CN110930693A - Online short-term traffic flow prediction method for road section - Google Patents
Online short-term traffic flow prediction method for road section Download PDFInfo
- Publication number
- CN110930693A CN110930693A CN201911067916.8A CN201911067916A CN110930693A CN 110930693 A CN110930693 A CN 110930693A CN 201911067916 A CN201911067916 A CN 201911067916A CN 110930693 A CN110930693 A CN 110930693A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- road section
- traffic flow
- time sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G08G1/0125—Traffic data processing
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides an online short-term traffic flow prediction method for a road section, which comprises the following steps: s1, acquiring floating vehicle speed data and traffic flow data of a road section, and processing the data into a time sequence form respectively; s2, converting the floating vehicle speed data time sequence and the traffic flow data time sequence into the same time window granularity; s3, smoothing and denoising the speed data time sequence of the floating car by utilizing wavelet transformation; s4, constructing a space-time state vector; s5, optimizing parameters C and gamma of the SVR model by adopting a particle swarm algorithm according to the space-time state vector to obtain an optimal SVR prediction model; s6, inputting the test sample into the prediction model obtained in the S5 to obtain a prediction result; and S7, optimizing S5 prediction model parameters according to the real-time prediction error feedback. The method can fuse floating car data of related road vehicles and traffic flow data collected by road equipment in two dimensions of time and space, can optimize a prediction model on line, and can accurately predict the traffic flow of a road section in a short-term prediction mode.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to an online short-term traffic flow prediction method for a road section.
Background
With the development of society, the problems of traffic jam, environmental pollution, energy consumption and the like become more and more serious, and the traffic problem becomes a hot topic of urban management more and more. 2015 Texas traffic research reports indicated that U.S. road overcrowding costs approximately 1600 billion dollars per year. Many big cities in China also fall into the dilemma of ' having the widest roads and ' having the widest parking lots ', the operation efficiency of the cities is seriously influenced, and the rapid development of the society and the economy is hindered.
The key to solve the above problems lies in using advanced intelligent transportation means such as Advanced Traffic Management System (ATMS), Advanced Traffic Information System (ATIS), and dynamic route guidance system (DGRS) to alleviate the traffic congestion problem. The key to implementing these systems requires real-time, reliable, and accurate traffic prediction information. The current short-time traffic prediction method has the advantages that the road space structure is rarely considered, the prediction method is carried out by adopting multi-source data, the possibility of acquiring more accurate, higher coverage rate and more comprehensive traffic data is realized along with the development of information technology, and the short-time traffic prediction method meeting the real-time requirement can better play the effect of practical application along with the development of computing technology.
Therefore, it is necessary to perform short-term traffic prediction by using a method that takes into account spatial characteristics of a road network and uses multi-source data, and an online prediction method is designed to better meet the requirement of real-time short-term traffic prediction.
Disclosure of Invention
In order to solve the defects, the invention provides an online road traffic speed space-time prediction method based on multi-source data. And constructing characteristic input variables containing spatial characteristics and multi-source data, and updating the model parameters on line through a real-time feedback result.
In order to achieve the aim, the invention designs an online short-term traffic flow prediction method for a road section aiming at an urban road intelligent traffic prediction technology, and the method comprises the following steps:
s1, acquiring floating vehicle speed data and traffic flow data of a road section, and processing the data into a time sequence form respectively;
s2, converting the floating vehicle speed data time sequence and the traffic flow data time sequence into the same time window granularity;
s3, smoothing and denoising the speed data time sequence of the floating car by utilizing wavelet transformation;
s4, constructing a space-time state vector based on the speed data time sequence and the traffic flow data time sequence of the road section to be predicted, the upstream and downstream road sections;
s5, optimizing parameters C and gamma of the SVR model by adopting a particle swarm algorithm according to the space-time state vector to obtain an optimal SVR prediction model;
s6, inputting the test sample into the prediction model obtained in the S5 to obtain a prediction result;
and S7, optimizing S5 prediction model parameters according to the real-time prediction error feedback.
Optionally, the step S1 includes:
s11, for the road section to be predicted, assuming that the time window granularity of the floating car speed data isThe time sequence of the data of one day is acquired as follows:
[v1,v2,…,vi,…,vn]
s12, determining an upstream road section and a downstream road section of the road section to be predicted according to the topological relation of the road network, and acquiring a time sequence formed by data of the upstream road section and the downstream road section in one day:
s13, obtaining traffic flow data of the section of the road section to be predicted, wherein the time when the vehicle j passes through the section of the road section is tjThe data format is as follows according to the time sequence:
[t1,t2,…,tj,…,tm]。
optionally, the step S2 includes:
and acquiring the traffic flow in each time window according to the passing time of each vehicle in one day, wherein the time sequence of acquiring the traffic flow is as follows:
[Q1,Q2,…,Qi,…,Qn]。
optionally, by counting time tjTraversing to obtain a traffic flow time sequence:
Optionally, the step S3 includes:
s31, historical speed data [ v ] of the target road section1,v2,v3,…,vn]As a one-dimensional time column v (t), it is subjected to wavelet decomposition of three layers:
V(t)=c(t)·V1(t)+d(t)·V2(t)+e(t)·V3(t)
wherein, V1(t),V2(t),V3(t) is a low to high frequency component
S32. That is, the processed speed time-series data, the data of the upstream and downstream links are also processed in the same manner.
Optionally, the state vector constructed in step S4 is:
vt+Δspeed to be predicted, v, for the target road sectiont+ΔAnd vtThe time interval between is determined by the specific prediction case, vtIndicating the speed, v, of the current instant of the selected road sectiont-5,vt-4,vt-3,vt-2,vt-1,vtFor the speed of 6 backtracking time windows of the road section to be predictedAndspeed at the current time, Q, for the upstream and downstream road sectionstIs the current traffic flow of the target road segment.
Optionally, the step S5 specifically includes:
s51, setting the number of the groups and the maximum iteration number;
s52, initializing the velocity vector of the particle r according to the parameter to be optimizedAnd a position vectorAnd satisfies the following conditions:
s53, enabling the position parameter of the q-th iteration of the particles rRespectively as a punishment coefficient C and a width coefficient gamma of the SVR model to obtain the prediction result of the training setTaking the average absolute error of the real value of the data of the training set and the average absolute error of the real value of the data of the training set as a fitness function:
s54, updating the optimal position pbest (r, q) of the particle r and the optimal position gbest (q) of the q-th iteration particle swarm according to a fitness function:
s55, evolving the speed and the position of the particles according to the following formula:
s56, judging whether an algorithm ending condition is met, and if so, outputting an optimal parameter; otherwise, return to step S52.
The method can fuse floating car data of related road vehicles and traffic flow data collected by road equipment in two dimensions of time and space, can optimize a prediction model on line, can accurately predict the traffic flow of a road section in a short-term prediction manner, and provides real-time data support for intelligent traffic.
Drawings
A more complete appreciation of the invention and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein the accompanying drawings are included to provide a further understanding of the invention and form a part of this specification, and wherein the illustrated embodiments and descriptions thereof are intended to illustrate and not limit the invention, wherein:
FIG. 1 is a schematic diagram of a data preprocessing flow according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an SVR parameter optimization by particle swarm optimization according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages more comprehensible, the present invention is described in detail below with reference to the accompanying drawings and the detailed description.
The invention provides an online short-term traffic flow prediction method for a road section, which comprises the following steps:
s1, data collection: the speed data and traffic flow data of the floating vehicles on the target road section are collected, the speed data of the floating vehicles can be collected by vehicle-mounted map navigation software, mobile phone map navigation software and mobile phone GPS positioning software, and the traffic flow data can be obtained through geomagnetic sensing equipment and traffic checkpoints arranged on roads. The data of the target road section are processed to form a time sequence form, and a time window granularity of 5min is taken as an example, and the specific method comprises the following steps:
s11, constructing speed data of the target road section and arranging the speed data into a time sequence format, wherein the data of one day is as follows:
[v1,v2,…,vi,…,v288]
s12, constructing a time sequence of upstream and downstream speed data of the target road section: according to the topological relation of the road network, the upstream and downstream road sections of the target road section are screened and determined, and the time sequence formed by the data of one day is respectively as follows:
s13, traffic flow data: acquiring traffic flow data of a target road section cross section, wherein the time when a vehicle j passes through the road section cross section is tjThe data format is as follows according to the time sequence:
[t1,t2,…,tj,…,tm]
s2, multi-source data fusion: and converting the section traffic flow data of the road section and the speed data of the floating car into the same time window granularity. The specific method comprises the following steps:
in order to fuse the data of the geomagnetic sensor and the data of the floating car, the data of the geomagnetic sensor and the data of the floating car need to have the same time window granularity, namely the granularity of the time window of 5min, and the time sequence format formed by the traffic flow data calculated by the geomagnetic sensor is as follows:
[Q1,Q2,…,Qi,…,Q288]
the specific calculation method comprises the following steps: if it is not(k is an integer from 1 to 288), then Qk+ 1; completion for tjThe above traffic flow data can be obtained by calculation according to the traversal judgment.
S3, data preprocessing: the method for smoothing and denoising the time sequence formed by the floating car speed data by adopting a wavelet transform method comprises the following specific steps:
as shown in fig. 1, let v (t) be ═ v1,v2,v3,…v288]The wavelet basis function Db1 is adopted to carry out three-layer decomposition, the high-frequency part is removed, and reconstruction is carried out to obtain processed data, and the method specifically comprises the following steps:
s31, wavelet decomposition: historical speed data [ v ] of target road section1,v2,v3,L,vn]As a one-dimensional time column v (t), it is subjected to wavelet decomposition of three layers:
V(t)=c(t)·V1(t)+d(t)·V2(t)+e(t)·V3(t)
wherein, V1(t),V2(t),V3(t) is a low to high frequency component
S32, wavelet reconstruction: the high frequency component contains much noise interference, and in order to reduce the noise interference and ensure that the data is not distorted, the high frequency component V3(t) after removal, performing wavelet reconstruction: that is, the processed speed time-series data, the data of the upstream and downstream links are also processed in the same manner.
S4, constructing a space-time state vector: and forming the speed data of the road section to be predicted, the speed data of the upstream and downstream road sections and the flow data into a state vector. The specific method comprises the following steps:
by vtRepresenting the speed of the selected road section at the current moment, with 15min as the prediction interval, vt+3For the speed to be predicted of the selected road section, the current 30min speed v of the selected road sectiont-5,vt-4,vt-3,vt-2,vt-1As the feature input amount, the feature input variable of the upstream and downstream road sections selected in consideration of the spatial feature isAndtraffic flow Q obtained from multi-source datatThe state vector thus constructed is:
and S5, optimizing the parameters C and gamma of the SVR model by adopting a particle swarm algorithm to obtain an optimal SVR prediction model.
The svr (supported Vector regression) model is a model in which support vectors are applied in the field of functional regression.
As shown in fig. 2, the specific method is:
1) initializing, setting the number of population to be 50 and the maximum iteration number to be 200
2) Initializing the velocity vector of the particle r according to the parameter to be optimizedAnd a position vectorAnd satisfies the following conditions:
3) the position parameter of the q-th iteration of the particle r is used in the training setRespectively as a punishment coefficient C and a width coefficient gamma of the SVR model to obtain the prediction result of the training setThe Mean Absolute Error (MAE) of the mean absolute error with the true value of the training set data is taken as the fitness function:
and updating the optimal position pbest (r, q) of the particle r and the optimal position gbest (q) of the q-th iteration particle swarm according to the condition of the fitness function.
4) The velocity and position of the particles were evolved according to the following formula:
5) judging whether an algorithm ending condition is met, and if so, outputting an optimal parameter; otherwise, returning to step 2)
And S6, inputting the state vector to be predicted into the prediction model obtained in the S5 to obtain a prediction result.
And S7, further updating the parameters of the model according to the real-time prediction error feedback.
The method can fuse floating car data of related road vehicles and traffic flow data collected by road equipment in two dimensions of time and space, can update and optimize the adopted prediction model on line, can accurately predict the traffic flow of a road section in a short time, and provides real-time data support for intelligent traffic.
Although specific embodiments of the present invention have been described above, it will be appreciated by those skilled in the art that these specific embodiments are merely illustrative and that various omissions, substitutions and changes in the form of the details of the algorithm and system described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the steps of the above-described algorithms to perform substantially the same function in substantially the same algorithm to achieve substantially the same result. Accordingly, the scope of the invention is to be limited only by the following claims.
Claims (7)
1. An online short-term traffic flow prediction method for a road section is characterized by comprising the following steps:
s1, acquiring floating vehicle speed data and traffic flow data of a road section, and processing the data into a time sequence form respectively;
s2, converting the floating vehicle speed data time sequence and the traffic flow data time sequence into the same time window granularity;
s3, smoothing and denoising the speed data time sequence of the floating car by utilizing wavelet transformation;
s4, constructing a space-time state vector based on the speed data time sequence and the traffic flow data time sequence of the road section to be predicted, the upstream and downstream road sections;
s5, optimizing parameters C and gamma of the SVR model by adopting a particle swarm algorithm according to the space-time state vector to obtain an optimal SVR prediction model;
s6, inputting the test sample into the prediction model obtained in the S5 to obtain a prediction result;
and S7, optimizing S5 prediction model parameters according to the real-time prediction error feedback.
2. The method of claim 1, further characterized in that said step S1 comprises:
s11, for the road section to be predicted, assuming that the time window granularity of the floating car speed data isThe time sequence of the data of one day is acquired as follows:
[v1,v2,…,vi,…,vn]
s12, determining an upstream road section and a downstream road section of the road section to be predicted according to the topological relation of the road network, and acquiring a time sequence formed by data of the upstream road section and the downstream road section in one day:
s13, obtaining traffic flow data of the section of the road section to be predicted, wherein the time when the vehicle j passes through the section of the road section is tjThe data format is as follows according to the time sequence:
[t1,t2,…,tj,…,tm]。
3. the method according to claim 1, wherein the step S2 includes:
and acquiring the traffic flow in each time window according to the passing time of each vehicle in one day, wherein the time sequence of acquiring the traffic flow is as follows:
[Q1,Q2,…,Qi,…,Qn]。
5. The method of claim 1, further characterized in that said step S3 comprises:
s31, historical speed data [ v ] of the target road section1,v2,v3,…,vn]As a one-dimensional time column v (t), it is subjected to wavelet decomposition of three layers:
V(t)=c(t)·V1(t)+d(t)·V2(t)+e(t)·V3(t)
wherein, V1(t),V2(t),V3(t) is a low to high frequency component
6. The method according to claim 1, further characterized in that the state vector constructed in step S4 is:
vt+Δspeed to be predicted, v, for the target road sectiont+ΔAnd vtThe time interval between is determined by the specific prediction case, vtPresentation instrumentSpeed, v, of the road section at the current momentt-5,vt-4,vt-3,vt-2,vt-1,vtFor the speed of 6 backtracking time windows of the road section to be predictedAndspeed at the current time, Q, for the upstream and downstream road sectionstIs the current traffic flow of the target road segment.
7. The method according to claim 1, wherein the step S5 specifically includes:
s51, setting the number of the groups and the maximum iteration number;
s52, initializing the velocity vector of the particle r according to the parameter to be optimizedAnd a position vectorAnd satisfies the following conditions:
s53, enabling the position parameter of the q-th iteration of the particles rRespectively as a punishment coefficient C and a width coefficient gamma of the SVR model to obtain the prediction result of the training setTaking the average absolute error of the real value of the data of the training set and the average absolute error of the real value of the data of the training set as a fitness function:
s54, updating the optimal position pbest (r, q) of the particle r and the optimal position gbest (q) of the q-th iteration particle swarm according to a fitness function:
s55, evolving the speed and the position of the particles according to the following formula:
s56, judging whether an algorithm ending condition is met, and if so, outputting an optimal parameter; otherwise, return to step S52.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911067916.8A CN110930693B (en) | 2019-11-04 | 2019-11-04 | Online short-term traffic flow prediction method for road section |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911067916.8A CN110930693B (en) | 2019-11-04 | 2019-11-04 | Online short-term traffic flow prediction method for road section |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110930693A true CN110930693A (en) | 2020-03-27 |
CN110930693B CN110930693B (en) | 2022-02-22 |
Family
ID=69852369
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911067916.8A Active CN110930693B (en) | 2019-11-04 | 2019-11-04 | Online short-term traffic flow prediction method for road section |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110930693B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112651570A (en) * | 2020-12-31 | 2021-04-13 | 长安大学 | Method and device for constructing and predicting traffic prediction model of expressway service area |
CN113111143A (en) * | 2021-04-09 | 2021-07-13 | 河南交通发展研究院有限公司 | Road multi-source heterogeneous data reconstruction integration and support sharing complete method and system |
CN115440029A (en) * | 2022-07-29 | 2022-12-06 | 重庆大学 | Vehicle inspection device data restoration method considering distribution of detection equipment |
CN116978222A (en) * | 2023-07-24 | 2023-10-31 | 重庆邮电大学 | Short-time traffic flow prediction method based on space-time data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001084479A (en) * | 1999-09-14 | 2001-03-30 | Matsushita Electric Ind Co Ltd | Method and device for forecasting traffic flow data |
CN203288091U (en) * | 2013-06-09 | 2013-11-13 | 长安大学 | City traffic flow forecast device |
CN104408913A (en) * | 2014-11-03 | 2015-03-11 | 东南大学 | Traffic flow three parameter real time prediction method taking regard of space-time correlation |
CN104599501A (en) * | 2015-01-26 | 2015-05-06 | 大连理工大学 | Traffic flow forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm |
CN106781465A (en) * | 2016-12-06 | 2017-05-31 | 广州市科恩电脑有限公司 | A kind of road traffic Forecasting Methodology |
CN106781464A (en) * | 2016-12-06 | 2017-05-31 | 广州市科恩电脑有限公司 | A kind of congestion in road situation method of testing |
CN108320516A (en) * | 2018-04-08 | 2018-07-24 | 华中师范大学 | Road passage capability evaluation method based on Cusp Catastrophe and quantum telepotation |
-
2019
- 2019-11-04 CN CN201911067916.8A patent/CN110930693B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001084479A (en) * | 1999-09-14 | 2001-03-30 | Matsushita Electric Ind Co Ltd | Method and device for forecasting traffic flow data |
CN203288091U (en) * | 2013-06-09 | 2013-11-13 | 长安大学 | City traffic flow forecast device |
CN104408913A (en) * | 2014-11-03 | 2015-03-11 | 东南大学 | Traffic flow three parameter real time prediction method taking regard of space-time correlation |
CN104599501A (en) * | 2015-01-26 | 2015-05-06 | 大连理工大学 | Traffic flow forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm |
CN106781465A (en) * | 2016-12-06 | 2017-05-31 | 广州市科恩电脑有限公司 | A kind of road traffic Forecasting Methodology |
CN106781464A (en) * | 2016-12-06 | 2017-05-31 | 广州市科恩电脑有限公司 | A kind of congestion in road situation method of testing |
CN108320516A (en) * | 2018-04-08 | 2018-07-24 | 华中师范大学 | Road passage capability evaluation method based on Cusp Catastrophe and quantum telepotation |
Non-Patent Citations (2)
Title |
---|
许子鑫: "基于支持向量回归的短时交通流预测方法研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
陆文琦 等: "基于时空融合的城市快速路短时交通流预测", 《计算机仿真》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112651570A (en) * | 2020-12-31 | 2021-04-13 | 长安大学 | Method and device for constructing and predicting traffic prediction model of expressway service area |
CN113111143A (en) * | 2021-04-09 | 2021-07-13 | 河南交通发展研究院有限公司 | Road multi-source heterogeneous data reconstruction integration and support sharing complete method and system |
CN115440029A (en) * | 2022-07-29 | 2022-12-06 | 重庆大学 | Vehicle inspection device data restoration method considering distribution of detection equipment |
CN115440029B (en) * | 2022-07-29 | 2023-08-08 | 重庆大学 | Vehicle detector data restoration method considering detection equipment distribution |
CN116978222A (en) * | 2023-07-24 | 2023-10-31 | 重庆邮电大学 | Short-time traffic flow prediction method based on space-time data |
CN116978222B (en) * | 2023-07-24 | 2024-04-16 | 重庆邮电大学 | Short-time traffic flow prediction method based on space-time data |
Also Published As
Publication number | Publication date |
---|---|
CN110930693B (en) | 2022-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110930693B (en) | Online short-term traffic flow prediction method for road section | |
Emami et al. | Using Kalman filter algorithm for short-term traffic flow prediction in a connected vehicle environment | |
Cheng et al. | Short-term traffic forecasting: An adaptive ST-KNN model that considers spatial heterogeneity | |
Zhao et al. | Travel time prediction: Based on gated recurrent unit method and data fusion | |
Kumar et al. | Short term traffic flow prediction in heterogeneous condition using artificial neural network | |
Zhao et al. | Truck traffic speed prediction under non-recurrent congestion: Based on optimized deep learning algorithms and GPS data | |
Dou et al. | A hybrid CEEMD-GMM scheme for enhancing the detection of traffic flow on highways | |
Yan et al. | Spatial-temporal chebyshev graph neural network for traffic flow prediction in iot-based its | |
Cheng et al. | Short-term traffic forecasting by mining the non-stationarity of spatiotemporal patterns | |
Zhao et al. | Highway travel time prediction using sparse tensor completion tactics and k‐nearest neighbor pattern matching method | |
Xiao et al. | Speed estimation of traffic flow using multiple kernel support vector regression | |
Zeroual et al. | Road traffic density estimation and congestion detection with a hybrid observer-based strategy | |
Huang et al. | Physics-informed deep learning for traffic state estimation: Illustrations with LWR and CTM models | |
Gao et al. | Short-term traffic speed forecasting using a deep learning method based on multitemporal traffic flow volume | |
CN111583628B (en) | Road network heavy truck traffic flow prediction method based on data quality control | |
Wang et al. | Forecasting traffic volume at a designated cross-section location on a freeway from large-regional toll collection data | |
CN114879192A (en) | Decision tree vehicle type classification method based on road side millimeter wave radar and electronic equipment | |
Anusha et al. | Dynamical systems approach for queue and delay estimation at signalized intersections under mixed traffic conditions | |
Zhang et al. | Method of speed data fusion based on Bayesian combination algorithm and high‐order multi‐variable Markov model | |
Yu et al. | GPS data mining at signalized intersections for congestion charging | |
Dong et al. | An identification model of urban critical links with macroscopic fundamental diagram theory | |
Mead | Hybrid CNN and LSTM Model (HCLM) for Short-Term Traffic Volume Prediction | |
Sassella et al. | On queue length estimation in urban traffic intersections via inductive loops | |
CN111371609B (en) | Internet of vehicles communication prediction method based on deep learning | |
Zhao et al. | Travel time prediction based on pattern matching method |
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 |