intersection network, the place A generates four nodes, 4 nodes of generation at C, node it
Between frontier juncture system, company determined according to corresponding intersection；
(3) it blocks up point: according to road data, thering is following index auxiliary to calculate
A, Rate Index: the relationship of speed and speed congestion index is in a linear relationship, is set as free stream velocity and (is defaulted as
80km/h), then differentiate that the index of traffic behavior can be calculate by the following formula:
Jv- speed congestion index,- this die rolled section speed；
B, time occupancy index: time occupancy and the relationship of time occupancy congestion index are inversely proportional, then the time accounts for
There is the calculation formula of rate traffic index as follows
JoFor time occupancy congestion index,This die rolled section time occupancy；
C, section composite index is established: being comprehensively considered the influence of speed and time occupancy, is established urban traffic index such as
Under:
J=η Jv+(1-η)Jo
J is the comprehensive sex index of traffic behavior；Jv is speed congestion index；Jo is time occupancy congestion index；η is speed
The weight coefficient of index and time occupancy index, value 0-1, system can be defaulted as 0.5, can be according to the actual situation
It is adjusted；
S2, congestion regions discovery:
The definition of congestion regions clear first, congestion regions should be the set of congestion points within the scope of one here, at this
In a region, stifled point distribution is more intensive, and stifled line all roads in region account for relatively high；
The congestion regions discovery of given period is described as follows:
Input: G blocks up point set P, accessed node setDensity threshold eC, distance threshold eD
Output: congestion regions F
Step1: traversing stifled point set P, and all block up is pressed illumination centrality by the density index and degree centrality of the stifled point of calculating
Descending arrangement deposit queue M, congestion regions serial number m=1；
Step2: if queue M is not sky, node a is taken out from M, otherwise goes to step8；
Step3: ifAnd otherwise Ca >=eC, node a enqueue R go to step2；
Step4: if queue R is not sky, node c is taken out from R, D=D ∪ { c }, Fm=Fm ∪ { c } are otherwise gone to
step7；
Step5: it if stifled point set P is not sky, takes out node b and otherwise goes to step4；
Step6: ifLinear distance dcb between calculate node cb, if dcb≤ed, and Cb >=ec, node
B enqueue R, D=D ∪ { b } otherwise goes to step5；
Step7: congestion regions Fm, F=F ∪ a Fm, m=m+1 are obtained；
Step8: the set F of congestion regions is exported；
S3, evaluation index:
Congestion regions state evaluation index: congestion regions can be measured in terms of following two
(1) congestion index defines intersection congestion index (CrC)
Wherein, M is the intersection set in single congestion regions, | M | the number for representing element in set, according to calculating
Congestion index is as a result, control jam level division table obtains the whole congestion status evaluation of congestion regions；
(2) congestion density, it is assumed that M is the intersection set in single congestion regions, | M | represent of element in set
Number, a is the highest stifled point of M moderate centrality, and D is the diameter of M, and congestion density (CrD) is defined as to the circle using D as diameter
Blocked up in domain point quantity and number of nodes ratio (numerical values recited of D can according to demand, the reality factors such as urban road actual conditions
It is adjusted), the bigger expression congestion regions of value for being apparent from CrD are more intensive,
N indicates the interstitial content in border circular areas, as shown in Fig. 2, point red in figure is stifled point, red line indicates the congestion
The diameter in region finds out intermediate point as the center of circle, finds out the border circular areas, and in example below, the value of CrD is 6/11；
Embodiment 2:
The present embodiment uses total seven days data of Qingdao City's operative sensor, given time period 7:00-8:30 (time
Section can customize), with five minutes for interval aggregated data, congestion regions are analyzed, following two aspects work is based primarily upon following
Table, table example is as follows, ID representative sensor number, NAME is position and the title of sensor, is followed by seven days numbers
According to the congestion index calculated, amount to 2016 (12*24*7), congestion threshold value is positioned 0.5 by result below；
1 operative sensor congestion coefficients statistics of table
Congestion regions few examples are as follows:
2 part congestion regions example of table
Following table is the range information of first congestion regions
Certain the congestion regions set of sensors example of table 3
Claims (4)
1. a kind of congestion regions find method, it is characterised in that the specific step that calculates is carried out as follows:
S1, preparation:
For the discovery work for realizing the congestion regions for giving the period, following three preconditions are needed:
(1) intersection network: when analysis congestion regions, it is necessary first to be established and be intersected according to syntople of the intersection on road
Mouth road, referred to as intersection network is loaded on the network of intersection according to data characteristics, further according to intersection network
Some data find congestion regions；
(2) networking rule: according to upstream and downstream syntople networking of the intersection on road, frontier juncture system, company between node according to
Corresponding intersection determines；
(3) it blocks up point: according to road data, thering is following index auxiliary to calculate
A, Rate Index: the relationship of speed and speed congestion index is in a linear relationship, is set as free stream velocity and (is defaulted as 80km/
H), then differentiate that the index of traffic behavior can be calculate by the following formula:
Jv is speed congestion index,For this die rolled section speed；
B, time occupancy index: time occupancy and the relationship of time occupancy congestion index are inversely proportional, then time occupancy
The calculation formula of traffic index is as follows:
JoFor time occupancy congestion index,This die rolled section time occupancy；
C, section composite index is established: comprehensively consider the influence of speed and time occupancy, it is as follows to establish urban traffic index:
J=η Jv+(1-η)Jo
J is the comprehensive sex index of traffic behavior；Jv is speed congestion index；Jo is time occupancy congestion index；η is speed index
With the weight coefficient of time occupancy index, value 0-1, system can be defaulted as 0.5, can be adjusted according to the actual situation
It is whole；
S2, congestion regions discovery:
The definition of congestion regions clear first, congestion regions should be the set of congestion points within the scope of one here, in this area
In domain, stifled point distribution is more intensive, and stifled line all roads in region account for relatively high；
Related definition, degree centrality is that the Measure Indexes of node center are portrayed in network analysis, the node degree of a node
The more big degree centrality for just meaning this node is higher, and the node is more important in a network, and directed networks are by the out-degree of node
With in-degree and as the degree centrality of node,
Surrounding intensively blocks up point: using node a as the center of circle, distance d is radius, when the stifled point around stifled is densely distributed, is defined as
Surrounding intensively blocks up point, and density index is as follows, and N is represented using a as in the circle in the center of circle, the number of node, M refers to that there are M in this N number of node
A stifled point defines density threshold ec, as the density C of node ii≥ec, claiming node i is around intensively to block up a little,
The congestion regions discovery of given period is described as follows:
Input: intersection network G blocks up point set P, accessed node setDensity threshold eC, distance threshold eD
Output: congestion regions F
Step1: traversing stifled point set P, and all block up is pressed illumination centrality descending by the density index and degree centrality of the stifled point of calculating
Arrangement deposit queue M, congestion regions serial number m=1；
Step2: if queue M is not sky, node a is taken out from M, otherwise goes to step8；
Step3: ifAnd Ca >=eC, node a enters transient node queue R and otherwise goes to step2；
Step4: if queue R is not sky, node c is taken out from R, D=D ∪ { c }, Fm=Fm ∪ { c } are otherwise gone to
step7；
Step5: it if stifled point set P is not sky, takes out node b and otherwise goes to step4；
Step6: ifLinear distance d between calculate node cbcbIf dcb≤ ed, and Cb >=ec, node b enqueue
R, D=D ∪ { b } otherwise go to step5；
Step7: congestion regions Fm, F=F ∪ a Fm, m=m+1 are obtained；
Step8: the set F of congestion regions is exported；
Each of last congestion regions set F element is exactly a congestion regions；
Wherein congestion regions state evaluation index is as follows: congestion regions can be measured in terms of following two
A, congestion index defines intersection congestion index CrC:
Wherein, M is the intersection set in single congestion regions, | M | the number for representing element in set, according to calculating congestion
Index results, control jam level division table obtain the whole congestion status evaluation of congestion regions；
B, congestion density, it is assumed that M is the intersection set in single congestion regions, | M | the number of element in set is represented, a is M
The highest stifled point of moderate centrality, D is the diameter of M, and congestion density CrD is defined as using D to block up point in the border circular areas of diameter
Quantity and number of nodes ratio (numerical values recited of D can according to demand, the reality factors such as urban road actual conditions are adjusted
It is whole), the bigger expression congestion regions of value for being apparent from CrD are more intensive,
N indicates the interstitial content in border circular areas, is stifled point with red point, and red line indicates the diameter of the congestion regions, finds out
Intermediate point finds out the border circular areas as the center of circle, and calculates the value of CrD.
2. a kind of congestion regions according to claim 1 find method, it is characterised in that apply clustering algorithm in the present invention
Stifled point is clustered according to the linear distance between node, it is contemplated that the set of the stifled point dense distribution of congestion regions description, therefore
The starting point that algorithm is determined according to the degree centrality size of node, ensure that the intensive of congestion regions.
3. a kind of congestion regions according to claim 1 find method, it is characterised in that middle distance threshold edAccording to such as lower section
Formula definition, edIt is an empirical value, situations such as different periods, urban road distribution, edValue it is different, edValue it is bigger,
It is bigger to will lead to a final congestion regions range；The wherein value of empirical value is obtained by historical data experience.
4. a kind of congestion regions according to claim 1 find method, it is characterised in that transient node queue R is to simulate
For under the conditions of code operating condition, node is stored in temporary queue, with the queue before pseudocode be same nature, first
A queue M is to be put into all point sequences, and second queue R is the point that filtration fraction does not meet threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035076.0A CN109712394A (en) | 2019-01-15 | 2019-01-15 | A kind of congestion regions discovery method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035076.0A CN109712394A (en) | 2019-01-15 | 2019-01-15 | A kind of congestion regions discovery method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109712394A true CN109712394A (en) | 2019-05-03 |
Family
ID=66260104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910035076.0A Pending CN109712394A (en) | 2019-01-15 | 2019-01-15 | A kind of congestion regions discovery method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712394A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116311990A (en) * | 2023-03-27 | 2023-06-23 | 南京莱斯信息技术股份有限公司 | Signal control method based on fusion of Internet data and detection data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007026300A (en) * | 2005-07-20 | 2007-02-01 | Matsushita Electric Ind Co Ltd | Traffic flow abnormality detector and traffic flow abnormality detection method |
| JP2007241987A (en) * | 2006-02-07 | 2007-09-20 | Matsushita Electric Ind Co Ltd | Method and device for generating traffic information |
| CN102968901A (en) * | 2012-11-30 | 2013-03-13 | 青岛海信网络科技股份有限公司 | Method for acquiring regional congestion information and regional congestion analyzing device |
| CN103021176A (en) * | 2012-11-29 | 2013-04-03 | 浙江大学 | Discriminating method based on section detector for urban traffic state |
| CN103198658A (en) * | 2013-03-25 | 2013-07-10 | 浙江大学 | Urban road traffic state non-equilibrium degree detection method |
| CN103593976A (en) * | 2013-11-28 | 2014-02-19 | 青岛海信网络科技股份有限公司 | Road traffic state determining method and system based on detector |
| CN108109382A (en) * | 2018-02-05 | 2018-06-01 | 青岛大学 | A kind of congestion points based on composite network, congestion line, the discovery method of congestion regions |
| EP3340203A1 (en) * | 2016-12-20 | 2018-06-27 | Bayerische Motoren Werke Aktiengesellschaft | Traffic velocity estimation system |
| CN108806250A (en) * | 2018-06-08 | 2018-11-13 | 北京航空航天大学 | A kind of area traffic jamming evaluation method based on speed sampling data |
-
2019
- 2019-01-15 CN CN201910035076.0A patent/CN109712394A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007026300A (en) * | 2005-07-20 | 2007-02-01 | Matsushita Electric Ind Co Ltd | Traffic flow abnormality detector and traffic flow abnormality detection method |
| JP2007241987A (en) * | 2006-02-07 | 2007-09-20 | Matsushita Electric Ind Co Ltd | Method and device for generating traffic information |
| CN103021176A (en) * | 2012-11-29 | 2013-04-03 | 浙江大学 | Discriminating method based on section detector for urban traffic state |
| CN102968901A (en) * | 2012-11-30 | 2013-03-13 | 青岛海信网络科技股份有限公司 | Method for acquiring regional congestion information and regional congestion analyzing device |
| CN103198658A (en) * | 2013-03-25 | 2013-07-10 | 浙江大学 | Urban road traffic state non-equilibrium degree detection method |
| CN103593976A (en) * | 2013-11-28 | 2014-02-19 | 青岛海信网络科技股份有限公司 | Road traffic state determining method and system based on detector |
| EP3340203A1 (en) * | 2016-12-20 | 2018-06-27 | Bayerische Motoren Werke Aktiengesellschaft | Traffic velocity estimation system |
| CN108109382A (en) * | 2018-02-05 | 2018-06-01 | 青岛大学 | A kind of congestion points based on composite network, congestion line, the discovery method of congestion regions |
| CN108806250A (en) * | 2018-06-08 | 2018-11-13 | 北京航空航天大学 | A kind of area traffic jamming evaluation method based on speed sampling data |
Non-Patent Citations (3)
| Title |
|---|
| 于泉: "高速公路交通状态判别模型研究", 《交通运输工程与信息学报》 * |
| 刘畅: "基于DBSCAN算法的城市交通拥堵区域发现", 《智能计算机与应用》 * |
| 吴梅: "一种基于加权道路网络的拥堵区域划分方法", 《青岛大学学报（工程技术版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116311990A (en) * | 2023-03-27 | 2023-06-23 | 南京莱斯信息技术股份有限公司 | Signal control method based on fusion of Internet data and detection data |
| CN116311990B (en) * | 2023-03-27 | 2023-12-22 | 南京莱斯信息技术股份有限公司 | Signal control method based on fusion of Internet data and detection data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| CN106816008B (en) | A kind of congestion in road early warning and congestion form time forecasting methods | |
| CN104050803B (en) | A kind of region highway network evaluation of running status method | |
| CN108364467A (en) | A kind of traffic information prediction technique based on modified decision Tree algorithms | |
| WO2019047905A1 (en) | Road traffic analysis system, method and apparatus | |
| CN103699775B (en) | Urban road traffic guidance strategy automatic generation method and system | |
| CN103198658B (en) | Urban road traffic state non-equilibrium degree detection method | |
| CN108470444A (en) | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization | |
| CN105761492B (en) | A kind of a wide range of highway network Dynamic Assignment method based on network flow | |
| CN104680788B (en) | A kind of eco-resi stance computational methods for traffic route selection | |
| CN104574968B (en) | Determining method for threshold traffic state parameter | |
| CN101789182A (en) | Traffic signal control system and method based on parallel simulation technique | |
| CN105679025B (en) | A kind of arterial street travel time estimation method based on Changeable weight mixed distribution | |
| CN106887141B (en) | Queuing theory-based continuous traffic node congestion degree prediction model, system and method | |
| CN111091295B (en) | Urban area boundary control system | |
| CN108427273A (en) | A kind of Feedback Control Design method reducing traffic congestion phenomenon | |
| WO2023216793A1 (en) | Dynamic speed limit control method for highway bottleneck section in mixed traffic flow environment | |
| CN112462603A (en) | Optimal regulation and control method, device, equipment and medium for regional atmosphere heavy pollution emergency | |
| CN106530710B (en) | A kind of freeway traffic index forecasting method and system towards manager | |
| CN105551250A (en) | Method for discriminating urban road intersection operation state on the basis of interval clustering | |
| CN109712394A (en) | A kind of congestion regions discovery method | |
| CN110097757B (en) | Intersection group critical path identification method based on depth-first search | |
| CN103000026A (en) | Bus arrival distribution analysis method of bus station | |
| CN113096377B (en) | Vehicle carpooling planning method based on urban heterogeneity | |
| CN115081846A (en) | Quantitative evaluation technology for air quality meteorological condition contribution rate |
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 |
Application publication date: 20190503 |
|
| RJ01 | Rejection of invention patent application after publication |