CN109377754B - Short-term traffic flow speed prediction method in Internet of vehicles environment - Google Patents
Short-term traffic flow speed prediction method in Internet of vehicles environment Download PDFInfo
- Publication number
- CN109377754B CN109377754B CN201811264868.7A CN201811264868A CN109377754B CN 109377754 B CN109377754 B CN 109377754B CN 201811264868 A CN201811264868 A CN 201811264868A CN 109377754 B CN109377754 B CN 109377754B
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- short
- prediction
- data
- time
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a short-time traffic flow speed prediction method under the environment of an Internet of vehicles, which comprises four steps of determining short-time traffic flow prediction parameters, acquiring and processing data, establishing a combined prediction model and predicting the short-time traffic flow speed under the environment of the Internet of vehicles.
Description
Field of the invention
The invention belongs to the technical field of short-term traffic flow prediction of a traffic system, and particularly relates to a short-term traffic flow speed prediction method in a vehicle networking environment.
Background
With the continuous development and the advance of the technology in the field of road traffic, the road traffic flow prediction and forecast becomes one of the most critical technologies of an intelligent traffic system, wherein the short-time traffic flow prediction is the basis of traffic control and traffic guidance, the running condition of the traffic flow coming in the future is sensed and forecasted in advance through various traffic running data, and the running condition is prepared in advance.
At present, the technologies of car networking, car road collaboration and the like are greatly promoted by governments of various countries, and information sharing among organic elements of a traffic system can be realized through communication and interaction between cars and roads, so that the operation efficiency and safety of the traffic system are improved. Under the environment of the Internet of vehicles, the prediction of the short-time traffic flow is promoted, on one hand, the traditional short-time traffic flow prediction needs to be based on traditional traffic information acquisition equipment, the acquired information point position is relatively fixed, errors or even errors of data acquisition exist, after the environment of the Internet of vehicles is introduced, the vehicles can transmit the self running state information to the system at any position and any time in the running process, and the precision of the information is completely guaranteed; on the other hand, under the environment of the Internet of vehicles, the fluctuation of traffic flow operation is reduced due to the interaction of information among vehicles, and the reliability of the traffic flow operation is indirectly improved, so that under the condition, a short-time traffic flow speed prediction method capable of being under the environment of the Internet of vehicles is actively developed, and the method is a great promotion and improvement on the technical field of short-time traffic flow prediction of a traffic system.
Disclosure of Invention
The invention provides the technical field of short-time traffic flow prediction of a traffic system aiming at the problems in the prior art, and compared with the prior short-time traffic flow prediction technology, the method is more beneficial to improving the precision and the prediction efficiency of the short-time traffic flow prediction and reducing the technology and the equipment threshold of the short-time traffic flow prediction.
In order to achieve the purpose, the invention adopts the technical scheme that: a short-time traffic flow speed prediction method under the environment of Internet of vehicles comprises the following steps:
s1, determining the short-term traffic flow prediction parameters: the prediction parameters at least comprise a short-time traffic flow speed prediction point position L, a short-time traffic flow speed prediction time interval G and a short-time traffic flow direction D;
s2, data acquisition and processing: the step is used for acquiring the speed and time when the motor vehicle passes through the predicted point location L, grouping and storing data according to the date and time of data acquisition, and then carrying out averaging processing;
s3, building a combined prediction model: the short-time traffic flow prediction is converted into fitting of a prediction parameter continuous change rule and prediction of a discrete residual error by adopting a combined prediction model;
s4, short-time traffic flow speed prediction in the car networking environment: and substituting the date and the time grouping sequence number which need to be subjected to the short-time traffic flow speed prediction into the combined prediction model in the step S3, and calculating to obtain the short-time traffic flow speed prediction value.
As an improvement of the invention, in the step S1, the short-time traffic flow speed prediction point position L adopts longitude and latitude coordinates, the unit of the time interval G is minute, and G belongs to {3,5,6,10,15,20,30,60 }.
As still another improvement of the present invention, the step S2 further includes:
s21, data acquisition; when a motor vehicle passes through the point location L and the driving direction of the motor vehicle is equal to D, the vehicle networking system automatically records the speed of the motor vehicle when passing through the point location L and automatically records the time when passing through the point location L;
s22, storing data; grouping and storing the traffic flow speed data acquired in the step S21 according to the date and time of the acquired data, and grouping and storing the data after grouping and storing
Respectively record the speed data of the traffic flow stored in the storage device as
Wherein, the superscript date is the date when the data is collected, and the subscript q is the time grouping serial number when the data is collected; said group
The number of the common storage traffic flow speed data is
A plurality of;
s23, processing data; the data stored in step S22 is subjected to averaging processing, that is: group of
Traffic flow of a representative speed of
As a further improvement of the invention, the time grouping sequence number q of the data acquisition in the step S22 is a positive integer, and q is less than or equal to 1440/G.
As a further improvement of the present invention, the step S3 further includes: the short-time traffic flow prediction is converted into fitting of a prediction parameter continuous change rule and prediction of a discrete residual error by adopting a combined prediction model;
s31, fitting a continuous variation model; constructing a fitting of the continuous variation model, wherein the fitting function is as follows:
wherein m is0、m1、m2Is the undetermined coefficient of the function;
s32, residual calculation; calculating the residual error of the speed after fitting according to the fitting function in the step S31, wherein the calculation formula is as follows:
wherein
Is the residual of the velocity;
s33, building a residual prediction model; adopting a support vector machine model as a residual prediction model, determining a function f (x) of input training sample data into the residual prediction model according to the size of q, training the model, and recording predicted residual values as residual values after the residual prediction model is trained
The above-mentioned
That is, when the traffic flow represents the speed
Then, a residual prediction value is obtained by calculation of a residual prediction model;
s34, establishing a short-term traffic flow speed prediction model in the Internet of vehicles environment; the short-time traffic flow speed prediction model under the Internet of vehicles environment is as follows:
wherein
The predicted value is the short-term traffic flow speed.
As another improvement of the present invention, in step S33, when q is greater than 1, q is greater than 1
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value; when q is equal to 1, will
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value.
As a further improvement of the present invention, the short-term traffic flow speed data collected and stored in step S2 at least includes the total historical data of 180 days ahead from the predicted day.
Compared with the prior art, the short-time traffic flow speed prediction method under the car networking environment provided by the invention has the advantages that the short-time traffic flow speed prediction model based on data is constructed and calibrated by acquiring, storing and processing the traffic flow operation data under the car networking environment, so that the short-time traffic flow speed prediction under the car networking environment is realized, compared with the existing short-time traffic flow prediction method based on a fixed point detection device, the method has the advantages that the vehicle can transmit the operation state information of the vehicle to the system at any position and any time in the operation process, the information precision is guaranteed, the requirements of the short-time traffic flow prediction on the location and the vehicle detection hardware equipment can be effectively reduced, and the information interaction among the vehicles is realized under the car networking environment, the fluctuation of the traffic flow operation is also reduced, and the traffic flow operation reliability is indirectly improved, the data acquisition precision is greatly improved, and the prediction precision of the short-time traffic flow speed combination prediction model based on the data is also improved to a certain extent.
Drawings
FIG. 1 is a flow chart illustrating the steps of a short-term traffic flow speed prediction method in an Internet of vehicles environment according to the present invention;
FIG. 2 is a schematic view of a road condition according to embodiment 2 of the present invention;
FIG. 3 is a schematic diagram showing the fitting result of the continuous variation model in the prediction method of embodiment 2 of the present invention;
fig. 4 is a schematic diagram of a residual calculation result in the prediction method according to embodiment 2 of the present invention.
Detailed Description
The invention will be explained in more detail below with reference to the drawings and examples.
Example 1
A method for predicting the short-term traffic flow speed in a car networking environment is shown as figure 1 and comprises the following steps:
s1, determining the short-term traffic flow prediction parameters: the determined prediction parameters at least comprise a short-time traffic flow speed prediction point position L, a short-time traffic flow speed prediction time interval G and a short-time traffic flow speed prediction traffic flow direction D; the position L of the short-time traffic flow speed prediction point adopts longitude and latitude coordinates, the unit of a time interval G is minutes, and G belongs to {3,5,6,10,15,20,30,60}
S2, data acquisition and processing: the step is used for acquiring the speed and time when the motor vehicle passes through the predicted point location L, grouping and storing data according to the date and time of data acquisition, and then carrying out averaging processing;
s21, data acquisition; when a motor vehicle passes through the point location L and the driving direction of the motor vehicle is equal to D, the vehicle networking system automatically records the speed of the motor vehicle when passing through the point location L and automatically records the time when passing through the point location L;
s22, storing data; grouping and storing the traffic flow speed data acquired in the step S21 according to the date and time of the acquired data, and grouping and storing the data after grouping and storing
Respectively record the speed data of the traffic flow stored in the storage device as
Wherein, the superscript date is the date when the data is collected, and the subscript q is the time grouping serial number when the data is collected; said group
Co-storage trafficThe number of the flow speed data is
A plurality of;
in this step, the time grouping sequence number q of data acquisition is a positive integer, and q is not more than 1440/G, and
is a group consisting of traffic flow speeds collected in a time interval from (q-1) G minute to qG minute on the date of date,
namely group
The number of the traffic flow speed data is stored in the memory; there is a need to collect and store historical data for at least 180 days prior to the current day of the short-term traffic flow speed forecast.
S23, processing data; the data stored in step S22 is subjected to averaging processing, that is: group of
Traffic flow of a representative speed of
S3, building a combined prediction model: the short-time traffic flow prediction is converted into fitting of a prediction parameter continuous change rule and prediction of a discrete residual error by adopting a combined prediction model;
s31, fitting a continuous variation model; the traffic flow representing speed processed by the step S23 is adopted
As a dependent variable, with q as an independent variable, fit the following function
Wherein m is0、m1、m2For the coefficients to be determined of the function,
is a fitted function of velocity;
s32, residual calculation; calculating the residual error of the speed after fitting according to the fitting function in the step S31, wherein the calculation formula is as follows:
wherein
Is the residual of the velocity;
s33, building a residual prediction model; a support vector machine model is used as a prediction model of residual errors, a training sample data input model is determined according to the size of q, and a predicted value is obtained;
when q is greater than 1, will
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value; when q is equal to 1, will
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
for predicting value, recording after residual prediction model training is completedIs composed of
The above-mentioned
That is, when the traffic flow represents the speed
Then, a residual prediction value is obtained by calculation of a residual prediction model;
s34, establishing a short-term traffic flow speed prediction model in the Internet of vehicles environment; the short-time traffic flow speed prediction model under the Internet of vehicles environment is as follows:
wherein
The predicted value is the short-term traffic flow speed.
S4, short-time traffic flow speed prediction in the car networking environment: and substituting the date and the time grouping sequence number which need to be subjected to the short-time traffic flow speed prediction into the combined prediction model in the step S3, and calculating to obtain the short-time traffic flow speed prediction value.
The vehicle can transmit the self running state information to the system at any position and any time in the running process, the information precision has guarantee, the requirements of short-time traffic flow prediction on places and vehicle detection hardware equipment can be effectively reduced, and the fluctuation of traffic flow running is reduced due to the fact that information among vehicles is interacted under the environment of the internet of vehicles, the reliability of traffic flow running is indirectly improved, the data acquisition precision is greatly improved, and the prediction precision of a short-time traffic flow speed combination prediction model based on the data is also improved to a certain extent.
Example 2
In this embodiment, a certain interstate in the united states is selected as an example, a road condition diagram is shown in fig. 2, and a short-time traffic flow speed prediction method in a car networking environment includes the following steps:
s1, determining the short-term traffic flow prediction parameters:
the determined parameters include: the position L of the short-term traffic flow speed prediction point, that is, the marking point shown in fig. 2, the time interval G of the short-term traffic flow speed prediction is 5 minutes, and the traffic flow direction D of the short-term traffic flow speed prediction is a direction from the left side to the right side in the figure;
s2, data acquisition and processing: the method comprises the following three steps of data acquisition, data storage and data processing:
s21, data acquisition: when a motor vehicle passes through the point location L and the driving direction of the motor vehicle is equal to D, the vehicle networking system automatically records the speed of the motor vehicle passing through the point location L and automatically records the time of the motor vehicle passing through the point location L;
s22, data storage: grouping and storing the traffic flow speed data acquired in the step according to the date and time of the acquired data; after storing the groups, the group
Co-storing traffic flow velocity data
Respectively mark as
Wherein, the superscript date is the date when the data is collected, the subscript q is the time grouping serial number when the data is collected, q is a positive integer and is not more than 1440/G,
is a group consisting of traffic flow speeds collected in a time interval from (q-1) G minute to qG minute on the date of date,
into a group
The number of the traffic flow speed data is stored in the memory;
s23, data processing: averaging the data stored in the step B2) to obtain a group
Traffic flow of a representative speed of
In this step, historical data of at least 180 days before the current day of short-term traffic flow speed prediction needs to be collected and stored.
S3, building a combined prediction model: the method adopts a combined prediction model to convert the short-time traffic flow prediction into the fitting of a prediction parameter continuous change rule and the prediction of a discrete residual error, and comprises the following steps:
s31, continuous variation model fitting: representing speed by adopting processed traffic flow
As a dependent variable, with q as an independent variable, fit the following function
Wherein m is0、m1、m2For the coefficients to be determined of the function,
is a fitted function of velocity; after the fitting is completed, m0、m1、m2The values of (a) are 70.9, -2.017 and 4.808 respectively, and a schematic diagram of a fitting result is shown in FIG. 3;
s32, residual calculation: after the fitting of the continuous variation model is completed, calculating the residual error of the speed after the fitting, as follows:
wherein
Is the residual of the velocity; the result (in part) of the residual is shown in fig. 4;
s33, residual prediction model establishment: a support vector machine model is adopted as a residual prediction model, and according to the size of q, the method is divided into two conditions: when q is greater than 1, will
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value; when q is equal to 1, will
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value; after the residual prediction model training is completed, it is recorded as
S34, establishing a short-term traffic flow speed prediction model in the Internet of vehicles environment; the short-term traffic flow speed prediction model in the Internet of vehicles environment is expressed as the following formula
Wherein
The predicted value is a short-term traffic flow speed value;
s4, predicting the short-term traffic flow speed in the Internet of vehicles environment; and substituting the date and the time grouping sequence number which need to be subjected to short-time traffic flow speed prediction into the short-time traffic flow speed prediction model under the car networking environment obtained in the step S34 to obtain the short-time traffic flow speed prediction value.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited by the foregoing examples, which are provided to illustrate the principles of the invention, and that various changes and modifications may be made without departing from the spirit and scope of the invention, which is also intended to be covered by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A short-time traffic flow speed prediction method under the environment of Internet of vehicles is characterized by comprising the following steps:
s1, determining the short-term traffic flow prediction parameters: the prediction parameters at least comprise a short-time traffic flow speed prediction point position L, a short-time traffic flow speed prediction time interval G and a short-time traffic flow direction D;
s2, data acquisition and processing: the step is used for acquiring the speed and time when the motor vehicle passes through the predicted point location L, grouping and storing data according to the date and time of data acquisition, and then carrying out averaging processing;
s21, data acquisition; when a motor vehicle passes through the point location L and the driving direction of the motor vehicle is equal to D, the vehicle networking system automatically records the speed of the motor vehicle when passing through the point location L and automatically records the time when passing through the point location L;
s22, storing data; grouping and storing the traffic flow speed data acquired in the step S21 according to the date and time of the acquired data, and grouping and storing the data after grouping and storing
Respectively record the speed data of the traffic flow stored in the storage device as
Wherein, the superscript date is the date when the data is collected, and the subscript q is the time grouping serial number when the data is collected; said group
The number of the common storage traffic flow speed data is
A plurality of;
s23, processing data; the data stored in step S22 is subjected to averaging processing, that is: group of
Traffic flow of a representative speed of
S3, building a combined prediction model: the short-time traffic flow prediction is converted into fitting of a prediction parameter continuous change rule and prediction of a discrete residual error by adopting a combined prediction model;
s31, continuous variation model fitting: and (3) constructing fitting of the continuous change model, wherein a fitting function is as follows:
wherein m is0、m1、m2Is the undetermined coefficient of the function;
s32, residual calculation: calculating the residual error of the speed after fitting according to the fitting function in the step S31, wherein the calculation formula is as follows:
wherein
Is the residual of the velocity;
s33, residual prediction model establishment: adopting a support vector machine model as a residual prediction model, determining a function f (x) of input training sample data into the residual prediction model according to the size of q, training the model, and recording predicted residual values as residual values after the residual prediction model is trained
The above-mentioned
That is, when the traffic flow represents the speed
Then, a residual prediction value is obtained by calculation of a residual prediction model;
s34, establishing a short-time traffic flow speed prediction model under the car networking environment: the short-time traffic flow speed prediction model under the Internet of vehicles environment is as follows:
wherein
The predicted value is a short-term traffic flow speed value;
s4, short-time traffic flow speed prediction in the car networking environment: and substituting the date and the time grouping sequence number which need to be subjected to the short-time traffic flow speed prediction into the combined prediction model in the step S3, and calculating to obtain the short-time traffic flow speed prediction value.
2. The method for predicting the speed of a short-term traffic flow in a car networking environment according to claim 1, wherein the position L of the short-term traffic flow speed prediction point in the step S1 is represented by latitude and longitude coordinates, the time interval G is in minutes, and G e {3,5,6,10,15,20,30,60 }.
3. The method for predicting the traffic flow speed in the internet of vehicles according to claim 2, wherein the time grouping sequence number q of the data acquisition in step S22 is a positive integer, and q is not more than 1440/G.
4. The method according to claim 3, wherein in step S33, when q is greater than 1, the method will be used to predict the speed of traffic flow in short time in car networking environment
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value; when q is equal to 1, will
Inputting training sample data as a support vector machine model, wherein
In order to input the parameters, the user can select the parameters,
is a predicted value.
5. The method according to any one of the preceding claims, wherein the short-term traffic flow speed data collected and stored in step S2 includes at least the total historical data of 180 days ahead from the predicted day.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811264868.7A CN109377754B (en) | 2018-10-29 | 2018-10-29 | Short-term traffic flow speed prediction method in Internet of vehicles environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811264868.7A CN109377754B (en) | 2018-10-29 | 2018-10-29 | Short-term traffic flow speed prediction method in Internet of vehicles environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109377754A CN109377754A (en) | 2019-02-22 |
| CN109377754B true CN109377754B (en) | 2021-07-02 |
Family
ID=65390043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811264868.7A Active CN109377754B (en) | 2018-10-29 | 2018-10-29 | Short-term traffic flow speed prediction method in Internet of vehicles environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109377754B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192453A (en) * | 2019-12-30 | 2020-05-22 | 深圳市麦谷科技有限公司 | Short-term traffic flow prediction method and system based on Bayesian optimization |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730006A (en) * | 2014-01-26 | 2014-04-16 | 吉林大学 | Short-time traffic flow combined forecasting method |
| CN106935034A (en) * | 2017-05-08 | 2017-07-07 | 西安电子科技大学 | Towards the regional traffic flow forecasting system and method for car networking |
| WO2017193556A1 (en) * | 2016-05-11 | 2017-11-16 | 杭州海康威视数字技术股份有限公司 | Speed prediction method and apparatus |
| CN107481523A (en) * | 2017-09-27 | 2017-12-15 | 中南大学 | A kind of traffic flow speed Forecasting Methodology and system |
| CN107705556A (en) * | 2017-09-01 | 2018-02-16 | 南京邮电大学 | A kind of traffic flow forecasting method combined based on SVMs and BP neural network |
| CN108564790A (en) * | 2018-06-12 | 2018-09-21 | 国交空间信息技术（北京）有限公司 | A kind of urban short-term traffic flow prediction technique based on traffic flow space-time similitude |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739819A (en) * | 2009-11-19 | 2010-06-16 | 北京世纪高通科技有限公司 | Method and device for predicting traffic flow |
| CN105355038A (en) * | 2015-10-14 | 2016-02-24 | 青岛观澜数据技术有限公司 | Method for predicting short-term traffic flow through employing PMA modeling |
| CN107145985A (en) * | 2017-05-09 | 2017-09-08 | 北京城建设计发展集团股份有限公司 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
| CN107967803A (en) * | 2017-11-17 | 2018-04-27 | 东南大学 | Traffic congestion Forecasting Methodology based on multi-source data and variable-weight combined forecasting model |
-
2018
- 2018-10-29 CN CN201811264868.7A patent/CN109377754B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730006A (en) * | 2014-01-26 | 2014-04-16 | 吉林大学 | Short-time traffic flow combined forecasting method |
| WO2017193556A1 (en) * | 2016-05-11 | 2017-11-16 | 杭州海康威视数字技术股份有限公司 | Speed prediction method and apparatus |
| CN106935034A (en) * | 2017-05-08 | 2017-07-07 | 西安电子科技大学 | Towards the regional traffic flow forecasting system and method for car networking |
| CN107705556A (en) * | 2017-09-01 | 2018-02-16 | 南京邮电大学 | A kind of traffic flow forecasting method combined based on SVMs and BP neural network |
| CN107481523A (en) * | 2017-09-27 | 2017-12-15 | 中南大学 | A kind of traffic flow speed Forecasting Methodology and system |
| CN108564790A (en) * | 2018-06-12 | 2018-09-21 | 国交空间信息技术（北京）有限公司 | A kind of urban short-term traffic flow prediction technique based on traffic flow space-time similitude |
Non-Patent Citations (3)
| Title |
|---|
| （网联环境下交通状态预测与诱导技术研究;程鑫;《中国博士学位论文全文数据库（电子期刊）》;20180615;全文21-51页 * |
| Space-Time Hybrid Model for Short-Time Travel Speed Prediction;Qi Fan;《Discrete Dynamics in Nature and Society》;20180223;全文 * |
| 双车道二级公路纵坡段车辆运行速度预测模型;许金良等;《中国公路学报》;20081130;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109377754A (en) | 2019-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10120381B2 (en) | Identifying significant locations based on vehicle probe data | |
| US10551842B2 (en) | Real-time vehicle state trajectory prediction for vehicle energy management and autonomous drive | |
| CN111860228B (en) | Method, device, equipment and storage medium for autonomous parking | |
| US8949028B1 (en) | Multi-modal route planning | |
| Li et al. | Prediction of urban human mobility using large-scale taxi traces and its applications | |
| US8229666B2 (en) | Generating and using pattern keys in navigation systems to predict user destinations | |
| US9778658B2 (en) | Pattern detection using probe data | |
| EP2646779B1 (en) | Method of enrichment of road information data | |
| CN107389080A (en) | A kind of vehicle route air navigation aid and electronic equipment | |
| CN109767619B (en) | Intelligent networking pure electric vehicle running condition prediction method | |
| Ye et al. | A method for driving route predictions based on hidden Markov model | |
| EP2743898A3 (en) | A method of and a navigation device for time-dependent route planning | |
| US20180045527A1 (en) | Systems and Methods for Predicting Vehicle Fuel Consumption | |
| CN109141456A (en) | Navigation path planning method and server | |
| CN105091890A (en) | Method and apparatus used for recommending candidate path | |
| CN106295849A (en) | Rapid transit parameter estimation | |
| CN103942312B (en) | Bus transfer lines planning method and device | |
| CN110174893A (en) | A kind of unmanned control method, system and vehicle | |
| CN114299712B (en) | Data processing method, device, equipment and readable storage medium | |
| CN109377754B (en) | Short-term traffic flow speed prediction method in Internet of vehicles environment | |
| CN109377758A (en) | A kind of running time predictor method and system | |
| CN113665576B (en) | Method, device, equipment and medium for predicting running condition of vehicle | |
| JP2014066542A (en) | Battery temperature estimation device and method | |
| CN110377671A (en) | A kind of city road planning method and apparatus | |
| CN113420942A (en) | Sanitation truck real-time route planning method based on deep Q learning |
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 |