CN111583649A - Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data - Google Patents
Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data Download PDFInfo
- Publication number
- CN111583649A CN111583649A CN202010414026.6A CN202010414026A CN111583649A CN 111583649 A CN111583649 A CN 111583649A CN 202010414026 A CN202010414026 A CN 202010414026A CN 111583649 A CN111583649 A CN 111583649A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- traffic
- characteristic parameters
- predicting
- rfid
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000010219 correlation analysis Methods 0.000 claims abstract description 5
- 238000003062 neural network model Methods 0.000 claims description 15
- 238000011144 upstream manufacturing Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 12
- 230000007704 transition Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Chemical & Material Sciences (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Analytical Chemistry (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for predicting characteristic parameters of traffic flow of RFID (radio frequency identification) space-time data, which comprises the following steps of: s1: acquiring traffic data of an RFID acquisition target road section, and performing time-space correlation analysis on the traffic data; s2: obtaining the correlation between the traffic flow characteristic parameters influencing the traffic state of the target road section and the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section; s3: predicting traffic flow characteristic parameters of the target road section in a traffic flow stable state and a traffic flow unstable state; s4: and carrying out weighted combination on the traffic flow characteristic parameters in the two states. The invention overcomes the problems of large calculated amount, poor real-time performance and anti-interference capability, low prediction precision, low prediction efficiency and the like of the existing prediction method, can realize accurate, comprehensive and reliable prediction of the characteristic parameters of the traffic flow, and provides a new idea for improving the problem of traffic jam.
Description
Technical Field
The invention relates to the field of traffic, in particular to a method for predicting characteristic parameters of traffic flow of RFID (radio frequency identification) space-time data.
Background
Accurate, comprehensive and reliable grasp of traffic flow characteristic parameter prediction information is a precondition, a basis and a key for realizing traffic control, traffic guidance and providing real-time traffic information. At present, the prediction of traffic parameters at home and abroad is mostly analyzed and researched by a large amount of data acquired by a camera sensor, a loop coil, a taxi GPS, a floating car and the like. On the one hand, however, some sensors do not recognize vehicle information well in harsh environments; on the other hand, most of the data collected by some sensors are sampled data. The invention provides a novel RFID electronic license plate acquisition technology which is not influenced by weather, obtains full-sample data, and has the capability of efficiently and reliably sensing vehicle information.
By referring to related papers and patents, most of the existing traffic flow characteristic parameter prediction methods are large in calculation amount, poor in real-time performance and anti-interference capability, low in prediction precision, low in prediction efficiency and the like.
Disclosure of Invention
In view of the above, the present invention provides a method for predicting characteristic parameters of traffic flow of RFID spatiotemporal data.
The purpose of the invention is realized by the following technical scheme:
a method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data comprises the following steps:
s1: acquiring traffic data of an RFID acquisition target road section, and performing time-space correlation analysis on the traffic data;
s2: obtaining the correlation between the traffic flow characteristic parameters influencing the traffic state of the target road section and the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section;
s3: predicting traffic flow characteristic parameters of the target road section in a traffic flow stable state and a traffic flow unstable state;
s4: and carrying out weighted combination on the traffic flow characteristic parameters in the two states.
Further, the S1 specifically includes:
acquiring the RFID base station number and the vehicle ID number of each vehicle passing through a target road section and the time of the vehicle passing through an acquisition point;
superposing the acquired information data to form a space-time data matrix;
and analyzing the correlation of each sampling moment and the number of the acquisition points at the moment.
Further, the traffic flow characteristic parameters influencing the traffic state of the target road section comprise upstream standard vehicle flow, slow running vehicle proportion, large vehicle proportion and intersection steering flow proportion;
the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section comprise average travel time and standard vehicle flow of a downstream intersection.
Further, the correlation obtaining method in S2 includes:
yi＝b0+b1x1+b2x2+b3x3+b4x4
wherein the content of the first and second substances,
the partial regression coefficients are represented by the coefficients of partial regression,
x1is the upstream standard traffic flow, x2Is the ratio of slow-moving vehicles, x3Is the large scale vehicle proportion, x4The ratio of the turning flow of the intersection is obtained;
y1is said mean time of flight, y2And standard vehicle flow is obtained for the downstream intersection.
Further, the method for predicting the traffic flow characteristic parameter of the traffic flow unstable state comprises the following steps: establishing a compact wavelet neural network model, wherein an input layer is the ratio of the upstream standard traffic flow, the slow running proportion, the large-scale traffic proportion and the intersection steering flow, and an output layer is the average travel time and the downstream intersection standard traffic flow;
the method for predicting the traffic flow characteristic parameters of the traffic flow in the stable state comprises the following steps: and establishing a Markov model, and predicting the average travel time of the target road section at the next moment and the standard vehicle flow of the downstream intersection.
Further, the setting conditions of the weight of the weighted combination in S4 are as follows: the absolute error between the predicted average travel time and the actual average travel time is less than 2-4s, and the absolute error between the predicted standard traffic flow and the actual standard traffic flow is less than 1-2.5 pcu.
Further, when the setting condition is not satisfied, r is determinedW1And rM1、rW2And rM2The relationship of (1);
when r isW1Greater than rM1，rW2Greater than rM2And selecting the predicted value of the wavelet neural network model as a predicted result, otherwise, selecting the predicted value of the Markov model as the predicted result.
The invention has the beneficial effects that:
the invention overcomes the problems of large calculated amount, poor real-time performance and anti-interference capability, low prediction precision, low prediction efficiency and the like of the existing prediction method, can realize accurate, comprehensive and reliable prediction of the characteristic parameters of the traffic flow, and provides a new idea for improving the problem of traffic jam.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, in which:
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a compact wavelet neural network traffic parameter prediction model.
Detailed Description
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are illustrative of the invention only and are not limiting upon the scope of the invention.
The implementation provides a method for predicting characteristic parameters of traffic flow of RFID (radio frequency identification) space-time data, as shown in figure 1, specifically:
firstly, traffic data of an RFID acquisition target road section are obtained, and time-space correlation analysis is carried out on the traffic data. The RFID electronic license plate system reads a vehicle provided with an electronic tag through a reader arranged on a road, stores collected information in a database processing center, and pre-processes the data, wherein the collected vehicle data information mainly comprises an RFID base station number, a vehicle ID number, the time when the vehicle passes through a collection point and the like. And programming by using MySQL software according to the RFID base stations on the selected target road section and the RFID base stations on other road sections influencing the traffic state of the target road section, and inquiring the vehicle ID number, the passing time and the same driving direction of all the selected RFID base stations.
The acquired information is superposed to form a space-time data matrix, which specifically comprises the following steps:
in the formula, αmnAnd the information indicating that the RFID acquisition vehicle passes through the m-th acquisition point at the moment n.
To further illustrate the strong spatio-temporal correlation between data, the following are included: time correlation and space correlation are obtained, a space-time data window of each sampling moment and the number of acquisition points at the moment is obtained, the correlation between the two is analyzed by using covariance and covariance matrix, when the covariance is a positive value, the positive correlation between the two variables is described, otherwise, the negative correlation is described, and the calculation formula is as follows:
where X denotes a sampling time and Y denotes an acquisition point. In addition, for convenience of representation, only the spatio-temporal correlation is listed in the calculation formula, and the temporal correlation and the spatial correlation can also be represented. By analyzing the correlation, the traffic flow characteristic parameters selected and calculated at different acquisition points at the same time, the same acquisition points at different times and different acquisition points at different times can be obtained. And taking the traffic flow characteristic parameters capable of influencing the traffic state of the target road section as input of the established model, and taking the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section as predicted values output by the established model.
A prediction time window is set, the time window of the embodiment is set to 60S, and the time unit of each prediction is second.
Thirdly, in order to enable the selected traffic flow characteristic parameters to be sufficiently reflected on the established combination model, a wavelet neural network model and a Markov model are respectively adopted to predict the traffic flow characteristic parameters of the target road section, wherein the traffic flow characteristic parameters comprise the traffic flow characteristic parameters capable of influencing the traffic state of the target road section and the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section, and the traffic flow characteristic parameters capable of influencing the traffic state of the target road section are independent variables X ═ { X ═ X1,x2,x3,x4}，x1,x2,x3,x4Respectively representing the upstream standard traffic flow, the slow running traffic proportion, the large-scale traffic proportion and the intersection steering traffic proportion as the input of a model, and the calculation method comprises the following steps:
the upstream standard traffic flow calculation formula: x is the number of1＝∑λm·Vm
The slow-speed vehicle proportion calculation formula is as follows: x is the number of2＝Vslow/Vall
The formula for calculating the proportion of the large-scale vehicle is as follows: x is the number of3＝Vbig/Vall
The intersection turning flow ratio calculation formula is as follows: x is the number of4＝Vrelative/Vobjective
In the formula, λmIs the conversion coefficient, V, of the m-th vehicle typemIs a unit timeThe number V of the m types of vehicles passing through the section of the RFID electronic license plate reader on the upstream road section in the workshopslowThe number V of slow-running vehicles with RFID electronic license plates installed on the cross section of a designated RFID electronic license plate collecting point in unit timebigThe number V of the large vehicles with the RFID electronic license plates installed on the cross section of the designated RFID electronic license plate collecting point in unit timeallThe number V of all motor vehicles provided with RFID electronic license plates in unit time through the section of the designated RFID electronic license plate acquisition pointrelativeRepresenting the number of vehicles entering a target section from a relevant section per unit of time, VobjectiveRepresenting the total number of vehicles traveling on the target road segment per unit time.
Y＝{y1,y2The method is characterized in that the method comprises the following steps of (1) taking a dependent variable as a model output prediction value, wherein the dependent variable respectively represents an average travel time and a standard traffic flow of a downstream intersection, and the calculation modes of the dependent variable and the model output prediction value are as follows:
the average travel time calculation formula:
the downstream standard traffic flow calculation formula: y is2＝∑λm·Vm
Wherein n represents the total number of vehicles passing through the target road section per unit time,
the section time of the kth vehicle passing through an RFID electronic license plate acquisition point of a downstream intersection of a target road section,
the section time, lambda, of the RFID electronic license plate acquisition point of the kth vehicle passing through the upstream intersection of the target road sectionmIs the conversion coefficient, V, of the m-th vehicle typemThe number of the m types of vehicles passing through the section where the RFID electronic license plate reader is located on the downstream road section in unit time.
In order to obtain the correlation between X and Y, a multiple regression correlation analysis model is established, and the calculation formula is as follows:
yi＝b0+b1x1+b2x2+b3x3+b4x4
wherein the content of the first and second substances,
the partial regression coefficients are represented by the coefficients of partial regression,
the wavelet neural network model is a method for predicting traffic flow characteristic parameters in a traffic flow unstable state, and specifically comprises the following steps: the theoretical model is as follows:
wherein, ω isijIs the weight, ω, connecting the input layer i and the hidden layer jjpIs the weight connecting the hidden layer j and the output layer p; psia,bIs a wavelet basis function; x is the number ofw(p) is an input variable of the compact wavelet neural network at the time p; σ denotes the transfer function.
As shown in fig. 2, the ratio of the standard traffic flow, the slow traffic ratio, the large traffic ratio and the intersection turning flow at the upstream side is used as an input layer of the wavelet neural network, the average travel time of the target road section and the standard traffic flow at the downstream side are used as an output layer, and the output values are used as the predicted values of the wavelet neural network model.
The Markov model is a method for predicting the average travel time and the standard vehicle flow of a downstream intersection aiming at a stable traffic state and selected traffic flow characteristic parameters. In order to construct a Markov traffic parameter prediction model, the state of a traffic parameter is required to be known, a state transition matrix is obtained according to the belonging traffic state, and urban road traffic characteristic parameters at the future moment are predicted by using the state transition matrix. The method comprises the following specific steps:
(1) determining the probability of a state transition as shown in the following equation:
in the formula, p (x)i(t-1))→xj(t)) represents the probability of the state transition to the state at time t-1, miIs represented by xiNumber of occurrences in different time periods, mijRepresenting a state xiTransition to State xjThe number of times.
(2) Determining a state transition matrix as shown in the following formula:
among them, the following conditions need to be satisfied:
(3) determining a state transition matrix as shown in the following formula:
xk＝x(t＝k)＝p×x(t＝k-1)
wherein x iskIt refers to a predicted value at time k, p is a state transition probability, and x (t ═ k-1) refers to a state boundary value.
(4) Determining a prediction equation as shown in the following formula:
yk＝Hxk+k
in the formula, ykWhat is shown is the observed value at time k,krepresenting the apparent noise at time k; denoted by H are observation coefficients, generally denoted by identity matrix E.
Aiming at the predicted values of a single model of the Markov model and the wavelet neural network model, the Markov model and the wavelet neural network model are weighted and combined to obtain the predicted value of a combined model with the following formula, which can be expressed as:
in the formula (I), the compound is shown in the specification,
is a predicted value of the wavelet neural network model,
as a predictor of the Markov model, k1，k2，k3，k4The weight is adaptively adjusted according to the error condition, and is specifically corrected according to the predicted error at the previous time, so that the predicted value meets the preset condition, where the preset condition adopted in this embodiment specifically is:
the absolute error between the predicted travel time and the actual travel time is less than 2-4s, the absolute error between the predicted standard traffic flow and the actual standard traffic flow is less than 1-2.5pcu, and if the set conditions are met, the predicted value is the result obtained by combined prediction, wherein the prediction error of the combined model can be expressed as:
in the formula: delta TW-M(t) is the absolute error of the predicted time of flight from the actual time of flight;
ΔQW-Mand (t) is the absolute error between the predicted standard traffic flow and the actual standard traffic flow.
And if the preset conditions are not met, further predicting the traffic parameters by adopting a 0-1 combined prediction model. The model predicts the traffic parameters based on wavelet neural network model prediction values and the correlation coefficient maximization criterion of Markov model prediction values and actual traffic true values so as to improve the prediction accuracy of the traffic parameters. The specific formula is as follows:
in the formula, rW1，rM1The predicted value of the travel time of the wavelet neural network model and the correlation coefficient of the predicted value of the travel time of the Markov model and the actual traffic true value are expressed as rW2，rM2The method is characterized in that the wavelet neural network model downstream standard traffic flow predicted value and the Markov model downstream standard traffic flow predicted value are expressed by the correlation coefficient with the actual traffic true value. When r isW1Greater than rM1，rW2Greater than rM2And the correlation between the predicted value and the actual value of the wavelet neural network model is higher, the predicted value and the actual value of the traffic parameter are closer, the predicted value of the wavelet neural network model is selected as a prediction result, and otherwise, the predicted value of the Markov model is selected as the prediction result.
And if t is less than 60, continuing to perform the steps, and continuing to predict the traffic flow characteristics at the next moment, otherwise, ending.
In order to verify the accuracy of the method, an average Absolute Error (MAE), an average Absolute Percentage Error (MAPE), a Mean Square Error (MSE), a Root Mean Square Error (RMSE), and a Mean Square Percentage Error (MSPE) are selected to analyze the prediction result, and the smaller the value is, the higher the prediction accuracy of the model is, the further the validity and the accuracy of the algorithm can be verified, the calculation formula is as follows:
the specific formula of MAE is:
the specific formula of MAPE is:
the specific formula for MSE is:
the specific formula of RMSE is:
the specific formula of MSPE is:
in the formula (I), the compound is shown in the specification,
it is shown that the predicted value is,
representing the actual values obtained in the actual traffic and N representing the number of predicted values.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (7)
1. A method for predicting characteristic parameters of traffic flow of RFID (radio frequency identification) space-time data is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring traffic data of an RFID acquisition target road section, and performing time-space correlation analysis on the traffic data;
s2: obtaining the correlation between the traffic flow characteristic parameters influencing the traffic state of the target road section and the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section;
s3: predicting traffic flow characteristic parameters of the target road section in a traffic flow stable state and a traffic flow unstable state;
s4: and carrying out weighted combination on the traffic flow characteristic parameters in the two states.
2. The method for predicting the characteristic parameters of the traffic flow by using the RFID space-time data according to claim 1, wherein the method comprises the following steps: the S1 specifically includes:
acquiring the RFID base station number and the vehicle ID number of each vehicle passing through a target road section and the time of the vehicle passing through an acquisition point;
superposing the acquired information data to form a space-time data matrix;
and analyzing the correlation of each sampling moment and the number of the acquisition points at the moment.
3. The method for predicting the characteristic parameters of the traffic flow by using the RFID space-time data according to claim 1, wherein the method comprises the following steps:
the traffic flow characteristic parameters influencing the traffic state of the target road section comprise upstream standard vehicle flow, slow running vehicle proportion, large vehicle proportion and intersection steering flow proportion;
the traffic flow characteristic parameters capable of reflecting the traffic state of the target road section comprise average travel time and standard vehicle flow of a downstream intersection.
4. The method for predicting the characteristic parameters of the traffic flow by using the RFID space-time data according to claim 3, wherein the method comprises the following steps: the correlation obtaining method of S2 includes:
yi＝b0+b1x1+b2x2+b3x3+b4x4
wherein the content of the first and second substances,
the partial regression coefficients are represented by the coefficients of partial regression,
x1is the upstream standard traffic flow, x2Is the slow speedDriving ratio, x3Is the large scale vehicle proportion, x4The ratio of the turning flow of the intersection is obtained;
y1is said mean time of flight, y2And standard vehicle flow is obtained for the downstream intersection.
5. The method for predicting the characteristic parameters of the traffic flow by using the RFID space-time data according to claim 4, wherein the method comprises the following steps:
the method for predicting the traffic flow characteristic parameters of the traffic flow unstable state comprises the following steps: establishing a compact wavelet neural network model, wherein an input layer is the ratio of the upstream standard traffic flow, the slow running proportion, the large-scale traffic proportion and the intersection steering flow, and an output layer is the average travel time and the downstream intersection standard traffic flow;
the method for predicting the traffic flow characteristic parameters of the traffic flow in the stable state comprises the following steps: and establishing a Markov model, and predicting the average travel time of the target road section at the next moment and the standard vehicle flow of the downstream intersection.
6. The method for predicting the characteristic parameters of the traffic flow by using the RFID space-time data according to claim 5, wherein the method comprises the following steps: the setting conditions of the weighted combination weight of S4 are as follows: the absolute error between the predicted average travel time and the actual average travel time is less than 2-4s, and the absolute error between the predicted standard traffic flow and the actual standard traffic flow is less than 1-2.5 pcu.
7. The method for predicting the characteristic parameters of the traffic flow by using the RFID space-time data according to claim 6, wherein the method comprises the following steps: when the setting condition is not satisfied, r is determinedW1And rM1、rW2And rM2The relationship of (1);
when r isW1Greater than rM1，rW2Greater than rM2And selecting the predicted value of the wavelet neural network model as a predicted result, otherwise, selecting the predicted value of the Markov model as the predicted result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010414026.6A CN111583649B (en) | 2020-05-15 | 2020-05-15 | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010414026.6A CN111583649B (en) | 2020-05-15 | 2020-05-15 | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111583649A true CN111583649A (en) | 2020-08-25 |
| CN111583649B CN111583649B (en) | 2022-02-01 |
Family
ID=72117564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010414026.6A Active CN111583649B (en) | 2020-05-15 | 2020-05-15 | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111583649B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233426A (en) * | 2020-11-23 | 2021-01-15 | 重庆市市政设计研究院有限公司 | Bridge real-time early warning method device and system based on RFID and multi-source data |
| CN115691164A (en) * | 2022-09-27 | 2023-02-03 | 广州玩鑫信息科技有限公司 | Intelligent traffic management method and system based on big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102985956A (en) * | 2010-06-29 | 2013-03-20 | 本田技研工业株式会社 | Method of displaying traffic congestion estimation |
| CN103745106A (en) * | 2014-01-10 | 2014-04-23 | 浙江银江研究院有限公司 | Short-term traffic flow forecasting method |
| CN104616498A (en) * | 2015-02-02 | 2015-05-13 | 同济大学 | Markov chain and neural network based traffic congestion state combined prediction method |
| CN106448156A (en) * | 2016-08-31 | 2017-02-22 | 广州地理研究所 | Automobile electronic identifier-based urban traffic operation state prediction method and device |
| DE102016216538A1 (en) * | 2016-09-01 | 2018-03-01 | Bayerische Motoren Werke Aktiengesellschaft | Method for operating a control device of a motor vehicle, control device and motor vehicle |
| CN108399745A (en) * | 2018-03-01 | 2018-08-14 | 北京航空航天大学合肥创新研究院 | A kind of city road network trend prediction method at times based on unmanned plane |
| CN109003446A (en) * | 2018-07-12 | 2018-12-14 | 重庆市城投金卡信息产业股份有限公司 | A kind of city based on RFID data is avoided the peak hour current effect analysis method |
| CN109961180A (en) * | 2019-03-15 | 2019-07-02 | 浙江工业大学 | A kind of short-term traffic flow forecast method based on temporal correlation |
-
2020
- 2020-05-15 CN CN202010414026.6A patent/CN111583649B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102985956A (en) * | 2010-06-29 | 2013-03-20 | 本田技研工业株式会社 | Method of displaying traffic congestion estimation |
| CN103745106A (en) * | 2014-01-10 | 2014-04-23 | 浙江银江研究院有限公司 | Short-term traffic flow forecasting method |
| CN104616498A (en) * | 2015-02-02 | 2015-05-13 | 同济大学 | Markov chain and neural network based traffic congestion state combined prediction method |
| CN106448156A (en) * | 2016-08-31 | 2017-02-22 | 广州地理研究所 | Automobile electronic identifier-based urban traffic operation state prediction method and device |
| DE102016216538A1 (en) * | 2016-09-01 | 2018-03-01 | Bayerische Motoren Werke Aktiengesellschaft | Method for operating a control device of a motor vehicle, control device and motor vehicle |
| CN108399745A (en) * | 2018-03-01 | 2018-08-14 | 北京航空航天大学合肥创新研究院 | A kind of city road network trend prediction method at times based on unmanned plane |
| CN109003446A (en) * | 2018-07-12 | 2018-12-14 | 重庆市城投金卡信息产业股份有限公司 | A kind of city based on RFID data is avoided the peak hour current effect analysis method |
| CN109961180A (en) * | 2019-03-15 | 2019-07-02 | 浙江工业大学 | A kind of short-term traffic flow forecast method based on temporal correlation |
Non-Patent Citations (1)
| Title |
|---|
| 赵烨华等: "一种新的基于小波分析理论的组合预测方法", 《鲁东大学学报(自然科学版)》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233426A (en) * | 2020-11-23 | 2021-01-15 | 重庆市市政设计研究院有限公司 | Bridge real-time early warning method device and system based on RFID and multi-source data |
| CN112233426B (en) * | 2020-11-23 | 2024-02-02 | 重庆市市政设计研究院有限公司 | Bridge real-time early warning method device and system based on RFID and multi-source data |
| CN115691164A (en) * | 2022-09-27 | 2023-02-03 | 广州玩鑫信息科技有限公司 | Intelligent traffic management method and system based on big data |
| CN115691164B (en) * | 2022-09-27 | 2024-05-03 | 新疆北鹰北创信息科技有限公司 | Intelligent traffic management method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111583649B (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832225B (en) | Method for constructing driving condition of automobile | |
| CN103258427B (en) | Urban expressway traffic real-time monitoring system and method based on information physical network | |
| CN112382095B (en) | Urban expressway traffic state estimation method based on multi-source data fusion | |
| CN109272745B (en) | Vehicle track prediction method based on deep neural network | |
| CN109191845B (en) | Bus arrival time prediction method | |
| CN111583649B (en) | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data | |
| US20050091176A1 (en) | Forecasting apparatus | |
| CN109118787B (en) | Vehicle speed prediction method based on deep neural network | |
| CN111882869B (en) | Deep learning traffic flow prediction method considering adverse weather | |
| CN110889444B (en) | Driving track feature classification method based on convolutional neural network | |
| CN110930693B (en) | Online short-term traffic flow prediction method for road section | |
| CN110910531B (en) | Rapid pavement friction coefficient detection method based on vehicle-mounted OBD information | |
| CN115436972A (en) | Method, system and medium for identifying stop point based on heavy-duty truck GPS track | |
| CN111583628B (en) | Road network heavy truck traffic flow prediction method based on data quality control | |
| Zhi-Peng et al. | An improved adaptive exponential smoothing model for short-term travel time forecasting of urban arterial street | |
| CN112785077A (en) | Travel demand prediction method and system based on space-time data | |
| CN110796317A (en) | Urban taxi scheduling method based on demand prediction | |
| CN109979194B (en) | Heavy vehicle ramp crawling behavior identification method based on Markov chain | |
| Kumar B | Time series traffic flow prediction with hyper-parameter optimized arima models for intelligent transportation system | |
| CN113658423A (en) | Vehicle track abnormity detection method based on circulating gate control unit | |
| CN108053646B (en) | Traffic characteristic obtaining method, traffic characteristic prediction method and traffic characteristic prediction system based on time sensitive characteristics | |
| CN111524358B (en) | Regional radiation sexual communication flow prediction method | |
| Thu et al. | Multi-source data analysis for bike sharing systems | |
| CN112927507A (en) | Traffic flow prediction method based on LSTM-Attention | |
| CN116778715A (en) | Multi-factor intelligent prediction method for high-speed traffic flow |
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 |