CN106652460A - Highway traffic state determination method and system - Google Patents
Highway traffic state determination method and system Download PDFInfo
- Publication number
- CN106652460A CN106652460A CN201710134402.4A CN201710134402A CN106652460A CN 106652460 A CN106652460 A CN 106652460A CN 201710134402 A CN201710134402 A CN 201710134402A CN 106652460 A CN106652460 A CN 106652460A
- Authority
- CN
- China
- Prior art keywords
- traffic
- cluster centre
- real
- parameter data
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention discloses a highway traffic state determination method and system. The method comprises: employing a fuzzy clustering algorithm to establish a traffic flow parameter fuzzy clustering center model according to the historical parameter data of the highway operation state and the number of preset classifications; according to the central model, determining the traffic state clustering center with the number of the preset classifications; according to the real-time parameter data and the clustering center, employing the minimum distance classification method to obtain the traffic state clustering center with the minimum distance real-time parameter data; and according to the clustering center, determining that the traffic state clustering including the real-time parameter data is the traffic state clustering where the traffic state clustering with the minimum distance real-time parameter data is located. The highway traffic state determination method and system improve the reliability of the determination of the highway traffic state through adoption of the highway traffic flow operation state parameter data, improve the link of the traffic state obtaining and provide the best traffic control measure and the travel plan for the road managers and users from the information obtaining link at the greatest extent.
Description
Technical field
The present invention relates to intelligent traffic control system field, more particularly to a kind of traffic status of express way method of discrimination and
System.
Background technology
The acquisition of freeway traffic running state information is highway intelligent transportation system reasonable management and control
Basis, is the important module in ITS (intelligent transportation system Intelligent Transport System, abbreviation ITS) researchs,
The monitor in real time of traffic status of express way and the issue of traffic state information be ensure traffic safety it is important with operational efficiency
Basis.Management to freeway traffic flow and control can be realized according to section real-time traffic states information, reduced crowded
Occur, give full play to expressway safety, it is quick and efficient the characteristics of.
The traffic of basic freeway sections traffic behavior differentiates that effectiveness is heavily dependent on the traffic behavior of employing
Whether the criteria for classifying is reasonable.The traffic behavior criteria for classifying is generally divided into two big class：Absolute measure standard and relative measure.Absolutely
Refer to the constant standard of interior value on a large scale to module, i.e., in the world or the standard that commonly uses of certain country.Such as U.S.
State《HCM》With average travel speed as index, traffic behavior is divided into into six grades of A-F, 2012 years I
What Department of Transportation of state promulgated《Network of highways operational monitoring and the provisional technical requirements of service》With road-section average travel speed as index,
Traffic behavior is divided into into five grades, as：" unimpeded ", " substantially unimpeded ", " slight congestion ", " moderate congestion ", " seriously gather around
It is stifled ".Traditional traffic behavior absolute measure standard objectively realizes different sections of highway or the traffic behavior unified quantization in region not
With the comparison of section or regional traffic state.But, basic freeway sections are subject to the various factors such as road, traffic, weather
Affect, can not be reflected under different space-time conditions using unified absolute estimation standard, the true traffic behavior in section or region.
Relative measure is to refer to fully reflect the traffic noise prediction of real road and the subjectivity of road traveler
Impression and the standard of acceptance.Due to considering the transportation conditions such as road environment, weather environment when estimating, utilization is section
Actual historical operating parameter, can more embody traffic behavior of the certain high-speed highway basic road under specific space-time condition, more
The demand of the users such as traffic participant, traffic administration person can be met.The division thinking of relative standard typically has two kinds：One kind is straight
Connect using the grade of service number of International or National regulation, such as six grades or Pyatyi；Another kind is by the service level of existing standard
Appropriate merging is carried out, express highway section is described with less grade.
In sum, the module disunity that current traffic status of express way differentiates, traffic status of express way is sentenced
Other method reliability is low, and correlation technique is excessively complicated, it is difficult to be applied in practice.
The content of the invention
It is an object of the invention to provide a kind of traffic status of express way method of discrimination and system, the present invention is with highway
Traffic intelligent system is object of study, deeply dissects the historical parameter data of freeway traffic flow running status, by adopting
The method of fuzzy clustering is analyzed research according to data mining theories thought to freeway traffic flow operational parameter data,
And then make that reliability is high and adaptable traffic status of express way sentences method for distinguishing.
For achieving the above object, the invention provides a kind of traffic status of express way method of discrimination, including：
Obtain the historical parameter data of freeway traffic flow running status；
According to historical parameter data and default classification quantity, traffic flow parameter fuzzy clustering is set up using fuzzy clustering algorithm
Center model；
According to traffic flow parameter fuzzy clustering center model, it is determined that the traffic behavior cluster centre of default classification quantity；
Obtain the real-time parameter data of freeway traffic flow running status；
According to real-time parameter data and traffic behavior cluster centre, obtained apart from real-time parameter using minimum distance classification
The minimum traffic behavior cluster centre of data；
According to apart from the minimum traffic behavior cluster centre of real-time parameter data, the traffic belonging to real-time parameter data is determined
State clustering is the traffic behavior cluster being located apart from the minimum traffic behavior cluster centre of real-time parameter data.
Optionally, the historical parameter data of freeway traffic flow running status, including：First flow, the very first time puts down
Equal speed, very first time occupation rate；The real-time parameter data of freeway traffic flow running status, including：Second flow, second
Time mean speed, the second time occupancy.
Optionally, the historical parameter data of freeway traffic flow running status is obtained；
According to historical parameter data and default four classification, traffic flow parameter fuzzy clustering is set up using fuzzy clustering algorithm
Center model；
According to traffic flow parameter fuzzy clustering center model, four traffic behavior cluster centres are determined；Four traffic behaviors
Cluster centre includes unimpeded cluster centre, and steady cluster centre, crowded cluster centre blocks cluster centre；
Obtain the real-time parameter data of freeway traffic flow running status；
According to real-time parameter data and four traffic behavior cluster centres, distance is obtained in real time using minimum distance classification
The minimum traffic behavior cluster centre of supplemental characteristic；
According to apart from the minimum traffic behavior cluster centre of real-time parameter data, the traffic belonging to real-time parameter data is determined
State clustering is the traffic behavior cluster being located apart from the minimum traffic behavior cluster centre of real-time parameter data.
Optionally, traffic flow parameter fuzzy clustering center model is set up using fuzzy clustering algorithm, is referred to using FCM algorithms
Traffic flow parameter fuzzy clustering center model is set up, is specifically included：
Initiation parameter, defines V(0)={ v1,v2,v3,v4, ε ＞ 0, t=1, Tmax, wherein V(0)For traffic flow parameter mould
Paste cluster centre, v1For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4For in obstruction cluster
The heart, ε is circulation cut-off error, and t is cycle-index, TmaxFor maximum cycle；
Using formulaCalculate subordinated-degree matrix；Wherein uijFor Subject Matrix, c is default classification quantity,
C=4, m ∈ [1, ∞), 1≤i≤4,1≤j≤n；uij∈ [0,1],(dij)2=| | xj-vi||2,
dijRepresent sample point xjWith cluster centre viEuclidean distance；
Using formulaCalculate cluster centre；
Judge | | V(t)-V(t-1)| | whether≤ε sets up, wherein V(t)For the t time cluster centre matrix, V(t-1)For the t-1 time
Cluster centre matrix, sets up loop termination, determines V(t)For Optimal cluster centers matrix；It is false execution next step；
Judge t whether more than or equal to Tmax, loop termination is set up, determine V(t)For Optimal cluster centers matrix；It is false
Perform next step；
Cycle-index t adds 1, and execution step utilizes formulaCalculate subordinated-degree matrix.
Optionally, obtained apart from the minimum traffic behavior cluster centre of real-time parameter data using minimum distance classification
Step is specifically included：
According to Optimal cluster centers V(t),
Wherein：V(t)For in optimum traffic flow parameter fuzzy clustering cluster
The heart, v1For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4To block cluster centre；
According to the formula of the minimum distance classification of Euclidean distanceObtain distance
The minimum traffic behavior cluster centre of real-time parameter data；Wherein fk(xj) for Real-time Collection traffic state data to four not
With the Euclidean distance minima of cluster centre, k is the numbering of traffic behavior generic, and here value 1,2,3,4, represent respectively
Unimpeded, steady, crowded, blocked state.xjFor the traffic state data matrix of Real-time Collection, djiFor the traffic behavior of Real-time Collection
Parameter to cluster centre Euclidean distance, vjiFor the cluster centre value of different traffic parameters under different traffic.
Present invention also offers a kind of freeway traffic corresponding with above-mentioned traffic status of express way method of discrimination
Condition discrimination system, the system includes：
Historical parameter data acquisition module, for obtaining the historical parameter data of freeway traffic flow operation；
Model building module, for according to historical parameter data and default classification quantity, being set up using fuzzy clustering algorithm
Traffic flow parameter fuzzy clustering center model；
Cluster centre determining module, for according to traffic flow parameter fuzzy clustering center model, it is determined that default classification quantity
Traffic behavior cluster centre；
Real-time parameter data acquisition module, for obtaining the real-time parameter data of freeway traffic flow running status；
Nearest cluster centre determining module, for according to real-time parameter data and traffic behavior cluster centre, using minimum
Distance classification is obtained apart from the minimum traffic behavior cluster centre of real-time parameter data.
Traffic behavior clusters determining module, for according to apart from the minimum traffic behavior cluster centre of real-time parameter data,
Determine that the cluster of the traffic behavior belonging to real-time parameter data is apart from the minimum traffic behavior cluster centre institute of real-time parameter data
Traffic behavior cluster.
Optionally, model building module, specifically includes：
Parameter initialization module, for initiation parameter, defines V(0)={ v1,v2,v3,v4, ε ＞ 0, t=1, Tmax, its
Middle V(0)For traffic flow parameter fuzzy clustering center, v1For unimpeded cluster centre, v2For steady cluster centre, v3For in crowded cluster
The heart, v4To block cluster centre, ε is circulation cut-off error, and t is cycle-index, TmaxFor maximum cycle；
Subordinated-degree matrix acquisition module, for utilizing formulaCalculate subordinated-degree matrix；Wherein uijTo be subordinate to
Category matrix, c is to preset classification quantity, and c=4, m ∈ [1, ∞), 1≤i≤4,1≤j≤n；uij∈ [0,1],(dij)2=| | xj-vi||2, dijRepresent sample point xjWith cluster centre viEuclidean distance；
Cluster centre acquisition module, for utilizing formulaCalculate cluster centre；
First judge module, for judging | | V(t)-V(t-1)| | whether≤ε sets up, wherein V(t)For the t time cluster centre square
Battle array, V(t-1)For the t-1 time cluster centre matrix, loop termination is set up, determine V(t)For Optimal cluster centers matrix；It is false and holds
Row next step；
Second judge module, for judging t whether more than or equal to Tmax, loop termination is set up, determine V(t)Gather for optimum
Class center matrix；It is false execution next step；
Circulation performing module, plus 1 for performing cycle-index t, and execution utilizes formulaCalculate degree of membership
Matrix.
Optionally, traffic behavior cluster determining module, specifically includes：
Optimal cluster centers acquisition module, for obtaining Optimal cluster centers V(t),
Wherein：V(t)For optimum traffic flow parameter fuzzy clustering center, v1
For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4To block cluster centre；
Cluster centre acquisition module, for according to the formula of the minimum distance classification of Euclidean distanceObtain apart from the minimum traffic behavior cluster centre of real-time parameter data；Wherein fk
(xj) for Real-time Collection the different cluster centre of traffic state data to four Euclidean distance minima, k is traffic behavior institute
The numbering of category classification, here value 1,2,3,4, represent respectively unimpeded, steady, crowded, blocked state.xjFor the friendship of Real-time Collection
Logical state parameter matrix, djiFor Real-time Collection traffic state data to cluster centre Euclidean distance, vjiFor different traffic shapes
The cluster centre value of different traffic parameters under state.
Beneficial effects of the present invention：The traffic status of express way method of discrimination and system of the present invention, magnanimity is public at a high speed
The historical parameter data of road traffic flow operation as the basic data for obtaining traffic state judging index, with fuzzy clustering algorithm
Fuzzy classification is carried out to historical parameter data, the real-time traffic in any room and time can be accurately judged according to class categories
State generic, the relative measure of the traffic behavior for having obtained more meeting actual solves existing distinguishing rule and obtains
Originate indefinite, the low problem of reliability, also improve the link of traffic behavior judgement, and then for road management person and user
Optimal traffic control measure and plan of travel is provided.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
The accompanying drawing that needs are used is briefly described, it should be apparent that, drawings in the following description are only some enforcements of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can be with according to these accompanying drawings
Obtain other accompanying drawings.
The flow chart of the traffic status of express way method of discrimination that Fig. 1 is provided for the present invention；
The structural representation of the traffic status of express way judgement system that Fig. 2 is provided for the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
At present most domestic highway adopts totally-enclosed, full-overpass operational management form.Stably transport in traffic flow
Under row state, traffic behavior can become as the increase and decrease of the volume of traffic is imported and exported in intercommunication on the basic road between adjacent intercommunication
Change, but traffic behavior is stable in certain shorter time period.Therefore theoretically we can to obtain highway basic
Road section traffic volume status information.And due to being presented different as regional economy development degree is different between slip-road (intercommunication)
Transport need feature, also show as on section (basic road) between adjacent slip-road in different periods different
Traffic circulation state, therefore, freeway traffic running status can present different spatial and temporal variations.But for specific
Under steric requirements, the Changing Pattern of traffic status of express way has Time Series Similarity, by the historical data in magnanimity
In find out traffic behavior with arithmetic for real-time traffic flow match parameters, it is possible to achieve the real-time traffic shape to basic freeway sections
State differentiates.
By research both at home and abroad for the evolving development of traffic state judging algorithm, following rule is summed up：(1) from research
Object analysis, the algorithm of early stage is concentrated mainly on the detection of traffic events, and the algorithm nowadays studied can not only judge whether occur
Event, moreover it is possible to judge the concrete form of traffic flow；(2) from Analysis of Study Methods, the algorithm of early stage mainly by traffic parameter with
Fixed threshold relatively judging traffic, the development of now algorithm passes through fuzzy theory, neutral net and supporting vector
Thinking model of the intelligent algorithms such as machine from people, the fuzzy expression mode with people are realized as means；(3) from the traffic of research
Say in stream parameter, early stage, the algorithm of now was mainly mainly place traffic parameter individually or by way of combination of two
By weighted analysises, it is considered to the weight of each parameter of traffic flow, and in algorithm of today, flow, speed not only considered, have accounted for
There are the factors such as rate.The parameters such as time headway, average travel speed are also added into, the operation of traffic flow can be more synthetically reacted
Characteristic.
To sum up, the invention provides a kind of traffic status of express way method of discrimination and system, with freeway traffic intelligence
Energy system is object of study, deeply dissects the historical parameter data of freeway traffic flow running status, by being gathered using fuzzy
The method of class is analyzed research to freeway traffic flow operational parameter data according to data mining theories thought, and then makes
Make that reliability is high and adaptable traffic status of express way sentences method for distinguishing.
It is understandable to enable the above objects, features and advantages of the present invention to become apparent from, it is below in conjunction with the accompanying drawings and concrete real
The present invention is further detailed explanation to apply mode.
Embodiment 1：
Fig. 1 is the flow chart of embodiment of the present invention traffic status of express way method of discrimination, as shown in figure 1, the present invention is carried
For traffic status of express way method of discrimination, specifically include：
Step 101, obtains the historical parameter data of freeway traffic flow running status；
Step 102, according to historical parameter data and default classification quantity, using fuzzy clustering algorithm traffic flow parameter is set up
Fuzzy clustering center model；
Step 103, according to traffic flow parameter fuzzy clustering center model, it is determined that the traffic behavior cluster of default classification quantity
Center；
Step 104, obtains the real-time parameter data of freeway traffic flow running status；
Step 105, according to real-time parameter data and traffic behavior cluster centre, using minimum distance classification distance is obtained
The minimum traffic behavior cluster centre of real-time parameter data；
Step 106, according to apart from the minimum traffic behavior cluster centre of real-time parameter data, determines real-time parameter data institute
The traffic behavior cluster of category is the traffic behavior cluster being located apart from the minimum traffic behavior cluster centre of real-time parameter data.
Wherein, the historical parameter data of freeway traffic flow running status, including：First flow, the very first time is average
Speed, very first time occupation rate；The real-time parameter data of freeway traffic flow running status, including：Second flow, when second
Between average speed, the second time occupancy.
Embodiment 2：Based on above-described embodiment, the present embodiment specifically sets classification quantity, and the present embodiment is in transport information control
Center processed completes, and by the model construction and traffic state judging decision model at traffic flow parameter fuzzy clustering center two are built
Divide content, the acquisition that traffic control system software realizes traffic status of express way module can be embedded in, comprise the following steps that：
S1：Obtain the historical parameter data of freeway traffic flow running status；
S2：According to historical parameter data and default four classification, traffic flow parameter is set up using fuzzy clustering algorithm and is obscured
Cluster centre model；
Wherein, traffic flow parameter fuzzy clustering center model is set up using fuzzy clustering algorithm, refers to and built using FCM algorithms
Grade separation is through-flow parameter fuzzy cluster centre model, specifically includes：
S21：Initiation parameter, defines V(0)={ v1,v2,v3,v4, ε ＞ 0, t=1, Tmax, wherein V(0)For traffic flow ginseng
Digital-to-analogue pastes cluster centre, v1For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4For obstruction cluster
Center, ε is circulation cut-off error, and t is cycle-index, TmaxFor maximum cycle；
S22：Using formulaCalculate subordinated-degree matrix；Wherein uijFor Subject Matrix, c is default classification
Quantity, and c=4, m ∈ [1, ∞), 1≤i≤4,1≤j≤n；uij∈ [0,1],(dij)2=| | xj-
vi||2, dijRepresent sample point xjWith cluster centre viEuclidean distance；
S23：Using formulaCalculate cluster centre；
S24：Judge | | V(t)-V(t-1)| | whether≤ε sets up, wherein V(t)For the t time cluster centre matrix, V(t-1)For
T-1 cluster centre matrix, sets up loop termination, determines V(t)For Optimal cluster centers matrix；It is false execution next step；
S25：Judge t whether more than or equal to Tmax, loop termination is set up, determine V(t)For Optimal cluster centers matrix；No
Set up and perform next step；
S26：Cycle-index t adds 1, and execution step utilizes formulaCalculate subordinated-degree matrix.
Specific implementation process is as follows：
Traffic behavior is divided into into four grades { unimpeded, steady, crowded, obstruction }, i.e. fuzzy clustering number c=4.FCM is calculated
Method is by error sum of squares in weighting class as object function Jm(U,V):
Wherein：m∈[1,∞),1≤i≤4,1≤j≤n；uij∈ [0,1],(dij)2=| |
xj-vi||2, dijRepresent sample point xjWith cluster centre viEuclidean distance
In FCM algorithms, m values are bigger, and the fog-level of cluster analyses is bigger, select rational m values extremely important, by
Know that document understands, the optimal interval of m values is [1.5,2.5], m=2 herein.FCM algorithms update sample by iterative algorithm
This cluster centre so that non-similarity target goals function reaches minimum, obtains cluster centre now and degree of membership, obtains
The optimal fuzzy partition U of sample set X*=[uij *]。
FCM algorithm reasoning processes：
First have to obtain the object function of minimum：
The extreme value of object function under in order to seek Prescribed Properties, introduces Lagrange coefficient and constructs new function：
Wherein：λjFor Lagrange multiplier, (dik)2=| | xk-vi||2；
Can be tried to achieve according to above formula：
The subordinated-degree matrix and cluster centre of requirement so just can be met with formula loop iteration.
S3：Obtain the real-time parameter data of freeway traffic flow running status；
S4：According to real-time parameter data and traffic behavior cluster centre, distance is obtained in real time using minimum distance classification
The minimum traffic behavior cluster centre of supplemental characteristic；
S5：According to apart from the minimum traffic behavior cluster centre of real-time parameter data, determine belonging to real-time parameter data
Traffic behavior cluster is the traffic behavior cluster being located apart from the minimum traffic behavior cluster centre of real-time parameter data
S6：According to the Optimal cluster centers V that fuzzy clustering is obtained, arithmetic for real-time traffic flow supplemental characteristic is entered according to Euclidean distance
Row classification judges.
By the fuzzy clustering algorithm of step S2, the expression formula of the Optimal cluster centers V for obtaining：
The real-time parameter data of traffic flow are carried out into classification judgement according to the minimum distance method of Euclidean distance to it：
If fkFor minima, then xjTraffic behavior be k classes.
Traffic status of express way method of discrimination provided in an embodiment of the present invention, using congestion index as traffic state judging
Based on the content of index, it is considered to which its existing distinguishing rule reliability is low and obtains the problems such as originating indefinite, with fuzzy poly-
Class realizes the precision of relative measure and obtains, and which not only improves carries out traffic status of express way and sentence using congestion index
Other reliability, also improves the link of traffic behavior acquisition, from acquisition of information link farthest for road management person and
User provides optimal traffic control measure and plan of travel.
Present invention also offers a kind of traffic status of express way judgement system, it is public that Fig. 2 rescues high speed for the embodiment of the present invention
The structural representation of road traffic state judging system, as shown in Fig. 2 the system includes：
Historical parameter data acquisition module 201, for obtaining the historical parameter data of freeway traffic flow operation；
Model building module 202, for according to historical parameter data and default classification quantity, being built using fuzzy clustering algorithm
Grade separation is through-flow parameter fuzzy cluster centre model；
Cluster centre determining module 203, for according to traffic flow parameter fuzzy clustering center model, it is determined that default classification number
The traffic behavior cluster centre of amount；
Real-time parameter data acquisition module 204, for obtaining the real-time parameter data of freeway traffic flow running status；
Apart from determining module 205, for according to real-time parameter data and the traffic behavior cluster centre, utilizing most narrow spacing
The minimum traffic behavior cluster centre of real-time parameter data with a distance from classification method acquisition.
Traffic behavior clusters determining module 206, for according to poly- apart from the minimum traffic behavior of real-time parameter data
Class center, determines that the cluster of the traffic behavior belonging to real-time parameter data is apart from the minimum traffic behavior of real-time parameter data
The traffic behavior cluster that cluster centre is located.
Wherein, model building module 202, specifically include：
Parameter initialization module, for initiation parameter, defines V(0)={ v1,v2,v3,v4, ε ＞ 0, t=1, Tmax, its
Middle V(0)For traffic flow parameter fuzzy clustering center, v1For unimpeded cluster centre, v2For steady cluster centre, v3For in crowded cluster
The heart, v4To block cluster centre, ε is circulation cut-off error, and t is cycle-index, TmaxFor maximum cycle；
Subordinated-degree matrix acquisition module, for utilizing formulaCalculate subordinated-degree matrix；Wherein uijTo be subordinate to
Category matrix, c is to preset classification quantity, and c=4, m ∈ [1, ∞), 1≤i≤4,1≤j≤n；uij∈ [0,1],(dij)2=| | xj-vi||2, dijRepresent sample point xjWith cluster centre viEuclidean distance；
Cluster centre acquisition module, for utilizing formulaCalculate cluster centre；
First judge module, for judging | | V(t)-V(t-1)| | whether≤ε sets up, wherein V(t)For the t time cluster centre square
Battle array, V(t-1)For the t-1 time cluster centre matrix, loop termination is set up, determine V(t)For Optimal cluster centers matrix；It is false and holds
Row next step；
Second judge module, for judging t whether more than or equal to Tmax, loop termination is set up, determine V(t)Gather for optimum
Class center matrix；It is false execution next step；
Circulation performing module, plus 1 for performing cycle-index t, and execution utilizes formulaCalculate degree of membership
Matrix.
Wherein, traffic behavior cluster determining module 206, specifically includes：
Optimal cluster centers acquisition module, for obtaining the Optimal cluster centers V(t),
Wherein：V(t)For in optimum traffic flow parameter fuzzy clustering cluster
The heart, v1For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4To block cluster centre；
Cluster centre acquisition module, for according to the formula of the minimum distance classification of Euclidean distanceObtain apart from the minimum traffic behavior cluster centre of the real-time parameter data；Its
Middle fk(xj) for Real-time Collection the different cluster centre of traffic state data to four Euclidean distance minima, k is traffic behavior
The numbering of generic, here value 1,2,3,4, represent respectively unimpeded, steady, crowded, blocked state.xjFor Real-time Collection
Traffic state data matrix, djiFor Real-time Collection traffic state data to cluster centre Euclidean distance, vjiFor different traffic
The cluster centre value of different traffic parameters under state.
Freeway traffic provided in an embodiment of the present invention sentences the acquisition of state module, using congestion index as traffic behavior
Based on the content of discriminant criterion, it is considered to which its existing distinguishing rule reliability is low and obtains the problems such as originating indefinite, with mould
Paste cluster realizes the precision of relative measure and obtains, and which not only improves carries out freeway traffic shape using congestion index
The reliability that state differentiates, also improves the link of traffic behavior acquisition, is farthest road management from acquisition of information link
Person and user provide optimal traffic control measure and plan of travel.
Multiple examples used herein are set forth to the principle and embodiment of the present invention, the explanation of above example
It is only intended to help and understands the method for the present invention and its core concept；Simultaneously for one of ordinary skill in the art, according to this
The thought of invention, will change in specific embodiments and applications.In sum, this specification content should not
It is interpreted as limitation of the present invention.
Claims (8)
1. a kind of traffic status of express way method of discrimination, it is characterised in that include：
Obtain the historical parameter data of freeway traffic flow running status；
According to the historical parameter data and default classification quantity, traffic flow parameter fuzzy clustering is set up using fuzzy clustering algorithm
Center model；
According to the traffic flow parameter fuzzy clustering center model, in determining the traffic behavior cluster of the default classification quantity
The heart；
Obtain the real-time parameter data of freeway traffic flow running status；
According to the real-time parameter data and the traffic behavior cluster centre, obtained apart from described using minimum distance classification
The minimum traffic behavior cluster centre of real-time parameter data；
According to apart from the minimum traffic behavior cluster centre of the real-time parameter data, the real-time parameter data institute is determined
The traffic behavior cluster of category is the traffic shape being located apart from the minimum traffic behavior cluster centre of the real-time parameter data
State is clustered.
2. a kind of traffic status of express way method of discrimination according to claim 1, it is characterised in that the highway
The historical parameter data of traffic flow running rate, including：First flow, very first time average speed, very first time occupation rate；Institute
The real-time parameter data of freeway traffic flow running status are stated, including：Second flow, the second time mean speed, when second
Between occupation rate.
3. a kind of traffic status of express way method of discrimination according to claim 1, it is characterised in that include：
Obtain the historical parameter data of freeway traffic flow running status；
According to the historical parameter data and default four classification, traffic flow parameter fuzzy clustering is set up using fuzzy clustering algorithm
Center model；
According to the traffic flow parameter fuzzy clustering center model, four traffic behavior cluster centres are determined；Four traffic
State clustering center includes unimpeded cluster centre, and steady cluster centre, crowded cluster centre blocks cluster centre；
Obtain the real-time parameter data of freeway traffic flow running status；
According to the real-time parameter data and four traffic behavior cluster centres, using minimum distance classification distance is obtained
The minimum traffic behavior cluster centre of the real-time parameter data；
According to apart from the minimum traffic behavior cluster centre of the real-time parameter data, the real-time parameter data institute is determined
The traffic behavior cluster of category is the traffic shape being located apart from the minimum traffic behavior cluster centre of the real-time parameter data
State is clustered.
4. a kind of traffic status of express way method of discrimination according to claim 3, it is characterised in that described using fuzzy
Clustering algorithm sets up traffic flow parameter fuzzy clustering center model, to refer to and set up traffic flow parameter fuzzy clustering using FCM algorithms
Center model, specifically includes：
Initiation parameter, defines V(0)={ v1,v2,v3,v4, ε ＞ 0, t=1, Tmax, wherein V(0)For traffic flow parameter fuzzy clustering
Center, v1For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4To block cluster centre, ε is to follow
Ring cut-off error, t is cycle-index, TmaxFor maximum cycle；
Using formulaCalculate subordinated-degree matrix；Wherein uijFor Subject Matrix, c is to preset classification quantity, c=
4, m ∈ [1, ∞), 1≤i≤4,1≤j≤n；uij∈[0,1],(dij)2=| | xj-vi||2, dij
Represent sample point xjWith cluster centre viEuclidean distance；
Using formulaCalculate cluster centre；
Judge | | V(t)-V(t-1)| | whether≤ε sets up, wherein V(t)For the cluster centre matrix of the t time iteration acquisition, V(t-1)For
The cluster centre matrix that t-1 iteration is obtained, ε is convergence cut-off error, and above formula sets up loop termination, determines V(t)Gather for optimum
Class center matrix；It is false execution next step；
Judge t whether more than or equal to Tmax, loop termination is set up, determine V(t)For Optimal cluster centers matrix；It is false execution
Next step；
Cycle-index t adds 1, and execution step utilizes formulaCalculate subordinated-degree matrix.
5. a kind of traffic status of express way determination methods according to claim 4, it is characterised in that described using minimum
Distance classification obtain apart from the real-time parameter data minimum traffic behavior cluster centre the step of specifically include：
Obtain the Optimal cluster centers V(t),
Wherein：V(t)For optimum traffic flow parameter fuzzy clustering center, v1For smooth
Logical cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4To block cluster centre；
According to the formula of the minimum distance classification of Euclidean distanceObtain apart from described
The minimum traffic behavior cluster centre of real-time parameter data；Wherein fk(xj) for Real-time Collection traffic state data to four not
With the Euclidean distance minima of cluster centre, k is the numbering of traffic behavior generic, and here value 1,2,3,4, represent respectively
Unimpeded, steady, crowded, blocked state.xjFor the traffic state data matrix of Real-time Collection, djiFor the traffic behavior of Real-time Collection
Parameter to cluster centre Euclidean distance, vjiFor the cluster centre value of different traffic parameters under different traffic.
6. a kind of traffic status of express way judges system, it is characterised in that the system includes：
Historical parameter data acquisition module, for obtaining the historical parameter data of freeway traffic flow operation；
Model building module, for according to the historical parameter data and default classification quantity, being set up using fuzzy clustering algorithm
Traffic flow parameter fuzzy clustering center model；
Cluster centre determining module, for according to the traffic flow parameter fuzzy clustering center model, determining the default classification
The traffic behavior cluster centre of quantity；
Real-time parameter data acquisition module, for obtaining the real-time parameter data of freeway traffic flow running status；
Nearest cluster centre determining module, for according to the real-time parameter data and the traffic behavior cluster centre, utilizing
Minimum distance classification is obtained apart from the minimum traffic behavior cluster centre of the real-time parameter data.
Traffic behavior clusters determining module, for according in the minimum traffic behavior cluster of the real-time parameter data
The heart, determines that the cluster of the traffic behavior belonging to the real-time parameter data is apart from the minimum traffic of the real-time parameter data
The traffic behavior cluster that state clustering center is located.
7. a kind of traffic status of express way according to claim 6 judges system, it is characterised in that the model is set up
Module, specifically includes：
Parameter initialization module, for initiation parameter, defines V(0)={ v1,v2,v3,v4, ε ＞ 0, t=1, Tmax, wherein V(0)
For traffic flow parameter fuzzy clustering cluster centre, v1For unimpeded cluster centre, v2For steady cluster centre, v3For in crowded cluster
The heart, v4To block cluster centre, ε is circulation cut-off error, and t is cycle-index, TmaxFor maximum cycle；
Subordinated-degree matrix acquisition module, for utilizing formulaCalculate subordinated-degree matrix；Wherein uijTo be subordinate to square
Battle array, c is to preset classification quantity, and c=4, m ∈ [1, ∞), 1≤i≤4,1≤j≤n；uij∈[0,1],(dij)2=| | xj-vi||2, dijRepresent sample point xjWith cluster centre viEuclidean distance；
Cluster centre acquisition module, for utilizing formulaCalculate cluster centre；
First judge module, for judging | | V(t)-V(t-1)| | whether≤ε sets up, wherein V(t)For the t time cluster centre matrix, V(t-1)For the t-1 time cluster centre matrix, loop termination is set up, determine V(t)For Optimal cluster centers matrix；It is false under execution
One step；
Second judge module, for judging t whether more than or equal to Tmax, loop termination is set up, determine V(t)For in optimum cluster
Heart matrix；It is false execution next step；
Circulation performing module, plus 1 for performing cycle-index t, and execution utilizes formulaCalculate degree of membership square
Battle array.
8. a kind of traffic status of express way according to claim 7 judges system, it is characterised in that the nearest cluster
Center determining module, specifically includes：
Optimal cluster centers acquisition module, for obtaining the Optimal cluster centers V(t),
Wherein：V(t)For optimum traffic flow parameter fuzzy clustering cluster centre, v1
For unimpeded cluster centre, v2For steady cluster centre, v3For crowded cluster centre, v4To block cluster centre；
Cluster centre acquisition module, for according to the formula of the minimum distance classification of Euclidean distanceObtain apart from the minimum traffic behavior cluster centre of the real-time parameter data；Its
Middle fk(xj) for Real-time Collection the different cluster centre of traffic state data to four Euclidean distance minima, k is traffic behavior
The numbering of generic, here value 1,2,3,4, represent respectively unimpeded, steady, crowded, blocked state.xjFor Real-time Collection
Traffic state data matrix, djiFor Real-time Collection traffic state data to cluster centre Euclidean distance, vjiFor different traffic
The cluster centre value of different traffic parameters under state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710134402.4A CN106652460A (en) | 2017-03-08 | 2017-03-08 | Highway traffic state determination method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710134402.4A CN106652460A (en) | 2017-03-08 | 2017-03-08 | Highway traffic state determination method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106652460A true CN106652460A (en) | 2017-05-10 |
Family
ID=58847116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710134402.4A Pending CN106652460A (en) | 2017-03-08 | 2017-03-08 | Highway traffic state determination method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106652460A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492557A (en) * | 2018-03-23 | 2018-09-04 | 四川高路交通信息工程有限公司 | Highway jam level judgment method based on multi-model fusion |
| CN108694832A (en) * | 2018-06-26 | 2018-10-23 | 徐然 | Vehicle congestion method of control and system when a kind of two-way two three-lane roads part construction |
| CN108765956A (en) * | 2018-06-14 | 2018-11-06 | 广东工业大学 | A kind of traffic status of express way comprehensive estimation method |
| CN109446881A (en) * | 2018-09-05 | 2019-03-08 | 重庆大学 | A kind of express highway section Traffic State Detection Method based on isomeric data |
| CN109697851A (en) * | 2019-01-10 | 2019-04-30 | 安徽工业大学 | Based on AFCM-l2Urban road traffic state method of discrimination and system |
| CN110197584A (en) * | 2019-04-03 | 2019-09-03 | 中国公路工程咨询集团有限公司 | Traffic status of express way evaluation method based on area detector |
| CN110338821A (en) * | 2019-08-12 | 2019-10-18 | 深圳市发掘科技有限公司 | A kind of driver's driving condition recognition methods |
| 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 |
| CN112085951A (en) * | 2020-08-17 | 2020-12-15 | 西安电子科技大学 | Traffic state discrimination method, system, storage medium, computer device and application |
| CN113380032A (en) * | 2021-06-09 | 2021-09-10 | 重庆大学 | Hierarchical clustering method-based highway congestion judgment method and device |
| CN115909741A (en) * | 2022-11-30 | 2023-04-04 | 山东高速股份有限公司 | Method, device and medium for judging traffic state |
| CN117292546A (en) * | 2023-10-23 | 2023-12-26 | 重庆交通大学 | Traffic travel mode OD calculation method based on mobile phone GPS data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101188064A (en) * | 2007-12-20 | 2008-05-28 | 北京交通大学 | 3D integrated freeway traffic event automatic detection method |
| 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) |
| CN103606274A (en) * | 2012-12-18 | 2014-02-26 | 北京科技大学 | Urban road traffic state assessment method |
| CN104809877A (en) * | 2015-05-14 | 2015-07-29 | 重庆大学 | Expressway site traffic state estimation method based on feature parameter weighted GEFCM algorithm |
| EP3149430A1 (en) * | 2014-05-26 | 2017-04-05 | Tomtom Traffic B.V. | Methods of obtaining and using point of interest data |
-
2017
- 2017-03-08 CN CN201710134402.4A patent/CN106652460A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101188064A (en) * | 2007-12-20 | 2008-05-28 | 北京交通大学 | 3D integrated freeway traffic event automatic detection method |
| 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) |
| CN103606274A (en) * | 2012-12-18 | 2014-02-26 | 北京科技大学 | Urban road traffic state assessment method |
| EP3149430A1 (en) * | 2014-05-26 | 2017-04-05 | Tomtom Traffic B.V. | Methods of obtaining and using point of interest data |
| CN104809877A (en) * | 2015-05-14 | 2015-07-29 | 重庆大学 | Expressway site traffic state estimation method based on feature parameter weighted GEFCM algorithm |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492557A (en) * | 2018-03-23 | 2018-09-04 | 四川高路交通信息工程有限公司 | Highway jam level judgment method based on multi-model fusion |
| CN108765956A (en) * | 2018-06-14 | 2018-11-06 | 广东工业大学 | A kind of traffic status of express way comprehensive estimation method |
| CN108694832B (en) * | 2018-06-26 | 2019-12-17 | 徐然 | Vehicle congestion control method and system during local construction of bidirectional two-lane road |
| CN108694832A (en) * | 2018-06-26 | 2018-10-23 | 徐然 | Vehicle congestion method of control and system when a kind of two-way two three-lane roads part construction |
| CN109446881A (en) * | 2018-09-05 | 2019-03-08 | 重庆大学 | A kind of express highway section Traffic State Detection Method based on isomeric data |
| CN109446881B (en) * | 2018-09-05 | 2022-06-24 | 重庆大学 | Heterogeneous data-based highway section traffic state detection method |
| CN109697851A (en) * | 2019-01-10 | 2019-04-30 | 安徽工业大学 | Based on AFCM-l2Urban road traffic state method of discrimination and system |
| CN109697851B (en) * | 2019-01-10 | 2022-01-18 | 安徽工业大学 | Urban road traffic state discrimination method and system based on AFCM-L2 |
| 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 |
| CN110197584A (en) * | 2019-04-03 | 2019-09-03 | 中国公路工程咨询集团有限公司 | Traffic status of express way evaluation method based on area detector |
| CN110338821A (en) * | 2019-08-12 | 2019-10-18 | 深圳市发掘科技有限公司 | A kind of driver's driving condition recognition methods |
| CN112085951A (en) * | 2020-08-17 | 2020-12-15 | 西安电子科技大学 | Traffic state discrimination method, system, storage medium, computer device and application |
| CN113380032A (en) * | 2021-06-09 | 2021-09-10 | 重庆大学 | Hierarchical clustering method-based highway congestion judgment method and device |
| CN115909741A (en) * | 2022-11-30 | 2023-04-04 | 山东高速股份有限公司 | Method, device and medium for judging traffic state |
| CN115909741B (en) * | 2022-11-30 | 2024-03-26 | 山东高速股份有限公司 | Traffic state judging method, equipment and medium |
| CN117292546A (en) * | 2023-10-23 | 2023-12-26 | 重庆交通大学 | Traffic travel mode OD calculation method based on mobile phone GPS data |
| CN117292546B (en) * | 2023-10-23 | 2024-05-07 | 重庆交通大学 | Traffic travel mode OD calculation method based on mobile phone GPS data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106652460A (en) | Highway traffic state determination method and system | |
| CN107862864B (en) | Driving condition intelligent prediction estimation method based on driving habits and traffic road conditions | |
| CN106205156B (en) | A kind of intersection self-healing combination control method for the mutation of part lane flow | |
| CN108492557A (en) | Highway jam level judgment method based on multi-model fusion | |
| CN102081846B (en) | Expressway charge data track matching based traffic state recognition method | |
| CN107071841A (en) | The vertical handoff method optimized in heterogeneous network based on changeable weight | |
| CN107153846A (en) | A kind of road traffic state modeling method based on Fuzzy C-Means Cluster Algorithm | |
| CN109525956B (en) | Energy-saving data collection method based on data-driven clustering in wireless sensor network | |
| CN109167805A (en) | Analysis and processing method based on car networking space-time data in City scenarios | |
| CN104200081B (en) | The forecasting procedure and system of landfall typhoon characterization factor based on historical data | |
| CN110162968A (en) | A kind of Network Intrusion Detection System based on machine learning | |
| CN107944628A (en) | A kind of accumulation mode under road network environment finds method and system | |
| CN109345434A (en) | A kind of method of open cell inside and outside highway layout safety evaluation | |
| CN113033899B (en) | Unmanned adjacent vehicle track prediction method | |
| CN107845260A (en) | A kind of recognition methods of user's bus trip mode | |
| CN107507421A (en) | Method for rapidly judging traffic state and device | |
| CN112084716B (en) | Red tide prediction and early warning method based on eutrophication comprehensive evaluation | |
| CN101551940A (en) | Urban high-speed road traffic state judging and issuing system and method thereof | |
| CN103095534B (en) | A kind of Technique of Computer Network Attack Effect Evaluation method of two-dimentional K average entropy | |
| Sun et al. | Mobile multi-sink nodes path planning algorithm concerned with energy balance in wireless sensor networks | |
| CN113553350B (en) | Traffic flow partition model for similar evolution mode clustering and dynamic time zone division | |
| CN114444922A (en) | Hybrid traffic efficiency evaluation method under group intelligent control | |
| CN110197584A (en) | Traffic status of express way evaluation method based on area detector | |
| CN111405605B (en) | Wireless network interruption detection method based on self-organizing mapping | |
| CN112512000A (en) | Power distribution Internet of things node deployment optimization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |
|
| RJ01 | Rejection of invention patent application after publication |