CN109858559A - Adaptive traffic analysis Railway network simplification method based on traffic flow macroscopic view parent map - Google Patents
Adaptive traffic analysis Railway network simplification method based on traffic flow macroscopic view parent map Download PDFInfo
- Publication number
- CN109858559A CN109858559A CN201910114744.9A CN201910114744A CN109858559A CN 109858559 A CN109858559 A CN 109858559A CN 201910114744 A CN201910114744 A CN 201910114744A CN 109858559 A CN109858559 A CN 109858559A
- Authority
- CN
- China
- Prior art keywords
- traffic
- road network
- section
- road
- period
- 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
Abstract
The present invention relates to a kind of adaptive traffic analysis Railway network simplification methods based on traffic flow macroscopic view parent map, include: step S1: drawing out traffic flow macroscopic view parent map according to road grid traffic stream state data, using clustering method, MFD is subjected to Time segments division by road network performance；Step S2: the road network of each sub-period is simplified respectively；Step S3: the Used in Dynamic Traffic Assignment based on emulation is carried out after combining the road network of several simplified different resolutions.Compared with prior art, the present invention, which has, to be adaptively adjusted Time segments division according to different road grid traffic situations, be more in line with true traffic condition, the reduction of road network scale improves the efficiency of traffic analysis, greatly reduces the calculation amount of emulation and distribution.
Description
Technical field
The present invention relates to traffic engineering fields, more particularly, to a kind of adaptive traffic based on traffic flow macroscopic view parent map
Analyze Railway network simplification method.
Background technique
The complexity of traffic analysis road network and traffic analysis efficiency are closely related: on the one hand, dense road network being capable of essence
The true traffic condition of true reflection, but calculation amount is huge, and computational efficiency is low；On the other hand, sparse road network can substantially reduce
Computation burden, but rush hour additional congestion may be brought.As it can be seen that single analysis road network cannot take into account analysis precision and
Analysis efficiency, therefore this research is intended to the dynamic traffic situation according to road network, and the heterogeneous time is adaptively divided on time dimension
Section simplifies the road network for obtaining traffic condition therewith and matching for each heterogeneous period, realizes that precision is adjustable on time dimension
The traffic analysis method of section improves the efficiency of traffic analysis while guaranteeing analysis precision.
Currently, Railway network simplification method both domestic and external be all largely static, not fine consideration traffic condition when
Between it is heterogeneous, i.e., what true road grid traffic situation always fluctuated, there are the early evening peak peace peak period, static simplification method is not
It can obtain the road network to match with each period traffic condition.In recent years, simple dynamic simplification method is gradually suggested, but only
It is that will be evenly dividing the period to cannot be guaranteed that road network performance is identical in each period.Traffic flow macroscopic view parent map (Macroscopic
Fundamental Diagram, MFD) as the parent map for describing network traffic flow overall operation rule, it is able to reflect road network
The dynamic change of integral level and traffic.Therefore, the adaptive traffic analysis Railway network simplification method based on MFD is established for road network
Real-time dynamic simplification have important practical significance.
Summary of the invention
It is macro based on traffic flow that it is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind
See the adaptive traffic analysis Railway network simplification method of parent map: a kind of " to be based on improved Teoplitz inverse covariance multi-dimensional time
The Railway network simplification method of Sequence clustering method " and " connectivity enhancing algorithm ", the Time Series Clustering based on MFD consider traffic
The temporal heterogeneity of situation shows the similar period to divide and obtain several road networks, reflects the traffic of each period respectively
Behavioral characteristics；" connectivity enhancing algorithm " can be obtained according to clustering obtaining as a result, extracting road network Important Sections at times
The simplification road network to match with traffic condition, peak time dense road network can guarantee to simplify road network analysis precision, when flat peak
Phase sparse road network can then improve computational efficiency, existing for the static simplified method of very good solution and simple dynamic simplification method
Problem, to realize the adaptive simplifying to traffic analysis road network.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of adaptive traffic analysis Railway network simplification method based on traffic flow macroscopic view parent map, comprising:
Step S1: drawing out traffic flow macroscopic view parent map according to road grid traffic stream state data, will using clustering method
MFD carries out Time segments division by road network performance；
Step S2: the road network of each sub-period is simplified respectively；
Step S3: the dynamic traffic based on emulation point is carried out after combining the road network of several simplified different resolutions
Match.
The step S1 is specifically included:
Step S11: the road grid traffic flow data in the Analysis on Selecting period obtains average flow rate and averag density；
Step S12: clustering road network average flow rate, averag density, so that objective function is reached minimum, obtains several
Road network shows approximately uniform cluster P={ P1,,,K, the endpoint of each cluster is exactly the timing node of each sub-period；
Step S13: according to road network actual traffic situation, number of segment S when presetting one reasonably, selection makes each period road network
The smallest scheme of the sum of density criterion difference obtains corresponding penalty term as optimal case；
Step S14: classification situation is embodied by traffic flow macroscopic view parent map, for different traffic conditions, is generated not
Same classification schemes.
The mathematic(al) representation of the average flow rate are as follows:
Wherein:For average flow rate, n is section quantity, qlFor the flow of section l,
The mathematic(al) representation of the averag density are as follows:
Wherein:For road network averag density, llFor the length of section l, lanelFor the number of track-lines of section l, klFor section l's
Density.
In the step S12, penalty term β ', and β '≤β are introduced separately into the time range where peak period morning and evening,
The mathematic(al) representation of the objective function are as follows:
Wherein: ΘiFor the covariance inverse matrix of the i-th class, P is that the time series of all classes distributes set, and Γ is all kinds of
Covariance inverse matrix set, K are the number of Time Sub-series, and λ is regularization parameter, determines the sparse degree of matrix, ‖ ‖1For
L1 norm, XtFor Time Sub-series ,-ll (Xt,Θi) it is Time Sub-series XtBelong to the log-likelihood of the i-th class, β is to work as the period of the day from 11 p.m. to 1 a.m
Between sequence Xt-1It is not belonging to penalty term when the i-th class, β ' is as Time Sub-series X 't-1It is not belonging to penalty term when the i-th class, PiFor
It is assigned to the time series set of the i-th class,To judge subsequence Xt-1Whether i-th class, X are belonged tot-1To be not belonging to morning
The Time Sub-series of evening peak period, X 't-1For the Time Sub-series for belonging to peak period morning and evening.
The mathematic(al) representation of the penalty term are as follows:
Wherein: ktFor the road mileage of t moment, k is road network averag density, kt(β ') is when belonging to the t of peak period morning and evening
The road mileage at quarter, k (β ') are the average road mileage of period s.
The step S2 is specifically included:
Step S21: from original road network NoIn extract only include high-grade section initial most simple road network Np；
Step S22: based on the timing node obtained after cluster, to the road network N of sub-period spsIt carries out section extension: being up to
The section travel time of dynamic Users equilibrium combines OD as section cost, to terminus any in road networkkIf connect the group and
Section lo(lo∈No) travel time toLess than NpsIn have section lps(lps∈Nps) travel time tps, then by loIncrease
To set NpsIn, last road network N after the simplification of the periodrsIn only comprising with obvious traffic impact Important Sections；
Step S23: the simplification road network set N by the simplification route combination of several differing complexities is obtainedr=
{Nr1,,,Nrs}。
The step S3 is specifically included:
Step S31: in original road network NoOn the basis of be every section addition label to distinguish the section at various moments
Existence；
Step S32: road network N will be combinedcApply to middle sight traffic simulation software and carry out operation, when section is in different periods
When existence is inconsistent, such as from making the vehicle stop motion on the section, while not having vehicle in the presence of in the absence of becoming
Into the section, until the existence in section reverts to presence, iteration is until NcReach dynamic Users equilibrium state.
Compared with prior art, the invention has the following advantages:
1) dynamic change of road network entirety flow, density, speed within the analysis period is considered.
2) Time segments division will be entirely analyzed into several sub-periods, guarantee the road net traffic state approximation phase of each sub-period
Together.
3) it can be adaptively adjusted Time segments division according to different road grid traffic situations, is more in line with true traffic shape
Condition.
4) reduction of road network scale improves the efficiency of traffic analysis, greatly reduces the calculation amount of emulation and distribution.
Detailed description of the invention
Fig. 1 is traffic analysis road network schematic diagram used in the embodiment of the present invention；
Fig. 2 is adaptive Railway network simplification flow chart of the present invention；
Fig. 3 is the road network traffic flow macroscopic view parent map (MFD) of the embodiment of the present invention；
Fig. 4 is MFD cluster result schematic diagram of the present invention；
Fig. 5 is the transport need schematic diagram for each sub-period that the present invention divides；
Fig. 6 is " connectivity enhancing algorithm " flow chart of the present invention；
Fig. 7 is that each sub-period of the present invention simplifies road network schematic diagram；
Fig. 8 is the comparison diagram that the present invention simplifies road network and original road network simulation time；
Fig. 9 is the comparison diagram that the present invention simplifies road network and original road network distributes the time.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
A kind of adaptive traffic analysis Railway network simplification method based on traffic flow macroscopic view parent map, comprising:
Step S1: drawing out traffic flow macroscopic view parent map according to road grid traffic stream state data, will using clustering method
MFD carries out Time segments division by road network performance, specifically includes:
Step S11: the road grid traffic flow data in the Analysis on Selecting period obtains average flow rate and averag density, wherein flat
The mathematic(al) representation of equal flow are as follows:
Wherein:For average flow rate, n is section quantity, qlFor the flow of section l,
The mathematic(al) representation of averag density are as follows:
Wherein:For road network averag density, llFor the length of section l, lanelFor the number of track-lines of section l, klFor section l's
Density.
Step S12: application " being based on improved Teoplitz inverse covariance multidimensional time-series clustering procedure " (Advanced
Toeplitz Inverse Covariance-Based Clustering, ATICC), to road network average flow rate, averag density into
Row cluster makes objective function reach minimum, obtains several road networks and shows approximately uniform cluster P={ P1,,,PK, each cluster
Endpoint is exactly the timing node of each sub-period, wherein in order to embody the distinctive early evening peak phenomenon of traffic, when to early evening peak
Time range where section is introduced separately into penalty term β ', and β '≤β, the mathematic(al) representation of objective function are as follows:
Wherein: ΘiFor the covariance inverse matrix of the i-th class, P is that the time series of all classes distributes set, and Γ is all kinds of
Covariance inverse matrix set, K are the number of Time Sub-series, and λ is regularization parameter, determines the sparse degree of matrix, ‖ ‖1For
L1 norm, XtFor Time Sub-series ,-ll (Xt,Θi) it is Time Sub-series XtBelong to the log-likelihood of the i-th class, β is to work as the period of the day from 11 p.m. to 1 a.m
Between sequence Xt-1It is not belonging to penalty term when the i-th class, β ' is as Time Sub-series X 't-1It is not belonging to penalty term when the i-th class, PiFor
It is assigned to the time series set of the i-th class,To judge subsequence Xt-1Whether i-th class, X are belonged tot-1To be not belonging to morning
The Time Sub-series of evening peak period, X 't-1For the Time Sub-series for belonging to peak period morning and evening.
The mathematic(al) representation of penalty term are as follows:
Wherein: ktFor the road mileage of t moment, k is road network averag density, kt(β ') is when belonging to the t of peak period morning and evening
The road mileage at quarter, k (β ') are the average road mileage of period s.
Step S13: according to road network actual traffic situation, number of segment S when presetting one reasonably, selection makes each period road network
The smallest scheme of the sum of density criterion difference obtains corresponding penalty term as optimal case；
Step S14: classification situation is embodied by traffic flow macroscopic view parent map, for different traffic conditions, is generated not
Same classification schemes.
Step S2: the road network of each sub-period is simplified respectively, is specifically included:
Step S21: from original road network NoIn extract only include high-grade section initial most simple road network Np；
Step S22: based on the timing node obtained after cluster, with " connectivity enhancing algorithm " (Connectivity
Enhancement Algorithm, CEA) to the road network N of sub-period spsIt carries out section extension: being up to dynamic Users equilibrium
The section travel time of (Dynamic User Equilibrium, DUE) as section cost, to terminus group any in road network
Close ODkIf connecting the section l of the group sumo(lo∈No) travel time toLess than NpsIn have section lps(lps∈Nps) go out
Row time tps, then by loIncrease to set NpsIn, last road network N after the simplification of the periodrsIn only comprising have obvious traffic shadow
Loud Important Sections；
Step S23: the simplification road network set N by the simplification route combination of several differing complexities is obtainedr=
{Nr1,,,rs}。
Step S3: the dynamic traffic based on emulation point is carried out after combining the road network of several simplified different resolutions
Match, specifically include:
Step S31: in original road network NoOn the basis of be every section addition label to distinguish the section at various moments
Existence；
Step S32: road network N will be combinedcApply to middle sight traffic simulation software and carry out operation, when section is in different periods
When existence is inconsistent, such as from making the vehicle stop motion on the section, while not having vehicle in the presence of in the absence of becoming
Into the section, until the existence in section reverts to presence, iteration is until NcReach dynamic Users equilibrium state.
Finally, comparing the road network performance for simplifying road network and original road network, the accuracy for simplifying method is verified.
Fig. 1 is the emulation road network of Alexandria used in the embodiment of the present invention, which is based on U.S. Fo Jini
Ya Zhou Alexandria city's traffic network exploitation, entire road network include 85 traffic analysis cells, 6,724 sections, 2,573
Node, section include each grade road, such as height/through street, major trunk roads, branch.
Adaptive Railway network simplification method overall flow of the invention is as shown in Fig. 2, first according to the reality of traffic analysis road network
Border traffic flow conditions draw out road network traffic flow macroscopic view parent map using road network average flow rate, averag density, as shown in Figure 3.Its
It is secondary, multidimensional time-series cluster is carried out to average flow rate, averag density, the traffic behavior in each period after guaranteeing cluster
It is as consistent as possible.In the present embodiment, plan will analyze period (for 24 hours) cluster entirely as the sub-period of 6 different durations, i.e. S
=6, penalty value β=300 are given, calibration obtains β '=80 of optimal case, specific each section of duration are as follows: 255min, 150min,
The cluster result of 195min, 380min, 225min, 235min, MFD are as shown in Figure 4.Fig. 5 is the transport need of each sub-period
Distribution situation, it can be seen that there were significant differences for the transport need of each sub-period.Meanwhile it being extracted from original road network high
Grade section forms initial most simple road network and uses each period the road network of Fig. 6 respectively further according to the segmentation result obtained after cluster
Simplifying method --- connectivity enhancing algorithm carries out Network extension appropriate on most simple road network, and the important road of the period is added
Section, obtains the simplification road network of 6 different resolutions shown in Fig. 7.Table 1 has counted the covering of each simplified road network and original road network
Time range and road network status information.It is can be found that in conjunction with the transport need of each sub-period: simplifying road network section number and traffic
Demand correlation, the transport need big period, simplifying road network has more sections.Finally, by 6 simplified road networks into
Row combination, operation Zhong Guan simulation software carries out traffic simulation and Used in Dynamic Traffic Assignment, until reaching dynamic Users equilibrium state.?
In specific emulation and assigning process, if certain section changes in the simplification road network of subsequent period " disappearance " to by the block status
Become the vehicle application " freezing " influenced, it may be assumed that if certain section label becomes 0 from 1, the vehicle travelled on the section originally will
Stop motion, while there will not be vehicle into the section, until the section reappears.
Table 1 simplifies road network and original road network information statistical form
In order to compare adaptive simplifying method and original scheme road network performance, by after combination simplification road network and original road
The simulation result of net is compared, including vehicle is averaged running time (Ave.time/min), average travel
(Ave.dist/mile), the vehicle influenced by block status variation be averaged running time (Aff.time/min) and emulation with
The distribution CPU time (CPU/sec) used.Table 2 has recorded simplified road network and original road network iteration 15 times emulation and distribution knot
Fruit:
2 road network of table performance verifying statistical form
| Ave.time/min | Ave.dist/mile | Aff.time/min | CPU/sec | |
| Simplify road network | 5.904 | 5.086 | 5.935 | 10905.44 |
| Original road network | 5.605 | 4.812 | 5.803 | 14366.44 |
| Mean error (%) | 5.34 | 5.69 | 2.27 | — |
| Improved efficiency (%) | — | — | — | 24.09 |
By simulation result comparison it is found that all vehicles are simplifying driving status (average running time, average row in road network
Sail mileage) with original road network error 5% or so, meanwhile, the error of impacted vehicle is less than 3%, it is believed that simplify
Road network performance afterwards is essentially identical with original road network.Emulating and distribute simultaneously CPU time more original road network used in entirety reduces
20% or more, from Fig. 8 and Fig. 9 it can also be seen that reduction procedure has biggish advantage in emulation and allocative efficiency, it was demonstrated that
This method can improve analysis efficiency significantly.
Claims (7)
1. a kind of adaptive traffic analysis Railway network simplification method based on traffic flow macroscopic view parent map characterized by comprising
Step S1: traffic flow macroscopic view parent map is drawn out according to road grid traffic stream state data and presses MFD using clustering method
Road network performance carries out Time segments division；
Step S2: the road network of each sub-period is simplified respectively；
Step S3: the Used in Dynamic Traffic Assignment based on emulation is carried out after combining the road network of several simplified different resolutions.
2. a kind of adaptive traffic analysis Railway network simplification side based on traffic flow macroscopic view parent map according to claim 1
Method, which is characterized in that the step S1 is specifically included:
Step S11: the road grid traffic flow data in the Analysis on Selecting period obtains average flow rate and averag density；
Step S12: clustering road network average flow rate, averag density, so that objective function is reached minimum, obtains several road networks
Show approximately uniform cluster P={ P1,,,PK, the endpoint of each cluster is exactly the timing node of each sub-period；
Step S13: according to road network actual traffic situation, number of segment S when presetting one reasonably, selection makes each period road mileage
The smallest scheme of the sum of standard deviation obtains corresponding penalty term as optimal case；
Step S14: classification situation is embodied by traffic flow macroscopic view parent map, for different traffic conditions, is generated different
Classification schemes.
3. a kind of adaptive traffic analysis Railway network simplification side based on traffic flow macroscopic view parent map according to claim 2
Method, which is characterized in that the mathematic(al) representation of the average flow rate are as follows:
Wherein:For average flow rate, n is section quantity, qlFor the flow of section l,
The mathematic(al) representation of the averag density are as follows:
Wherein:For road network averag density, llFor the length of section l, lanelFor the number of track-lines of section l, klFor the density of section l.
4. a kind of adaptive traffic analysis Railway network simplification side based on traffic flow macroscopic view parent map according to claim 2
Method, which is characterized in that in the step S12, penalty term β ' is introduced separately into the time range where peak period morning and evening, and
β '≤β, the mathematic(al) representation of the objective function are as follows:
Wherein: ΘiFor the covariance inverse matrix of the i-th class, P is that the time series of all clusters distributes set, and Γ is the association of each cluster
Variance inverse matrix set, K are the number of Time Sub-series, and λ is regularization parameter, determines the sparse degree of matrix, ‖ ‖1For L1
Norm, XtFor Time Sub-series ,-ll (Xt,Θi) it is Time Sub-series XtBelong to the log-likelihood of the i-th class, β is the group time
Sequence Xt-1It is not belonging to penalty term when the i-th class, β ' is as Time Sub-series X 't-1It is not belonging to penalty term when the i-th class, PiTo divide
It is fitted on the time series set of the i-th class,To judge subsequence Xt-1Whether i-th class, X are belonged tot-1To be not belonging to sooner or later
The Time Sub-series of peak period, X 't-1For the Time Sub-series for belonging to peak period morning and evening.
5. a kind of adaptive traffic analysis Railway network simplification side based on traffic flow macroscopic view parent map according to claim 4
Method, which is characterized in that the mathematic(al) representation of the penalty term are as follows:
Wherein: ktFor the road mileage of t moment, k is road network averag density, kt(β ') is the t moment for belonging to peak period morning and evening
Road mileage, k (β ') are the average road mileage of period s.
6. a kind of adaptive traffic analysis Railway network simplification side based on traffic flow macroscopic view parent map according to claim 1
Method, which is characterized in that the step S2 is specifically included:
Step S21: from original road network NoIn extract only include high-grade section initial most simple road network Np；
Step S22: based on the timing node obtained after cluster, to the road network N of sub-period spsIt carries out section extension: being up to dynamic
The section travel time of user equilibrium combines OD as section cost, to terminus any in road networkkIf connecting the road of the group sum
Section lo(lo∈No) travel time toLess than NpsIn have section lps(lps∈Nps) travel time tps, then by loIncrease to collection
Close NpsIn, last road network N after the simplification of the periodrsIn only comprising with obvious traffic impact Important Sections；
Step S23: the simplification road network set N by the simplification route combination of several differing complexities is obtainedr={ Nr1,,,
Nrs}。
7. a kind of adaptive traffic analysis Railway network simplification side based on traffic flow macroscopic view parent map according to claim 6
Method, which is characterized in that the step S3 is specifically included:
Step S31: in original road network NoOn the basis of be every section addition label to distinguish the presence of the section at various moments
State；
Step S32: road network N will be combinedcApply to middle sight traffic simulation software and carry out operation, when section is in the presence of different periods
When state is inconsistent, such as from making the vehicle stop motion on the section in the presence of in the absence of becoming, while vehicle entrance is not had
The section, until the existence in section reverts to presence, iteration is until NcReach dynamic Users equilibrium state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910114744.9A CN109858559B (en) | 2019-02-14 | 2019-02-14 | Self-adaptive traffic analysis road network simplification method based on traffic flow macroscopic basic graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910114744.9A CN109858559B (en) | 2019-02-14 | 2019-02-14 | Self-adaptive traffic analysis road network simplification method based on traffic flow macroscopic basic graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109858559A true CN109858559A (en) | 2019-06-07 |
| CN109858559B CN109858559B (en) | 2020-11-27 |
Family
ID=66897857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910114744.9A Active CN109858559B (en) | 2019-02-14 | 2019-02-14 | Self-adaptive traffic analysis road network simplification method based on traffic flow macroscopic basic graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858559B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127880A (en) * | 2019-12-16 | 2020-05-08 | 西南交通大学 | MFD-based grid network traffic performance analysis method |
| CN112991729A (en) * | 2021-02-25 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | Time interval dividing method and device and computer storage medium |
| CN113380022A (en) * | 2021-03-30 | 2021-09-10 | 广东工业大学 | Road network time-varying running state analysis method based on coupling-deviation process |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN103632212A (en) * | 2013-12-11 | 2014-03-12 | 北京交通大学 | System and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow |
| CN104866654A (en) * | 2015-05-06 | 2015-08-26 | 广州市交通规划研究院 | Construction method for integrated dynamic traffic simulation platform of city |
| CN104899360A (en) * | 2015-05-18 | 2015-09-09 | 华南理工大学 | Method for drawing macroscopic fundamental diagram |
| CN105023445A (en) * | 2014-07-04 | 2015-11-04 | 吴建平 | Regional traffic dynamic regulation-control method and system |
| CN105355049A (en) * | 2015-11-05 | 2016-02-24 | 北京航空航天大学 | Highway running state evaluation method based on macroscopic fundamental diagram |
| CN105702031A (en) * | 2016-03-08 | 2016-06-22 | 北京航空航天大学 | Macroscopic fundamental diagram-based road network key section identification method |
| CN106504536A (en) * | 2016-12-09 | 2017-03-15 | 华南理工大学 | A kind of traffic zone coordination optimizing method |
| CN106781558A (en) * | 2017-01-20 | 2017-05-31 | 华南理工大学 | The quick leading method of main channel traffic flow based on macroscopical parent map under car networking |
| CN107591004A (en) * | 2017-11-01 | 2018-01-16 | 中原智慧城市设计研究院有限公司 | A kind of intelligent traffic guidance method based on bus or train route collaboration |
| CN107808518A (en) * | 2017-10-26 | 2018-03-16 | 东南大学 | A kind of traffic zone division methods theoretical based on multi-path spectral clustering |
| CN108198412A (en) * | 2017-12-06 | 2018-06-22 | 广东交通职业技术学院 | Supersaturated road network multi layer control boundary dynamics division methods based on MFD under car networking |
| CN108364465A (en) * | 2018-02-09 | 2018-08-03 | 太原理工大学 | The method for dynamically partitioning of city road network control work zone based on macroscopical parent map |
| CN108665703A (en) * | 2018-04-23 | 2018-10-16 | 东南大学 | Road network state transition point method of discrimination based on macroscopical parent map |
-
2019
- 2019-02-14 CN CN201910114744.9A patent/CN109858559B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN103632212A (en) * | 2013-12-11 | 2014-03-12 | 北京交通大学 | System and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow |
| CN105023445A (en) * | 2014-07-04 | 2015-11-04 | 吴建平 | Regional traffic dynamic regulation-control method and system |
| CN104866654A (en) * | 2015-05-06 | 2015-08-26 | 广州市交通规划研究院 | Construction method for integrated dynamic traffic simulation platform of city |
| CN104899360A (en) * | 2015-05-18 | 2015-09-09 | 华南理工大学 | Method for drawing macroscopic fundamental diagram |
| CN105355049A (en) * | 2015-11-05 | 2016-02-24 | 北京航空航天大学 | Highway running state evaluation method based on macroscopic fundamental diagram |
| CN105702031A (en) * | 2016-03-08 | 2016-06-22 | 北京航空航天大学 | Macroscopic fundamental diagram-based road network key section identification method |
| CN106504536A (en) * | 2016-12-09 | 2017-03-15 | 华南理工大学 | A kind of traffic zone coordination optimizing method |
| CN106781558A (en) * | 2017-01-20 | 2017-05-31 | 华南理工大学 | The quick leading method of main channel traffic flow based on macroscopical parent map under car networking |
| CN107808518A (en) * | 2017-10-26 | 2018-03-16 | 东南大学 | A kind of traffic zone division methods theoretical based on multi-path spectral clustering |
| CN107591004A (en) * | 2017-11-01 | 2018-01-16 | 中原智慧城市设计研究院有限公司 | A kind of intelligent traffic guidance method based on bus or train route collaboration |
| CN108198412A (en) * | 2017-12-06 | 2018-06-22 | 广东交通职业技术学院 | Supersaturated road network multi layer control boundary dynamics division methods based on MFD under car networking |
| CN108364465A (en) * | 2018-02-09 | 2018-08-03 | 太原理工大学 | The method for dynamically partitioning of city road network control work zone based on macroscopical parent map |
| CN108665703A (en) * | 2018-04-23 | 2018-10-16 | 东南大学 | Road network state transition point method of discrimination based on macroscopical parent map |
Non-Patent Citations (4)
| Title |
|---|
| DAVID HALLAC 等: ""Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data"", 《ARXIV:1706.03161V2 [CS.LG]》 * |
| LEI ZHU 等: ""Road network abstraction approach for traffic analysis: framework and numerical analysis"", 《IET INTELLIGENT TRANSPORT SYSTEMS》 * |
| YE TIAN 等: ""Variable Time Discretization for a Time-Dependent Shortest Path Algorithm"", 《2011 14TH INTERNATIONAL IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS》 * |
| YE TIAN等: ""Numerical Analysis for Adaptive Traffic Simulation"", 《RESEARCHGATE》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127880A (en) * | 2019-12-16 | 2020-05-08 | 西南交通大学 | MFD-based grid network traffic performance analysis method |
| CN112991729A (en) * | 2021-02-25 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | Time interval dividing method and device and computer storage medium |
| CN112991729B (en) * | 2021-02-25 | 2022-05-20 | 杭州海康威视数字技术股份有限公司 | Time interval dividing method and device and computer storage medium |
| CN113380022A (en) * | 2021-03-30 | 2021-09-10 | 广东工业大学 | Road network time-varying running state analysis method based on coupling-deviation process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109858559B (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858559A (en) | Adaptive traffic analysis Railway network simplification method based on traffic flow macroscopic view parent map | |
| CN104156524B (en) | The Aggregation Query method and system of transport data stream | |
| CN108875816A (en) | Merge the Active Learning samples selection strategy of Reliability Code and diversity criterion | |
| CN109598936B (en) | Short-term traffic prediction method based on dynamic STKNN model | |
| Lu et al. | Modeling the heterogeneous traffic correlations in urban road systems using traffic-enhanced community detection approach | |
| CN110276966B (en) | Intersection signal control time interval dividing method | |
| CN106652441A (en) | Urban road traffic condition prediction method based on spatial-temporal data | |
| CN108415975A (en) | Taxi hot spot recognition methods based on BDCH-DBSCAN | |
| CN104464304A (en) | Urban road vehicle running speed forecasting method based on road network characteristics | |
| CN108665703B (en) | Road network state transition point discrimination method based on macroscopic basic graph | |
| CN106803347B (en) | Urban intersection traffic state judging method based on RFID data | |
| WO2021073526A1 (en) | Trajectory data-based signal control period division method | |
| CN105551250A (en) | Method for discriminating urban road intersection operation state on the basis of interval clustering | |
| CN112183605B (en) | Civil aviation control sector classification method based on operation characteristics | |
| CN110070734A (en) | Signalized intersections saturation headway estimation method based on gauss hybrid models | |
| CN104574968A (en) | Determining method for threshold traffic state parameter | |
| CN113947899B (en) | Queuing service time dynamic estimation method under low-permeability track data | |
| Xu et al. | A novel algorithm for urban traffic congestion detection based on GPS data compression | |
| CN101964061B (en) | Binary kernel function support vector machine-based vehicle type recognition method | |
| CN110445726A (en) | A kind of adaptive network stream concept drift detection method based on comentropy | |
| CN106297296A (en) | A kind of fine granularity distribution method hourage based on sparse tracing point data | |
| CN103793438A (en) | MapReduce based parallel clustering method | |
| CN108053646B (en) | Traffic characteristic obtaining method, traffic characteristic prediction method and traffic characteristic prediction system based on time sensitive characteristics | |
| CN107577727B (en) | Group movement behavior characteristic analysis method | |
| CN111275073B (en) | Regional people stream analysis method based on mobile phone signaling data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |