CN108734337A - Based on the modified customization public transport rideshare website generation method of cluster centre - Google Patents
Based on the modified customization public transport rideshare website generation method of cluster centre Download PDFInfo
- Publication number
- CN108734337A CN108734337A CN201810348137.4A CN201810348137A CN108734337A CN 108734337 A CN108734337 A CN 108734337A CN 201810348137 A CN201810348137 A CN 201810348137A CN 108734337 A CN108734337 A CN 108734337A
- Authority
- CN
- China
- Prior art keywords
- rideshare
- website
- cluster
- public transport
- point
- 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 67
- 238000010276 construction Methods 0.000 claims abstract description 10
- 238000011160 research Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000004048 modification Effects 0.000 claims description 10
- 238000012986 modification Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 238000011017 operating method Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
-
- G06Q50/40—
Abstract
An embodiment of the present invention provides one kind being based on the modified customization public transport rideshare website generation method of cluster centre.This method includes:The determination of public transport optimal site number, the construction of initial clustering rideshare set of sites, the amendment operation of cluster centre and cluster rideshare website is customized to generate result and judge.The present invention can be based on passenger's reservation data and reasonably be laid to customization public transport rideshare website, and customizing bus station addressing for the current generation provides corresponding reference, and providing method support is opened and implement for customization public transport.Customization public transport rideshare website generation method proposed by the present invention is suitable for the network topology structure of arbitrary true road network, the drawbacks of traditional bus station planning needs artificially rule of thumb subjective adjustment is abandoned, it overcomes current customization bus station and lays the shortcomings that research is not based on practical road network environment, it is ensured that science, accuracy, reasonability and the validity that rideshare website is laid.
Description
Technical field
The present invention relates to Intelligent public transportation technical fields, more particularly to one kind being based on the modified customization public transport of cluster centre
Rideshare website generation method.
Background technology
With the quickening of Urbanization in China and the limitation of urban mass-transit system, customization public transport progresses into people
The visual field.Up to the present, domestic many cities have opened up customization public bus network, such as Beijing, Qingdao, Jinan, and customization is public
It hands over because it is different from the good service characteristic of traditional public transport, has become the primary selection of urban resident trip.And China
The development of public transport is customized still in the desk study stage, the website laying, circuit design, vehicle scheduling etc. that customize public transport are gone back
Unified methodology is not formed.Therefore, how it to be based on practical road network environment, according to passenger's reservation data reasonably to customizing public transport
It is Current traffic researcher major issue worth thinking deeply about that rideshare website, which lay,.
Currently, opening and rise with customization public transport, domestic small part scholar starts to be conceived to customization bus station cloth
If theoretical research, wherein scholar more outstanding includes Hu Liege, Ma Jihui etc., but since search time is shorter, achievement is opposite
It is less.The method that current research is used is based on the methods of K-means clusters, hierarchical clustering more, and most of achievement is taken wherein
A kind of clustering method studies this problem, does not consider the limitation of used single method itself, while also simultaneously
Website distribution method is not got up with practical road network, is also mostly according to actual conditions and website even if considering practical road network
The artificial subjective adjustment in position is generated, scientific and validity is lacked.And foreign countries' density of population is relatively low, demand response type public transport
" door-to-door " transport of positioning predominantly service traffic trip demand density regions, most of correlative study do not consider rideshare
Website offering question, but each passenger demand o'clock is studied as a website, it is not appropriate for China's actual conditions.
Therefore, it is necessary to design a kind of generation method of customization public transport rideshare website, customization public transport rideshare website is carried out
It reasonably lays, customizing bus station addressing for the current generation provides corresponding reference.
Invention content
The embodiment provides one kind being based on the modified customization public transport rideshare website generation method of cluster centre, with
Solve the problems in above-mentioned background technology.
To achieve the goals above, this invention takes following technical solutions:
One kind that the embodiment of the present invention provides is based on the modified customization public transport rideshare website generation method of cluster centre,
It is characterized in that, including:
Step 1:Demand point is preengage to passenger to classify, determine of customization public transport optimal site using hierarchical clustering method
Number;
Step 2:According to the optimal site number and the space coordinate of demand point, constructs passenger demand set and sample is special
Sign vector set, and obtain initial clustering rideshare set of sites;
Step 3:To the initial cluster center not overlapped with alternative rideshare website in the initial clustering rideshare set of sites, into
Row is corrected and cluster operation, and cluster centre is made to fall on road network, obtains cluster rideshare website;
Step 4:By newer cost function value, the generation result of the cluster rideshare website is judged.
Preferably, described demand point is preengage to passenger using hierarchical clustering method to classify, determine that customization public transport is best
The number of website, including:
Step 1.1:The spatial position coordinate data that passenger preengages demand point is acquired, the passenger preengages demand and includes:On
It vehicle point and gets off a little;
Step 1.2:Calculate the Euclidean distance between all demand points;
Step 1.3:By all demand points according to the Euclidean distance, it is poly- to carry out level according to maximum distance measurement criterion
Class generates clustering tree;
Step 1.4:The value for determining maximum distance, according to the clustering tree, using maximum distance value as criteria for classification, really
Make the optimal site number c of customization public transport.
Preferably, the value of the determination maximum distance, according to the clustering tree, using maximum distance value as contingency table
Standard determines the optimal site number c of customization public transport, including:
It is as follows to the value of maximum distance:Determine that station services radius R, the station services radius R are the maximum of passenger
Distance travelled, value is:The coverage area of 500~1000m, website are using the website as the center of circle, by radius of R to external radiation
Maximum distance value between two websites is by circular scope:4R;
According to the clustering tree, using the maximum distance value 4R as criteria for classification, the best station of customization public transport is determined
Point number c.
Preferably, described according to optimal site number and the space coordinate of demand point, construct passenger demand set and sample
Eigen vector set, and initial clustering rideshare set of sites is obtained, including:
Step 2.1:Constructing passenger demand set X is:
X={ x1,x2,...,xn, (1)
Wherein, n is demand number;
Each demand x in the passenger demand setiSampling feature vectors be:
(xi1,xi2,...,xim)T, (2)
Wherein, m is the index number of sort research, is spatially assembled in demand point, takes m=2;
Step 2.2:Using Fuzzy c-means Clustering method, initial clustering rideshare set of sites is obtained.
Preferably, the utilization Fuzzy c-means Clustering method, obtains initial clustering rideshare set of sites, including:
Step 2.2.1:The spaces ambiguity in definition c, obtain the matrix U of c × n, are initialized and are subordinate to random number of the value between [0,1]
Belong to matrix U, it is made to meet following formula:
Step 2.2.2:Construction cluster rideshare website coordinate set Y:
Y=(x, y) | and (x, y) ∈ S }, (4)
Wherein, S indicates the alternative rideshare set of sites in road network, and S is can be as in website in road-net node and section
Between the summation put;
Y is initialized, is enabled
Step 2.2.3:The matrix U is substituted into following formula:
Wherein, p is a Weighted Index, and p ∈ (1, ∞);
It obtains the initial cluster center of c rideshare website, while constructing interim cluster rideshare website and being:
CL={ ci| i=1 ..., c }, Card (CL)=c, (6)
Wherein, CLThe i.e. described initial clustering rideshare set of sites.
Preferably, in the initial clustering not overlapped with alternative rideshare website in the rideshare set of sites to initial clustering
The heart, is modified and cluster operation, and cluster centre is made to fall on road network, obtains cluster rideshare website, including:
Step 3.1:It repeats to judge operation, until
Step 3.2:The judgement operates:
If ci∈ Y then reacquire the initial clustering rideshare set of sites, if not, then judge cluster centre ciPosition
It sets, generates corresponding alternative clusters Website Hosting Ci;
Step 3.3:Enable CL=CL\{ci, and to the alternative clusters Website Hosting CiJudged, if CiIt, will for empty set
Ci is stored in Y, and return to step 3.1 carries out the repetition and judges operation;IfReturn to step 2.2, utilizes fuzzy c-means
Clustering procedure obtains the initial clustering rideshare website;Otherwise, by CiIn element take out and be denoted as a successively, then current cluster is closed
Multiplying set of sites Y' is:
Y'={ Y, a, CL, (7)
The formula for calculating cost function value is as follows:
Wherein, dijIndicate the Euclidean distance of cluster centre i and demand point j;
IfSelect the CiIn so that the point of cost function value minimum is otherwise enabled as cluster website deposit Y
Ci'=Ci-Ci∩ Y select Ci' in make the point of cost function value minimum as cluster website deposit Y, and remember corresponding value letter
Numerical value is F;
Step 3.4:I+1 to the c rows of U matrixes, return to step 3.1 are updated according to formula (10), (11);
Preferably, the corresponding alternative clusters Website Hosting C of the generationi, including:
It is minimal path net unit if UNIT is the minimum closed polygon that road-net node can be constituted;
Step 3.2.1:If the cluster centre c generatediIn road network unit UNIT, then CiIt is covered by each side of the unit
All S in the set that constitutes of point, the point in all S includes vertex;
Step 3.2.2:If the cluster centre ci generated is located on road network, two lateral extent c on the section is selected respectivelyiMost
Point in close S is as ciThe alternative clusters website of point, at this time CiIt constitutes and gathers for selected two websites;
Step 3.2.3:If the point in the S that the cluster centre ci generated is covered with each sides road network unit UNIT overlaps,Point in S includes vertex.
Preferably, described by newer cost function value, the generation result of the cluster rideshare website is sentenced
It is disconnected, including:
Knots modifications of the cost function value F that calculating final updated obtains with respect to last time cost function value;
If the knots modification is greater than or equal to predetermined threshold value ε, it is that the passenger described in step 3 gathers to enable the U matrixes of initialization
The U matrixes that the amendment operating method final updated at class center obtains, and return to step 2.2 reacquires initial clustering rideshare website
Collection continues iteration;
If the knots modification is less than predetermined threshold value ε, stop calculating, Y is that required customization public transport clusters rideshare website
Set.
The embodiment of the present invention is by proposing a kind of base it can be seen from the technical solution that embodiments of the invention described above provide
In the modified customization public transport rideshare website generation method of cluster centre, public transport optimal site number is customized by determining, construction is just
The cluster that begins rideshare set of sites is modified operation and generates result to cluster rideshare website and sentences to passenger's cluster centre
It is disconnected, to realize the Reasonable Arrangement to customizing public transport rideshare website.The present invention is suitable for the network topology knot of arbitrary true road network
Structure can overcome current customization bus station to lay the shortcomings that research is not based on practical road network environment, it can be ensured that rideshare website is laid
Science, accuracy, reasonability and validity, for the current generation customize bus station addressing corresponding reference is provided, be fixed
Providing method support is opened and is implemented in public transport processed.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without having to pay creative labor, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Process chart;
Fig. 2 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Customization public transport optimal site number determine method flow diagram;
Fig. 3 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Initial clustering rideshare website set construction method flow chart;
Fig. 4 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Passenger's cluster centre correct flow chart;
Fig. 5 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Passenger's cluster centre correct operation chart;
Fig. 6 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Initial clustering rideshare set of sites generate result figure;
Fig. 7 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Revised customization public transport rideshare website generate result figure;
Fig. 8 is provided in an embodiment of the present invention a kind of based on the modified customization public transport rideshare website generation method of cluster centre
Demand sample classification effect analysis figure.
Specific implementation mode
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng
The embodiment for examining attached drawing description is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that is used in the specification of the present invention arranges
It refers to there are the feature, integer, step, operation, element and/or component, but it is not excluded that presence or addition to take leave " comprising "
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.Wording used herein
"and/or" includes any cell of one or more associated list items and all combines.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology) there is meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, which should be understood that, to be had and the meaning in the context of the prior art
The consistent meaning of justice, and unless defined as here, will not be with idealizing or the meaning of too formal be explained.
For ease of the understanding to the embodiment of the present invention, done further by taking several specific embodiments as an example below in conjunction with attached drawing
Explanation, and each embodiment does not constitute the restriction to the embodiment of the present invention.
Embodiment one
An embodiment of the present invention provides one kind being based on the modified customization public transport rideshare website generation method of cluster centre, is based on
Passenger's reservation data carries out Reasonable Arrangement to customization public transport rideshare website.
A kind of place based on the modified customization public transport rideshare website generation method of cluster centre provided in an embodiment of the present invention
Flow chart is managed as shown in Figure 1, specifically comprising the following steps:
S110:Demand point is preengage to passenger to classify, determine of customization public transport optimal site using hierarchical clustering method
Number.
Step 1.1:The spatial position coordinate data that passenger preengages demand point is acquired, the passenger preengages demand and includes:On
It vehicle point and gets off a little.
Step 1.2:Calculate the Euclidean distance between all demand points.
Step 1.3:By all demand points according to the Euclidean distance, it is poly- to carry out level according to maximum distance measurement criterion
Class generates clustering tree.
Step 1.4:The value for determining maximum distance, according to the clustering tree, using maximum distance value as criteria for classification, really
Make the optimal site number c of customization public transport.
It is as follows to the value of maximum distance:Determine that station services radius R, the station services radius R are the maximum of passenger
Distance travelled, value is:The coverage area of 500~1000m, website are using the website as the center of circle, by radius of R to external radiation
Maximum distance value between two websites is by circular scope:4R.
According to the clustering tree, using the maximum distance value 4R as criteria for classification, the best station of customization public transport is determined
Point number c.
S120:According to optimal site number and the space coordinate of demand point, construct passenger demand set and sample characteristics to
Duration set, and obtain initial clustering rideshare set of sites.
Step 2.1:Constructing passenger demand set X is:
X={ x1,x2,...,xn, (1)
Wherein, n is demand number.
Each demand x in the passenger demand setiSampling feature vectors be:
(xi1,xi2,...,xim)T, (2)
Wherein, m is the index number of sort research, is spatially assembled in demand point, takes m=2.
Step 2.2:Using Fuzzy c-means Clustering method, initial clustering rideshare set of sites is obtained.
Step 2.2.1:The spaces ambiguity in definition c, obtain the matrix U of c × n, are initialized and are subordinate to random number of the value between [0,1]
Belong to matrix U, it is made to meet following formula:
Step 2.2.2:Construction cluster rideshare website coordinate set Y:
Y=(x, y) | and (x, y) ∈ S }, (4)
Wherein, S indicates the alternative rideshare set of sites in road network, and S is can be as in website in road-net node and section
Between the summation put.
Y is initialized, is enabled
Step 2.2.3:The matrix U is substituted into following formula:
Wherein, p is a Weighted Index, and p ∈ (1, ∞).
It obtains the initial cluster center of c rideshare website, while constructing interim cluster rideshare website and being:
CL={ ci| i=1 ..., c }, Card (CL)=c, (6)
Wherein, CLThe i.e. described initial clustering rideshare set of sites.
S130:To the initial cluster center not overlapped with alternative rideshare website in initial clustering rideshare set of sites, repaiied
Just and cluster operation, so that cluster centre is fallen on road network, obtain cluster rideshare website.
Step 3.1:It repeats to judge operation, until
Step 3.2:Judge that operation is:If ci∈ Y then reacquire the initial clustering rideshare set of sites, if not,
Then judge cluster centre ciPosition, generate corresponding alternative clusters Website Hosting Ci。
It is minimal path net unit if UNIT is the minimum closed polygon that road-net node can be constituted.
Step 3.2.1:If the cluster centre c generatediIn road network unit UNIT, then CiIt is covered by each side of the unit
All S in the set that constitutes of point, the point in all S includes vertex.
Step 3.2.2:If the cluster centre c generatediOn road network, then two lateral extent c on the section is selected respectivelyiMost
Point in close S is as ciThe alternative clusters website of point, at this time CiIt constitutes and gathers for selected two websites.
Step 3.2.3:If the point in the S that the cluster centre ci generated is covered with each sides road network unit UNIT overlaps,Point in S includes vertex.
Step 3.3:Enable CL=CL\{ci, and to the alternative clusters Website Hosting CiJudged, if CiIt, will for empty set
Ci is stored in Y, and return to step 3.1 carries out the repetition and judges operation;IfReturn to step 2.2, utilizes fuzzy c-means
Clustering procedure obtains the initial clustering rideshare website;Otherwise, by CiIn element take out and be denoted as a successively, then current cluster is closed
Multiplying set of sites Y' is:
Y'={ Y, a, CL}。 (7)
The formula for calculating cost function value is as follows:
Wherein, dijIndicate the Euclidean distance of cluster centre i and demand point j.
IfSelect the CiIn so that the point of cost function value minimum is otherwise enabled as cluster website deposit Y
Ci'=Ci-Ci∩ Y select Ci' in make the point of cost function value minimum as cluster website deposit Y, and remember corresponding value letter
Numerical value is F.
Step 3.4:I+1 to the c rows of U matrixes, return to step 3.1 are updated according to formula (10), (11).
Calculation formula is:
S140:By newer cost function value, the generation result of the cluster rideshare website is judged.
Knots modifications of the cost function value F that calculating final updated obtains with respect to last time cost function value.
If the knots modification is greater than or equal to predetermined threshold value ε, it is the passenger described in step S130 to enable the U matrixes of initialization
The U matrixes that the amendment operating method final updated of cluster centre obtains, and return to step 2.2 reacquires initial clustering rideshare station
Point set continues iteration.
If the knots modification is less than predetermined threshold value ε, stop calculating, Y is that required customization public transport clusters rideshare website
Set.
Embodiment two
This embodiment offers a kind of processing streams based on the modified customization public transport rideshare website generation method of cluster centre
Journey is as shown in Figure 1, include following processing step:
Step 1:Demand point is preengage to passenger to classify, determine of customization public transport optimal site using hierarchical clustering method
Number.
Classification refers to, all demand point (including get on the bus a little and get off a little), being divided into several classes according to spatial position, dividing
At classification number be website number;Get on the bus a little and get off a little respectively refer to every passenger select the starting point submitted when customization public transport and
Destination, it is all a little demand point to get on the bus a little and get off.
Step 2:According to obtained optimal site number and the space coordinate of demand point, passenger demand set and sample are special
Sign vector set, and obtain initial clustering rideshare set of sites.
Step 3:To the initial cluster center that is not overlapped with the alternative rideshare website of road network in initial clustering rideshare set of sites into
The a series of amendment of row and cluster operation, make cluster centre fall on road network.
Step 4:It clusters rideshare website and generates result judgement.
It is illustrated in figure 2 customization public transport optimal site number and determines method flow diagram, be as follows:
(1) acquisition reservation passenger demand point is to position coordinate data, including gets on the bus a little and get off a little.
(2) distance between all demand points is calculated.
(3) hierarchical clustering is carried out according to maximum distance measurement criterion, until all demand points cluster finishes, generation clusters
Tree.
(4) maximum distance value is determined, the clustering tree generated according to step 3 as criteria for classification using the maximum distance value
Determine customization public transport optimal site number c.
It is illustrated in figure 3 initial clustering rideshare website set construction method flow chart, is as follows:
(1) construction passenger demand set X={ x1,x2,...,xn, wherein n is demand number, each demand xiHave
Sampling feature vectors (xi1,xi2,...,xim)T, wherein m is the index number of sort research.This method relates generally to demand point sky
Between on aggregation, therefore m=2, involved index is the transverse and longitudinal coordinate of demand point.
(2) Fuzzy c-means Clustering method is utilized to obtain initial clustering rideshare set of sites.It is above-mentioned based on Fuzzy c-means Clustering
Initial clustering rideshare set of sites acquisition methods, detailed process are as follows:
A. the spaces ambiguity in definition c obtain the matrix U of c × n, and Subject Matrix U is initialized with random number of the value between [0,1],
It is set to meet following formula:
B. construction cluster rideshare website coordinate set Y={ (x, y) | (x, y) ∈ S }, S indicates the alternative rideshare website of road network
Collection, being can be as the summation of the intermediate point of website in road-net node and section.Y is initialized, is enabled
C. following formula is calculated using the matrix U that initialization generates, obtains c rideshare website initial cluster center, constructs simultaneously
Interim cluster rideshare set of sites CL={ ci| i=1 ..., c }, Card (CL)=c, CLAs initial clustering rideshare set of sites;Meter
Formula is:
Wherein, p is a Weighted Index, and p ∈ (1, ∞).
It is illustrated in figure 4 passenger's cluster centre and corrects flow chart, be as follows:
(1) operations described below is repeated, until
(2) judge ciWhether ∈ Y are true, if so, it then needs to reacquire initial clustering rideshare set of sites;Otherwise judge poly-
Class center ciPosition generates corresponding alternative clusters Website Hosting Ci。
ciCorresponding alternative clusters Website Hosting CiGeneration method is as follows:
If UNIT is the minimum closed polygon that road-net node can be constituted.The present embodiment is carried out by taking square grid shape road network as an example
Illustrate, all road-net nodes constitute the alternative rideshare set of sites of road network.Operation chart is corrected as shown in figure 5, point A, B, C, D are road
Net node collectively forms a road network unit UNIT.
If the cluster centre c A. generatediIn road network unit UNIT, as shown in Fig. 5 (1), then the top of the unit is selected
Point A, B, C, D are as ciThe alternative clusters website of point, at this time Ci={ A, B, C, D }.
If the cluster centre c B. generatediOn road network, then c is selectediThe vertex in place section is as ciThe alternative of point gathers
Class website, in the case of shown in Fig. 5 (2), ciCorresponding alternative clusters Website Hosting is denoted as Ci={ A, B }.
If the cluster centre c C. generatediIt is overlapped with the vertex of road network unit UNIT, then
(3) C is enabledL=CL\{ci}.Judge CiWhether it is empty set, if empty set, by ciIt is stored in Y, return to step 1;IfThen reacquire initial clustering rideshare set of sites;Otherwise, C is taken successivelyiMiddle element (being denoted as a) then currently clusters rideshare
Set of sites is Y'={ Y, a, CL, cost function value is calculated according to formula (3), (4) respectively, ifSelect CiIn make valence
The point of value function value minimum is stored in Y as cluster website, otherwise enables Ci'=Ci-Ci∩ Y select Ci' in make cost function value most
Small point is stored in Y as cluster website, remembers that corresponding cost function value is F.
Calculating formula is:
Wherein, dijIndicate the Euclidean distance of cluster centre i and demand point j.
(4) i+1 to the c rows of U matrixes, return to step (1) are updated according to following two formulas;
The cluster rideshare website of the present embodiment generates result judgment method, is implemented as follows:
The cost function value F that calculating final updated obtains judges whether to be more than with respect to the knots modification of last time cost function value
Or it is equal to predetermined threshold value ε;If so, it is the U matrixes corrected operation final updated and obtained to enable the Subject Matrix of initialization, return just
The step of beginning to cluster rideshare website set construction method;Otherwise, then algorithm stops, and Y is that required customization public transport clusters rideshare station
Point set.
Embodiment three
This embodiment offers one kind being based on the modified customization public transport rideshare website generation method of cluster centre, specific real
It is now as follows:
(1) embodiment has chosen square grid shape road network environment, and network node is all alternative rideshare websites.
(2) it is 12 to determine that method can be calculated optimal site number by customization public transport optimal site number.
(3) it is based on optimal site number, initial clustering rideshare set of sites is constructed, the results are shown in Figure 6 for generation, can
To find out that initial clustering rideshare website deviates road network, do not overlapped with alternative rideshare website.
(4) initial cluster center is modified, and judge generating result, final website generates result such as Fig. 7
It is shown, it can be seen that passenger's rideshare website of generation is distributed on road network and is overlapped with alternative rideshare website.
Be illustrated in figure 8 subordinated-degree matrix solve schematic diagram, the classifying quality for evaluating sample, it can be seen that it is all kinds of it
Between subordinated-degree matrix there are larger differences, discrimination is higher, and Clustering Effect is good.
In conclusion the embodiment of the present invention is a kind of based on the modified customization public transport rideshare website life of cluster centre by proposing
At method, passenger's reservation data can be based on, customization public transport rideshare website is reasonably laid, abandon traditional bus station
Point planning needs artificially the drawbacks of rule of thumb subjective adjustment, overcomes current customization bus station and lays research and is not based on practical road
The shortcomings that net environment, it is ensured that science, accuracy, reasonability and the validity that rideshare website is laid customize for the current generation
Bus station addressing provides corresponding reference.
One of ordinary skill in the art will appreciate that:Attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Flow is not necessarily implemented necessary to the present invention.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for device or
For system embodiment, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to method
The part of embodiment illustrates.Apparatus and system embodiment described above is only schematical, wherein the conduct
The unit that separating component illustrates may or may not be physically separated, the component shown as unit can be or
Person may not be physical unit, you can be located at a place, or may be distributed over multiple network units.It can root
According to actual need that some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Ordinary skill
Personnel are without creative efforts, you can to understand and implement.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
Subject to.
Claims (8)
1. one kind being based on the modified customization public transport rideshare website generation method of cluster centre, which is characterized in that including:
Step 1:Demand point is preengage to passenger to classify, determine the number of customization public transport optimal site using hierarchical clustering method;
Step 2:According to the optimal site number and the space coordinate of demand point, construct passenger demand set and sample characteristics to
Duration set, and obtain initial clustering rideshare set of sites;
Step 3:To the initial cluster center not overlapped with alternative rideshare website in the initial clustering rideshare set of sites, repaiied
Just and cluster operation, so that cluster centre is fallen on road network, obtain cluster rideshare website;
Step 4:By newer cost function value, the generation result of the cluster rideshare website is judged.
2. according to claim 1 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In described classifies to passenger's reservation demand point using hierarchical clustering method, determines the number of customization public transport optimal site, packet
It includes:
Step 1.1:The spatial position coordinate data that passenger preengages demand point is acquired, the passenger preengages demand and includes:It gets on the bus a little
With get off a little;
Step 1.2:Calculate the Euclidean distance between all demand points;
Step 1.3:By all demand points according to the Euclidean distance, hierarchical clustering is carried out according to maximum distance measurement criterion, it is raw
At clustering tree;
Step 1.4:The value for determining maximum distance is determined according to the clustering tree using maximum distance value as criteria for classification
Customize the optimal site number c of public transport.
3. according to claim 2 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In the value of the determination maximum distance, according to the clustering tree, using maximum distance value as criteria for classification, it is fixed to determine
The optimal site number c of public transport processed, including:
It is as follows to the value of maximum distance:Determine that station services radius R, the station services radius R are the maximum traveling of passenger
Distance, value are:The coverage area of 500~1000m, website are using the website as the center of circle, by radius of R to the circle of external radiation
Maximum distance value between two websites is by range:4R;
According to the clustering tree, using the maximum distance value 4R as criteria for classification, the optimal site of customization public transport is determined
Number c.
4. according to claim 1 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In, it is described according to optimal site number and the space coordinate of demand point, construct passenger demand set and sampling feature vectors collection
It closes, and obtains initial clustering rideshare set of sites, including:
Step 2.1:Constructing passenger demand set X is:
X={ x1,x2,...,xn, (1)
Wherein, n is demand number;
Each demand x in the passenger demand setiSampling feature vectors be:
(xi1,xi2,...,xim)T, (2)
Wherein, m is the index number of sort research, is spatially assembled in demand point, takes m=2;
Step 2.2:Using Fuzzy c-means Clustering method, initial clustering rideshare set of sites is obtained.
5. according to claim 4 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In, described utilizes Fuzzy c-means Clustering method, obtains initial clustering rideshare set of sites, including:
Step 2.2.1:The spaces ambiguity in definition c, obtain the matrix U of c × n, are subordinate to square with random number initialization of the value between [0,1]
Battle array U, makes it meet following formula:
Step 2.2.2:Construction cluster rideshare website coordinate set Y:
Y=(x, y) | and (x, y) ∈ S }, (4)
Wherein, S indicates the alternative rideshare set of sites in road network, and S is can be as the intermediate point of website in road-net node and section
Summation;
Y is initialized, is enabled
Step 2.2.3:The matrix U is substituted into following formula:
Wherein, p is a Weighted Index, and p ∈ (1, ∞);
It obtains the initial cluster center of c rideshare website, while constructing interim cluster rideshare website and being:
CL={ ci| i=1 ..., c }, Card (CL)=c, (6)
Wherein, CLThe i.e. described initial clustering rideshare set of sites.
6. according to claim 1 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In, the initial cluster center not overlapped with alternative rideshare website in the rideshare set of sites to initial clustering, be modified and
Cluster operation makes cluster centre fall on road network, obtains cluster rideshare website, including:
Step 3.1:It repeats to judge operation, until
Step 3.2:The judgement operates:
If ci∈ Y then reacquire the initial clustering rideshare set of sites, if not, then judge cluster centre ciPosition,
Generate corresponding alternative clusters Website Hosting Ci;
Step 3.3:Enable CL=CL\{ci, and to the alternative clusters Website Hosting CiJudged, if CiFor empty set, by ciIt deposits
Enter in Y, return to step 3.1 carries out the repetition and judges operation;IfReturn to step 2.2, utilizes Fuzzy c-means Clustering
Method obtains the initial clustering rideshare website;Otherwise, by CiIn element take out and be denoted as a successively, then current cluster rideshare station
Point set Y' is:
Y'={ Y, a, CL, (7)
The formula for calculating cost function value is as follows:
Wherein, dijIndicate the Euclidean distance of cluster centre i and demand point j;
IfSelect the CiIn so that the point of cost function value minimum is otherwise enabled C as cluster website deposit Yi'
=Ci-Ci∩ Y select Ci' in make the point of cost function value minimum as cluster website deposit Y, and remember corresponding cost function value
For F;
Step 3.4:I+1 to the c rows of U matrixes, return to step 3.1 are updated according to formula (10), (11);
7. according to claim 6 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In the corresponding alternative clusters Website Hosting C of the generationi, including:
It is minimal path net unit if UNIT is the minimum closed polygon that road-net node can be constituted;
Step 3.2.1:If the cluster centre c generatediIn road network unit UNIT, then CiThe institute covered for each side of the unit
There is the set that the point in S is constituted, the point in all S includes vertex;
Step 3.2.2:If the cluster centre c generatediOn road network, then two lateral extent c on the section is selected respectivelyiNearest S
In point as ciThe alternative clusters website of point, at this time CiIt constitutes and gathers for selected two websites;
Step 3.2.3:If the cluster centre c generatediPoint in the S covered with each sides road network unit UNIT overlaps, then
Point in S includes vertex.
8. according to claim 1 be based on the modified customization public transport rideshare website generation method of cluster centre, feature exists
In, it is described that the generation result of the cluster rideshare website is judged by newer cost function value, including:
Knots modifications of the cost function value F that calculating final updated obtains with respect to last time cost function value;
If the knots modification is greater than or equal to predetermined threshold value ε, it is during the passenger described in step 3 clusters to enable the U matrixes of initialization
The U matrixes that the amendment operating method final updated of the heart obtains, and return to step 2.2 reacquires initial clustering rideshare set of sites,
Continue iteration;
If the knots modification is less than predetermined threshold value ε, stop calculating, Y is that required customization public transport clusters rideshare Website Hosting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810348137.4A CN108734337B (en) | 2018-04-18 | 2018-04-18 | Customized bus station generation method based on cluster center correction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810348137.4A CN108734337B (en) | 2018-04-18 | 2018-04-18 | Customized bus station generation method based on cluster center correction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108734337A true CN108734337A (en) | 2018-11-02 |
CN108734337B CN108734337B (en) | 2022-03-18 |
Family
ID=63939569
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810348137.4A Active CN108734337B (en) | 2018-04-18 | 2018-04-18 | Customized bus station generation method based on cluster center correction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108734337B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109781130A (en) * | 2019-02-01 | 2019-05-21 | 上海雷腾软件股份有限公司 | The method and apparatus that bus route is planned automatically |
CN110458309A (en) * | 2019-06-29 | 2019-11-15 | 东南大学 | A kind of net based on practical road network environment about share-car bus station position method |
CN112396324A (en) * | 2020-11-19 | 2021-02-23 | 北京清研宏达信息科技有限公司 | Implementation method of microcirculation network appointment bus Minibus automatic scheduling system |
CN113096377A (en) * | 2021-02-18 | 2021-07-09 | 西南交通大学 | Vehicle ride sharing planning method based on urban heterogeneity |
CN113326989A (en) * | 2021-06-15 | 2021-08-31 | 北京沃东天骏信息技术有限公司 | Method and system for optimizing vehicle route |
CN115186049A (en) * | 2022-09-06 | 2022-10-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Intelligent bus alternative station site selection method, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102592447A (en) * | 2011-12-20 | 2012-07-18 | 浙江工业大学 | Method for judging road traffic state of regional road network based on fuzzy c means (FCM) |
CN104318324A (en) * | 2014-10-13 | 2015-01-28 | 南京大学 | Taxi GPS (Global Positioning System) record based airport bus station and path planning method |
CN105070044A (en) * | 2015-08-17 | 2015-11-18 | 南通大学 | Dynamic scheduling method for customized buses and car pooling based on passenger appointments |
US20170109764A1 (en) * | 2015-10-19 | 2017-04-20 | Xerox Corporation | System and method for mobility demand modeling using geographical data |
CN107832779A (en) * | 2017-12-11 | 2018-03-23 | 北方工业大学 | Track station classification system |
-
2018
- 2018-04-18 CN CN201810348137.4A patent/CN108734337B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102592447A (en) * | 2011-12-20 | 2012-07-18 | 浙江工业大学 | Method for judging road traffic state of regional road network based on fuzzy c means (FCM) |
CN104318324A (en) * | 2014-10-13 | 2015-01-28 | 南京大学 | Taxi GPS (Global Positioning System) record based airport bus station and path planning method |
CN105070044A (en) * | 2015-08-17 | 2015-11-18 | 南通大学 | Dynamic scheduling method for customized buses and car pooling based on passenger appointments |
US20170109764A1 (en) * | 2015-10-19 | 2017-04-20 | Xerox Corporation | System and method for mobility demand modeling using geographical data |
CN107832779A (en) * | 2017-12-11 | 2018-03-23 | 北方工业大学 | Track station classification system |
Non-Patent Citations (3)
Title |
---|
王飞: "定制公交线路和站点规划研究", 《中国优秀硕士学位论文全文数据库(电子期刊)》 * |
胡列格 等: "城市定制公交合乘站点的布局研究", 《徐州工程学院学报(自然科学版)》 * |
马继辉 等: "定制公交线路开行方案研究", 《城市公共交通》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109781130A (en) * | 2019-02-01 | 2019-05-21 | 上海雷腾软件股份有限公司 | The method and apparatus that bus route is planned automatically |
CN110458309A (en) * | 2019-06-29 | 2019-11-15 | 东南大学 | A kind of net based on practical road network environment about share-car bus station position method |
CN110458309B (en) * | 2019-06-29 | 2023-07-11 | 东南大学 | Network about splicing station point location method based on actual road network environment |
CN112396324A (en) * | 2020-11-19 | 2021-02-23 | 北京清研宏达信息科技有限公司 | Implementation method of microcirculation network appointment bus Minibus automatic scheduling system |
CN113096377A (en) * | 2021-02-18 | 2021-07-09 | 西南交通大学 | Vehicle ride sharing planning method based on urban heterogeneity |
CN113096377B (en) * | 2021-02-18 | 2022-07-29 | 西南交通大学 | Vehicle carpooling planning method based on urban heterogeneity |
CN113326989A (en) * | 2021-06-15 | 2021-08-31 | 北京沃东天骏信息技术有限公司 | Method and system for optimizing vehicle route |
CN115186049A (en) * | 2022-09-06 | 2022-10-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Intelligent bus alternative station site selection method, electronic equipment and storage medium |
CN115186049B (en) * | 2022-09-06 | 2023-02-03 | 深圳市城市交通规划设计研究中心股份有限公司 | Intelligent bus alternative station site selection method, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108734337B (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108734337A (en) | Based on the modified customization public transport rideshare website generation method of cluster centre | |
Hu et al. | Federated region-learning: An edge computing based framework for urban environment sensing | |
Xu et al. | Incentive mechanism for multiple cooperative tasks with compatible users in mobile crowd sensing via online communities | |
CN104809877B (en) | The highway place traffic state estimation method of feature based parameter weighting GEFCM algorithms | |
CN103744733B (en) | Method for calling and configuring imaging satellite resources | |
CN110135630A (en) | The short term needing forecasting method with multi-step optimization is returned based on random forest | |
CN110009455A (en) | It is a kind of based on network representation study net about share out administrative staff's matching process | |
CN109191004A (en) | A kind of multiple no-manned plane mapping method for allocating tasks and device | |
CN106203867A (en) | Grid division methods based on power distribution network assessment indicator system and cluster analysis | |
CN108090510A (en) | A kind of integrated learning approach and device based on interval optimization | |
CN108009575A (en) | A kind of community discovery method for complex network | |
CN108062720A (en) | A kind of load forecasting method based on similar day selection and random forests algorithm | |
CN108537683A (en) | A kind of load forecasting method based on similar day selection and random forests algorithm | |
CN103888541A (en) | Method and system for discovering cells fused with topology potential and spectral clustering | |
CN109948695A (en) | A kind of power grid fragility node automatic identifying method based on neighbour's propagation clustering algorithm | |
CN108734413A (en) | A kind of high ferro station road network evaluation method and device | |
Rodrigues et al. | Measures in sectorization problems | |
CN109213926A (en) | A kind of location recommendation method divided based on community with Multi-source Information Fusion | |
CN110533072A (en) | Based on the SOAP service similarity calculation and clustering method of Bigraph structure under Web environment | |
CN105930531A (en) | Method for optimizing cloud dimensions of agricultural domain ontological knowledge on basis of hybrid models | |
CN107451617A (en) | One kind figure transduction semisupervised classification method | |
CN110110914A (en) | Student's degree of difficulty prediction technique based on transformation decision tree and intelligent optimization method | |
CN110137951A (en) | Market segmentation method and device based on node electricity price | |
CN105550711A (en) | Firefly algorithm based selective ensemble learning method | |
CN108038518A (en) | A kind of photovoltaic generation power based on meteorological data determines method and system |
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 |