CN111581325B - K-means station area division method based on space-time influence distance - Google Patents
K-means station area division method based on space-time influence distance Download PDFInfo
- Publication number
- CN111581325B CN111581325B CN202010668005.7A CN202010668005A CN111581325B CN 111581325 B CN111581325 B CN 111581325B CN 202010668005 A CN202010668005 A CN 202010668005A CN 111581325 B CN111581325 B CN 111581325B
- Authority
- CN
- China
- Prior art keywords
- station
- sites
- cluster
- site
- center point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000003064 k means clustering Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Remote Sensing (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a K-means station area division method based on space-time influence distance, S100 obtains the travel data of a certain urban rail transit, and preprocesses the data; s200 all the sites xiAs a clustering data set omega, randomly selecting a site as an initial clustering center, and then sequentially selecting K clustering centers; s300, calculating the space-time influence distance from each station to each clustering center point, and dividing the stations into the classes of the clustering centers when the space-time influence distance from the station to which clustering center point is the smallest; s400, aiming at each category after the re-division, newly calculating the clustering center of the category; s500, repeating S300 and S400 until the position of the clustering center of each category is not changed any more, and outputting the clustering center and all the sites in each category. The classification method not only considers the spatial positions among the sites, but also considers the actual positions among the sites, so that the classification is more accurate.
Description
Technical Field
The invention relates to a method for predicting rail passenger flow, in particular to a method for dividing K-means station areas based on space-time influence distances.
Background
At present, under the large environment of vigorously developing urban rail transit all over the world, the proportion of passenger capacity occupied by the urban rail transit in urban public transit is larger and larger. The increase of urban rail transit passenger flow brings great challenges for new development opportunities of urban rail transit bands.
The networking complexity of urban rail transit is continuously increased, the future traffic trend analysis is more and more emphasized, and based on the analysis result of passenger flow prediction, a traffic operation plan can be made, and early warning of congestion or abnormity is made to improve the operation efficiency and the service quality of rail transit, so that the urban rail transit becomes one of key technologies of an Intelligent Transportation System (ITS). However, since passenger flow is affected by various factors such as weather, holidays, geographical positions and the like, high nonlinearity and uncertainty bring huge challenges to passenger flow prediction. In order to be able to orchestrate the overall planning of the track, better regional traffic prediction needs to be achieved. The city regional passenger flow measurement needs a scientific and effective city site regional classification method to ensure the effectiveness of prediction.
Clustering is an important algorithm in unsupervised learning, and clustering analysis is performed by dividing an original sample into a plurality of independent clusters which are not wanted to be intersected, wherein the cluster samples have the same or similar characteristics. It is also said that "things-by-things and people-by-groups" in the natural science and social science of the big data era, there are a lot of data classification problems, and the samples are classified by the clustering according to the similarity of the samples, and the samples in the same cluster have more similarity than the samples not in the same cluster.
Complex wire grids require reasonable and scientific operation planning, and regional OD passenger flow prediction can often provide data support for wire grid site placement, thus showing the importance and necessity of regional OD prediction. However, the OD passenger flow prediction of a plurality of areas is area division finished by GPS geographical position clustering by directly using a clustering algorithm similar to a K-means algorithm. However, the K-means algorithm using only geographic distance as a clustering classification standard is very limited to the classification of urban rail transit stations. Firstly, the track distance and the geographic distance have larger deviation under most conditions, and secondly, in cities like Chongqing, the complicated and disordered urban topography and geomorphology can bring great trouble to area division.
Disclosure of Invention
Aiming at the problems in the prior art, the technical problems to be solved by the invention are as follows: a K-means site area division algorithm based on space-time influence distance is provided to better overcome the defects of the original K-means algorithm and more scientifically and reasonably finish the urban site area division.
In order to solve the technical problems, the invention adopts the following technical scheme: a K-means station area division method based on space-time influence distance comprises the following steps:
s100: acquiring the trip data of a certain urban rail transit, and preprocessing the data;
s200: all sites xiAs a cluster data set omega, randomly selecting a site from the cluster data set omega as an initial cluster center C1Then, K clustering centers are sequentially selected as a clustering center point set Θ, where Θ is equal to{c1,c2,c3…ct…ck}；
S300: aiming at each station in the cluster data set omega, calculating the space-time influence distance d from each station to each cluster central point, and determining the station xiThe minimum spatio-temporal impact distance to which cluster center point is, the site x is determinediDividing into the cluster center class;
s400: for each category i after being re-divided in S300, newly calculating the clustering center C of the categoryi；
S500: and repeating S300 and S400 until the position of the clustering center of each category is not changed any more, finishing the division of the regional sites, and outputting the clustering centers and all the sites in each category.
As an improvement, in S100, preprocessing is performed on the data:
the following original values are obtained through cleaning the acquired travel data of the urban rail transit:
wherein, TaTo average the journey time between neighbouring sites, TbAveraging the total journey time of each route, n is the number of adjacent station pairs, m is the total number of routes, tiFor the average journey time between each neighbouring site, txThe global average journey time for each route.
As an improvement, the process of constructing the clustered center point set Θ in S200 is as follows:
let Ω ═ x1,x2,x3……}；
Set site xiWith the initial cluster center point C1Expressed as D (x); then site x is recalculatediProbability of being selected as next cluster center point
Where k is the coordinate parameter dimension, xikAnd cjkRespectively represent sites xiAnd cluster center point C1The kth-dimension data of (1);
according to each site xiIs/are as follows
Determining the area of the wheel disc of each station, and selecting a cluster center point by using a wheel disc method.
As an improvement, the specific method for calculating the spatio-temporal influence distance from each station to each cluster center point in S300 is as follows:
the spatiotemporal impact distance between two sites is represented by the normalized result of the average journey time between sites and the euclidean distance between sites:
Db＝max{D1,2,D1,3,D1,4……} (3-3)；
Da＝min{D1,2,D1,3,D1,4……} (3-4)；
wherein, Ti,jAnd Di,jRespectively representing the journey time and Euclidean distance between two stations, DbAnd DaRespectively the minimum Euclidean distance and the maximum Euclidean distance, T, between all the sitesbAnd TaRespectively, the average minimum journey time between all stationsAnd average route maximum journey time, site xiThe minimum spatio-temporal impact distance to which cluster center point is, the site x is determinediAnd dividing into classes corresponding to the cluster centers.
As an improvement, in S400, for each category i obtained by re-dividing S300, the cluster center C of the category is newly calculatediThe method comprises the following steps:
wherein, | m | represents the total number of sites of the cluster center point, and x is CmStation(s).
Compared with the prior art, the invention has at least the following advantages:
according to the method for dividing the station area, the space-time influence distance of the station is determined by combining the Euclidean distance from the station to the clustering center and the travel time, and then the space-time influence distance is used for classifying the station. The method has more guiding and reference significance for site flow evaluation and site planning in the later period.
Drawings
FIG. 1 shows clustering results of the K-means site region partitioning method based on spatio-temporal influence distances.
FIG. 2 is a K-means site area division diagram based on spatio-temporal influence distances.
FIG. 3 is a K-means site area division diagram based on traditional geographic distance.
Detailed Description
The present invention is described in further detail below.
A K-means station area division method based on space-time influence distance comprises the following steps:
s100: and acquiring the trip data of a certain urban rail transit, and preprocessing the data.
Specifically, the following original values are obtained through cleaning the acquired urban rail transit trip data:
wherein, TaTo average the journey time between neighbouring sites, TbAveraging the total journey time of each route, n is the number of adjacent station pairs, m is the total number of routes, tiFor the average journey time between each neighbouring site, txThe global average journey time for each route.
S200: all sites xiAs a cluster data set omega, randomly selecting a site from the cluster data set omega as an initial cluster center C1Then, K cluster centers are sequentially selected as a cluster center point set Θ, and Θ ═ c1,c2,c3…ct…ck}。
The process of constructing the clustered center point set Θ in S200 is as follows:
let Ω ═ x1,x2,x3……}；
Set site xiWith the initial cluster center point C1Expressed as D (x); then site x is recalculatediProbability of being selected as next cluster center point
Where k is the coordinate parameter dimension, xikAnd cjkRespectively represent sites xiAnd cluster center point C1The kth-dimension data of (1);
according to each site xiIs/are as follows
Determining the area of the wheel disc of each station, and selecting a cluster center point by using a wheel disc method.
S300: aiming at each station in the cluster data set omega, calculating the space-time influence distance d from each station to each cluster central point, and determining the station xiThe minimum spatio-temporal impact distance to which cluster center point is, the site x is determinediInto a class of the cluster center.
The specific method for calculating the space-time influence distance from each station to each cluster center point in the step S300 is as follows:
the spatiotemporal impact distance between two sites is represented by the normalized result of the average journey time between sites and the euclidean distance between sites:
Db＝max{D1,2,D1,3,D1,4……} (3-3)；
Da＝min{D1,2,D1,3,D1,4……} (3-4)；
wherein, Ti,jAnd Di,jRespectively representing the journey time and Euclidean distance between two stations, DbAnd DaRespectively the minimum Euclidean distance and the maximum Euclidean distance, T, between all the sitesbAnd TaAverage minimum journey time and average route maximum journey time between all stations, station xiThe minimum spatio-temporal impact distance to which cluster center point is, the site x is determinediAnd dividing into classes corresponding to the cluster centers.
S400: for each category i after being re-divided in S300, newly calculating the clustering center C of the categoryi。
For each category i after being re-divided in S300, newly calculating the clustering center C of the categoryiThe method comprises the following steps:
wherein, | m | represents the total number of sites of the cluster center point, and x is CmStation(s).
S500: and repeating S300 and S400 until the position of the clustering center of each category is not changed any more, completing the division of the regional sites, and outputting the clustering centers and all the sites of each category.
And (3) experimental verification:
in the experiment, the Chongqing city is taken as an example, and track traffic data in Chongqing city areas are taken as an experiment original data set. All stations of track traffic in Chongqing cities are scientifically classified by adopting a K-means clustering algorithm based on space-time influence distances, so that OD passenger flow analysis and prediction of track traffic areas in Chongqing cities and track traffic planning in Chongqing cities are facilitated.
The experimental results clearly show that the optimized clustering algorithm has stronger environmental adaptability and good dividing effect, and avoids the misclassification condition that the geographic position is close but the track distance is far.
The invention adopts a division mode of combining journey time and space GPS. The journey time data is derived from statistics of historical passenger flow journey times. The statistics of regional OD traffic are also based on historical OD traffic data at the site level. Table 1 includes several fields for card ID, date, origination site, arrival site, origination time, and arrival time. The experimental data time range is data from 2017 to 2018.
TABLE 1
Journey time data as shown in table 2, the attributes are in turn start site, arrival site, and average journey time.
TABLE 2
The invention uses GPS positioning data of the station when spatial clustering is carried out on the track station, and the attributes are as follows in sequence: card id, site number, site name, longitude and latitude, detailed in table 3.
TABLE 3
Analysis of the data in table 1, table 2 and table 3 gave:
FIG. 1 is a graph of the experimental results of the K-means clustering algorithm based on spatio-temporal influence distance, from which two points can be clearly seen: firstly, the influence of the geographic factors of clustering division is still obvious, the geographic position distance of each clustered station in the division result is relatively close, and the clustering condition with large geographic difference for meeting the influence of time dimension can not occur; secondly, the distribution of the clustering stations does not depend on the straight line geographic distance completely, and the clustering stations are all located at the similar positions of the rail transit lines from the view point of the distribution of the stations.
FIG. 2 shows the track traffic division result of Chongqing city by the K-means station area division method based on the space-time influence distance, wherein the maximum value of the cluster average minimum station spacing set is 9.9 stations, which is smaller than 10.5 stations of the traditional K-means, which shows that the K-means station area division method based on the space-time influence distance has better performance on the clustering effect of the track stations. The division of all the station areas is reasonable, scientific and effective.
FIG. 3 shows the track traffic division result of Chongqing city by the station area division method of the original K-means clustering algorithm, wherein the maximum value of the clustering average minimum station spacing set is 10.5 stations. Not all the station areas are scientifically and effectively divided, for example, it is unreasonable to cluster the YueNei station and the Boque station into the same area, and 18 rail traffic journeys are arranged between the two stations, and although the rail traffic journeys can be divided into a group in geographic distance, the rail distance between the two places is far larger than the straight line distance.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (2)
1. A K-means station area division method based on space-time influence distance is characterized by comprising the following steps:
s100: acquiring the trip data of a certain urban rail transit, and preprocessing the data;
and in the step S100, preprocessing data:
the following original values are obtained through cleaning the acquired travel data of the urban rail transit:
wherein, TaTo average the journey time between neighbouring sites, TbAveraging the total journey time of each route, n is the number of adjacent station pairs, m is the total number of routes, tiFor the average journey time between each neighbouring site, txA global average journey time for each route;
s200: will be describedWith site xiAs a cluster data set omega, randomly selecting a site from the cluster data set omega as an initial cluster center C1Then, K cluster centers are sequentially selected as a cluster center point set Θ, and Θ ═ c1，c2，c3…ct…ck}；
The process of constructing the clustered center point set Θ in S200 is as follows:
let Ω ═ x1，x2，x3……}；
Set site xiWith the initial cluster center point C1Expressed as D (x); then site x is recalculatediProbability of being selected as next cluster center point
Where k is the coordinate parameter dimension, xikAnd cjkRespectively represent sites xiAnd cluster center point CjThe kth-dimension data of (1);
according to each site xiIs/are as follows
Determining the area of the wheel disc of each station, and selecting a clustering center point by using a wheel disc method;
s300: aiming at each station in the cluster data set omega, calculating the space-time influence distance d from each station to each cluster central point, and determining the station xiThe minimum spatio-temporal impact distance to which cluster center point is, the site x is determinediDividing into the cluster center class;
the specific method for calculating the space-time influence distance from each station to each cluster center point in the step S300 is as follows:
the spatiotemporal impact distance between two sites is represented by the normalized result of the average journey time between sites and the euclidean distance between sites:
Db＝max{D1，2，D1，3，D1，4……}
Da＝min{D1，2，D1，3，D1，4……}
wherein, Ti，jAnd Di，jRespectively representing the journey time and Euclidean distance between two stations, DbAnd DaRespectively the minimum Euclidean distance and the maximum Euclidean distance, T, between all the sitesbAnd TaAverage minimum journey time and average route maximum journey time between all stations, station xiThe minimum spatio-temporal impact distance to which cluster center point is, the site x is determinediDividing the cluster into classes corresponding to the cluster centers;
s400: for each category i after being re-divided in S300, newly calculating the clustering center C of the categoryi；
S500: and repeating S300 and S400 until the position of the clustering center of each category is not changed any more, finishing the division of the regional sites, and outputting the clustering centers and all the sites in each category.
2. The method for partitioning site area by K-means based on spatio-temporal influence distance as claimed in claim 1, wherein for each class i re-partitioned in S300 in S400, the clustering center C of the class is newly calculatediThe method comprises the following steps:
wherein, | m | represents the total number of sites of the cluster center point, and x is CmStation(s).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010668005.7A CN111581325B (en) | 2020-07-13 | 2020-07-13 | K-means station area division method based on space-time influence distance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010668005.7A CN111581325B (en) | 2020-07-13 | 2020-07-13 | K-means station area division method based on space-time influence distance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111581325A CN111581325A (en) | 2020-08-25 |
| CN111581325B true CN111581325B (en) | 2021-02-02 |
Family
ID=72125784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010668005.7A Active CN111581325B (en) | 2020-07-13 | 2020-07-13 | K-means station area division method based on space-time influence distance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111581325B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112963160B (en) * | 2021-02-10 | 2024-06-11 | 上海市隧道工程轨道交通设计研究院 | Method for identifying and determining stratum characteristics by using shield real-time tunneling parameters |
| CN113705623B (en) * | 2021-08-06 | 2024-07-19 | 深圳须弥云图空间科技有限公司 | Method and device for classifying rail transit stations |
| CN113887916A (en) * | 2021-09-27 | 2022-01-04 | 国网山西省电力公司电力科学研究院 | Dynamic quantitative evaluation method and system for line loss of power distribution network |
| CN115186049B (en) * | 2022-09-06 | 2023-02-03 | 深圳市城市交通规划设计研究中心股份有限公司 | Intelligent bus alternative station site selection method, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110389982A (en) * | 2019-07-25 | 2019-10-29 | 东北师范大学 | A kind of spatiotemporal mode visual analysis system and method based on air quality data |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2927849A1 (en) * | 2014-04-02 | 2015-10-07 | Deutsche Lufthansa AG | Method and computer program product for analysis of flight passenger ticket bulk data sets |
| CN107103392A (en) * | 2017-05-24 | 2017-08-29 | 北京航空航天大学 | A kind of identification of bus passenger flow influence factor and Forecasting Methodology based on space-time Geographical Weighted Regression |
| CN109034474A (en) * | 2018-07-26 | 2018-12-18 | 北京航空航天大学 | It is a kind of to be clustered and regression analysis and system based on the subway station of POI data and passenger flow data |
| CN110276474A (en) * | 2019-05-22 | 2019-09-24 | 南京理工大学 | A kind of track traffic station passenger flow forecasting in short-term |
-
2020
- 2020-07-13 CN CN202010668005.7A patent/CN111581325B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110389982A (en) * | 2019-07-25 | 2019-10-29 | 东北师范大学 | A kind of spatiotemporal mode visual analysis system and method based on air quality data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111581325A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111581325B (en) | K-means station area division method based on space-time influence distance | |
| CN110298500B (en) | Urban traffic track data set generation method based on taxi data and urban road network | |
| CN104318324A (en) | Taxi GPS (Global Positioning System) record based airport bus station and path planning method | |
| CN109686090B (en) | Virtual traffic flow calculation method based on multi-source data fusion | |
| CN104025075A (en) | Method and system for fleet navigation, dispatching and multi-vehicle, multi-destination routing | |
| CN111814596B (en) | Automatic city function partitioning method for fusing remote sensing image and taxi track | |
| CN110990661B (en) | Region of interest access extraction method based on road network constraint and density clustering | |
| CN110472999B (en) | Passenger flow mode analysis method and device based on subway and shared bicycle data | |
| CN114363842B (en) | Bus passenger departure station prediction method and device based on mobile phone signaling data | |
| Qu et al. | Location optimization for urban taxi stands based on taxi GPS trajectory big data | |
| CN112036757A (en) | Parking transfer parking lot site selection method based on mobile phone signaling and floating car data | |
| CN104024801A (en) | Method and system for navigation using bounded geograhic regions | |
| CN116542709A (en) | Electric vehicle charging station planning analysis method based on traffic situation awareness | |
| Chen et al. | An analysis of movement patterns between zones using taxi GPS data | |
| CN116796904A (en) | Method, system, electronic equipment and medium for predicting new line passenger flow of rail transit | |
| CN114723596A (en) | Urban functional area identification method based on multi-source traffic travel data and theme model | |
| Vuurstaek et al. | GTFS bus stop mapping to the OSM network | |
| CN114186146A (en) | Network appointment service network site selection method and system with capacity limitation | |
| CN111860699B (en) | Commuting trip mode identification method based on fluctuation rate | |
| CN115759660A (en) | Scheduling method, device, equipment and medium for unmanned vehicle | |
| CN110610446A (en) | County town classification method based on two-step clustering thought | |
| Yue et al. | Classification and determinants of high-speed rail stations using multi-source data: A case study in Jiangsu Province, China | |
| CN115687551A (en) | Method for determining walking service range of rail transit station | |
| CN108764518A (en) | A kind of traffic resource dynamic optimization method based on Internet of Things big data | |
| CN110458309B (en) | Network about splicing station point location method based on actual road network environment |
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 |