CN108665715A - A kind of road junction intelligent traffic is studied and judged and signal optimizing method - Google Patents
A kind of road junction intelligent traffic is studied and judged and signal optimizing method Download PDFInfo
- Publication number
- CN108665715A CN108665715A CN201810439951.7A CN201810439951A CN108665715A CN 108665715 A CN108665715 A CN 108665715A CN 201810439951 A CN201810439951 A CN 201810439951A CN 108665715 A CN108665715 A CN 108665715A
- Authority
- CN
- China
- Prior art keywords
- crossing
- target
- indicate
- track
- target crossing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000003066 decision tree Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 230000002068 genetic effect Effects 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000012913 prioritisation Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 229920006395 saturated elastomer Polymers 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000011664 signaling Effects 0.000 claims description 6
- 230000003694 hair properties Effects 0.000 claims description 4
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 36
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000000819 phase cycle Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000010429 evolutionary process Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
Abstract
The technical problem to be solved by the present invention is to Traffic Signal Timing project plan comparison is extensive, it is undesirable to often result in signal control effect.In order to solve the above-mentioned technical problem, it studies and judges the technical solution of the present invention is to provide a kind of road junction intelligent traffic and signal optimizing method, including is based on Road Detection equipment and crossing traffic operating condition is monitored；Object function and the noninferior solution set in corresponding crossing signals period and phase duration are obtained based on multi-objective genetic algorithm；It calculates average Euclidean distance and clusters and obtain the more excellent solution set of crossing signals scheme, then crossing is obtained based on C4.5 traditional decision-trees and mainly optimizes direction, the foundation as signal optimization；Finally, mainly optimize direction with crossing and determine crossing traffic signal prioritization scheme.According to the above technology, the present invention can make urban traffic signal control program more rationally, science.
Description
Technical field
It is studied and judged the present invention relates to a kind of road junction intelligent traffic and signal optimizing method, belongs to urban traffic signal control system
Field.
Background technology
With society and expanding economy, vehicles number rapid growth, urban traffic blocking, traffic order confusion shape
Condition is on the rise.Preferably traffic signal control scheme can alleviate traffic congestion, improve operational efficiency, save energy consumption, reduce
Pollution of the vehicle to environment, alleviation driver is impatient at heart, increases traffic safety.Currently, Traffic Signal Timing scheme ratio
It is more extensive, it is undesirable to often result in signal control effect.
Invention content
Purpose of the present invention is to：Based on crossing main traffic problem, rationally, more excellent signal time distributing conception is scientifically exported, carried
High crossing traffic efficiency.
In order to achieve the above object, the technical solution of the present invention is to provide a kind of road junction intelligent traffic study and judge it is excellent with signal
Change method, which is characterized in that include the following steps：
Step 1, the crossing weighted mean velocity that target crossing is obtained based on Road Detection equipment, to obtain crossing traffic
Congestion status, then target crossing judge according to crossing weighted mean velocity and crossing traffic congestion status in certain time period
Whether target crossing, which needs, optimizes signaling plan, if desired, then enters step 2；
Step 2, flow, saturation volume, the number of track-lines for acquiring each track in target crossing, establish the mesh of multi-objective genetic algorithm
Scalar functions and constraint, wherein object function include intersection period vehicles average delay function, intersection capacity function,
Period is averaged stop frequency function, saturation overflow queue length function, constraint include green light time interval constrain, cycle duration about
Beam, effective green time constraint, saturation degree constraint, in conjunction with crossing actual traffic data, using multi-objective genetic algorithm obtain by
The noninferior solution set that target function value and corresponding crossing cycle duration and each phase Effective Green Time duration are composed；
The noninferior solution set that step 2 obtains is normalized in step 3, by the target function value of noninferior solution set
It is converted into the dimensionless number with mechanical periodicity；
Step 4 is obtained based on euclidean metric with the average Euclidean distance between the target function value of mechanical periodicity；
The average Euclidean distance that step 5, comparison step 4 obtain carries out clustering, according to the flat of the object function of acquisition
The equalization point of equal Euclidean distance is barycenter or carries out clustering close to barycenter, determines using equalization point as barycenter or close to barycenter
Cluster, cluster is mapped to original target function value and corresponding crossing signals cycle duration and each phase Effective Green Time duration is
More excellent solution set；
Step 6 with target crossing essential attribute and target crossing traffic problem influence factor is C4.5 traditional decision-trees
Input quantity obtains target crossing based on C4.5 traditional decision-trees and mainly optimizes direction；
Step 6 is obtained target crossing and mainly optimizes direction being combined with more excellent solution that step 5 obtains set by step 7, most
Confirm that the signal at target crossing controls prioritization scheme eventually.
Preferably, it in the step 1, is alarmed according to the crossing traffic congestion status obtained in real time.
Preferably, in the step 1, i-th of target crossing is fint_speed in the weighted mean velocity of moment t
(t, i) then has：
In formula, rjIndicate i-th target crossing
Jth entrance driveway,Indicate the total quantity of the entrance driveway at i-th of target crossing, fint_speed (t, rj) indicate i-th of target road
The jth entrance driveway of mouth is in the travel speed value of moment t, fint_volume (t, rj) indicate i-th of target crossing jth import
Flow value of the road in moment t.
Preferably, it in the step 1, if target crossing is normal hair property intersection, needs to carry out signaling plan
Optimization.
Preferably, in the step 2, the intersection period vehicles average delay function is
In formula：
aijIndicate that the number of track-lines in the track of j-th of carriageway type of i-th of entrance driveway at target crossing, I indicate target road
The sum of the entrance driveway of mouth, J indicate the sum of carriageway type；
dijIndicate that the vehicle of the track of j-th of carriageway type of i-th of entrance driveway at target crossing in one cycle is flat
It is delayed
qijIndicate the bicycle road vehicle flowrate in the track of j-th of carriageway type of i-th of entrance driveway at target crossing；
Q indicates all vehicle total flows in target crossing in a cycle,
The intersection capacity function is c：
In formula, cij=sij*λij, sijIndicate j-th of i-th of entrance driveway at target crossing
The saturation volume in the track of carriageway type, λijIndicate that the track of j-th of carriageway type of i-th of entrance driveway at target crossing is each
Phase split；
The period stop frequency function that is averaged is
In formula, hijIndicate j-th of vehicle of i-th of entrance driveway at target crossing
The vehicle of the track of road type in one cycle is averaged stop frequency；
Saturation overflow queue length function isIndicate j-th of track of i-th of entrance driveway at target crossing
The saturation overflow queue length function in the track of type：
In formula, NijIndicate j-th of carriageway type of i-th of entrance driveway at target crossing
Track average saturation overflow queue length in one cycle.
Preferably, the dijCalculation formula be：
Work as xij≤xij0When,
Work as xij0＜ xijWhen ＜ 1,
As 1≤xijWhen≤1.15,
Work as xijWhen ＞ 1.15,In formula：
C indicates the cycle duration at target crossing；xijIndicate j-th of carriageway type of i-th of entrance driveway at target crossing
The saturation degree in track；xij0Indicate the saturation critical point in the track of j-th of carriageway type of i-th of entrance driveway at target crossing；yij
Indicate the flow-rate ratio in the track of j-th of carriageway type of i-th of entrance driveway at target crossing,
Indicate the traffic capacity in the track of j-th of carriageway type of i-th of entrance driveway at target crossing, cij=sij*λij；
rijIndicate the phase red time in the track of j-th of carriageway type of i-th of entrance driveway at target crossing, rij=C-gij, gijTable
Show each phase effective green time in the track of j-th of carriageway type of i-th of entrance driveway at target crossing.
Preferably, the hijCalculation formula be：
Work as xij≤xij0When：
Work as xij0＜ xijWhen ＜ 1：
As 1≤xijWhen≤1.15：
Work as xijWhen ＞ 1.15：
Preferably, the NijCalculation formula be：Work as xij≤xij0When：
Work as xij0＜ xijWhen ＜ 1：
As 1≤xijWhen≤1.15：
Work as xijWhen ＞ 1.15：
Preferably, in step 7, the input quantity of the C4.5 decision trees include target crossing each entrance driveway whether based on
Through Lane number, each entrance driveway in target crossing in distance apart from upstream crossing of arterial highway, target crossing, each entrance driveway in target crossing
Middle left turn lane number, the crossing flow at target crossing, target crossing average saturation overflow queue length, target crossing delay
Time；
One of four conclusions below the C4.5 decision trees final output：(1) preferentially optimization intersection is saturated overflow queue
Length；(2) preferentially optimize the delay time at stop；(3) preferentially optimize the traffic capacity；(4) preferentially optimize stop frequency.
Road junction intelligent traffic according to the present invention is studied and judged avoids normal signal control program not with signal optimizing method
Rationally, phenomena such as crossing wasting of resources, public discontent.Analysis result is studied and judged to being based on engineering in conjunction with urban road crossing main problem
The crossing signals prioritization scheme of habit is determined, and keeps crossing traffic signaling plan more scientific, reasonable, promotes going through ability.
Description of the drawings
Fig. 1 is that the road junction intelligent traffic of the present invention is studied and judged and signal optimizing method structural schematic diagram；
Fig. 2 is the crossing object function traffic capacity of the present invention, stop frequency, delay and is averagely saturated overflow queue length
Noninferior Solution Set normalized result schematic diagram；
Fig. 3 is that being obtained based on euclidean metric for the present invention is shown with the object function average distance result that the period is measurement
It is intended to；
Fig. 4 be the present invention based on K-means to object function Euclidean distance cluster analysis result schematic diagram；
Fig. 5 is the C4.5 decision Tree algorithms flow diagrams involved in the present invention.
Specific implementation mode
To keep the present invention more aobvious understandable, elaborate below in conjunction with the accompanying drawings to the embodiment of the present invention：The present embodiment exists
Implemented under technical solution of the present invention, gives the implementation process and implementation result of the present invention.Protection scope of the present invention is not
It is limited to following embodiments.
Step S-1：The traffic circulation at target crossing is monitored based on Road Detection equipment, and is alarmed
The link travel speed index at target crossing is obtained according to Road Detection equipment (such as crossing video tollgate devices).
According to the relationship at target crossing and each corresponding access road, the crossing weighted mean velocity at target crossing is obtained：
In formula, fint_speed (t, i) indicate i-th of target crossing moment t weighted mean velocity, when target crossing
The flow of each entrance driveway when being 0, then the average speed for giving tacit consent to fint_speed (t, i) is 0；
rjIndicate the jth entrance driveway at i-th of target crossing；
nrjIndicate the total quantity of the entrance driveway at i-th of target crossing；
Fint_speed (t, rj) indicate i-th of target crossing jth entrance driveway moment t travel speed value；
Fint-volume (t, rj) indicate i-th of target crossing jth entrance driveway moment t flow value.
Reference road prevailing state information issues specification (GA/T 994-2012), obtains the traffic congestion shape at target crossing
State index is alarmed according to the traffic congestion state index obtained in real time.Meanwhile according to the target road in a period of time length
Whether the historical data of the traffic congestion state index of mouth can be counted, be that normal hair property intersection carries out to target crossing
Judge, if crossing is normal hair property intersection, the signaling plan to target crossing is needed to optimize.
Step S-2：Target function value and corresponding crossing cycle duration and each phase are obtained based on multi-objective genetic algorithm
The noninferior solution set of position Effective Green Time duration
Multi-objective optimization question is always research field hot spot, has the ability for handling big problem space, primary
Multiple feasible solutions (Noninferior Solution Set) can be obtained in evolutionary process, the priori of Problem Areas is not required, and function is defined
The convexity in domain is insensitive.Multi-objective genetic algorithm is using specific as follows：
1) model hypothesis
(1) assume that target crossing is signalized crossing, and carry out multi-period timing controlled；
(2) assume optimum angle number and phase sequence it has been determined that and without lapping phases；
(3) assume that the green light time interval of each intersection is 5s, wherein 3s amber lights and 2s is entirely red, corresponding green light loss
Time is 5s per phase；
(4) assume that vehicle uniformly reaches intersection within whole time；
(5) within whole time, straight line increases at any time for the queue length of supersaturated vehicle.
2) model foundation
Passed through to each track flow q based on multi-objective genetic algorithmij, saturation volume sij, number of track-lines aijThe number of three variables
According to acquisition, by a series of conversion, intersection period vehicles average delay is established, intersection capacity, period averagely stop
Train number number, saturation overflow queue four object functions of length, with green light time interval, cycle duration, effective green time, saturation
Four constraints of degree.Wherein control targe need to make as possible intersection capacity is maximum, the vehicles average delay in a cycle most
Small, average stop frequency is minimum and to be always saturated overflow queue's length most short for intersection.
Wherein：qijIndicate the bicycle road vehicle flowrate in the track of j-th of carriageway type of i-th of entrance driveway, pcu/s；
sijIndicate the saturation volume s in the track of j-th of carriageway type of i-th of entrance drivewayij, pcu/s；
aijIndicate the number of track-lines in the track of j-th of carriageway type of i-th of entrance driveway.Wherein 3≤i≤6, i.e. entrance driveway are extremely
It is less three, is up to 6；Carriageway type j=7 respectively turns left, keeps straight on, turning right, a straight left side shares track, the straight right side and shares vehicle
Road, straight left and right share track, left and right and share track.
(1) foundation of object function
Period vehicles average delay
Work as xij≤xij0When,
Work as xij0＜ xijWhen ＜ 1,
As 1≤xijWhen≤1.15,
Work as xijWhen ＞ 1.15,
Wherein：
Then all vehicle total flows in intersection are in a cycle
Then all vehicles average delays in intersection are in a cycle
In formula：dijIndicate that the vehicle of the track of j-th of carriageway type of i-th of entrance driveway in one cycle averagely prolongs
Accidentally, s；
Indicate the period vehicles average delay at target crossing, s；
cijIndicate the traffic capacity in the track of j-th of carriageway type of i-th of entrance driveway, cij=sij*λij, pcu/s；
xijIndicate the saturation degree in the track of j-th of carriageway type of i-th of entrance driveway, xij=qij/cij。
C indicates the cycle duration at target crossing, s；
λijIndicate each phase split in the track of j-th of carriageway type of i-th of entrance driveway；
yijIndicate the flow-rate ratio in the track of j-th of carriageway type of i-th of entrance driveway, yij=qij/sij；
gijIndicate the effective green time of each phase in the track of j-th of carriageway type of i-th of entrance driveway, s；
rijIndicate the phase red time in the track of j-th of carriageway type of i-th of entrance driveway, rij=C-gij, s；
N0Indicate track period average superfluous delay vehicle number, pcu；
xij0Indicate the saturation degree critical point in the track of j-th of carriageway type of i-th of entrance driveway；
hijIndicate that the vehicle of the track of j-th of carriageway type of i-th of entrance driveway in one cycle is averaged stop frequency,
Secondary/；
Indicate that the vehicle of target crossing in one cycle is averaged stop frequency, secondary/；
NijIndicate that the period in the track of j-th of carriageway type of i-th of entrance driveway is averagely saturated overflow queue's length, pcu；
Indicate that the target crossing period is always saturated overflow queue's length, pcu.
Intersection capacity
Calculation formula is：cij=sij*λij
Then the total traffic capacity in intersection is：
Period is averaged stop frequency
Work as xij≤xij0When,
Work as xij0＜ xijWhen ＜ 1,
As 1≤xijWhen≤1.15,
Work as xijWhen ＞ 1.15,
Then all vehicles in the intersection stop frequency that is averaged is in a cycle
Intersection is always saturated overflow queue's length
Work as xij≤xij0When,
Work as xij0＜ xijWhen ＜ 1,
As 1≤xijWhen≤1.15,
Work as xijWhen ＞ 1.15,
Then each track in intersection is always saturated overflow queue's length and is in a cycle
(2) constraints is analyzed
Model includes green light time interval, cycle duration, effective green time and saturation degree binding target, specifically such as
Under：
Green light time interval constrains
Green light time interval refers to that a phase green light terminates the interval time started to next conflict phase green light.Green light
Interval time is ensured that last motor vehicle and green first be driven out at the beginning of next phase that conflicts of this phase green light tail
Motor vehicle its conflict point can secure cross pass through.Green light time interval is separation traffic conflict, ensures that access connection traffic flow is transported
The key parameter of row safety.
Cycle duration constrains
Period equality constraint：
K indicates intersection number of phases；
gkIndicate the display green time of kth phase, s；
IkIndicate the green light time interval of kth phase, s.
In out of phase phase sequence, gkWith gijThere is different correspondences, concrete case is answered to make a concrete analysis of.
Period inequality constrains：
Cmin≤C≤Cmax
In formula：CminIndicate minimum period duration, CmaxIndicate maximum cycle duration, gminIndicate phase Minimum Green Time.
Effective green time constrains
gij＞ gmin
gWEminEast and West direction Minimum Green Time, gSNminIndicate north-south Minimum Green Time, East and West direction pedestrian's street crossing length
It is up to LWE, north-south pedestrian's street crossing length is up to LSN, pedestrian's average pace is vp, 1m/s or 1.2m/s is generally taken, then
Saturation degree constrains
General traffic flow is in (0.8,0.9), it is proposed that takes the value no more than 0.85, special traffic flow is in (0.9,1.0), it is proposed that
Take the value no more than 0.95.If supersaturation situation in crossing can not be alleviated, saturation degree value is up to the 75% of former saturation degree.
By the foundation of the above object function and constraints, in conjunction with crossing actual traffic data, using multi-objective Genetic
Algorithm acquisition is composed of four target function values and corresponding crossing cycle duration and each phase Effective Green Time duration
Noninferior solution set.
Step S-3：The normalized of crossing object function noninferior solution set
Data normalization processing is an element task of data mining, and different evaluation index often has different dimensions
And dimensional unit, such situation influence whether data analysis as a result, in order to eliminate the dimension impact between index, need into
Row data standardization, to solve the comparativity between data target.Initial data respectively refers to after data normalization is handled
Mark is in the same order of magnitude, is appropriate for Comprehensive Correlation evaluation.Noninferior solution set mainly uses min-max by normalized
Standardization carries out.Min-max standardization be also referred to as deviation standardization, be the linear transformation to initial data, make result fall on [-
1,1] section, conversion function are as follows：
x※Transfer function, xorFor initial data, xmaxFor the maximum value of sample data, xminFor the minimum value of sample data,
xmeanIndicate the mean value of data.When there is new data addition, xmaxAnd xminIt needs to redefine.
Four target function values of crossing noninferior solution set (be detained by the traffic capacity, delay, stop frequency and average saturation
Motorcade length) pass through min-max standardizations, it is converted into [- 1,1] dimensionless number with mechanical periodicity, it can be in same amount
Guiding principle is expressed, as Fig. 2 illustrates.
Step S-4：Based on euclidean metric obtain with the average Euclidean between the target function value of mechanical periodicity away from
From
Euclidean metric (also referred to as Euclidean distance) is the distance definition of a generally use, refers in m-dimensional space two
Actual distance between point.This refers to the actual distances between two desired values in two-dimensional space.
Indicate average Euclidean distance, i.e., the arithmetic mean of instantaneous value of Euclidean distance between each desired value, m indicates target
Number, x and y indicate that the coordinate of desired value, n indicate the number per target two-by-two.
WhenMore hour, then four target function value relative equilibriums, then pass throughRelative equilibrium can be found.Base
The dimensionless number of the traffic capacity, delay, stop frequency in target function value and saturation overflow queue length, by Europe it is several in
The average Euclidean distance that the target function value that processing can be obtained with mechanical periodicity must be measured, if Fig. 3 illustrates, relative equilibrium is
It is Euclidean distance smallest point.
Step S-5：The more excellent solution set of crossing signals prioritization scheme determines
The more excellent solution set of crossing signals prioritization scheme, which determines, to be needed to be analyzed using K-means clusters.K-means is clustered
It is the single layer division that the clustering technique based on prototype creates data object for the object in multidimensional continuous space.It is general to carry out
K-means clusters K initial barycenter of selection first, wherein K is the parameter that user specifies, and is the number of desirable cluster.Each
Point is assigned to nearest barycenter, and the point set for being assigned to a barycenter is a cluster, then, according to the point for the cluster being assigned to, more
The barycenter of new each cluster, until barycenter does not change.
To being obtained based on euclidean metric as the average Euclidean distance between the target function value of mechanical periodicity carries out
K-means clusterings are barycenter according to the equalization point of the average Euclidean distance of the object function of acquisition or are carried out close to barycenter
Clustering determines the cluster using equalization point as barycenter or close to barycenter, and if Fig. 4 illustrates, which is mapped to original, and there are four targets
Functional value and corresponding crossing signals cycle duration and each phase Effective Green Time duration are more excellent solution set.
Step S-6：Urban road crossing, which is obtained, based on C4.5 traditional decision-trees mainly optimizes direction
Road network overall condition is differentiated based on historical data, crossing situation is carried out to study and judge analysis, is signal timing dial
Optimization provides auxiliary opinion.
● input data
The input value of C4.5 is mainly crossing essential attribute and crossing traffic problem influence factor, including：(1) whether based on
Arterial highway；(2) apart from the distance of upstream crossing；(3) Through Lane number；(4) left turn lane number；(5) crossing flow；(6) crossing is flat
Saturation overflow queue length；(7) the crossing delay time at stop.
● output conclusion
According to input value, algorithm is by established decision tree, one of four conclusions below final output：(1) preferential excellent
Change intersection saturation overflow queue length；(2) preferentially optimize the delay time at stop；(3) preferentially optimize the traffic capacity；(4) preferential optimization
Stop frequency.
Specific algorithm
C4.5 decision Tree algorithms are a series of algorithms in the classification problem of machine learning and data mining.Its mesh
Mark is supervised learning：A data set is given, each tuple can be described with one group of attribute value, each tuple
Certain belonged in the classification of a mutual exclusion is a kind of.The target of C4.5 is to find dependence value reflecting to classification by study
Relationship is penetrated, and this mapping can be used for the entity unknown to new classification and classify.
Decision tree is a kind of tree construction of similar flow chart, wherein each internal node (non-leaf nodes) is indicated at one
Test on attribute, each branch represents a test output, and each leaf nodes store a class label.Once establishing
Decision tree, for the tuple of given class label, as soon as tracking has the root node to the path of leaf node, the leaf node
Store the prediction of the tuple.The advantage of decision tree is not needing any domain knowledge or parameter setting, is suitable for detection property
Knowledge Discovery, the signal of specific algorithm flow is such as Fig. 5.
Some are first done it is assumed that letting d be class label tuple training set, class label attribute has m different value, m inhomogeneity
Ci (i=1,2 ..., m), CiD are the set of the tuple of Ci classes in D, | D | and | CiD | it is the tuple number in D and CiD respectively.
(1) information gain
It is following formula to the expectation information needed for the tuple classification in D：
Info (D) is also known as entropy, wherein piIndicate the probability that i-th of value occurs in the sample.
Currently assume the tuple divided according to attribute A in D, and D is divided into v different classes by attribute A.The division it
Afterwards, the information also needed to of accurately classifying in order to obtain is measured by following formula：
Information gain is defined as original information requirement (being based only upon class ratio) and (is obtained after being divided to A with new demand
Arrive) between difference, i.e.,
Gain (A)=Info (D)-InfoA(D)
Gain (A) is information gain.
(2) information gain-ratio
Classification information is similar to Info (D), is defined as follows：
This value indicates the v division generation by the way that training dataset D to be divided into the v output corresponding to attribute A
Information.
Information gain-ratio defines：
GainRatio (A) is information gain-ratio.
Select the attribute with maximum gain ratio as Split Attribute.
Step S-7：Crossing traffic signal prioritization scheme determines
By C4.5 decision tree methods by the analysis of studying and judging to crossing problem, the intelligent crossing main traffic studied and judged out is asked
Topic preferentially optimizes direction.General crossing problem is predominantly delayed that excessive, the traffic capacity is too low, stop frequency is excessive, saturation is stagnant
The long four classes problem of motorcade length is stayed, maximum main target type problem output will wherein be influenced based on C4.5 decision trees,
Such as preferential optimization intersection delay, gathers more excellent solution set, intersection delay optimization optimal result is picked out, is finally obtained
One solves delay problems of too, while taking into account the intersection signal prioritization scheme of other target function values.
Accordingly, determine that road junction intelligent traffic is studied and judged and signal optimizing method, make traffic signal control scheme more rationally, section
It learns, and traffic signalization effect can be given full play to.
Claims (9)
1. a kind of road junction intelligent traffic is studied and judged and signal optimizing method, which is characterized in that include the following steps：
Step 1, the crossing weighted mean velocity that target crossing is obtained based on Road Detection equipment, to obtain crossing traffic congestion
State, then target crossing judge target according to crossing weighted mean velocity and crossing traffic congestion status in certain time period
Whether crossing, which needs, optimizes signaling plan, if desired, then enters step 2；
Step 2, flow, saturation volume, the number of track-lines for acquiring each track in target crossing, establish the target letter of multi-objective genetic algorithm
Number and constraint, wherein object function includes intersection period vehicles average delay function, intersection capacity function, period
Average stop frequency function, saturation overflow queue length function, constraint include green light time interval constraint, cycle duration constrain,
Effective green time constraint, saturation degree constraint are obtained using multi-objective genetic algorithm by target in conjunction with crossing actual traffic data
The noninferior solution set that functional value and corresponding crossing cycle duration and each phase Effective Green Time duration are composed；
The noninferior solution set that step 2 obtains is normalized in step 3, and the target function value of noninferior solution set is converted
For with the dimensionless number of mechanical periodicity；
Step 4 is obtained based on euclidean metric with the average Euclidean distance between the target function value of mechanical periodicity；
The average Euclidean distance that step 5, comparison step 4 obtain carries out clustering, according to the average Europe of the object function of acquisition
The equalization point of formula distance is barycenter or carries out clustering close to barycenter, determines using equalization point as barycenter or close to barycenter
Cluster, cluster be mapped to original target function value and corresponding crossing signals cycle duration and each phase Effective Green Time duration be compared with
Excellent solution set；
Step 6, with input that target crossing essential attribute and target crossing traffic problem influence factor are C4.5 traditional decision-trees
Amount obtains target crossing based on C4.5 traditional decision-trees and mainly optimizes direction；
Step 6 is obtained target crossing and mainly optimizes direction being combined with more excellent solution that step 5 obtains set by step 7, it is final really
Recognize the signal control prioritization scheme at target crossing.
2. a kind of road junction intelligent traffic as described in claim 1 is studied and judged and signal optimizing method, which is characterized in that in the step
In rapid 1, alarmed according to the crossing traffic congestion status obtained in real time.
3. a kind of road junction intelligent traffic as described in claim 1 is studied and judged and signal optimizing method, which is characterized in that in the step
In rapid 1, weighted mean velocity of i-th of target crossing in moment t is fint_speed (t, i), then has：
In formula, rjIndicate the jth at i-th of target crossing into
Mouth road, nriIndicate the total quantity of the entrance driveway at i-th of target crossing, fint_speed (t, rj) i-th of target crossing of expression
Jth entrance driveway is in the travel speed value of moment t, fint-volume (t, rj) indicate that the jth entrance driveway at i-th of target crossing exists
The flow value of moment t.
4. a kind of road junction intelligent traffic as described in claim 1 is studied and judged and signal optimizing method, which is characterized in that in the step
In rapid 1, if target crossing is normal hair property intersection, need to optimize signaling plan.
5. a kind of road junction intelligent traffic as described in claim 1 is studied and judged and signal optimizing method, which is characterized in that in the step
In rapid 2, the intersection period vehicles average delay function is
In formula：
aijIndicate that the number of track-lines in the track of j-th of carriageway type of i-th of entrance driveway at target crossing, I indicate target crossing
The sum of entrance driveway, J indicate the sum of carriageway type；
dijIndicate that the vehicle of the track of j-th of carriageway type of i-th of entrance driveway at target crossing in one cycle averagely prolongs
Accidentally
qijIndicate the bicycle road vehicle flowrate in the track of j-th of carriageway type of i-th of entrance driveway at target crossing；
Q indicates all vehicle total flows in target crossing in a cycle,
The intersection capacity function is c：
In formula, cij=sij*λij, sijIndicate j-th of track of i-th of entrance driveway at target crossing
The saturation volume in the track of type, λijIndicate each phase in track of j-th of carriageway type of i-th of entrance driveway at target crossing
Split；
The period stop frequency function that is averaged is
In formula, hijIndicate j-th of track class of i-th of entrance driveway at target crossing
The vehicle of the track of type in one cycle is averaged stop frequency；
Saturation overflow queue length function is Indicate j-th of carriageway type of i-th of entrance driveway at target crossing
Track saturation overflow queue length function：
In formula, NijIndicate the vehicle of j-th of carriageway type of i-th of entrance driveway at target crossing
The average saturation overflow queue length in one cycle in road.
6. a kind of road junction intelligent traffic as claimed in claim 5 is studied and judged and signal optimizing method, which is characterized in that the dij's
Calculation formula is：
Work as xij≤xij0When,
Work as xij0＜ xijWhen ＜ 1,
As 1≤xijWhen≤1.15,
Work as xijWhen ＞ 1.15,In formula：
C indicates the cycle duration at target crossing；xijIndicate the track of j-th of carriageway type of i-th of entrance driveway at target crossing
Saturation degree；xij0Indicate the saturation critical point in the track of j-th of carriageway type of i-th of entrance driveway at target crossing；yijIt indicates
The flow-rate ratio in the track of j-th of carriageway type of i-th of entrance driveway at target crossing,
Indicate the traffic capacity in the track of j-th of carriageway type of i-th of entrance driveway at target crossing, cij=sij*λij；rijTable
Show the phase red time in the track of j-th of carriageway type of i-th of entrance driveway at target crossing, rij=C-gij, gijIndicate mesh
Mark each phase effective green time in the track of j-th of carriageway type of i-th of entrance driveway at crossing.
7. a kind of road junction intelligent traffic as claimed in claim 6 is studied and judged and signal optimizing method, which is characterized in that the hij's
Calculation formula is：
Work as xij≤xij0When：
Work as xij0＜ xijWhen ＜ 1：
As 1≤xijWhen≤1.15：
Work as xijWhen ＞ 1.15：
8. a kind of road junction intelligent traffic as claimed in claim 6 is studied and judged and signal optimizing method, which is characterized in that the Nij's
Calculation formula is：__
Work as xij≤xij0When：
Work as xij0＜ xijWhen ＜ 1：
As 1≤xijWhen≤1.15：
Work as xijWhen ＞ 1.15：
9. a kind of road junction intelligent traffic as described in claim 1 is studied and judged and signal optimizing method, which is characterized in that in step 7
In, whether it is major trunk roads, target crossing apart from upstream that the input quantities of the C4.5 decision trees includes each entrance driveway at target crossing
Left turn lane number, target crossing in Through Lane number, each entrance driveway in target crossing in the distance at crossing, each entrance driveway in target crossing
Crossing flow, the average saturation overflow queue length at target crossing, target crossing delay time at stop；
One of four conclusions below the C4.5 decision trees final output：(1) preferentially optimization intersection is saturated overflow queue's length；
(2) preferentially optimize the delay time at stop；(3) preferentially optimize the traffic capacity；(4) preferentially optimize stop frequency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810439951.7A CN108665715B (en) | 2018-05-09 | 2018-05-09 | Intelligent traffic studying and judging and signal optimizing method for intersection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810439951.7A CN108665715B (en) | 2018-05-09 | 2018-05-09 | Intelligent traffic studying and judging and signal optimizing method for intersection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108665715A true CN108665715A (en) | 2018-10-16 |
| CN108665715B CN108665715B (en) | 2021-04-09 |
Family
ID=63778974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810439951.7A Active CN108665715B (en) | 2018-05-09 | 2018-05-09 | Intelligent traffic studying and judging and signal optimizing method for intersection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108665715B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335469A (en) * | 2019-08-25 | 2019-10-15 | 苏州布德泽信息科技有限公司 | A kind of optimization method of traffic signalization |
| CN110491145A (en) * | 2018-10-29 | 2019-11-22 | 魏天舒 | A kind of traffic signal optimization control method and device |
| CN110634287A (en) * | 2019-08-26 | 2019-12-31 | 上海电科智能系统股份有限公司 | Urban traffic state refined discrimination method based on edge calculation |
| CN110956804A (en) * | 2019-11-19 | 2020-04-03 | 中电海康集团有限公司 | Intersection signal timing diagnosis method |
| CN111429721A (en) * | 2020-03-27 | 2020-07-17 | 江苏智通交通科技有限公司 | Intersection traffic signal scheme optimization method based on queuing dissipation time |
| CN111477019A (en) * | 2020-04-14 | 2020-07-31 | 上海电科智能系统股份有限公司 | Local signal intervention method based on SCATS system |
| CN112330957A (en) * | 2020-10-14 | 2021-02-05 | 北京博研智通科技有限公司 | Intersection signal lamp control effect analysis system and method |
| CN113223322A (en) * | 2018-12-23 | 2021-08-06 | 合肥工业大学 | Lane traffic priority calculation method and urban comprehensive intelligent traffic system thereof |
| CN113706860A (en) * | 2021-07-14 | 2021-11-26 | 石家庄铁道大学 | Intelligent timing traffic light control method based on raspberry group |
| CN114548298A (en) * | 2022-02-25 | 2022-05-27 | 阿波罗智联(北京)科技有限公司 | Model training method, traffic information processing method, device, equipment and storage medium |
| CN114898565A (en) * | 2022-07-14 | 2022-08-12 | 山东领军智能交通科技有限公司 | Self-adaptive control method of buried traffic signal lamp |
| CN115410392A (en) * | 2022-08-31 | 2022-11-29 | 联想(北京)有限公司 | Information processing method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038700A (en) * | 2007-04-20 | 2007-09-19 | 东南大学 | Mixed controlling method of single dot signal controlling crossing |
| JP2012043066A (en) * | 2010-08-16 | 2012-03-01 | Toyota Infotechnology Center Co Ltd | Transportation infrastructure improvement plan creation device and method therefor |
| CN102542818A (en) * | 2012-01-13 | 2012-07-04 | 吉林大学 | Organic-calculation-based coordination control method for traffic signal of zone boundary |
| CN104021685A (en) * | 2014-06-26 | 2014-09-03 | 广东工业大学 | Traffic control method of intersections containing mixed traffic flows |
| CN104408944A (en) * | 2014-11-10 | 2015-03-11 | 天津市市政工程设计研究院 | Lamp group based mixed traffic flow signal timing optimization method |
| CN105809958A (en) * | 2016-03-29 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Traffic control method and system based on intersection group |
| CN106781464A (en) * | 2016-12-06 | 2017-05-31 | 广州市科恩电脑有限公司 | A kind of congestion in road situation method of testing |
| CN106816018A (en) * | 2017-02-16 | 2017-06-09 | 上海电科智能系统股份有限公司 | A kind of city changeable-message sign traffic above-ground induction section determines method |
| CN106997669A (en) * | 2017-05-31 | 2017-08-01 | 青岛大学 | A kind of method of the judgement traffic congestion origin cause of formation of feature based importance |
| CN107016857A (en) * | 2017-04-13 | 2017-08-04 | 同济大学 | A kind of signal-control crossing left-turning traffic Combination Design optimization method |
-
2018
- 2018-05-09 CN CN201810439951.7A patent/CN108665715B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038700A (en) * | 2007-04-20 | 2007-09-19 | 东南大学 | Mixed controlling method of single dot signal controlling crossing |
| JP2012043066A (en) * | 2010-08-16 | 2012-03-01 | Toyota Infotechnology Center Co Ltd | Transportation infrastructure improvement plan creation device and method therefor |
| CN102542818A (en) * | 2012-01-13 | 2012-07-04 | 吉林大学 | Organic-calculation-based coordination control method for traffic signal of zone boundary |
| CN104021685A (en) * | 2014-06-26 | 2014-09-03 | 广东工业大学 | Traffic control method of intersections containing mixed traffic flows |
| CN104408944A (en) * | 2014-11-10 | 2015-03-11 | 天津市市政工程设计研究院 | Lamp group based mixed traffic flow signal timing optimization method |
| CN105809958A (en) * | 2016-03-29 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Traffic control method and system based on intersection group |
| CN106781464A (en) * | 2016-12-06 | 2017-05-31 | 广州市科恩电脑有限公司 | A kind of congestion in road situation method of testing |
| CN106816018A (en) * | 2017-02-16 | 2017-06-09 | 上海电科智能系统股份有限公司 | A kind of city changeable-message sign traffic above-ground induction section determines method |
| CN107016857A (en) * | 2017-04-13 | 2017-08-04 | 同济大学 | A kind of signal-control crossing left-turning traffic Combination Design optimization method |
| CN106997669A (en) * | 2017-05-31 | 2017-08-01 | 青岛大学 | A kind of method of the judgement traffic congestion origin cause of formation of feature based importance |
Non-Patent Citations (2)
| Title |
|---|
| YINGJIE XIA,等: "Weakly Supervised Multilabel Clustering and its Applications in Computer Vision", 《IEEE TRANSACTIONS ON CYBERNETICS》 * |
| 曲鑫: "环境友好型的交通信号多目标优化控制方法研究", 《中国优秀硕士学位论文全文数据库（工程科技II辑）》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110491145A (en) * | 2018-10-29 | 2019-11-22 | 魏天舒 | A kind of traffic signal optimization control method and device |
| CN113223322B (en) * | 2018-12-23 | 2022-03-04 | 合肥工业大学 | Lane traffic priority calculation method and urban comprehensive intelligent traffic system thereof |
| CN113223322A (en) * | 2018-12-23 | 2021-08-06 | 合肥工业大学 | Lane traffic priority calculation method and urban comprehensive intelligent traffic system thereof |
| CN110335469A (en) * | 2019-08-25 | 2019-10-15 | 苏州布德泽信息科技有限公司 | A kind of optimization method of traffic signalization |
| WO2021036278A1 (en) * | 2019-08-26 | 2021-03-04 | 上海电科智能系统股份有限公司 | Edge computing-based fine determination method for urban traffic state |
| US11361658B1 (en) | 2019-08-26 | 2022-06-14 | Shanghai Seari Intelligent System Co., Ltd. | Edge computing-based method for fine determination of urban traffic state |
| CN110634287B (en) * | 2019-08-26 | 2021-08-17 | 上海电科智能系统股份有限公司 | Urban traffic state refined discrimination method based on edge calculation |
| CN110634287A (en) * | 2019-08-26 | 2019-12-31 | 上海电科智能系统股份有限公司 | Urban traffic state refined discrimination method based on edge calculation |
| CN110956804B (en) * | 2019-11-19 | 2021-01-19 | 中电海康集团有限公司 | Intersection signal timing diagnosis method |
| CN110956804A (en) * | 2019-11-19 | 2020-04-03 | 中电海康集团有限公司 | Intersection signal timing diagnosis method |
| CN111429721A (en) * | 2020-03-27 | 2020-07-17 | 江苏智通交通科技有限公司 | Intersection traffic signal scheme optimization method based on queuing dissipation time |
| CN111477019A (en) * | 2020-04-14 | 2020-07-31 | 上海电科智能系统股份有限公司 | Local signal intervention method based on SCATS system |
| CN111477019B (en) * | 2020-04-14 | 2022-03-04 | 上海电科智能系统股份有限公司 | Local signal intervention method based on SCATS system |
| CN112330957A (en) * | 2020-10-14 | 2021-02-05 | 北京博研智通科技有限公司 | Intersection signal lamp control effect analysis system and method |
| CN113706860A (en) * | 2021-07-14 | 2021-11-26 | 石家庄铁道大学 | Intelligent timing traffic light control method based on raspberry group |
| CN114548298A (en) * | 2022-02-25 | 2022-05-27 | 阿波罗智联(北京)科技有限公司 | Model training method, traffic information processing method, device, equipment and storage medium |
| CN114898565A (en) * | 2022-07-14 | 2022-08-12 | 山东领军智能交通科技有限公司 | Self-adaptive control method of buried traffic signal lamp |
| CN115410392A (en) * | 2022-08-31 | 2022-11-29 | 联想(北京)有限公司 | Information processing method and device |
| CN115410392B (en) * | 2022-08-31 | 2024-04-23 | 联想(北京)有限公司 | Information processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108665715B (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108665715A (en) | A kind of road junction intelligent traffic is studied and judged and signal optimizing method | |
| CN111540198B (en) | Urban traffic situation recognition method based on directed graph convolution neural network | |
| CN100444210C (en) | Mixed controlling method of single dot signal controlling crossing | |
| CN109544945B (en) | Regional control phase timing optimization method based on lane saturation | |
| CN109785619B (en) | Regional traffic signal coordination optimization control system and control method thereof | |
| WO2017166474A1 (en) | Method and system for intersection group-based traffic control | |
| CN106205156B (en) | A kind of intersection self-healing combination control method for the mutation of part lane flow | |
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| WO2019061933A1 (en) | Traffic signal chord panning control method and system | |
| CN108109382A (en) | A kind of congestion points based on composite network, congestion line, the discovery method of congestion regions | |
| CN113538910B (en) | Self-adaptive full-chain urban area network signal control optimization method | |
| CN105046987A (en) | Road traffic signal lamp coordination control method based on reinforcement learning | |
| CN102708688A (en) | Secondary fuzzy comprehensive discrimination-based urban road condition recognition method | |
| CN109035811B (en) | A kind of intelligent traffic lamp real-time monitoring method based on digital information element | |
| CN108648445A (en) | Dynamic traffic Tendency Prediction method based on traffic big data | |
| CN113516854B (en) | Multi-interface coordination self-adaptive control method based on police card and video detector | |
| CN111341109B (en) | City-level signal recommendation system based on space-time similarity | |
| CN109859475B (en) | Intersection signal control method, device and system based on DBSCAN density clustering | |
| CN111524345A (en) | Induction control method for multi-objective optimization under constraint of real-time queuing length of vehicle | |
| CN109615885A (en) | A kind of intelligent traffic signal control method, apparatus and system | |
| CN109345825B (en) | Signal intersection one-way traffic flow control system and method under cooperative vehicle and road environment | |
| CN110097757A (en) | A kind of intersection group critical path recognition methods based on depth-first search | |
| CN113345230B (en) | Optimization method and optimization system for researching and judging coordination trunk management and control problem | |
| Tong et al. | Real time dynamic regulation method of main road signal lights based on data clustering in the environment of internet of vehicles. | |
| Guo et al. | Spectral bisection community detection method for urban road networks |
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 |