CN110798802A - Method for extracting shared bicycle skeleton network - Google Patents

Method for extracting shared bicycle skeleton network Download PDF

Info

Publication number
CN110798802A
CN110798802A CN201911066648.8A CN201911066648A CN110798802A CN 110798802 A CN110798802 A CN 110798802A CN 201911066648 A CN201911066648 A CN 201911066648A CN 110798802 A CN110798802 A CN 110798802A
Authority
CN
China
Prior art keywords
network
nodes
shared bicycle
backbone
node
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201911066648.8A
Other languages
Chinese (zh)
Other versions
CN110798802B (en
Inventor
袁汉宁
吕媛媛
王树良
耿晶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN201911066648.8A priority Critical patent/CN110798802B/en
Publication of CN110798802A publication Critical patent/CN110798802A/en
Application granted granted Critical
Publication of CN110798802B publication Critical patent/CN110798802B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
    • H04W40/32—Connectivity information management, e.g. connectivity discovery or connectivity update for defining a routing cluster membership
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a shared bicycle skeleton network extraction method, which belongs to the technical field of computer application and can be used for extracting a backbone network from a network consisting of network nodes with spatial position characteristics. The method comprises the following steps: a shared bicycle network is constructed. Calculating the significance of all edges in the shared bicycle network, and keeping the edges with the significance larger than zero as the edges of the backbone network. The topological potential of all nodes in the shared bicycle network is calculated. And carrying out space density clustering on all nodes in the shared bicycle network according to the geographic positions of the nodes to obtain a riding area cluster. And for each riding area cluster, performing descending sorting on the network nodes in the current riding area cluster according to the value of the topological potential, and selecting the nodes with the preset number after the descending sorting to form the backbone core nodes of the current riding area cluster. And merging the backbone core nodes of all the riding area clusters, and connecting the backbone core nodes by using the edges of the backbone network to form the backbone network.

Description

Method for extracting shared bicycle skeleton network
Technical Field
The invention relates to the technical field of computer application, in particular to a shared bicycle skeleton network extraction method.
Background
With the large-scale development and progress of the society of today, more and more complex systems can be abstracted into complex networks for research, such as transportation systems. The entities are regarded as nodes, the relations among the entities are called edges, and the construction of the edges can be formed according to a certain rule or naturally, so that many complex systems in the real world can be regarded as complex networks and can be represented by graphs. The complex network has a rapid growth trend in terms of quantity, scale, propagation and the like, and the large amount of data generally leads to high complexity of the network structure, so that the extraction of the skeleton network is the most reasonable selection and future development trend.
Building backbone networks based on traffic networks is a relatively new field, and in recent years it has been most popular to share bicycle communities, the reasons behind this popularity being the many advantages of public bicycles: social activities, health benefits, green environmental protection, timely supplement of urban public transport and the like. Increasing data has led to an increasing complexity of connections between bicycle pile points, in which case the development of shared bicycle networks, route planning and rental point distribution are urgent requirements of today's society.
In the current research, all backbone network extraction methods are developed in networks without spatial location information, such as protein networks and social networks, and these backbone network extraction methods generally use topological characteristics of the networks, weighted edges of the networks are filtered, or minimum spanning trees are constructed to construct the backbone networks. At present, most backbone network extraction methods are designed almost based on the edges with weights of the network, and the edges with smaller weights in the network are filtered to delete nodes at two ends of unimportant connecting edges to construct a skeleton network. Some methods construct a backbone network by extracting important nodes, but usually ignore the positions of the nodes and ignore the geographical position distribution of the whole network. For the bicycle network, it is considered that selecting a proper node is better than filtering the connecting edge of the proper node, and a backbone network extracted by using a current existing algorithm is difficult to control the position distribution of the node, sometimes the nodes of the backbone network are uniformly distributed, sometimes the backbone network is centrally distributed, and the unstable performance of the application of the backbone network extraction methods to a space network is also considered.
At present, no technical scheme for extracting a backbone network of a network composed of network nodes with spatial position characteristics exists.
Disclosure of Invention
In view of this, the present invention provides a method for extracting a shared bicycle skeleton network, which can extract a skeleton network from a network composed of network nodes having spatial location characteristics.
In order to achieve the purpose, the technical scheme of the invention comprises the following steps:
and constructing a shared bicycle network, taking bicycle rental points as network nodes, and taking riding records between the two bicycle rental points as edges.
Calculating the significance of all edges in the shared bicycle network, and keeping the edges with the significance larger than zero as the edges of the backbone network.
The topological potential of all nodes in the shared bicycle network is calculated.
And carrying out space density clustering on all nodes in the shared bicycle network according to the geographic positions of the nodes to obtain a riding area cluster.
For each riding area cluster, selecting backbone core nodes according to the following modes: and performing descending sorting on the network nodes in the current riding area cluster according to the value of the topological potential, and selecting the nodes with the preset number after the descending sorting to form the backbone core nodes of the current riding area cluster.
And merging the backbone core nodes of all the riding area clusters, and connecting the backbone core nodes by using the edges of the backbone network to form the backbone network.
Further, the topological potential of all nodes in the shared bicycle network is calculated, wherein the normalized value of the k-shell of the node is adopted to replace the quality attribute in the topological potential.
Further, calculating the topology potential of all nodes in the shared bicycle network, specifically:
the network topology of the constructed shared bicycle network is G ═ V, E,
wherein V ═ { V ═ V1,...,vnIs the set of nodes in the shared bicycle network, and E is the set of edges in the shared bicycle network.
Any one of the nodes viTopological potential of epsilon V
Figure BDA0002259577240000031
Comprises the following steps:
Figure BDA0002259577240000032
wherein m isiThe node v is represented by more than or equal to 0iThe quality attribute of (2).
dijRepresentative node viTo node vjσ is the impact factor.
Further, the influence factor σ is solved by:
solving the potential entropy H of the bicycle network as
Figure BDA0002259577240000033
Figure BDA0002259577240000034
Is a node viTopological potential of (d); z is a normalization factor used to constrain the topological potential of all nodes to [0,1]An interval; h is a function of the influence factor sigma, and the value of sigma corresponding to the H minimum value is used as the solving result of the influence factor sigma.
Has the advantages that:
1. the invention provides a novel backbone network extraction method for a bicycle network with spatial position information, which comprises the steps of filtering network edges and extracting important nodes, meanwhile, the position information of the nodes is fully considered, a bicycle riding hot spot area cluster is firstly found by utilizing spatial density clustering, the important nodes are respectively extracted from different hot spot area clusters, and a backbone network is further constructed. The method can be applied to a space network data set, and the position distribution of the nodes is comprehensively considered to extract the backbone network, so that the backbone network and the original network keep nearly consistent structural distribution.
2. And a topological potential sorting algorithm is improved based on k-shell. The K-shell decomposition is to recursively strip nodes with the degree less than or equal to K in the network and endow the stripped nodes with the K-shell values at the time to form the respective K of the nodessThe value is obtained. The k-shell decomposition is an algorithm different from other various classical node importance evaluation methods, the method measures the importance degree of nodes according to the structure of the nodes in a network, and has the advantages that the time complexity is very low.
Drawings
Fig. 1 is a flowchart of a method for extracting a shared bicycle frame network according to an embodiment of the present invention.
Detailed Description
The invention is described in detail below by way of example with reference to the accompanying drawings.
The invention provides a shared bicycle skeleton network extraction method, the flow of which is shown in figure 1, and the method comprises the following steps:
s1 a shared bicycle network is constructed, bicycle rental points are used as network nodes, and riding records between the two bicycle rental points are used as edges. The constructed shared bicycle network can be constructed according to the existing bicycle riding data, for example, bicycle riding records in a metribuke bicycle data set or a Niceride bicycle data set can be adopted. The bicycle riding record comprises the rental point addresses of the rented bicycles and the returned bicycles, and the rented bicycles and the returned bicycles time.
S2, calculating the significance of all edges in the shared bicycle network, and keeping the edges with the significance larger than zero as the edges of the backbone network. The significance of the edge can be calculated by adopting the existing edge significance calculation method.
S3, calculating the topological potentials of all nodes in the shared bicycle network; in the invention, the topological potentials of all the nodes in the shared bicycle network are calculated, wherein the normalized value of the k-shell of the node is adopted to replace the quality attribute in the topological potentials.
The specific principle is as follows:
the network topology of the constructed shared bicycle network is G ═ V, E;
wherein V ═ { V ═ V1,...,vnIs the set of nodes in the shared bicycle network, and E is the set of edges in the shared bicycle network.
Any one of the nodes viTopological potential of epsilon V
Figure BDA0002259577240000051
Comprises the following steps:
wherein m isiThe node v is represented by more than or equal to 0iThe quality attribute of (2); dijRepresentative node viTo node vjσ is the impact factor.
The influence factor σ is solved by the following method:
solving the potential entropy H of the bicycle network as
Figure BDA0002259577240000053
Figure BDA0002259577240000054
Is a node viTopological potential of (d); z is a normalization factor used to constrain the topological potential of all nodes to [0,1]An interval; h is a function of the influence factor sigma, and the value of sigma corresponding to the H minimum value is taken as the valueAnd solving the influence factor sigma.
The K-shell decomposition is to recursively strip nodes with the degree less than or equal to K in the network and endow the stripped nodes with the K-shell values at the time to form respective KsThe value is obtained. The k-shell decomposition is an algorithm different from other various classical node importance evaluation methods, measures the importance degree of nodes according to the structure of the nodes in a network, and has the advantage of very low time complexity. Therefore, the quality of a node in the topological potential field is defined as:
mi＝KSv
KSvis the normalized value of the k-shell of the node. Thus, K of a nodesThe larger the value, the node quality miThe larger.
S4, performing space density clustering on all nodes in the bicycle sharing network according to the geographic positions of the nodes to obtain riding area clusters. The spatial density clustering method can adopt the existing conventional method, for example, the DBSCAN algorithm is a classic density-based spatial clustering analysis algorithm. This algorithm was first proposed in 1996 and has been currently used in a number of areas.
The invention mainly aims to select top level backbone nodes from different riding area clusters according to the density clustering result. The shape and the number of the riding area clusters in the city are related to the topographic distribution of the city, the shape is often irregular, and the DBSCAN algorithm is adopted to find the riding area clusters in the city in consideration that the density clustering algorithm such as DBSCAN can effectively find the clusters in any shape and the number of the clusters does not need to be specified.
S5, for each riding area cluster, selecting backbone core nodes as follows: the network nodes in the current riding area cluster are sorted in a descending order according to the value of the topological potential, and the nodes with the preset number after the descending order are selected to form the backbone core nodes of the current riding area cluster;
and S6 merging the backbone core nodes of all riding area clusters, and connecting the backbone core nodes by using the edges of the backbone network to form the backbone network.
For the extracted skeleton network, the following three network interaction traffic evaluations are carried out:
1. interactive traffic from a node perspective
Defining Node Flow in-degree (Node Flow in-degree): a certain node V in the traffic networki(rental Point) traffic in-degree
Figure BDA0002259577240000061
Can be pointed to the node V by starting from other nodesiIs expressed by the number of all routes, i.e. the number of cars returned at the rental lot, which is defined as
Figure BDA0002259577240000062
Where N is the set of nodes in the network, node VjIs node ViOf the neighboring node.
Defining Node Flow out-degree (Node Flow out-degree): a certain node V in the traffic networki(rental Point) traffic out-of-line
Figure BDA0002259577240000071
Can be controlled by a slave node ViThe number of all paths from which points to other neighboring nodes, i.e. the number of borrowers at the rental point, is defined as
Figure BDA0002259577240000072
Where N is the set of nodes in the network, node VjIs node ViOf the neighboring node.
Define Node Flow metric (Node Flow degree): a certain node V in the traffic networki(rental Point) traffic metrics
Figure BDA0002259577240000073
Is node ViThe sum of the flow rate, the degree of entry, and the flow rate, which is defined as:
the flow rate considered from the point of view shows that the higher the frequency with which the node is used (by or returned) by the user, the higher the value thereof, indicating the greater the demand of the user on the bicycle station. Therefore, in a real transportation network, if the rental point is reserved, great convenience is brought to the user for traveling, and the possibility that the user chooses to ride is high. So from the traffic point of view of the node, the interactive traffic Flow of the whole networkVComprises the following steps:
Figure BDA0002259577240000075
where N is the set of all nodes in the network,
Figure BDA0002259577240000076
is node ViThe node flow metric of (2).
So the network interaction traffic Skeleton (Flow) reserved by the backbone network considered from the node point of viewV) Percentage of network interaction traffic F occupying the original networkVCan be defined as:
wherein Skeleton (Flow)V) Representing interaction traffic based on a skeleton network under node view, origin (Flow)V) Representing the interactive traffic of the original network under the node view.
2. Interactive traffic from connectivity angle considerations
The network interactive traffic considered from the node perspective only considers the connection of a plurality of nodes and does not consider the problem of the connection times of two nodes, so the concept of the network interactive traffic considered from the connection degree is introduced in the patent again.
Define Edge Flow metric (Edge Flow metric): in a complex network, wijIs a certain edge eijThe edge weight value of (2) is used for expressing the edge flow degree of the edge
Figure BDA0002259577240000081
It is defined as:
Figure BDA0002259577240000082
in a real traffic network, the edge eijA route of borrowing and returning of a ride, w, representing a userijIndicating the frequency with which the route occurs.
It can be seen that the edge flow metric valueThe larger the route is, the more frequently the user selects to ride, the more likely the user will need to be, and the more likely the user will select to ride if the rental points at both ends of the route are reserved. Therefore, the network interaction traffic Folw considered from the connection angleECan be expressed as the sum of all edge weights in the network, which is defined as follows:
where E is the set of all connected edges in the network.
Figure BDA0002259577240000085
Is an edge eijIs measured.
So the network interaction traffic Skeleton (Flow) reserved by the backbone network considered from the point angleE) Percentage of network interaction traffic F occupying the original networkECan be defined as:
Figure BDA0002259577240000086
wherein Skeleton (Flow)E) Representing interaction traffic based on a skeleton network under a continuous view, origin (Flow)E) Representation is based on concatenationsAnd (4) interactive traffic of the original network under the side view.
3. Interactive traffic from gravity model considerations
Spatial interactions, created by ullman, are a particularly important method of assessing traffic for geographical transportation, i.e. estimating flow between different locations. Spatial interaction it is considered that there is a constant exchange of materials, energy, information, etc. between cities, between persons, etc. in time and space, and these exchanges belong to spatial interaction. Thus, in practice, spatial interactions are a wide variety of "flows" running between cities, person-to-person, location-to-location, such as population flows, cargo flows, financial flows, and so forth.
The Gravity Model (The Gravity Model), The most common Model in The spatial interaction method, is extracted from The distance attenuation origin and newtonian Gravity equations, i.e. The attraction between two locations is directly proportional to their mass properties and inversely proportional to their distance, as follows:
Figure BDA0002259577240000091
wherein, TijRepresenting the spatial interaction force, P, between node i and node jiIs the attribute importance of node i, PjIs the attribute importance of node j, DijWhich represents the distance between the positions of node i and node j, k is a gravity constant, and is typically chosen to be 1.
So the interactive Flow of the whole network considered from the gravity modelGCan be expressed as follows:
Figure BDA0002259577240000092
where N is the set of all nodes in the network, TijRepresents a node ViAnd node VjThe space between them interacts with each other.
So the network interaction traffic Skeleto reserved by the backbone network under the angle of the gravity modeln(FlowG) Percentage of network interaction traffic F occupying the original networkGCan be defined as:
Figure BDA0002259577240000101
wherein Skeleton (Flow)G) Representing interaction traffic, origin (Flow), based on a skeleton network under a view of a gravity modelG) And representing the interactive traffic of the original network based on the view point of the gravity model.
The extracted shared bicycle backbone network is evaluated according to the three flow models, so that the extracted backbone network is proved to have good effect on the aspect of space traffic flow.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (4)

1. A shared bicycle skeleton network extraction method is characterized by comprising the following steps:
constructing a shared bicycle network, taking bicycle rental points as network nodes, and taking riding records between the two bicycle rental points as edges;
calculating the significance of all edges in the shared bicycle network, and reserving edges with the significance greater than zero as edges of the backbone network;
calculating the topological potentials of all nodes in the shared bicycle network;
performing space density clustering on all nodes in the shared bicycle network according to the geographic positions of the nodes to obtain riding area clusters;
for each riding area cluster, selecting backbone core nodes according to the following modes: the network nodes in the current riding area cluster are sorted in a descending order according to the value of the topological potential, and the nodes with the preset number after the descending order are selected to form the backbone core nodes of the current riding area cluster;
and merging the backbone core nodes of all the riding area clusters, and connecting the backbone core nodes by using the edges of the backbone network to form the backbone network.
2. The method of claim 1, wherein the topological potential of all nodes in the shared bicycle network is calculated, wherein a normalized value of k-shell of a node is used in place of a quality attribute in the topological potential.
3. The method according to claim 1 or 2, characterized in that said calculating the topological potentials of all nodes in said shared bicycle network is in particular:
the network topology of the constructed shared bicycle network is G ═ V, E,
wherein V ═ { V ═ V1,...,vnIs the set of nodes in the shared bicycle network, E is the set of edges in the shared bicycle network;
any one of the nodes viTopological potential of epsilon V
Figure FDA0002259577230000011
Comprises the following steps:
wherein m isiThe node v is represented by more than or equal to 0iThe quality attribute of (2);
dijrepresentative node viTo node vjσ is the impact factor.
4. The method of claim 3, wherein the impact factor σ is solved by:
solving the potential entropy H of the bicycle network as
Figure FDA0002259577230000021
Figure FDA0002259577230000022
Is a node viTopological potential of (d); z is a normalization factor used to constrain the topological potential of all nodes to [0,1]An interval; h is a function of the influence factor sigma, and the value of sigma corresponding to the H minimum value is used as the solving result of the influence factor sigma.
CN201911066648.8A 2019-11-04 2019-11-04 Method for extracting shared bicycle skeleton network Active CN110798802B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911066648.8A CN110798802B (en) 2019-11-04 2019-11-04 Method for extracting shared bicycle skeleton network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911066648.8A CN110798802B (en) 2019-11-04 2019-11-04 Method for extracting shared bicycle skeleton network

Publications (2)

Publication Number Publication Date
CN110798802A true CN110798802A (en) 2020-02-14
CN110798802B CN110798802B (en) 2020-10-02

Family

ID=69442611

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911066648.8A Active CN110798802B (en) 2019-11-04 2019-11-04 Method for extracting shared bicycle skeleton network

Country Status (1)

Country Link
CN (1) CN110798802B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112287503A (en) * 2020-11-18 2021-01-29 成都星宇数云科技有限公司 Dynamic space network construction method for traffic demand prediction
CN113779318A (en) * 2021-08-09 2021-12-10 中国中医科学院中医药信息研究所 Backbone network extraction method and device, computer equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101383748A (en) * 2008-10-24 2009-03-11 北京航空航天大学 Community division method in complex network
CN103888541A (en) * 2014-04-01 2014-06-25 中国矿业大学 Method and system for discovering cells fused with topology potential and spectral clustering
CN105787143A (en) * 2014-12-25 2016-07-20 北京仿真中心 Method and system for adjusting structure of complex network based on backbone network
CN107301469A (en) * 2017-05-02 2017-10-27 广东电网有限责任公司惠州供电局 A kind of power network bulk transmission grid recognition methods
CN107776613A (en) * 2015-03-31 2018-03-09 江苏理工学院 Subway traffic flow optimization control system
CN109285386A (en) * 2018-11-02 2019-01-29 东莞理工学院 A kind of city vehicle-mounted net network data transmission mechanism towards intelligent transportation

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101383748A (en) * 2008-10-24 2009-03-11 北京航空航天大学 Community division method in complex network
CN103888541A (en) * 2014-04-01 2014-06-25 中国矿业大学 Method and system for discovering cells fused with topology potential and spectral clustering
CN105787143A (en) * 2014-12-25 2016-07-20 北京仿真中心 Method and system for adjusting structure of complex network based on backbone network
CN107776613A (en) * 2015-03-31 2018-03-09 江苏理工学院 Subway traffic flow optimization control system
CN107301469A (en) * 2017-05-02 2017-10-27 广东电网有限责任公司惠州供电局 A kind of power network bulk transmission grid recognition methods
CN109285386A (en) * 2018-11-02 2019-01-29 东莞理工学院 A kind of city vehicle-mounted net network data transmission mechanism towards intelligent transportation

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
HANNING YUAN ET.AL: "A Multi-Granularity Backbone Network Extraction Method Based on the Topology Potential", 《COMPLEXITY》 *
YU ZHANG ET.AL: "HotGraph：Efficient Asynchronous Processing for Real-Word Graphs", 《IEEE TRANSACTIONS ON COMPUTERS》 *
张泽聪: "抽取复杂网络中的骨干结构的方法研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 *
赵德: "多方式公共交通资源耦合效能评价", 《中国博士学位论文全文数据库 工程科技II辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112287503A (en) * 2020-11-18 2021-01-29 成都星宇数云科技有限公司 Dynamic space network construction method for traffic demand prediction
CN112287503B (en) * 2020-11-18 2023-04-07 成都星宇数云科技有限公司 Dynamic space network construction method for traffic demand prediction
CN113779318A (en) * 2021-08-09 2021-12-10 中国中医科学院中医药信息研究所 Backbone network extraction method and device, computer equipment and storage medium
CN113779318B (en) * 2021-08-09 2024-03-19 中国中医科学院中医药信息研究所 Backbone network extraction method, backbone network extraction device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN110798802B (en) 2020-10-02

Similar Documents

Publication Publication Date Title
CN107818534B (en) Human activity network region division method with space constraint
Bao et al. Spatial analysis of bikeshare ridership with smart card and POI data using geographically weighted regression method
Rovelli et al. From railways to greenways: A complex index for supporting policymaking and planning. A case study in Piedmont (Italy)
CN110798802B (en) Method for extracting shared bicycle skeleton network
CN109377048A (en) A kind of comprehensive traffic network hub node selection method
Pagliara et al. Choice set generation in spatial contexts: a review
CN112819659B (en) Tourist attraction development and evaluation method
CN105427001A (en) Optimal route of school bus of regional middle and primary school
CN107742169A (en) A kind of Urban Transit Network system constituting method and performance estimating method based on complex network
CN113806419B (en) Urban area function recognition model and recognition method based on space-time big data
Feng et al. An integrated model system and policy evaluation tool for maximizing mobility under environmental capacity constraints: A case study in Dalian City, China
CN115062873A (en) Traffic travel mode prediction method and device, storage medium and electronic device
CN115063276A (en) Urban ecological corridor space dividing method based on MSPA and circuit theory
Jaber et al. How do land use, built environment and transportation facilities affect bike-sharing trip destinations?
CN111008730B (en) Crowd concentration prediction model construction method and device based on urban space structure
CN111738527A (en) Urban traffic zone dividing method based on hot spot detection model
Faure et al. How to anticipate the level of activity of a sustainable collaborative network: The case of urban freight delivery through logistics platforms
Bonin et al. Evaluation of a transit-oriented development scenario in a medium-sized French city by simulation models
CN114462898A (en) Road planning management method and system based on geographic information
Kong et al. Charging pile siting recommendations via the fusion of points of interest and vehicle trajectories
Yang et al. GIS‐Based Analysis of Railway’s Origin/Destination Path‐Selecting Behavior
Dobrzyńska et al. Structure and dynamics of a public bike-sharing system. Case study of the public transport system in Białystok
Yu et al. Ranking spatial units with structural property and traffic distributions for uncovering spatial interaction patterns in a city
Consilvio et al. On exploring the potentialities of autonomous vehicles in urban spatial planning
Mirzahossein et al. Land-Use Modification Based on Transit-Oriented Development Adjacent to Historical Context (Case Study: Qazvin City)

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