CN113409578B - Traffic network health portrait method and system based on fuzzy clustering - Google Patents
Traffic network health portrait method and system based on fuzzy clustering Download PDFInfo
- Publication number
- CN113409578B CN113409578B CN202110712265.4A CN202110712265A CN113409578B CN 113409578 B CN113409578 B CN 113409578B CN 202110712265 A CN202110712265 A CN 202110712265A CN 113409578 B CN113409578 B CN 113409578B
- Authority
- CN
- China
- Prior art keywords
- network
- traffic flow
- road
- urban traffic
- health
- 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.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims 1
- 230000003862 health status Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Images
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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a traffic network health portrait method and system based on fuzzy clustering. The method comprises the steps of obtaining vehicle road information in set time in a road network region to be analyzed; preprocessing the vehicle road information, and constructing an urban traffic flow network of the road network region to be analyzed according to the preprocessed data; determining the health state of the urban traffic flow network at different moments by adopting a seepage analysis method; dividing the health states of the urban traffic flow network at different moments by adopting a clustering analysis method; and performing health portrayal on the urban traffic flow network of the road network area to be analyzed by using the division result. The invention can accurately classify the health state of the traffic network, thereby solving the problem of health portrait of the urban road network.
Description
Technical Field
The invention relates to the field of traffic network states, in particular to a traffic network health portrait method and system based on fuzzy clustering.
Background
In recent years, with the increasing of climate change, extreme disaster events such as typhoon, rainstorm, epidemic situation, earthquake and other sudden events occur continuously, research on urban traffic toughness has very important theoretical value and practical significance, and relevant expressions such as 'strengthening urban disaster coping capability and improving urban toughness' are provided in a new round of urban overall planning of cities such as Beijing, Shanghai and the like. The emergent epidemic crisis in the year, the more perceptual knowledge of city toughness is given, and the more rational thinking is given to how cities normally operate and maintain toughness in the increasing and unrealistic risks and challenges. The occurrence of an emergency brings huge impact and influence to the definition and use of the current urban space. Emergencies continuously remold cities and society and indirectly promote the birth and the evolution of modern city planning. During epidemic situations, the city service and supply mode are changed on line, and the functional form and use mode of the spaces such as city living, employment and traffic are redefined. The urban traffic network is used as a lifeline of a 'flexible city', national development, social security guarantee and guarantee of quality of life of people are achieved, and the health level of the traffic network can reflect the comprehensive ability of the urban network in maintaining daily operation and responding to emergencies, so that monitoring and evaluating the health level of the urban traffic network becomes an important task.
The traffic health portrait is the basis of the evaluation of the health status of the traffic network. Previous traffic health assessments were primarily based on a sum or average of statistical measures for each link, such as average speed, average travel delay time, average distance to congested links, and the like. However, since the urban traffic system has high complexity and coupling, these statistical-based measurements rarely consider the coupling relationship between road performances, and cannot reasonably evaluate the health status of the traffic network from the perspective of the overall network, which affects the accuracy of the health evaluation of the traffic network. On the other hand, research has been carried out to describe the overall operation state of a traffic network based on an analysis method of seepage, and the description can be used as a health assessment index of an urban traffic network.
In addition, a great deal of cognitive uncertainty exists in traffic system assessment, the cognitive uncertainty is subjective, and is generally caused by the complexity of the system, the incompleteness and ambiguity of information, the lack of human cognition and the like, so that the essential characteristics of things cannot be mastered or understood within a certain time range, and the characteristics of serious 'large data volume and poor knowledge' exist. The previous definition of the health level of the traffic network is mainly based on the artificial definition of an index interval, and the traffic network usually has strong subjectivity and cannot well reflect the objective mechanism of objects.
Therefore, the problem of strong subjectivity can be effectively solved by mining the road network health mechanism from the big data, researchers can carry out statistical analysis on historical data of the road network by applying a statistical mathematical theory and a statistical method at present, real-time running characteristics of the traffic road network are mined, and influences of subjective factors on road network evaluation are reduced, but the existing statistical analysis method cannot divide the road network into health states according to the characteristics.
Disclosure of Invention
The invention aims to provide a traffic network health portrait method and system based on fuzzy clustering, which can accurately classify the health state of a traffic network so as to solve the problem of urban road network health portrait.
In order to achieve the purpose, the invention provides the following scheme:
a traffic network health image method based on fuzzy clustering comprises the following steps:
obtaining vehicle road information in set time in a road network region to be analyzed; the vehicle road information includes: the road number, the road starting point number, the road end point number, the road grade, the road information, the road vehicle speed and the longitude and latitude information at each moment;
preprocessing the vehicle road information, and constructing an urban traffic flow network of the road network region to be analyzed according to the preprocessed data;
determining the health state of the urban traffic flow network at different moments by adopting a seepage analysis method;
dividing the health states of the urban traffic flow network at different moments by adopting a clustering analysis method;
and performing health portrayal on the urban traffic flow network of the road network area to be analyzed by using the division result.
Optionally, the preprocessing the vehicle road information and constructing the urban traffic flow network of the road network region to be analyzed according to the preprocessed data specifically include:
matching the road information with the speed of the road vehicle at each moment; completing the speed of the missing road vehicle;
matching the road starting point number, the road end point number and the longitude and latitude;
and constructing the urban traffic flow network by taking the roads in the road network area to be analyzed as connecting edges of the urban traffic flow network, taking intersections as nodes of the urban traffic flow network and taking the real-time relative vehicle speed of each road as a connecting edge weight.
Optionally, the determining the health state of the urban traffic flow network at different times by using a seepage analysis method specifically includes:
acquiring a relative speed threshold; the relative speed threshold is a numerical value which is changed from 0 to 1 according to set precision;
deleting the connecting edges of each road in the urban traffic flow network, the real-time relative vehicle speed of which is less than the relative speed threshold value at the corresponding moment, and determining the maximum connected sub-cluster size of the urban traffic flow network at the corresponding moment;
determining G-q curve graphs at different moments according to the maximum connected sub-cluster size of the urban traffic flow network at each moment and the corresponding relative speed threshold; wherein G is the size of the maximum connected cluster, and q is a relative speed threshold;
converting G-q curve graphs at different moments into G-f curve graphs; wherein f is the ratio of the deleted connecting edge to the total number of edges of the urban traffic flow network;
and determining the health state of the urban traffic flow network at different moments according to the G-f curve graphs at different moments.
Optionally, the dividing the health state of the urban traffic flow network at different times by using a cluster analysis method specifically includes:
determining clustering characteristic vectors at corresponding moments according to G-f curve graphs at different moments;
and carrying out fuzzy clustering on the feature vectors by utilizing an FCM clustering algorithm to classify the health state of the urban traffic flow network into healthy or unhealthy.
Optionally, the performing the health representation of the urban traffic flow network of the road network region to be analyzed by using the division result specifically includes:
respectively determining network structure indexes and network operation indexes of healthy urban traffic flow networks and unhealthy urban traffic flow networks; the network structure indicators include: average degree and dynamic betweenness; the network operation indicators include: TTI index and network average speed;
the network structure index and the network operation index respectively carry out health portrayal on the corresponding urban traffic flow network.
A traffic network health representation system based on fuzzy clustering comprises:
the vehicle road information acquisition module is used for acquiring vehicle road information in set time in a road network region to be analyzed; the vehicle road information includes: the road number, the road starting point number, the road end point number, the road grade, the road information, the road vehicle speed and the longitude and latitude information at each moment;
the urban traffic flow network construction module is used for preprocessing the vehicle road information and constructing an urban traffic flow network of the road network area to be analyzed according to the preprocessed data;
the health state determining module of the urban traffic flow network is used for determining the health states of the urban traffic flow network at different moments by adopting a seepage analysis method;
the division result determining module is used for dividing the health states of the urban traffic flow network at different moments by adopting a clustering analysis method;
and the health portrait module is used for performing health portrait on the urban traffic flow network of the road network area to be analyzed by utilizing the division result.
Optionally, the urban traffic flow network construction module specifically includes:
a first matching unit for matching the road information with the road vehicle speed at each moment; completing the speed of the missing road vehicle;
the second matching unit is used for matching the road starting point number, the road end point number and the longitude and latitude;
and the urban traffic flow network construction unit is used for constructing the urban traffic flow network by taking the roads in the road network area to be analyzed as the connecting edges of the urban traffic flow network, taking the intersections as the nodes of the urban traffic flow network and taking the real-time relative vehicle speed of each road as the connecting edge weight.
Optionally, the health status determining module of the urban traffic flow network specifically includes:
a relative speed threshold value acquisition unit for acquiring a relative speed threshold value; the relative speed threshold is a numerical value which is changed from 0 to 1 according to set precision;
the maximum connected sub-cluster size determining unit is used for deleting the connected edges of each road in the urban traffic flow network, of which the real-time relative vehicle speed is smaller than the relative speed threshold at the corresponding moment, and determining the maximum connected sub-cluster size of the urban traffic flow network at the corresponding moment;
the G-q curve graph determining unit is used for determining G-q curve graphs at different moments according to the maximum connected sub-cluster size of the urban traffic flow network at each moment and the corresponding relative speed threshold; wherein G is the size of the maximum connected cluster, and q is a relative speed threshold;
the conversion unit is used for converting the G-q curve graphs at different moments into G-f curve graphs; wherein f is the ratio of the deleted continuous edge to the total number of edges of the urban traffic flow network
And the health state determining unit of the urban traffic flow network is used for determining the health states of the urban traffic flow network at different moments according to the G-f curve graphs at different moments.
Optionally, the dividing result determining module specifically includes:
the clustering feature vector determining unit is used for determining clustering feature vectors at corresponding moments according to G-f curve graphs at different moments;
and the division result determining unit is used for carrying out fuzzy clustering on the characteristic vectors by utilizing an FCM clustering algorithm to divide the health state of the urban traffic flow network into healthy state or unhealthy state.
Optionally, the health representation module specifically includes:
the index determining unit is used for respectively determining network structure indexes and network operation indexes of a healthy urban traffic flow network and an unhealthy urban traffic flow network; the network structure indicators include: average degree and dynamic betweenness; the network operation indicators include: TTI index and network average speed;
and the health portrait unit is used for respectively portraying the health of the corresponding urban traffic flow network by the network structure index and the network operation index.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the traffic network health image method and system based on fuzzy clustering provided by the invention can be used for analyzing and describing the states of the traffic network through traffic seepage and performing health classification on the states of the traffic network by using the fuzzy clustering method, thereby solving the problem of urban network health image. The fuzzy clustering method is adopted to solve the problem that the road network health boundary division is not clear, two types of networks, namely a healthy road network and an unhealthy road network, are mined from big data, and the difference of the healthy network and the unhealthy network in characteristic indexes is determined, so that the health image function of the road network is realized, and a foundation is laid for the subsequent traffic network health assessment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a traffic network health representation method based on fuzzy clustering according to the present invention;
FIG. 2 is a schematic view of the health status of an urban traffic flow network at different times;
FIG. 3 is a schematic diagram of a characteristic index of an urban traffic flow network;
FIG. 4 is a schematic diagram of a traffic network health representation system based on fuzzy clustering according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a traffic network health portrait method and system based on fuzzy clustering, which can accurately classify the health state of a traffic network so as to solve the problem of urban road network health portrait.
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the accompanying drawings and the detailed description thereof.
Fig. 1 is a schematic flow chart of a traffic network health image method based on fuzzy clustering provided by the present invention, and as shown in fig. 1, the traffic network health image method based on fuzzy clustering provided by the present invention includes:
s101, obtaining vehicle road information in set time in a road network region to be analyzed; the vehicle road information includes: the road number, the road starting point number, the road end point number, the road grade, the road information, the road vehicle speed and the longitude and latitude information at each moment;
s102, preprocessing the vehicle road information, and constructing an urban traffic flow network of the road network region to be analyzed according to preprocessed data;
s102 specifically comprises the following steps:
matching the road information with the speed of the road vehicle at each moment; completing the speed of the missing road vehicle; the missing phenomenon of the acquired speed data is caused by the fact that some road sections lack arrangement of related data acquisition equipment and vehicles do not pass through the data acquisition equipment of the road at some time, and the speed data is compensated for, so that the missing speed is compensated.
Matching the road starting point number, the road end point number and the longitude and latitude;
and constructing the urban traffic flow network by taking the roads in the road network area to be analyzed as the connecting edges of the urban traffic flow network, taking the intersections as the nodes of the urban traffic flow network and taking the real-time relative vehicle speed of each road as the weight of the connecting edges.
Wherein,
vcrepresents a relative velocity; v denotes the road actual speed, vmaxIndicating the maximum speed of the road over a specified time.
S103, determining the health states of the urban traffic flow network at different moments by adopting a seepage analysis method;
s103 specifically comprises the following steps:
acquiring a relative speed threshold; the relative speed threshold is a numerical value which is changed from 0 to 1 according to set precision; the setting accuracy is as 0.1.
Deleting the connecting edges of each road in the urban traffic flow network, the real-time relative vehicle speed of which is less than the relative speed threshold value at the corresponding moment, and determining the maximum connected sub-cluster size of the urban traffic flow network at the corresponding moment;
determining G-q curve graphs at different moments according to the maximum connected sub-cluster size of the urban traffic flow network at each moment and the corresponding relative speed threshold; wherein G is the size of the maximum connected cluster, and q is a relative speed threshold;
i.e. each time v is deletedcAnd (3) calculating the maximum connected sub-cluster size G of the road network under the deleted connected side, and finally obtaining a G-q curve graph at each moment through multiple seepage of the road network under each moment.
Converting G-q curve graphs at different moments into G-f curve graphs; wherein f is the ratio of the deleted connecting edge to the total number of edges of the urban traffic flow network.
The edge-deletion ratio f, i.e. v, at each relative velocity threshold qcAnd the number of the connecting edges smaller than q accounts for the proportion of the number of the connecting edges of the whole road network, so that the G-q curve graph is converted into a G-f curve graph, and the health state of the road network at the moment is described by using the G-f curve at each moment.
And determining the health state of the urban traffic flow network at different moments according to the G-f curve graphs at different moments.
S104, dividing the health states of the urban traffic flow network at different moments by adopting a clustering analysis method;
s104 specifically comprises the following steps:
determining clustering characteristic vectors at corresponding moments according to G-f curve graphs at different moments;
as a specific embodiment, the area of each G-f curve from the x axis is calculated to serve as the clustering feature vector of the network at each moment.
And carrying out fuzzy clustering on the feature vectors by utilizing an FCM clustering algorithm to classify the health state of the urban traffic flow network into healthy or unhealthy.
Specifically, the divided G-f curves are labeled, wherein the G-f curve is first in a descending trend and is in an unhealthy state, and the other G-f curve is in a healthy state, as shown in fig. 2.
And S105, performing health representation on the urban traffic flow network of the road network area to be analyzed by using the division result.
S105 specifically comprises the following steps:
network structure indexes and network operation indexes of healthy urban traffic flow networks and unhealthy urban traffic flow networks are respectively determined and are shown in fig. 3; the network structure index includes but is not limited to average degree and dynamic betweenness; the network operation indicators include, but are not limited to, TTI index and network average speed; namely, characteristic indexes which can be used for evaluating the efficiency of the traffic network are proposed and calculated from multiple angles.
The network structure index and the network operation index respectively carry out health portrayal on the corresponding urban traffic flow network.
And respectively drawing a characteristic index membership degree change graph along with the health type, different types of characteristic index boxline graphs and a characteristic index change graph along with time, and describing the difference of the two types of networks on the characteristic index from multiple angles, thereby describing the characteristics of the healthy state and the unhealthy state of the urban traffic network and realizing the healthy portrait.
The difference of the healthy network and the unhealthy network in the characteristic indexes is described by calculating the structural indexes, the operation indexes and other related characteristic indexes of the urban traffic network, so that the healthy image function of the road network is realized, and a foundation is laid for the subsequent health assessment of the traffic road network.
Fig. 4 is a schematic structural diagram of a traffic network health representation system based on fuzzy clustering, as shown in fig. 4, the traffic network health representation system based on fuzzy clustering provided by the present invention includes:
a vehicle road information obtaining module 401, configured to obtain vehicle road information within a set time in a road network region to be analyzed; the vehicle road information includes: the method comprises the following steps of (1) carrying out road numbering, road starting point numbering, road end point numbering, road grade, road information, road vehicle speed and longitude and latitude information at each moment;
an urban traffic flow network construction module 402, configured to preprocess the vehicle road information, and construct an urban traffic flow network of the road network region to be analyzed according to the preprocessed data;
a health status determination module 403 of the urban traffic flow network, configured to determine health statuses of the urban traffic flow network at different times by using a seepage analysis method;
a partitioning result determining module 404, configured to partition the health states of the urban traffic flow network at different times by using a clustering analysis method;
and a health portrait module 405, configured to portrait health of the urban traffic flow network of the road network area to be analyzed by using the partitioning result.
The urban traffic flow network construction module 402 specifically includes:
a first matching unit for matching the road information with the road vehicle speed at each moment; completing the speed of the missing road vehicle;
the second matching unit is used for matching the road starting point number, the road end point number and the longitude and latitude;
and the urban traffic flow network construction unit is used for constructing the urban traffic flow network by taking the roads in the road network area to be analyzed as the connecting edges of the urban traffic flow network, taking the intersections as the nodes of the urban traffic flow network and taking the real-time relative vehicle speed of each road as the connecting edge weight.
The health status determination module 403 of the urban traffic flow network specifically includes:
a relative speed threshold value acquisition unit for acquiring a relative speed threshold value; the relative speed threshold is a numerical value which is changed from 0 to 1 according to set precision;
the maximum connected sub-cluster size determining unit is used for deleting the connected edges of each road in the urban traffic flow network, of which the real-time relative vehicle speed is smaller than the relative speed threshold at the corresponding moment, and determining the maximum connected sub-cluster size of the urban traffic flow network at the corresponding moment;
the G-q curve graph determining unit is used for determining G-q curve graphs at different moments according to the maximum connected sub-cluster size of the urban traffic flow network at each moment and the corresponding relative speed threshold; wherein G is the size of the maximum connected cluster, and q is a relative speed threshold;
the conversion unit is used for converting the G-q curve graphs at different moments into G-f curve graphs; wherein f is the ratio of the deleted connecting edge to the total number of edges of the urban traffic flow network;
and the health state determining unit of the urban traffic flow network is used for determining the health states of the urban traffic flow network at different moments according to the G-f curve graphs at different moments.
The dividing result determining module 404 specifically includes:
the clustering characteristic vector determining unit is used for determining clustering characteristic vectors at corresponding moments according to G-f curve graphs at different moments;
and the division result determining unit is used for carrying out fuzzy clustering on the characteristic vectors by utilizing an FCM clustering algorithm to divide the health state of the urban traffic flow network into healthy state or unhealthy state.
The health representation module 405 specifically includes:
the index determining unit is used for respectively determining network structure indexes and network operation indexes of a healthy urban traffic flow network and an unhealthy urban traffic flow network; the network structure indicators include: average degree and dynamic betweenness; the network operation indicators include: TTI index and network average speed;
and the health portrait unit is used for respectively portraying the health of the corresponding urban traffic flow network by the network structure index and the network operation index.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (6)
1. A traffic network health image method based on fuzzy clustering is characterized by comprising the following steps:
obtaining vehicle road information in set time in a road network region to be analyzed; the vehicle road information includes: the road number, the road starting point number, the road end point number, the road grade, the road information, the road vehicle speed and the longitude and latitude information at each moment;
preprocessing the vehicle road information, and constructing an urban traffic flow network of the road network region to be analyzed according to the preprocessed data;
determining the health state of the urban traffic flow network at different moments by adopting a seepage analysis method;
dividing the health states of the urban traffic flow network at different moments by adopting a clustering analysis method;
carrying out health portrait on the urban traffic flow network of the road network area to be analyzed by utilizing the division result;
the method for determining the health state of the urban traffic flow network at different moments by adopting the seepage analysis method specifically comprises the following steps:
acquiring a relative speed threshold; the relative speed threshold is a numerical value which is changed from 0 to 1 according to set precision;
deleting the connecting edges of each road in the urban traffic flow network, the real-time relative vehicle speed of which is less than the relative speed threshold value at the corresponding moment, and determining the maximum connected sub-cluster size of the urban traffic flow network at the corresponding moment;
determining the maximum connected sub-cluster size of the urban traffic flow network at different moments and corresponding relative speed threshold valuesG-qA graph; wherein,Gis the maximum connected cluster size,qis a relative velocity threshold;
will be at different timesG-qGraph conversion toG-fA graph; wherein,fthe ratio of the deleted connecting edge to the total number of edges of the urban traffic flow network;
according to different time instantsG-fThe curve graph determines the health state of the urban traffic flow network at different moments;
the method for dividing the health states of the urban traffic flow network at different moments by adopting the cluster analysis specifically comprises the following steps:
according to different time instantsG-fDetermining clustering feature vectors at corresponding moments by the curve graph; the clustering feature vectors are of corresponding timeG-fArea of the graph from the x-axis;
and carrying out fuzzy clustering on the feature vectors by utilizing an FCM clustering algorithm to classify the health state of the urban traffic flow network into healthy or unhealthy.
2. The traffic network health imaging method based on fuzzy clustering according to claim 1, wherein the preprocessing is performed on the vehicle road information, and the urban traffic flow network of the road network region to be analyzed is constructed according to the preprocessed data, specifically comprising:
matching the road information with the speed of the road vehicle at each moment; completing the speed of the missing road vehicle;
matching the road starting point number, the road end point number and the longitude and latitude;
and constructing the urban traffic flow network by taking the roads in the road network area to be analyzed as the connecting edges of the urban traffic flow network, taking the intersections as the nodes of the urban traffic flow network and taking the real-time relative vehicle speed of each road as the weight of the connecting edges.
3. The traffic network health image method based on fuzzy clustering as claimed in claim 1, wherein said performing health image on urban traffic flow network of road network region to be analyzed by using division result specifically comprises:
respectively determining network structure indexes and network operation indexes of healthy urban traffic flow networks and unhealthy urban traffic flow networks; the network structure indicators include: average degree and dynamic betweenness; the network operation indicators include: TTI index and network average speed;
the network structure index and the network operation index respectively carry out health portrayal on the corresponding urban traffic flow network.
4. A traffic network health representation system based on fuzzy clustering is characterized by comprising:
the vehicle road information acquisition module is used for acquiring vehicle road information in set time in a road network region to be analyzed; the vehicle road information includes: the road number, the road starting point number, the road end point number, the road grade, the road information, the road vehicle speed and the longitude and latitude information at each moment;
the urban traffic flow network construction module is used for preprocessing the vehicle road information and constructing an urban traffic flow network of the road network area to be analyzed according to the preprocessed data;
the health state determining module of the urban traffic flow network is used for determining the health states of the urban traffic flow network at different moments by adopting a seepage analysis method;
the division result determining module is used for dividing the health states of the urban traffic flow network at different moments by adopting a clustering analysis method;
the health portrait module is used for carrying out health portrait on the urban traffic flow network of the road network area to be analyzed by utilizing the division result;
the health state determination module of the urban traffic flow network specifically comprises:
a relative speed threshold value acquisition unit for acquiring a relative speed threshold value; the relative speed threshold is a numerical value which is changed from 0 to 1 according to set precision;
the maximum connected sub-cluster size determining unit is used for deleting the connected edges of each road in the urban traffic flow network, of which the real-time relative vehicle speed is smaller than the relative speed threshold at the corresponding moment, and determining the maximum connected sub-cluster size of the urban traffic flow network at the corresponding moment;
G-qa graph determining unit for determining different time according to the maximum connected sub-cluster size of the urban traffic flow network at each time and the corresponding relative speed thresholdG-qA graph; wherein,Gis the maximum connected cluster size,qis a relative velocity threshold;
a conversion unit for converting the different time instantsG-qConversion of the graph intoG-fA graph; wherein,fthe ratio of the deleted connecting edge to the total number of edges of the urban traffic flow network;
a health state determining unit of the urban traffic flow network for determining the health state according to different timeG-fThe curve graph determines the health state of the urban traffic flow network at different moments;
the division result determining module specifically includes:
a clustering feature vector determining unit for determining the clustering feature vectors according to different time instantsG-fDetermining clustering feature vectors at corresponding moments by the curve graph; the clustering feature vectors are of corresponding timeG-fArea of the graph from the x-axis;
and the division result determining unit is used for carrying out fuzzy clustering on the characteristic vectors by utilizing an FCM clustering algorithm to divide the health state of the urban traffic flow network into healthy state or unhealthy state.
5. The fuzzy clustering-based traffic network health representation system according to claim 4, wherein the urban traffic flow network construction module specifically comprises:
a first matching unit for matching the road information with the road vehicle speed at each moment; completing the speed of the missing road vehicle;
the second matching unit is used for matching the road starting point number, the road end point number and the longitude and latitude;
and the urban traffic flow network construction unit is used for constructing the urban traffic flow network by taking the roads in the road network area to be analyzed as the connecting edges of the urban traffic flow network, taking the intersections as the nodes of the urban traffic flow network and taking the real-time relative vehicle speed of each road as the connecting edge weight.
6. The traffic network health representation system based on fuzzy clustering of claim 4, wherein the health representation module specifically comprises:
the index determining unit is used for respectively determining network structure indexes and network operation indexes of a healthy urban traffic flow network and an unhealthy urban traffic flow network; the network structure indicators include: average degree and dynamic betweenness; the network operation indicators include: TTI index and network average speed;
and the health portrait unit is used for respectively portraying the health of the corresponding urban traffic flow network by the network structure index and the network operation index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712265.4A CN113409578B (en) | 2021-06-25 | 2021-06-25 | Traffic network health portrait method and system based on fuzzy clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712265.4A CN113409578B (en) | 2021-06-25 | 2021-06-25 | Traffic network health portrait method and system based on fuzzy clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113409578A CN113409578A (en) | 2021-09-17 |
| CN113409578B true CN113409578B (en) | 2022-05-13 |
Family
ID=77679654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110712265.4A Active CN113409578B (en) | 2021-06-25 | 2021-06-25 | Traffic network health portrait method and system based on fuzzy clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409578B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093168B (en) * | 2021-11-18 | 2022-11-11 | 长安大学 | Method for evaluating urban road traffic running state based on toughness visual angle |
| CN115311858B (en) * | 2022-08-08 | 2023-07-21 | 长安大学 | Urban road section hierarchical control method based on traffic flow toughness |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107908645A (en) * | 2017-10-09 | 2018-04-13 | 北京航空航天大学 | A kind of immunization method of the online social platform gossip propagation based on Analysis of The Seepage |
| CN110222950A (en) * | 2019-05-16 | 2019-09-10 | 北京航空航天大学 | A kind of the health indicator system and appraisal procedure of urban transportation |
| CN110705827A (en) * | 2019-09-04 | 2020-01-17 | 北京航空航天大学 | Urban traffic health index establishing method based on traffic cloud |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7164797B2 (en) * | 2002-04-25 | 2007-01-16 | Microsoft Corporation | Clustering |
| WO2012112555A1 (en) * | 2011-02-14 | 2012-08-23 | Andrew Llc | Method for mobile location by dynamic clustering |
| CN111819550B (en) * | 2018-03-26 | 2022-04-05 | 华为技术有限公司 | Data processing method and network equipment |
| CN109377750B (en) * | 2018-09-18 | 2020-10-09 | 北京航空航天大学 | Traffic system elastic critical point determining method based on seepage analysis |
-
2021
- 2021-06-25 CN CN202110712265.4A patent/CN113409578B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107908645A (en) * | 2017-10-09 | 2018-04-13 | 北京航空航天大学 | A kind of immunization method of the online social platform gossip propagation based on Analysis of The Seepage |
| CN110222950A (en) * | 2019-05-16 | 2019-09-10 | 北京航空航天大学 | A kind of the health indicator system and appraisal procedure of urban transportation |
| CN110705827A (en) * | 2019-09-04 | 2020-01-17 | 北京航空航天大学 | Urban traffic health index establishing method based on traffic cloud |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113409578A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023056696A1 (en) | Urban rail transit short-term passenger flow forecasting method based on recurrent neural network | |
| CN113409578B (en) | Traffic network health portrait method and system based on fuzzy clustering | |
| US20210407284A1 (en) | Vehicle traffic flow prediction method with missing data | |
| CN109086910B (en) | Urban rail transit operation road network topological structure modeling method | |
| CN110111575A (en) | A kind of Forecast of Urban Traffic Flow network analysis method based on Complex Networks Theory | |
| CN110222950B (en) | Health index system and evaluation method for urban traffic | |
| CN111724589B (en) | Multi-source data-based highway section flow estimation method | |
| WO2018122804A1 (en) | Road traffic anomaly detection method using non-isometric time/space division | |
| CN113361665B (en) | Highland mountain tourism safety risk early warning method based on reinforcement learning | |
| CN112949999A (en) | High-speed traffic accident risk early warning method based on Bayesian deep learning | |
| CN103745089A (en) | Multi-dimensional public transport operation index evaluation method | |
| CN103746750A (en) | Radio monitoring electromagnetic situation prediction system | |
| CN112561304A (en) | Evaluation method of urban conventional public transport network | |
| CN105740643A (en) | Self-adaptive PM<2.5>concentration speculating method based on city region grid | |
| CN115774953B (en) | Pollution space-time risk supervision and evaluation system and method based on data processing | |
| CN103366224B (en) | Passenger demand prediction system and method based on public transport network | |
| CN113506013B (en) | Multi-source data-based comprehensive benefit evaluation method for medium-traffic volume public transportation system | |
| CN114093168A (en) | Urban road traffic running state evaluation method based on toughness view angle | |
| CN113537626B (en) | Method for predicting neural network combined time sequence by aggregating information difference | |
| CN107067129A (en) | Way and structures risk case possibility acquisition methods and system based on grid | |
| CN105205565A (en) | Controller workload prediction method and system based on multiple regression model | |
| Jiao et al. | Resilience assessment of metro stations against rainstorm disaster based on cloud model: a case study in Chongqing, China | |
| CN117558124A (en) | Channel running state deduction prediction method based on multi-source information depth fusion | |
| CN103077312B (en) | A kind of city rail traffic route builds the automatic judging method of sequential | |
| CN116935643A (en) | Traffic management method, device, equipment and storage medium |
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 |