CN108682153A - A kind of urban road traffic congestion condition discrimination method based on RFID electronic license plate data - Google Patents
A kind of urban road traffic congestion condition discrimination method based on RFID electronic license plate data Download PDFInfo
- Publication number
- CN108682153A CN108682153A CN201810549401.0A CN201810549401A CN108682153A CN 108682153 A CN108682153 A CN 108682153A CN 201810549401 A CN201810549401 A CN 201810549401A CN 108682153 A CN108682153 A CN 108682153A
- Authority
- CN
- China
- Prior art keywords
- cluster
- cluster centre
- value
- traffic congestion
- traffic
- 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
Classifications
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- 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
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of urban road traffic congestion condition discrimination methods based on RFID electronic license plate data, include the following steps：1) pass through RFID electronic license plate data acquisition traffic flow evaluation parameters, including standard vehicle equivalents and average speed；2) the standard vehicle equivalents and average speed obtained step 1) carries out cluster operation as two dimensions of cluster operation, obtains preferable clustering number mesh and cluster result；3) by cluster centre according to the descending sequence of value of ordinate subpoint, for the value of ordinate subpoint identical cluster centre point, it to abscissa project and be ranked up according to the value of abscissa subpoint is ascending, the cluster centre point corresponding to the subpoint after sequence represents traffic congestion state from unimpeded to the consecutive variations trend of congestion.The present invention replaces the volume of traffic as the dimension of GEFCM clustering algorithms using standard vehicle equivalents, it can preferably reflect traffic congestion state, and relative to traditional FCM Algorithms, the different influences to final cluster result because of sample class capacity can be avoided with GEFCM, improve the accuracy of cluster；And it solves the problems, such as to match between cluster centre and specific traffic congestion state.
Description
Technical field
The present invention relates to transport data processing technical fields, and in particular to a kind of city based on RFID electronic license plate data
Road traffic congestion condition discrimination method.
Background technology
RFID technique, that is, radio frequency identification (Radio Frequency Identification) technology, operation principle pass through
The identification technology that contactless two-way communication is carried out using wireless radio frequency mode, to realize the function of Urine scent.RFID technique
Have many advantages, such as that high confidentiality, reading/writing distance are remote, can recognize that such as automobile swiftly passing object, contactless two-way communication,
And it can work under rugged environment.By the way that RFID technique is combined with the communication technology, Internet technology etc., current big model
Enclose the fields such as anti-fake applied to Internet of Things, intelligent transportation and commodity.
With the development of the social economy, the vehicle guaranteeding organic quantity in China constantly rises, people's trip is all the more frequent in addition, this
Certain pressure will certainly be brought to road traffic, the case where to cause traffic congestion, so for the reasonable control of traffic
It is to alleviate the key point of traffic congestion with induction, wherein the acquisition of traffic congestion state is the basis of traffic control and induction,
Therefore accurate to differentiate that traffic congestion state seems most important in field of traffic.
Urban road traffic congestion condition discrimination is mainly based on automatic discrimination technology at present, with the technology of field of traffic
Theory continues to develop and perfect, and the technologies such as fuzzy theory, neural network, interdisciplinary theory are more and more used in friendship
In the research that logical congestion differentiates.Traffic congestion state differentiates based on the Rational choice of traffic flow evaluation parameter, based on not
The sample data of same type, type, complexity and the accuracy rate that traffic flow evaluation parameter is chosen all can be variant.Base of the present invention
In RFID electronic license plate data, since RFID technique is embodied in the advantage of field of traffic, vehicle recongnition technique is fast, vehicle identification
Do not influenced by weather condition, vehicle identification information comprehensively etc., so RFID electronic license plates data are relative to other traffic flows
Data are more suitable for the basic data of traffic jam judging.Existing traffic congestion state discrimination technology is often based on various
The quantitative analysis of traffic flow parameter, but the traffic congestion state of different roads has very big difference, even if at same time point
It can be different, it is therefore desirable to have a kind of more pervasive method to differentiate traffic congestion state.
Invention content
In view of this, the present invention provides a kind of more pervasive traffic congestion state differentiation based on RFID electronic license plate data
Method.
The purpose of the present invention is achieved through the following technical solutions：A kind of city road stroke based on RFID data
Time forecasting methods include the following steps：
1) pass through RFID electronic license plate data acquisition traffic flow evaluation parameters, including standard vehicle equivalents and average speed；
2) the standard vehicle equivalents and average speed obtained step 1) is clustered as two dimensions of cluster operation
Operation obtains preferable clustering number mesh and cluster result；
3) using average speed as ordinate, standard vehicle equivalents is thrown as abscissa, by cluster centre according to ordinate
The descending sequence of value of shadow point, for the value of ordinate subpoint identical cluster centre point, by its to abscissa into
Row is projected and is ranked up according to the value of abscissa subpoint is ascending, the cluster centre corresponding to subpoint after sequence
Point represents traffic congestion state from unimpeded to the consecutive variations trend of congestion, then according to most left state continuous coupling principle
Match the traffic congestion state of cluster centre.
Further, the step 1) specifically comprises the following steps：
11) RFID electronic license plate data are acquired by the collection points RFID, obtains the volume of traffic of all vehicles in a period
With the volume of traffic of oversize vehicle, the standard vehicle equivalents in the period is calculated according to following formula：
Pcu=n+n2；
Wherein, pcu indicates that standard vehicle equivalents, n indicate the volume of traffic of all vehicles, n2Indicate the traffic of oversize vehicle
Amount；
12) average speed for calculating vehicle is obtained by following formula：
V indicates that average speed, unit are km/h in formula, and L indicates the distance between section collection points Liang Ge, and unit is
Rice, ti1And ti2Indicating time of i-th vehicle by first collection point RFID and second collection point RFID, unit respectively is
Second, n indicates the volume of traffic of all vehicles in the period.
Further, the clustering algorithm of the step 2) specifically comprises the following steps：
21) it is 2 to enable cluster centre number c；
22) initialization subordinated-degree matrix uij, u when initializationijValue be random number in [0,1] range；
23) each cluster centre c is calculated according to subordinated-degree matrixiIn the numerical value of each dimension：
M is FUZZY WEIGHTED coefficient in formula, and n indicates the data volume of sample data, uijBelong to i-th for j-th of sample to gather
The degree of membership at class center, uikBelong to the degree of membership at ith cluster center, x for k-th of samplejIndicate j-th of sample data；
24) according to cluster centre ciCalculate subordinated-degree matrix uij：
M is FUZZY WEIGHTED coefficient in formula, and c is cluster centre number, ciIndicate ith cluster center, ckIt indicates k-th
Cluster centre, xjIndicate j-th of sample data, uijBelong to the degree of membership at ith cluster center, u for j-th of sampleisIt is s-th
Sample belongs to the degree of membership at ith cluster center, ursBelong to the degree of membership of r-th of cluster centre, u for s-th of samplerjFor jth
A sample belongs to the degree of membership of r-th of cluster centre.；
25) the i-th ii steps are returned if target function value is more than ε, otherwise carry out vi steps；
26) cluster operation at this time at cluster centre number c has been completed, and enables c=c+1, if c≤2ln n, is calculated
The adjacency matrix expression-form of cluster result, the adjacency matrix meaning are as follows under current cluster centre number：I-th row jth row
Element then shows that i-th of sample data and j-th of sample data belong to same category if 1, and completion is calculated in adjacency matrix
After return the i-th i step；If c>2ln n then carry out vii steps；
27) cluster operation at this time under all cluster centre numbers is complete, and is counted in each cluster centre number
Now the adjacency matrix in the vi steps of cluster operation, all of its neighbor matrix is added, total adjacency matrix O is obtainedJ；It utilizes
TreeMap comes Statistical Clustering Analysis center number and corresponding iterations, and it is cluster centre number to enable the key of TreeMap, and value is to change
Generation number；By OJIn be 0 value subtract 1, count current OJThe number num of middle connected subgraph judges whether have in TreeMap
Num is added in TreeMap if not having for the key of num, corresponding value is 1；It, will if the key of existing num in TreeMap
The value of the key adds 1, until OJUntil middle all elements are all 0；
28) the maximum key of TreeMap intermediate values is chosen as cluster centre number, and with the cluster knot of the cluster centre number
Cluster result of the fruit as sample data；If the identical key of existence value, is judged with Clustering Effect evaluation index, is calculated separately
It is worth identical key as the Clustering Effect evaluation index value in the case of cluster centre number using these, chooses Clustering Effect evaluation and refer to
The cluster centre number under smaller value is marked as selected cluster centre number, the calculation formula of Clustering Effect evaluation index is：
C is cluster centre number in formula, and m is FUZZY WEIGHTED coefficient, and n indicates sample data data volume, uijFor j-th of sample
Originally belong to the degree of membership at ith cluster center, ciIndicate ith cluster center, ckIndicate k-th of cluster centre, xjIndicate jth
A sample data.
Further, step 3) specifically comprises the following steps：
31) by cluster centre point-rendering respectively using standard vehicle equivalents and average speed as the reference axis of transverse and longitudinal coordinate
On；
32) by cluster centre according to the descending sequence of value of ordinate subpoint；
If 33) there are identical ordinate projection value, for ordinate projection value identical cluster centre point, by it to cross
Coordinate project and be ranked up according to abscissa projection value is ascending, the cluster centre corresponding to subpoint after sequence
Point represents traffic congestion state from unimpeded to the consecutive variations trend of congestion；
34) traffic congestion state of cluster centre is identified according to most left state continuous coupling principle；Most left state is continuous
Matching principle refers to：Ordering c cluster centre always matches preceding c traffic congestion state TC from left to right, one by one；Traffic
Congestion status TC is divided into very unimpeded, unimpeded, jogging, slight congestion, congestion, 6 kinds of heavy congestion, corresponds to respectively<TC1,
TC2,…,TC6>；
35) by the traffic congestion state of cluster centre, then the traffic that can obtain all sample points around all cluster centres is gathered around
Stifled state.
By adopting the above-described technical solution, the present invention has the advantage that：
1. replacing the volume of traffic as the dimension of GEFCM clustering algorithms using standard vehicle equivalents, it can preferably reflect friendship
Logical congestion status, and relative to traditional FCM Algorithms, the difference because of sample class capacity can be avoided right with GEFCM
The influence of final cluster result, improves the accuracy of cluster.
2. the principle for proposing " sequence of cluster centre subpoint " rule and " most left state continuous coupling " solves cluster
The problem of being matched between center and specific traffic congestion state.
Other advantages, target and the feature of the present invention will be illustrated in the following description to a certain extent, and
And to a certain extent, based on will be apparent to those skilled in the art to investigating hereafter, Huo Zheke
To be instructed from the practice of the present invention.The target and other advantages of the present invention can by following specification realizing and
It obtains.
Description of the drawings
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
The detailed description of one step：
Fig. 1 is the flow chart of the present invention；
Fig. 2 is that cluster centre is projected to the schematic diagram of the subpoint of ordinate；
Fig. 3 is the schematic diagram of the identical cluster centre point of ordinate projection value；
Fig. 4 is the consecutive variations process example of traffic congestion state.
Specific implementation mode
Illustrate that embodiments of the present invention, those skilled in the art can be by this specification below by way of specific specific example
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also be based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.
Referring to Fig. 1, the present invention provides a kind of urban road traffic congestion condition discrimination based on RFID electronic license plate data
Method includes the following steps：
1) traffic flow evaluation parameter is calculated, evaluation parameter here refers to the section standard vehicle equivalents within the period
And average speed.The period is divided with time threshold T before the calculating of traffic flow evaluation parameter, the T that the present invention chooses is 10 points
Clock, the sample data of every day can be divided into 144 equal portions by us, i.e. the period is divided into [00:00,00:10), [00:10,
00:20), [00:20,00:30) ..., [23:50,00:00)., wherein standard vehicle equivalents refers to travel in urban road
On various motor vehicles and the volume of traffic number of non-motor vehicle be converted into a kind of Standard of vehicle according to certain vehicle conversion coefficient
Volume of traffic number.Here is to calculate the process of traffic flow evaluation parameter：
I) before calculating standard vehicle equivalents, the volume of traffic is first calculated.The volume of traffic is traveling all classes on road
The number of type vehicle, it is possible that two RFID in section acquire the unmatched feelings of point data when counting the volume of traffic
Condition, this may be related to the position of the collection points RFID deployed with devices, since distance is long between two collection points RFID and the two
Between have other sections appearance so that the case where traveling of vehicle be divided into following 3 kinds：
1. vehicle have passed through collection point 1 and collection point 2 simultaneously.
2. vehicle have passed through collection point 1, but there is no by collection point 2.
3. vehicle have passed through collection point 2 not by collection point 1.
In view of above-mentioned three kinds of situations, the acquisition point data that selects the volume of traffic of statistics larger within each period as
The volume of traffic in the period, the large car volume of traffic calculate similarly.It is obtained calculating traffic by original RFID electronic license plate data
The input tuple of amount is：
＜ rfid1,passtime1,rfid2,passtime2, carType ＞；
Wherein rfid1Be by first collection point RFID, rfid2Be by second collection point RFID,
passtime1It is by the time of first collection point RFID, passtime2Be by the time of first collection point RFID,
CarType is the vehicle of vehicle, and a tuple can describe the passage situation of a vehicle.
According to input tuple, the volume of traffic of the volume of traffic and oversize vehicle of all vehicles in each period is found out, and
The standard vehicle equivalents in each period is calculated according to following formula：
Pcu=n+n2；
N indicates the volume of traffic of all vehicles, n in formula2Indicate the volume of traffic of oversize vehicle.
The tuple for finally obtaining output is as follows：
＜ Ti,pcui＞；
Wherein TiIndicate i-th of period, pcuiIndicate the standard vehicle equivalents within i-th of period.
Ii) calculating of average speed only need to obtain vehicle within some period by two collection points it is specific when
Between, the input tuple for obtaining calculating average speed by original RFID electronic license plate data is：
＜ rfid1,passtime1,rfid2,passtime2, L ＞；
Wherein rfid1Be by first collection point RFID, rfid2Be by second collection point RFID,
passtime1It is by the time of first collection point RFID, passtime2It is by the time of second collection point RFID, L
It is the distance between two collection points RFID.
The average speed of all vehicles in some period is calculated according to following formula later：
V indicates average speed (unit is km/h) in formula, and L indicates that (unit is for the distance between section collection points Liang Ge
Rice), ti1And ti2Indicate that (unit is i-th vehicle by time of first collection point RFID and second collection point RFID respectively
Second), n indicates the volume of traffic in the period (attention is not standard vehicle equivalents).It is noted herein that in formula
3.6 be in order to which unit is converted into km/h from m/s.
The tuple for finally obtaining output is as follows：
＜ Ti,vi＞
Wherein TiIndicate i-th of period, viIndicate the average speed of all vehicles within i-th of period
2) two dimensions of standard vehicle equivalents and average speed that step 1 obtains as cluster operation are enabled, are carried out below
Cluster operation.Cluster centre number is enabled to be iterated in [2,2 ln n] range, wherein n is sample data volume.Cluster every time
Using the result of object function as standard：
U is subordinated-degree matrix in formula, and C is cluster centre set, and m is FUZZY WEIGHTED coefficient, and n indicates sample data data
Amount, c are cluster centre number, uijBelong to the degree of membership at ith cluster center, u for j-th of sampleisBelong to for s-th of sample
The degree of membership at ith cluster center, xjIndicate j-th of sample data, ciIndicate ith cluster center, | | xj-ci| | indicate jth
Euclidean distance of a sample point to ith cluster center.
Regulation ε is 10-6, when the value of subordinated-degree matrix is less than ε, then terminate the secondary cluster process.
Cluster process is the process of subordinated-degree matrix and cluster centre constantly iterated to calculate, and subordinated-degree matrix calculates public
Formula：
M is FUZZY WEIGHTED coefficient in formula, and c is cluster centre number, ciIndicate ith cluster center, ckIt indicates k-th
Cluster centre, xjIndicate j-th of sample data, uijBelong to the degree of membership at ith cluster center, u for j-th of sampleisIt is s-th
Sample belongs to the degree of membership at ith cluster center, ursBelong to the degree of membership of r-th of cluster centre, u for s-th of samplerjFor jth
A sample belongs to the degree of membership of r-th of cluster centre.
The calculation formula of cluster centre：
M is FUZZY WEIGHTED coefficient in formula, and n indicates sample data data volume, uijBelong to ith cluster for j-th of sample
The degree of membership at center, uikBelong to the degree of membership at ith cluster center, x for k-th of samplejIndicate j-th of sample data.
Specifically cluster operation process is：
I) it is 2 to enable cluster centre number c.
Ii) initialization subordinated-degree matrix uij, u when initializationijValue be random number in [0,1] range.
Iii each cluster centre c) is calculated according to subordinated-degree matrixiIn the numerical value of each dimension.
Iv) according to cluster centre ciCalculate subordinated-degree matrix uij。
V) the i-th ii steps are returned if target function value is more than ε, otherwise carry out vi steps.
Vi) cluster operation at this time at cluster centre number c has been completed, and enables c=c+1, if c≤2ln n, is calculated
The adjacency matrix expression-form of cluster result, the adjacency matrix meaning are as follows under current cluster centre number：I-th row jth row
Element then shows that i-th of sample data and j-th of sample data belong to same category if 1, and completion is calculated in adjacency matrix
After return the i-th i step.If c>2ln n then carry out vii steps.
Vii) cluster operation at this time under all cluster centre numbers is complete, and is counted in each cluster centre number
Now the adjacency matrix in the vi steps of cluster operation, all of its neighbor matrix is added, total adjacency matrix O is obtainedJ.It utilizes
TreeMap comes Statistical Clustering Analysis center number and corresponding iterations, and it is cluster centre number to enable the key of TreeMap, and value is to change
Generation number.By OJIn be 0 value subtract 1, count current OJThe number num of middle connected subgraph judges whether have in TreeMap
Num is added in TreeMap if not having for the key of num, corresponding value is 1；It, will if the key of existing num in TreeMap
The value of the key adds 1, until OJUntil middle all elements are all 0.
Viii the maximum key of TreeMap intermediate values) is chosen as cluster centre number, and with the cluster of the cluster centre number
As a result as the cluster result of sample data.If the identical key of existence value, is judged with Clustering Effect evaluation index, is counted respectively
It calculates and is worth identical key as the Clustering Effect evaluation index value in the case of cluster centre number using these, choose Clustering Effect evaluation
Cluster centre number under the smaller value of index is as selected cluster centre number, the calculation formula of Clustering Effect evaluation index
For：
C is cluster centre number in formula, and m is FUZZY WEIGHTED coefficient, and n indicates sample data data volume, uijFor j-th of sample
Originally belong to the degree of membership at ith cluster center, ciIndicate ith cluster center, ckIndicate k-th of cluster centre, xjIndicate jth
A sample data.
3) total traffic congestion state TC is divided into very unimpeded, unimpeded, jogging, slight congestion, congestion, heavy congestion
It 6 kinds, corresponds to respectively<TC1,TC2,…,TC6>, the traffic congestion state that all roads occur should be the subset in TC；With average
Speed as ordinate, standard vehicle equivalents as abscissa, by cluster centre according to ordinate subpoint value by greatly to
It to abscissa project and according to horizontal seat by small sequence for the value of ordinate subpoint identical cluster centre point
The value of mark subpoint is ascending to be ranked up, and the cluster centre point corresponding to the subpoint after sequence represents traffic and gathers around
Then stifled state matches the friendship of cluster centre from unimpeded to the consecutive variations trend of congestion according to most left state continuous coupling principle
Logical congestion status, specifically comprises the following steps：
31) by cluster centre point-rendering respectively using standard vehicle equivalents and average speed as the reference axis of transverse and longitudinal coordinate
On；
32) by cluster centre according to the descending sequence of value of ordinate subpoint；
33) if there are identical ordinate projection value (as shown in Figure 3), cluster centres identical for ordinate projection value
It to abscissa project and be ranked up according to abscissa projection value is ascending by point, and the subpoint institute after sequence is right
The cluster centre point answered represents traffic congestion state from unimpeded to the consecutive variations trend of congestion.
34) traffic congestion state of cluster centre is identified according to " most left state continuous coupling " principle；
" most left state continuous coupling " principle：Ordering c cluster centre always matches first c from left to right, one by one
Traffic congestion state TC.
35) by the traffic congestion state of cluster centre, then the traffic that can obtain all sample points around all cluster centres is gathered around
Stifled state.
Fig. 4 approximations give the example of the consecutive variations process of traffic congestion state, wherein TC1And TC6Respectively total friendship
The lower bound of logical congestion status and the upper bound, it is TC to enable the traffic congestion state of random time pointi, traffic congestion state is whether later
Increase (congestion direction) towards i or i reduces the direction change in (unimpeded direction), can all show a kind of continuous feature, and
The case where being not in multistage jump variation, i.e., each traffic congestion state is only possible to towards the traffic congestion shape adjacent with it
State changes.
After obtaining ordering cluster centre, according to " most left state continuous coupling " principle, by cluster centre institute's generation
The traffic congestion state and traffic congestion state label TC of table from left to right correspond to one by one.It is hereby achieved that cluster centre and category
In the traffic congestion state of all sample points of the cluster centre.
Finally illustrate, the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although with reference to compared with
Good embodiment describes the invention in detail, it will be understood by those of ordinary skill in the art that, it can be to the skill of the present invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of the technical program, should all be covered in the present invention
Protection domain in.
Claims (4)
1. a kind of urban road traffic congestion condition discrimination method based on RFID electronic license plate data, which is characterized in that the party
Method includes the following steps：
1) pass through RFID electronic license plate data acquisition traffic flow evaluation parameters, including standard vehicle equivalents and average speed；
2) the standard vehicle equivalents and average speed obtained step 1) carries out cluster behaviour as two dimensions of cluster operation
Make, obtains preferable clustering number mesh and cluster result；
3) using average speed as ordinate, standard vehicle equivalents is as abscissa, by cluster centre according to ordinate subpoint
Value descending sequence the value of ordinate subpoint identical cluster centre point is thrown it to abscissa
Shadow is simultaneously ranked up according to the value of abscissa subpoint is ascending, and the cluster centre point corresponding to the subpoint after sequence is
Traffic congestion state is represented from unimpeded to the consecutive variations trend of congestion, is then matched according to most left state continuous coupling principle
The traffic congestion state of cluster centre.
2. a kind of urban road traffic congestion condition discrimination side based on RFID electronic license plate data according to claim 1
Method, which is characterized in that the step 1) specifically comprises the following steps：
11) RFID electronic license plate data are acquired by the collection points RFID, obtains in a period volume of traffic of all vehicles and big
The volume of traffic of type vehicle calculates the standard vehicle equivalents in the period according to following formula：
Pcu=n+n2；
Wherein, pcu indicates that standard vehicle equivalents, n indicate the volume of traffic of all vehicles, n2Indicate the volume of traffic of oversize vehicle；
12) average speed for calculating vehicle is obtained by following formula：
V indicates that average speed, unit are km/h in formula, and L indicates the distance between section collection points Liang Ge, and unit is rice, ti1
And ti2Time of i-th vehicle by first collection point RFID and second collection point RFID is indicated respectively, and unit is second, n tables
Show the volume of traffic of all vehicles in the period.
3. obtaining a kind of urban road traffic congestion state based on RFID electronic license plate data described in 2 according to claim 1 to sentence
Other method, which is characterized in that the clustering algorithm of the step 2) specifically comprises the following steps：
21) it is 2 to enable cluster centre number c；
22) initialization subordinated-degree matrix uij, u when initializationijValue be random number in [0,1] range；
23) each cluster centre c is calculated according to subordinated-degree matrixiIn the numerical value of each dimension：
M is FUZZY WEIGHTED coefficient in formula, and n indicates the data volume of sample data, uijBelong in ith cluster for j-th of sample
The degree of membership of the heart, uikBelong to the degree of membership at ith cluster center, x for k-th of samplejIndicate j-th of sample data；
24) according to cluster centre ciCalculate subordinated-degree matrix uij：
M is FUZZY WEIGHTED coefficient in formula, and c is cluster centre number, ciIndicate ith cluster center, ckIndicate k-th of cluster
Center, xjIndicate j-th of sample data, uijBelong to the degree of membership at ith cluster center, u for j-th of sampleisFor s-th of sample
Belong to the degree of membership at ith cluster center, ursBelong to the degree of membership of r-th of cluster centre, u for s-th of samplerjFor j-th of sample
Originally belong to the degree of membership of r-th of cluster centre.；
25) the i-th ii steps are returned if target function value is more than ε, otherwise carry out vi steps；
26) cluster operation at this time at cluster centre number c has been completed, and enables c=c+1, if c≤2ln n, is calculated current
The adjacency matrix expression-form of cluster result under cluster centre number, the adjacency matrix meaning are as follows：The element of i-th row jth row
If 1, then show that i-th of sample data and j-th of sample data belong to same category, is calculated in adjacency matrix and complete to return later
Return the i-th i steps；If c>2ln n then carry out vii steps；
27) cluster operation at this time under all cluster centre numbers is complete, and is counted under each cluster centre number
Adjacency matrix in the vi steps of cluster operation, all of its neighbor matrix is added, total adjacency matrix O is obtainedJ；It utilizes
TreeMap comes Statistical Clustering Analysis center number and corresponding iterations, and it is cluster centre number to enable the key of TreeMap, and value is to change
Generation number；By OJIn be 0 value subtract 1, count current OJThe number num of middle connected subgraph judges whether have in TreeMap
Num is added in TreeMap if not having for the key of num, corresponding value is 1；It, will if the key of existing num in TreeMap
The value of the key adds 1, until OJUntil middle all elements are all 0；
28) the maximum key of TreeMap intermediate values is chosen as cluster centre number, and with the cluster result of the cluster centre number to make
For the cluster result of sample data；If the identical key of existence value, is judged with Clustering Effect evaluation index, is calculated separately with this
It is worth the Clustering Effect evaluation index value in the case that identical key is cluster centre number a bit, chooses Clustering Effect evaluation index more
As selected cluster centre number, the calculation formula of Clustering Effect evaluation index is cluster centre number under small value：
C is cluster centre number in formula, and m is FUZZY WEIGHTED coefficient, and n indicates sample data data volume, uijFor j-th of sample category
Degree of membership in ith cluster center, ciIndicate ith cluster center, ckIndicate k-th of cluster centre, xjIndicate j-th of sample
Notebook data.
4. a kind of urban road traffic congestion state based on RFID electronic license plate data according to claim 1 or 2 is sentenced
Other method, which is characterized in that step 3) specifically comprises the following steps：
31) by cluster centre point-rendering in the reference axis respectively using standard vehicle equivalents and average speed as transverse and longitudinal coordinate；
32) by cluster centre according to the descending sequence of value of ordinate subpoint；
If 33) there are identical ordinate projection value, for ordinate projection value identical cluster centre point, by it to abscissa
Project and be ranked up according to abscissa projection value is ascending, the cluster centre point corresponding to the subpoint after sequence is
Traffic congestion state is represented from unimpeded to the consecutive variations trend of congestion；
34) traffic congestion state of cluster centre is identified according to most left state continuous coupling principle；Most left state continuous coupling
Principle refers to：Ordering c cluster centre always matches preceding c traffic congestion state TC from left to right, one by one；Traffic congestion
State TC is divided into very unimpeded, unimpeded, jogging, slight congestion, congestion, 6 kinds of heavy congestion, corresponds to respectively<TC1,TC2,…,
TC6>；
35) by the traffic congestion state of cluster centre, then the traffic congestion shape of all sample points around all cluster centres can be obtained
State.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810549401.0A CN108682153B (en) | 2018-05-31 | 2018-05-31 | Urban road traffic jam state discrimination method based on RFID electronic license plate data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810549401.0A CN108682153B (en) | 2018-05-31 | 2018-05-31 | Urban road traffic jam state discrimination method based on RFID electronic license plate data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108682153A true CN108682153A (en) | 2018-10-19 |
| CN108682153B CN108682153B (en) | 2020-12-29 |
Family
ID=63809412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810549401.0A Active CN108682153B (en) | 2018-05-31 | 2018-05-31 | Urban road traffic jam state discrimination method based on RFID electronic license plate data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108682153B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785622A (en) * | 2018-12-03 | 2019-05-21 | 南京三宝科技股份有限公司 | A kind of congestion regions recognition methods based on vehicle carried electronic label technology |
| CN111613049A (en) * | 2019-02-26 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Road state monitoring method and device |
| CN112330953A (en) * | 2020-10-10 | 2021-02-05 | 杭州翔毅科技有限公司 | Traffic control method, device and equipment based on cloud data and storage medium |
| CN112767684A (en) * | 2020-12-22 | 2021-05-07 | 重庆大学 | Highway traffic jam detection method based on charging data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102546771A (en) * | 2011-12-27 | 2012-07-04 | 西安博构电子信息科技有限公司 | Cloud mining network public opinion monitoring system based on characteristic model |
| CN103500504A (en) * | 2013-09-30 | 2014-01-08 | 同济大学 | Urban road traffic parameter estimation and road situation discrimination method based on RFID (Radio Frequency Identification) data and application system |
| CN104517113A (en) * | 2013-09-29 | 2015-04-15 | 浙江大华技术股份有限公司 | Image feature extraction method and device and image sorting method and device |
| CN106056923A (en) * | 2016-06-27 | 2016-10-26 | 安徽四创电子股份有限公司 | Road traffic state discrimination method based on traffic scene radar |
| CN106530709A (en) * | 2016-12-16 | 2017-03-22 | 东南大学 | User-oriented highway traffic index publishing system |
| CN107153846A (en) * | 2017-05-26 | 2017-09-12 | 南京邮电大学 | A kind of road traffic state modeling method based on Fuzzy C-Means Cluster Algorithm |
| WO2017174623A1 (en) * | 2016-04-05 | 2017-10-12 | Tomtom Traffic B.V. | Method and apparatus for identifying congestion bottlenecks |
| CN107705551A (en) * | 2016-08-08 | 2018-02-16 | 阿里巴巴集团控股有限公司 | The appraisal procedure and device of traffic |
-
2018
- 2018-05-31 CN CN201810549401.0A patent/CN108682153B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102546771A (en) * | 2011-12-27 | 2012-07-04 | 西安博构电子信息科技有限公司 | Cloud mining network public opinion monitoring system based on characteristic model |
| CN104517113A (en) * | 2013-09-29 | 2015-04-15 | 浙江大华技术股份有限公司 | Image feature extraction method and device and image sorting method and device |
| CN103500504A (en) * | 2013-09-30 | 2014-01-08 | 同济大学 | Urban road traffic parameter estimation and road situation discrimination method based on RFID (Radio Frequency Identification) data and application system |
| WO2017174623A1 (en) * | 2016-04-05 | 2017-10-12 | Tomtom Traffic B.V. | Method and apparatus for identifying congestion bottlenecks |
| CN106056923A (en) * | 2016-06-27 | 2016-10-26 | 安徽四创电子股份有限公司 | Road traffic state discrimination method based on traffic scene radar |
| CN107705551A (en) * | 2016-08-08 | 2018-02-16 | 阿里巴巴集团控股有限公司 | The appraisal procedure and device of traffic |
| CN106530709A (en) * | 2016-12-16 | 2017-03-22 | 东南大学 | User-oriented highway traffic index publishing system |
| CN107153846A (en) * | 2017-05-26 | 2017-09-12 | 南京邮电大学 | A kind of road traffic state modeling method based on Fuzzy C-Means Cluster Algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 李丽娟: "基于XML的数学试题标记语言的试题转化及应用", 《产业与科技论坛》 * |
| 王旭琴 等: "基于FCM聚类的多路段城市道路车流数据分析及其应用", 《系统工程理论与应用》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785622A (en) * | 2018-12-03 | 2019-05-21 | 南京三宝科技股份有限公司 | A kind of congestion regions recognition methods based on vehicle carried electronic label technology |
| CN109785622B (en) * | 2018-12-03 | 2020-12-11 | 南京三宝科技股份有限公司 | Congestion area identification method based on vehicle-mounted electronic tag technology |
| CN111613049A (en) * | 2019-02-26 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Road state monitoring method and device |
| CN111613049B (en) * | 2019-02-26 | 2022-07-12 | 北京嘀嘀无限科技发展有限公司 | Road state monitoring method and device |
| CN112330953A (en) * | 2020-10-10 | 2021-02-05 | 杭州翔毅科技有限公司 | Traffic control method, device and equipment based on cloud data and storage medium |
| CN112767684A (en) * | 2020-12-22 | 2021-05-07 | 重庆大学 | Highway traffic jam detection method based on charging data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108682153B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108682153A (en) | A kind of urban road traffic congestion condition discrimination method based on RFID electronic license plate data | |
| Abbasabadi et al. | An integrated data-driven framework for urban energy use modeling (UEUM) | |
| CN101719315B (en) | Method for acquiring dynamic traffic information based on middleware | |
| CN105184307B (en) | A kind of generation method of medical domain image, semantic similarity matrix | |
| CN109859468A (en) | Multilane traffic volume based on YOLOv3 counts and wireless vehicle tracking | |
| CN107248283A (en) | A kind of urban area road network evaluation of running status method of consideration section criticality | |
| CN102081846A (en) | Expressway charge data track matching based traffic state recognition method | |
| CN107845260B (en) | Method for identifying public transport trip mode of user | |
| CN109191849B (en) | Traffic jam duration prediction method based on multi-source data feature extraction | |
| CN109089314A (en) | A kind of indoor orientation method of the wifi sequence assistant GPS based on proposed algorithm | |
| CN106910199A (en) | Towards the car networking mass-rent method of city space information gathering | |
| CN108986453A (en) | A kind of traffic movement prediction method based on contextual information, system and device | |
| CN108597227A (en) | Road traffic flow forecasting method under freeway toll station | |
| CN103632547B (en) | The lower link travel time prediction system of moving bottleneck impact and implementation method | |
| CN103425994B (en) | A kind of feature selection approach for pattern classification | |
| CN105046673A (en) | Self-learning based hyperspectral image and visible image fusion classification method | |
| Sahu et al. | Designing freight traffic analysis zones for metropolitan areas: identification of optimal scale for macro-level freight travel analysis | |
| CN114944053A (en) | Traffic flow prediction method based on spatio-temporal hypergraph neural network | |
| Tu et al. | Research on intelligent calculation method of intelligent traffic flow index based on big data mining | |
| Seaver et al. | Estimation of traffic volume on rural local roads | |
| CN108447265A (en) | Road traffic accident stain section discrimination method based on TOPSIS methods | |
| Zhang et al. | How road network transformation may be associated with reduced carbon emissions: An exploratory analysis of 19 major Chinese cities | |
| Cui et al. | A framework of boundary collision data aggregation into neighbourhoods | |
| Jiang et al. | Pedestrian volume prediction with high spatiotemporal granularity in urban areas by the enhanced learning model | |
| Bhuyan | Defining Level of Service Criteria for Urban Streets in Indian Context |
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 |