CN102376025A - Method for simulating mobile phone data and evaluating urban road network traffic condition - Google Patents
Method for simulating mobile phone data and evaluating urban road network traffic condition Download PDFInfo
- Publication number
- CN102376025A CN102376025A CN2010102547715A CN201010254771A CN102376025A CN 102376025 A CN102376025 A CN 102376025A CN 2010102547715 A CN2010102547715 A CN 2010102547715A CN 201010254771 A CN201010254771 A CN 201010254771A CN 102376025 A CN102376025 A CN 102376025A
- Authority
- CN
- China
- Prior art keywords
- traffic
- agent
- base station
- highway section
- mobile phone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a method for simulating mobile phone data and evaluating an urban road network traffic condition. The method comprises the following steps of: constructing an Agent platform to generate the simulated mobile phone data, and storing into a database; and excavating a travel speed, and dynamically estimating the urban road network traffic condition by using a matlab neural network module. In the invention, the traffic condition is estimated on the basis of a mobile phone information technology; and the method has the advantages of not additionally increasing the cost and further improving the estimation accuracy, along with high information amount and the like.
Description
Technical field
The invention belongs to areas of information technology, relate to the method for utilizing data in mobile phone to carry out city road network and regional traffic state assessment.
Background technology
For a long time, the development of The development in society and economy and traffic exists the relation of mutually promoting with mutual restriction always.How letting congested in traffic problem no longer perplex social and economic development is the target that the people in the industry seek assiduously.Strengthen the embodiment of urban traffic control countermeasure and correlation technique thereof, to the potentiality of abundant excavation existing traffic system with improve traffic management level and have great importance.Simultaneously the surge of mobile phone recoverable amount has also produced a large amount of useful informations easily simultaneously bringing our communication per capita, therefore if can therefrom excavate the required information of traffic administration, will greatly promote transport informationization and intelligentized development.
Along with the evolution of mobile communications network to 3G, also constantly accelerate the developing steps of mobile location service countries in the world.Promptly developed mobile phone road information monitoring net in 2005 like U.S. traffic control department; Mobile phone with driver in going is collected information of road surface; In time send the traffic congestion alarm, upgrade electronic chart and traffic site information automatically, the text message that reflects road conditions is sent on the automobile instrument panel to the driver.Embodiment adopts mobile phone to obtain transport information, can not increase the cost of information acquisition equipment on the one hand, will replenish on the other hand and gather transport information, improves the accuracy that road net traffic state is estimated.But owing to relate to the problems such as confidentiality of cellphone subscriber's privacy; Embodiment to the monitoring of mobile phone road information, gathering technique is ripe not enough at present; Do not dialyse comprehensively, be still waiting a large amount of practices and carry out real example to aspects such as its technical characterictic, practicality and existing problems.
Summary of the invention
The object of the present invention is to provide a kind of analogue mobile phone data and assess the method for city road net traffic state, on the basis of the cost that does not increase information acquisition equipment, improve the accuracy that road net traffic state is estimated.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of analogue mobile phone data are also assessed the method for city road net traffic state, comprising:
(a) building the Agent platform produces the analogue mobile phone data and deposits in the database;
(b) travel speed is excavated processing, utilize the matlab neural network dynamic to estimate road net traffic state.
Aforesaid method, wherein:
Step (a) specifically comprises:
(a1) simulated experiment road network and design base station distribution;
The simulated experiment road network need obtain the topological diagram of actual road network, comprises the network description of highway section, crossing, and the traffic administration of current employing and control mode,
The design of base station distribution is to adopt the cellular regular hexagon base station cell of mobile network's method of operation that actual road network is carried out comprehensive covering, to obtain accurate data in mobile phone.
(a2) build experiment porch, programming realizes the mutual relationship between each Agent module.
Said Agent module is three:
Produce the Agent that the class of all Agent: CreatAgent is responsible for before the whole flat operation, producing a statistics non-intersection speed, and produced a vehicle Agent in per 2 seconds;
Statistics non-intersection speed Agent class: CalLinkNum whenever searched for once the traffic behavior in all highway sections at a distance from 10 seconds, deposited search time at that time, the traffic behavior in each highway section in database then;
Vehicle Agent class: CarAgent mutual through with road section information compute classes MinPath obtains the real-time speed of a motor vehicle and selects the path in real time, and every at a distance from clockwise database submission in fen information of this Agent once.
Step (b) specifically comprises:
(b1) dynamically obtain the highway section travel speed, from the highway section and the aspect of road network handle respectively, with the average stroke speed of a motor vehicle as the average basis of road section traffic volume state;
(b2) combine the road use attribute, with after the travel speed obfuscation with the unimpeded degree in the comprehensive average highway section of Fuzzy Inference, to obtaining the sub-district traffic behavior after the state weighted mean of highway section;
(b3) carrying out dynamic cell and divide, is minimum unit with the base station overlay area, and identical and geographic position base stations neighboring areal coverage is combined into the dynamic traffic sub-district with traffic behavior in a certain period.
In the step (b1) 20 seconds travel speed is on average become the travel speed in 5 minutes, define the threshold value of two travel speeds then, convert travel speed the traffic behavior of highway section to, and show through GIS.Utilization matlab three-layer neural network module is carried out dynamic estimation and prediction to cell status in the step (b3); A last period traffic state information draws the traffic state information in the current slot base station overlay area in Dynamic OD value in each base station overlay area of certain period that utilization gets according to cellphone information and this base station overlay area, thereby divides the dynamic traffic sub-district.
The inventive method relates generally to several important steps:
(1) preparation of basic data comprises:
A, simulated experiment road network
The simulated experiment road network need obtain the topological diagram of actual road network, relates to the network description of highway section, crossing, and the traffic administration of current employing and control mode, like one-way road, a taboo left side etc.
B, design base station distribution
The design of base station distribution is to adopt the cellular regular hexagon base station cell of mobile network's method of operation that actual road network is carried out comprehensive covering, to obtain accurate data in mobile phone.
(2) Agent behavior design
Agent be one have character such as independence, social ability, reactivity and dynamic role based on hardware or more common computer system based on software.Each Agent has its factum, the task that on behalf of intelligent body, behavior just to carry out.Three Agent among the present invention:
A, the class that produces all Agent: CreatAgent of startup are responsible for before the whole flat operation, producing the Agent of a statistics non-intersection speed, and vehicle Agent of generation in per 2 seconds;
Here; The reason that produced a vehicle Agent in per 2 seconds is set is the vehicle of thinking in the simulating reality as far as possible and get into the frequency of road network, and to be made as 2s be the peak load of considering computing machine, because frequency is high more; Then the vehicle agent in the road network is many more within a certain period of time, and the resource of consumption computing machine is big more.But if underfrequency then is difficult to form congestion in road network, so after taking into account two aspects, confirms to be spaced apart 2s.
B, statistics non-intersection speed Agent class: CalLinkNum whenever searched for once the traffic behavior in all highway sections at a distance from 10 seconds, deposited search time at that time, the traffic behavior in each highway section in database then;
High more good more on the statistical frequency theory to the highway section state; But consider that this value is relevant with the statistical frequency of highway section travel speed; In order on computing power and statistical accuracy, to reach balance; At this statistical interval is set at 10s, certainly under the situation that computing power allows, can be littler with what establish at interval.
Mutual through with road section information compute classes MinPath of C, vehicle Agent class: CarAgent obtains the real-time speed of a motor vehicle and selects the path in real time, and every at a distance from clockwise database submission in fen information of this Agent once.
Submitting agent information here to is the mode of the collection cellphone subscriber region in the simulation mobile communication in fact; The present frequency of mobile operator be 15 hours/inferior; But they consider from commercial, thus this frequency establish very low, technical complete can the realization searched once in 1 minute.It is higher that this value can be provided with, as 10 minutes once, or 30 minutes once, but should value be provided with high more, then the result of statistics gets over out of true, therefore considers the accuracy of operation result, is set to per minute here once.
(3) regularly carrying out road net traffic state estimates
A, in the analogue mobile phone information data generates platform; Every in adding up road network in 20 seconds the travel speed in all highway sections; Therefore the acquisition methods of highway section real-time traffic states is fairly simple, only needs the travel speed with 20 seconds on average to become the travel speed in 5 minutes, defines the threshold value of two travel speeds then; Convert travel speed the traffic behavior of highway section to, show through GIS at last.
High more good more on the statistical frequency theory to the highway section state, but consider the pressure of database and the pressure of computing machine, be made as 20s once at this, and in 20s, the variation of each road section traffic volume state is also little.Certainly under the situation that computing machine and database resource allow, this frequency configuration high more good more.
B, to obtaining the sub-district traffic behavior after the state weighted mean of highway section.Through cell status, get into the OD amount of this sub-district, the traffic behavior of next this sub-district of period of utilization matlab neural network prediction to the former moment.
Behind C, the traffic behavior in obtaining each base station overlay area, be minimum unit with the base station overlay area, with (5 minutes) interior traffic behavior of a certain period identical and on the geographic position base stations neighboring areal coverage be combined into a dynamic traffic sub-district.
Owing to adopted such scheme, the present invention to have following characteristics: the present invention is based on the cellphone information technology and carry out traffic behavior and estimate, have that quantity of information is abundant, not extra increase cost, further improve advantage such as accuracy of estimation.The present invention utilizes Agent simulation generation data in mobile phone to carry out the estimation of road net traffic state, and shows estimated result through GIS.Adopt this appraisal procedure obtained service condition satisfied, simple easily, obtain result's effect accurately.
Description of drawings
Fig. 1 is the Agent plateform system structural drawing of the embodiment of the invention.
Fig. 2 is the basic road network and the base station overlay area topological diagram of the embodiment of the invention.
Fig. 3 is the vehicle Agent driving trace synoptic diagram of the embodiment of the invention.
Fig. 4 be the embodiment of the invention divide dynamic traffic sub-district process flow diagram based on information data of mobile phone.
Fig. 5 is the RBF neural network structure of the embodiment of the invention.
Embodiment
This method is one and utilizes Agent analogue mobile phone data to regional road net traffic state estimation approach.Relate to and utilize that the Agent platform simulation produces data in mobile phone, the highway section road net traffic state is estimated and divide based on the road network dynamic cell of cellphone information.
1, utilize the Agent platform simulation to produce data in mobile phone
As shown in Figure 1, the concise and to the point course of work of this experiment porch is following:
(1) start the class that produces all Agent a: CreatAgent, it is administering all Agent except own in the platform.The task of this Agent is: the Agent (acquisition real-time traffic states) that produces a statistics non-intersection speed before the whole flat operation; Whenever produced a vehicle Agent at a distance from 2 seconds.The duration of CreatAgent: whole experiment;
(2) statistics non-intersection speed Agent class: CalLinkNum is every searches for once the traffic behavior in all highway sections at a distance from 10s, deposits search time at that time, the traffic behavior in each highway section in database then.The duration of CalLinkNum: whole experiment;
(3) vehicle Agent class: CarAgent mutual through with road section information compute classes: MinPath obtains the real-time speed of a motor vehicle and selects the path in real time, and every at a distance from clockwise database submission in fen information of this Agent once.The duration of CarAgent: generated to the arrival destination of going by CreatAgent;
All arrive the destination of oneself as all CarAgent after, this experiment finishes.
By learning in the simple description of front to Agent: Agent be one have character such as independence, social ability, reactivity and dynamic role based on hardware or more common computer system based on software.Each Agent has its factum, the task that on behalf of intelligent body, behavior just to carry out.Equally, three kinds of Agent in the present invention also have distinctive separately behavior, and are corresponding with some behavior based on corresponding individuality in the real world:
(1) Agent:CreatAgent of generation Agent
● produce the Agent of a statistics non-intersection speed
● whenever produced a car Agent at a distance from 2 seconds
● give starting point O and point of destination D when vehicle Agent is initial at random, and in its operational process, remain unchanged.
(2) statistics non-intersection speed Agent:
● every current travel speed that obtained each highway section at a distance from 20 seconds
● whenever the current travel speed in each highway section is write database at a distance from 20 seconds
(3) vehicle Agent (giving the Behaviour of vehicle Agent):
● the every new highway section of vehicle Agent, just in this highway section, register, and in last highway section, cancel its log-on message
● vehicle Agent in operational process, every searched once at a distance from 1 second " Yellow Page " (so-called Yellow Page, promptly stored each activity Agent like information such as ID number), obtain the vehicle number information of its running section, then according to three formula:
Traffic density is low, the Carrie Underwood exponential model:
Traffic density is medium:
Traffic density is high, Green uncle model:
Come the own current vehicle speed of real-time update.Wherein: V
fBe the free-flow operating speed in highway section, V is a current vehicle speed, K
jBe the jam density in this highway section, K is the current density in this highway section.
● when vehicle Agent goes to the crossing, search Yellow Page, obtain the vehicle speed value in current each highway section,, find out a shortest path of journey time through calculating, therefrom select next bar the highway section that will go.
● vehicle Agent whenever goes into its current place base station information at a distance from 1 fen clockwise database write.
● when vehicle Agent drove to its D point, this Agent disappeared.
In this experiment porch, topmost one type of Agent is vehicle Agent, i.e. CarAgent below just is that example is told about a CarAgent and produced to arriving the detailed process that its destination disappears from it with Fig. 3.
Existing hypothesis produces a vehicle Agent:Car10 by CreatAgent; This Agent just gives its starting point O and point of destination D at random when producing; In Fig. 3; Be respectively node 3 and node 38, and suppose this vehicle Agent from the path of the final selection of node 3 to node 38 for shown in the arrow Fig. 3.
When (1) just having produced, Car10 searches the vehicle number on all highway sections, and calculates the journey time in each highway section according to the length gauge in formula and each highway section, therefrom finds out one to the shortest path of D point.Among Fig. 3, Car10 has selected highway section (3,4), and registration in " Yellow Page " immediately indicates that Car10 is in highway section (3,4);
(2) search " Yellow Page ", drawing in highway section (3,4) has several cars, and how many speed of a motor vehicle calculate current car according to formula then should go with.This step was just moved once at a distance from 1 second with every in every new highway section, so that concern to come the speed of a motor vehicle of real time altering oneself according to the close speed of stream, thereby pressed close to real world more;
(3) every at a distance from 1 minute, Car10 will search and belong in the overlay area of which base station this moment, and time, basic station number information are deposited in the database, the behavior that mobile phone location is registered in the behavior simulating reality;
(4) when Car10 goes to node 4, search for whole road network once more, search the vehicle number on all highway sections, and calculate the journey time in each highway section according to the length gauge in formula and each highway section, therefrom find out one once more to the shortest path of D point.Among Fig. 3, Car10 has selected highway section (4,5), in " Yellow Page ", upgrades its log-on message then immediately, indicates that Car10 is in highway section (4,5);
(5) like this, according to given rule circulation execution in step (1) (2) (3) (4), go to D point (38) until Car10, disappear then, to show the Car10 investigation scope of having gone out.
In this experiment, in road network, distribute 2000 vehicle Agent altogether, on average whenever put into a vehicle Agent at a distance from 2 seconds to different starting points, each vehicle Agent carries out the process the same with Car10.The most all result datas deposit database in, to treat post-processed.
2, the highway section road net traffic state is estimated
Generate in the platform in the analogue mobile phone information data; Every in road network of 20 seconds statistics the travel speed in all highway sections, so the acquisition methods of highway section real-time traffic states is fairly simple, only need on average become the travel speed in 5 minutes with 20 seconds travel speed; Define the threshold value of two travel speeds then; Convert travel speed the traffic behavior of highway section to, at last that the time period is corresponding with the time period of OD statistics, and through the GIS demonstration.
In the present embodiment, in order to let the result more obviously and typically show, therefore important to choosing of two thresholdings of travel speed, the method step that adopts among the present invention is following:
1. 20 seconds highway section travel speed is on average become the travel speed in 5 minutes, and with the stored in form of 5 minutes data;
2. add up in all road networks, the average stroke speed of a motor vehicle in each highway section is seen the distribution situation of its codomain; 3. with the distribution situation trisection of codomain, promptly the crowded thresholding of hypothesis is x, and the obstruction thresholding is y, then
Wherein v on average becomes 5 minutes highway section travel speed in the road network, and (v) be the sum of the per 5 minutes records in every highway section in the database, (v＜x) satisfied the bar number of v＜x in per 5 minutes to num to num in a record for every highway section.
Crowd according to the highway section that defines in the road network and to describe the degree of crowding in the base station overlay area.The green corresponding respectively crowded index of reddish yellow of supposing a highway section (crossing) is 2; 1; 0, add the crowded index of all highway sections (crossing) in the base station overlay area with the back and to obtain the overall crowded index of this base station overlay area divided by the highway section bar number in the areal coverage, totally crowded index is greater than 1.33; Just explain that this zone is tending towards crowded, it is crowded more that this value approaches 2 explanations more; Overall crowded index is tending towards unimpeded less than 0.667 this areal coverage of explanation, and this index approaches in 0 this areal coverage of explanation unimpeded more more.Utilize the notion of the crowded index of base station overlay area to make an appraisal to overall road conditions in the areal coverage.At last with the traffic behavior of base station overlay area unit as the dynamic traffic sub-district; With adjacent on the geographic position; And the consistent base station of traffic behavior merges in the base station overlay area, forms the dynamic traffic sub-district of particular moment, certain specific region, for the traffic guidance management provides foundation.
3, divide based on the road network dynamic cell of cellphone information
Said method is just can mark off the dynamic traffic sub-district after utilizing coil or gps data to draw the traffic behavior in each highway section in the base station overlay area; Provide below that a last period traffic state information draws the traffic state information in the current slot base station overlay area in Dynamic OD value how to utilize in each base station overlay area of certain period that gets according to cellphone information and this base station overlay area, thereby divide the dynamic traffic sub-district.Shown in Figure 4 being utilizes information data of mobile phone to divide the flow process of dynamic traffic sub-district.Below introduce dynamic cell OD Data Acquisition method:
The Dynamic OD Data Acquisition mainly is to add up to each car, investigates the driving trace of each car, thereby draws in each base station overlay area OD amount at regular intervals.
Each base station overlay area OD statistic procedure:
1. the selected time period that will add up;
2. take out each vehicle code name (being the mobile phone code name) from database, with its record (is that Car10 is an example with the mobile phone code name) in this time period of time sequencing statistics;
3. deal with data, per car produce moving between base station at every turn, and then the O in the base station adds 1, and the D in another base station adds 1;
4. 2000 (the equaling the number of vehicle) of so circulating are inferior, draw in this time period the OD of all base station overlay areas;
5. add up the OD in 5 minutes among the present invention, so above four go on foot repetitions 12 times at every turn.
The base station overlay area traffic behavior of present stage is relevant with OD and the traffic behavior in last this base station overlay area of a period in this base station overlay area of this period, promptly satisfies formula:
Wherein
Be the traffic behavior of i period b base station overlay area,
Be the traffic behavior of i-1 period b base station overlay area,
Be the O in the i period b base station overlay area,
Be the D in the i period b base station overlay area, f
bFor in the b base station, the function that formula is set up.Because the geographic position of each base station overlay area is different, the highway section of its covering is also different, so the corresponding f of each base station overlay area
bMust be inequality.RBF RBF neural network (being called for short radially base net network) method in the utilization artificial neural network can be found out this mathematical law.Below just this method is introduced.
As shown in Figure 5, the RBF neural network is three layers of feedforward neural network, comprises input layer, latent layer, output layer.Input layer is made up of the input signal node; Middle be latent layer, its excitation function is the non-negative non-linear basis function to center radial symmetry and decay, and basis function only produces response to input signal in the part, and the basis function that uses usually is as Gaussian function etc.; The 3rd layer is output layer, is generally linear function, is the linear combination of output basis function.At first set up the RBF network traffic state estimation model of single base station areal coverage; Collect day part different
and
then as sample, the RBF network that adopts the latent layer of a list is to the sample training.At last, through test network, verify that this network is made for base station overlay area traffic behavior results estimated to analyze and estimate.
Concrete steps are following:
1. the selected object of investigating
Selection of base stations number is 7 areal coverage here;
2. the collection of sample estimates and design output variable: know that by formula output variable should be
input variable: wherein the obtaining value method of
is the same with
for
for input variable.
3. network design
Radially base (RBF) network mainly comprises hidden layer and output layer, and wherein the transport function of hidden layer is radbas, and the transport function of output layer is pure linear function purelin.Radially the hidden layer of base has S1 neuron, and output layer has S2 neuron.
The function that is used to create the RBF network in the Neural Network Toolbox is newrbe, and in design process, most important parameter is the distributed constant of RBF.Because the number of samples in the present embodiment instance is not very big, so among the present invention distributed constant is set at 1.2.Utilizing function newrbe to create in the RBF network development process, can increase the neuron number of hidden layer automatically, till square error meets the demands.So the constructive process of network is exactly a training process.
4. next one group of data is tested, see whether network can correctly estimate the traffic behavior in the base station overlay area.
5. network test aim parameter result and former test target amount contrast does not then increase the training sample amount if do not satisfy accuracy requirement.Repeat above step, until algorithm convergence.
The above-mentioned description to embodiment is can understand and use the present invention for ease of the those of ordinary skill of this technical field.The personnel of skilled obviously can easily make various modifications to these embodiment, and needn't pass through performing creative labour being applied in the General Principle of this explanation among other embodiment.Therefore, the invention is not restricted to the embodiment here, those skilled in the art should be within protection scope of the present invention for improvement and modification that the present invention makes according to announcement of the present invention.
Claims (7)
1. analogue mobile phone data and assess the method for city road net traffic state, it is characterized in that: it comprises:
(a) building the Agent platform produces the analogue mobile phone data and deposits in the database;
(b) travel speed is excavated processing, utilize the matlab neural network dynamic to estimate road net traffic state.
2. the method for claim 1 is characterized in that:
Step (a) specifically comprises:
(a1) simulated experiment road network and design base station distribution;
(a2) build experiment porch, programming realizes the mutual relationship between each Agent module.
3. method as claimed in claim 2 is characterized in that:
Said simulated experiment road network need obtain the topological diagram of actual road network, comprises the network description of highway section, crossing, and the traffic administration of current employing and control mode;
The design of said base station distribution is to adopt the cellular regular hexagon base station cell of mobile network's method of operation that actual road network is carried out comprehensive covering, to obtain accurate data in mobile phone.
4. method as claimed in claim 2 is characterized in that: said Agent module is three types:
Produce the class of all Agent: be responsible for before the whole flat operation, producing the Agent of a statistics non-intersection speed, and produced a vehicle Agent in per 2 seconds;
Statistics non-intersection speed Agent class: whenever the traffic behavior in all highway sections is searched for once, deposited search time at that time, the traffic behavior in each highway section in database then at a distance from 10 seconds;
Vehicle Agent class: mutual through with road section information compute classes MinPath, obtain the real-time speed of a motor vehicle and select the path in real time, and every at a distance from clockwise database submission in fen information of this Agent once.
5. the method for claim 1, it is characterized in that: step (b) specifically comprises:
(b1) dynamically obtain the highway section travel speed, from the highway section and the aspect of road network handle respectively, with the average stroke speed of a motor vehicle as the average basis of road section traffic volume state;
(b2) combine the road use attribute, with after the travel speed obfuscation with the unimpeded degree in the comprehensive average highway section of Fuzzy Inference, to obtaining the sub-district traffic behavior after the state weighted mean of highway section;
(b3) carrying out dynamic cell and divide, is minimum unit with the base station overlay area, and identical and geographic position base stations neighboring areal coverage is combined into the dynamic traffic sub-district with traffic behavior in a certain period.
6. method as claimed in claim 5 is characterized in that: in the step (b1) 20 seconds travel speed is on average become the travel speed in 5 minutes, define the threshold value of two travel speeds then, convert travel speed the traffic behavior of highway section to, and show through GIS.
7. method as claimed in claim 5 is characterized in that: utilization matlab three-layer neural network module is carried out dynamic estimation and prediction to cell status in the step (b3); A last period traffic state information draws the traffic state information in the current slot base station overlay area in Dynamic OD value in each base station overlay area of certain period that utilization gets according to cellphone information and this base station overlay area, thereby divides the dynamic traffic sub-district.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102547715A CN102376025A (en) | 2010-08-17 | 2010-08-17 | Method for simulating mobile phone data and evaluating urban road network traffic condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102547715A CN102376025A (en) | 2010-08-17 | 2010-08-17 | Method for simulating mobile phone data and evaluating urban road network traffic condition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102376025A true CN102376025A (en) | 2012-03-14 |
Family
ID=45794589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010102547715A Pending CN102376025A (en) | 2010-08-17 | 2010-08-17 | Method for simulating mobile phone data and evaluating urban road network traffic condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102376025A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890860A (en) * | 2012-09-28 | 2013-01-23 | 北京世纪高通科技有限公司 | Method and device for classifying traffic zone |
| CN104484993A (en) * | 2014-11-27 | 2015-04-01 | 北京交通大学 | Processing method of cell phone signaling information for dividing traffic zones |
| CN104850653A (en) * | 2015-06-03 | 2015-08-19 | 江苏马上游科技股份有限公司 | Short-term tourist traffic and trend prediction system based on streaming data extraction |
| WO2017211377A1 (en) * | 2016-06-06 | 2017-12-14 | Nokia Solutions And Networks Oy | Method, apparatus and system for mobile edge computing |
| CN109949574A (en) * | 2018-05-18 | 2019-06-28 | 中山大学 | A kind of urban road network traffic zone GradeNDivision method of data-driven |
| CN110047277A (en) * | 2019-03-28 | 2019-07-23 | 华中科技大学 | Road traffic congestion arrangement method and system based on signaling data |
| CN113808388A (en) * | 2021-08-03 | 2021-12-17 | 珠海市规划设计研究院 | Traffic jam analysis method comprehensively considering operation of cars and public traffic |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1912837A (en) * | 2006-08-31 | 2007-02-14 | 上海交通大学 | Expansable distributed system of supporting large scale micro-traffic simulation |
| CN101014173A (en) * | 2006-12-31 | 2007-08-08 | 姜宏伟 | Method and system for transmitting monitoring data of communication base station |
| CN101477581A (en) * | 2008-12-19 | 2009-07-08 | 上海理工大学 | Multi-agent area road intersection signal integrated control simulation system |
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
-
2010
- 2010-08-17 CN CN2010102547715A patent/CN102376025A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1912837A (en) * | 2006-08-31 | 2007-02-14 | 上海交通大学 | Expansable distributed system of supporting large scale micro-traffic simulation |
| CN101014173A (en) * | 2006-12-31 | 2007-08-08 | 姜宏伟 | Method and system for transmitting monitoring data of communication base station |
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN101477581A (en) * | 2008-12-19 | 2009-07-08 | 上海理工大学 | Multi-agent area road intersection signal integrated control simulation system |
Non-Patent Citations (4)
| Title |
|---|
| TANG SHOUPENG,ET AL.: "Multi-agent Traveler Route Choice Behavior Simulation Research When Supplied Individual Traffic Condition Information", 《2009 INTERNATIONAL JOINT CONFERENCE ON ARTIFICAL INTELLIGENCE》 * |
| 孙剑，等。: "拥挤交通流交织区车道变换行为仿真", 《系统仿真学报》 * |
| 庄斌，等。: "动态路网交通状态估计理论及其在ATMS中的应用", 《第一届中国智能交通年会论文集》 * |
| 李俊卫，等。: "快速路通道动态OD 流估计模型", 《北京交通大学学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890860A (en) * | 2012-09-28 | 2013-01-23 | 北京世纪高通科技有限公司 | Method and device for classifying traffic zone |
| CN102890860B (en) * | 2012-09-28 | 2014-10-22 | 北京世纪高通科技有限公司 | Method and device for classifying traffic zone |
| CN104484993A (en) * | 2014-11-27 | 2015-04-01 | 北京交通大学 | Processing method of cell phone signaling information for dividing traffic zones |
| CN104850653A (en) * | 2015-06-03 | 2015-08-19 | 江苏马上游科技股份有限公司 | Short-term tourist traffic and trend prediction system based on streaming data extraction |
| WO2017211377A1 (en) * | 2016-06-06 | 2017-12-14 | Nokia Solutions And Networks Oy | Method, apparatus and system for mobile edge computing |
| US11089523B2 (en) | 2016-06-06 | 2021-08-10 | Nokia Solutions And Networks Oy | Method, apparatus and system for mobile edge computing |
| CN109949574A (en) * | 2018-05-18 | 2019-06-28 | 中山大学 | A kind of urban road network traffic zone GradeNDivision method of data-driven |
| CN109949574B (en) * | 2018-05-18 | 2021-09-28 | 中山大学 | Data-driven urban road network traffic cell multistage division method |
| CN110047277A (en) * | 2019-03-28 | 2019-07-23 | 华中科技大学 | Road traffic congestion arrangement method and system based on signaling data |
| CN113808388A (en) * | 2021-08-03 | 2021-12-17 | 珠海市规划设计研究院 | Traffic jam analysis method comprehensively considering operation of cars and public traffic |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102376025A (en) | Method for simulating mobile phone data and evaluating urban road network traffic condition | |
| Burgholzer et al. | Analysing the impact of disruptions in intermodal transport networks: A micro simulation-based model | |
| CN103077604B (en) | traffic sensor management method and system | |
| CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
| CN110111574B (en) | Urban traffic imbalance evaluation method based on flow tree analysis | |
| CN102610092A (en) | Urban road speed predication method based on RBF (radial basis function) neural network | |
| Psaltoglou et al. | Enhanced connectivity index–A new measure for identifying critical points in urban public transportation networks | |
| Chen et al. | Reliable shortest path finding in stochastic time-dependent road network with spatial-temporal link correlations: A case study from Beijing | |
| CN112489426A (en) | Urban traffic flow space-time prediction scheme based on graph convolution neural network | |
| Cheng et al. | Developing a travel time estimation method of freeway based on floating car using random forests | |
| Bachechi et al. | Implementing an urban dynamic traffic model | |
| Jamil et al. | Taxi passenger hotspot prediction using automatic ARIMA model | |
| CN115100848A (en) | Travel tracing method and system for ground traffic congestion | |
| Park et al. | Calibration and validation of TRANSIMS microsimulator for an urban arterial network | |
| Dong et al. | Simulation of transportation infrastructures resilience: a comprehensive review | |
| Dogaroglu et al. | Investigation of car park preference by intelligent system guidance | |
| Bellini et al. | Vehicular traffic flow reconstruction analysis to mitigate scenarios with large city changes | |
| Li et al. | Multiagent reinforcement learning-based signal planning for resisting congestion attack in green transportation | |
| Nasiboglu | Dijkstra solution algorithm considering fuzzy accessibility degree for patch optimization problem | |
| Si et al. | Data-based sorting algorithm for variable message sign location: Case study of Beijing | |
| Pathak et al. | A framework for designing policies for networked systems with uncertainty | |
| CN114666738A (en) | Territorial space planning method and system based on mobile phone signaling | |
| CN110942622B (en) | Parking lot planning method based on real-time operation big data of parking lot | |
| Ye et al. | Hybrid calibration of agent-based travel model using traffic counts and AVI data | |
| Plakolb et al. | Automated detection of entry and exit nodes in traffic networks of irregular shape |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120314 |