CN104064023A - Dynamic traffic flow prediction method based on space-time correlation - Google Patents
Dynamic traffic flow prediction method based on space-time correlation Download PDFInfo
- Publication number
- CN104064023A CN104064023A CN201410272800.9A CN201410272800A CN104064023A CN 104064023 A CN104064023 A CN 104064023A CN 201410272800 A CN201410272800 A CN 201410272800A CN 104064023 A CN104064023 A CN 104064023A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- data
- neighbour
- matrix
- 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.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of intelligent traffic, in particular to a dynamic traffic flow prediction method based on space-time correlation. The method comprises the steps that a space-time matrix is established after traffic flow data are preprocessed, an adjacent local linear reconstitution method is used for training the space-time matrix, a set of adjacent and weight values used for prediction are found out, prediction is conducted after non-negative correction, and at last the space-time matrix is updated through a prediction value. The dynamic traffic flow prediction method based on space-time correlation has the advantages that the adaptability is high, the method is suitable for any microwave detection road section; the feasibility is high, the data can be trained and predicted as long as a historical traffic flow database is given; the calculation speed is high, the complexity is low, and the calculation time is in a second level; the prediction precision is high, the randomness and volatility of dynamic data are removed, and the accuracy and reliability of a prediction result are improved; the prediction efficiency is high, multi-step traffic flow prediction of multiple five-minute time periods can be achieved, and high-efficiency short-time and long-time traffic flow prediction can be achieved.
Description
Technical field
The present invention relates to intelligent transportation field, relate in particular to a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation.
Background technology
Along with social development and economic growth, urban traffic jam is more serious.For the Effective Regulation magnitude of traffic flow, optimize the service efficiency of road, intelligent transportation system becomes the emphasis that people pay close attention to, and along with deeply progressively intellectuality, mobilism and the informationization of studying.As the important component part of intelligent transportation system, the effective way that vehicle guidance system has become vehicle supervision department dredges road traffic, and its gordian technique is the prediction to road traffic condition, effectively utilize historical traffic data and real time traffic data to carry out performance prediction to the magnitude of traffic flow of following moment road.Traffic flow forecasting mainly comprises two parts: set up magnitude of traffic flow historical data base and build forecast model.By historical data base being carried out to pre-service and utilizing algorithm that forecast model provides to train and draw and predict the outcome data.Aspect these two, predictive model algorithm is the most insoluble key component wherein, and its direct relation the quality predicting the outcome, and is the Focal point and difficult point of traffic flow forecasting.
At present the method for traffic flow forecasting is mainly contained to the historical method of average, neural network model, support vector regression, least square method, time series method etc.Said method is simple to operate, and convenience of calculation is suitable for compared with the prediction of rule data, but the more complicated and irregular fluctuation of the unstable data stream causing of traffic flow for road model, predictablity rate is lower.In addition, most methods is all to predict according to property time correlation, has ignored the relevance of the magnitude of traffic flow on section, space, makes to predict the outcome accurate not.Therefore,, in order to overcome the random fluctuation of dynamic data and the unstable prediction effect that fluctuation brings and the impact of considering space, section, need to introduce new method the magnitude of traffic flow is predicted on spacetime correlation.
Summary of the invention
The present invention overcomes above-mentioned weak point, and object is to provide a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation with high accuracy, reliability.
The present invention achieves the above object by the following technical programs: a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation, comprising:
1) by layout, the data acquisition equipment on microwave section gathers historical traffic flows data, predicts the traffic flow data that be T interval time on the same day;
2) traffic flow data carries out pre-service, cleans extraneous data, and missing data is carried out to data interpolation according to threshold value is set;
3) taking data acquisition time as the longitudinal axis, microwave section is transverse axis, empty matrix while building traffic flow data;
4) while carrying out the traffic flow data based on the reconstruct of neighbour's local linear, empty matrix training, finds the weight matrix and the test sample book neighbour that predict use;
5) weight matrix is carried out to non-negative correction, set up the weight matrix of the linear positive weighting of neighbour;
6) carry out traffic flow forecasting according to weight matrix and test sample book neighbour, predictor formula is:
wherein: X
ijfor test specimens X
ij neighbour, w
ijfor sample X
ij neighbour's weights, K ' is weight matrix length, K ' is less than test sample book neighbour number;
7) traffic flow data of prediction and True Data are contrasted, obtain predicated error;
8) empty matrix while predicted value being added to traffic flow data, and remove the flow value in moment the earliest, empty matrix while being combined to form new traffic flow data, repeating step 4).
As preferably, described traffic flow data pre-service comprises the following steps:
2.1) it is the mean value of this time point data on flows in history that data cleansing: T minute inside lane flow is greater than 300 data replacement;
2.2) missing values interpolation: for the disappearance of T minutes groove data on certain microwave section, utilize linear programming method:
min||x||
1st. Ax=y (2)
Wherein, the each microwave link flow in complete T minutes groove is shown in history in the list of matrix A, vector y represents the non-disappearance part of the each link flow of T time slot that has disappearance, and x represents the coefficient vector of each column vector in the time of linear reconstruct y in A, and solving the x obtaining is sparse vector.
As preferably, described step 4) in empty matrix training when traffic flow data based on the reconstruct of neighbour's local linear, specifically comprise the following steps:
4.1) taking predicted time point traffic flow data as test sample book, before this time point, the traffic flow data of moment and historical time is training sample, taking different microwaves section data as basis, calculation training sample and the test sample book Euclidean distance under spacetime correlation, finds out K the neighbour of K the minimum training sample of distance as test sample book; Euclidean distance between two vectors is as follows:
Wherein n is vector length, X
ifor test sample book, x
iand y
ibe respectively the element in vectorial X and Y;
4.2) calculate weight matrix:
Set up error minimize function:
Wherein, X
i
For test sample book, N is total sample number, X
ijfor test sample book X
ij neighbour, neighbour adds up to K, w
ijfor sample X
ij neighbour's weights.The local covariance matrix of sample is: C
jk(i)=(X
i-X
ij)
t(X
i-X
ik) (5), be the matrix of a KxK, it is carried out to Regularization and obtain C
jk(i)=C
jk(i)+rI (6), the unit matrix that wherein I is KxK, r is regularization coefficient; Can obtain weights according to local covariance matrix:
As preferably, described interval time, T was 5 minutes.
Beneficial effect of the present invention is: 1, applicability is strong, has gathered the traffic flow data of multiple different microwave points, can be applicable to any microwave and detect section; 2, feasibility is strong, only needs given historical traffic flows database, just can data be trained and be predicted; 3, computing velocity is fast, and the method complicacy is lower, and for hundreds of thousands bar data, be a second level computing time; 4, precision of prediction is high, and the inventive method has been eliminated randomness and the undulatory property of dynamic data, reduces predicted data error, has improved the accuracy and the reliability that predict the outcome; 5, forecasting efficiency is high, and the inventive method can realize the multistep forecasting traffic flow of multiple 5 minutes sections, forecasting traffic flow can accomplish efficiently in short-term with length time, and precision of prediction kept stable.
Brief description of the drawings
Fig. 1 is flow chart of steps of the present invention;
Fig. 2 is that the inventive method and the historical method of average contrast schematic diagram in the volume forecasting result of [2013-9-5] 10:45 on the same day and the fitting effect of actual value;
Fig. 3 is that the inventive method and the historical method of average contrast schematic diagram in the volume forecasting result of [2013-9-5] 10:50 on the same day and the fitting effect of actual value;
Fig. 4 is that the inventive method and the historical method of average contrast schematic diagram in the volume forecasting result of [2013-9-5] 10:55 on the same day and the fitting effect of actual value;
Fig. 5 is that the inventive method and the historical method of average contrast schematic diagram in the volume forecasting result of [2013-9-5] 11:00 on the same day and the fitting effect of actual value;
Fig. 6 be the inventive method and the historical method of average in 45 minutes grooves based on predicted value basis on the error schematic diagram of prediction again.
Embodiment
Below in conjunction with specific embodiment, the present invention is described further, but protection scope of the present invention is not limited in this:
Embodiment 1: as shown in Figure 1, a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation comprises the following steps:
Step 1: gather multiple microwave road section traffic volume flow data of historical traffic flows data and prediction Time of Day point, wherein data are the Short-Term Traffic Flow data of every 5 minutes.
Step 2: traffic flow microwave data pre-service.
2.1) data cleansing.Because the data that data collector fault or other reasons cause are undesired, need to clean it, cleaning rule is as follows:
5 minutes inside lane flows are greater than at 300 o'clock and think that these data are abnormal, are the mean value of this time point data on flows in history by this data replacement.
2.2) missing values interpolation.Due to the shortage of data that the factors such as communication equipment fault cause, need to carry out interpolation to missing values, interpolation rule is as follows:
For the disappearance of certain 5 minutes groove data of some section, utilize linear programming method to train other times and put the linear relationship in this disappearance section and other sections, then according to the data of the coefficient reconstruct disappearance section time point training.Linear programming is for solving following problems:
min||x||
1st. Ax=y (2)
Wherein, the each link flow in 5 complete in history minutes grooves is shown in the list of matrix A, and vectorial y represents the non-disappearance part of the each link flow of certain time slot that has disappearance, and x represents the coefficient vector of each column vector in the time of linear reconstruct y in A.According to formula (2), solving the x obtaining is sparse vector.
Step 3: empty matrix while building traffic flow data.By pretreated data, taking the 5 minutes grooves of continuous 30 days as the time longitudinal axis, all microwaves section is space transverse axis, builds the time empty matrix of traffic flow microwave data.
Step 4: the time empty matrix based on the reconstruct of neighbour's local linear is trained.
4.1) find neighbour.Taking certain time point traffic flow data as test sample book, before this time point, the data of moment and historical time are training sample, taking different microwaves section data as basis, calculation training sample and the test sample book Euclidean distance under spacetime correlation, finds out K the neighbour of K the minimum training sample of distance as test sample book.Euclidean distance between two vectors is as follows:
Wherein n is vector length, X
ifor test sample book, x
iand y
ibe respectively the element in vectorial X and Y.By trying to achieve the distance of test sample book and the each time point of training sample, and by sorting apart from size, K the neighbour that sample is exactly test sample book that distance is minimum.
4.2) calculate weight matrix W.
Set up error minimize function:
Wherein, X
ifor test sample book, N is total sample number, X
ijtest sample book X
ij neighbour, neighbour adds up to K, w
ijfor sample X
ij neighbour's weights.The local covariance matrix of sample is: C
jk(i)=(X
i-X
ij)
t(X
i-X
ik) (5), be the matrix of a KxK, it is carried out to Regularization and obtain C
jk(i)=C
jk(i)+rI (6), the unit matrix that wherein I is KxK, r is regularization coefficient; Can obtain weights according to local covariance matrix:
Step 5: weight matrix is carried out to non-negative correction, set up the weight matrix of the linear positive weighting of neighbour.
To being negative item in weight matrix W, more accurate for making to predict the outcome, will be in W be made as 0 for negative, then be normalized, can obtain like this weight matrix of the positive weighting of training set, the length of weight matrix will become K ', K '≤K.
Step 6: forecasting traffic flow.Calculate predicted value according to weight matrix and neighbour, predicted value is the traffic flow of next 5 minutes of test sample book time point, and computing formula is as follows:
Wherein X
ijit is the item that weights corresponding in neighbour are greater than 0.
Step 7: the error of calculating predicted value and actual value:
Wherein, Z
i' be the predicted value actual value in corresponding moment.
Step 8: time empty matrix incremental update.Empty matrix when predicted value is added, and remove the flow value in moment the earliest, be combined to form new time empty matrix, repeat said process, carry out multi-step prediction.
Using many sections microwave point being set in city, Hangzhou as acquisition target, in taking [2013-8-7] to [2013-9-5] continuous 30 days, 10:00 is the period of sampling to 11:00 every day, add up every 5 minutes by the vehicle number of microwave point on section, as magnitude of traffic flow source data.In when training, with predicted time point before half an hour and in history in 30 days this time point and above halfhour data predict.Data taking 10:00 to 10:40 are training sample set, and 2013-9-5 10:45 on the same day is test sample book collection to the data of 11:00, and the model of traffic flux forecast obtaining according to training is carried out the volume forecasting of 2013-9-5 10:45 on the same day to 11:00.
Before prediction, first need traffic flow data to carry out pre-service:
Data cleansing.The traffic flow data collecting is cleaned according to said cleaning rule above, and cleaning threshold is 300, and the flow that is greater than 300 is replaced with to the mean value of this time point data on flows in history.
Missing values interpolation.In the data that collect, for the disappearance of certain 5 minutes groove data of some section, utilize linear programming method to train other times and put the linear relationship in this disappearance section and other sections, then according to the data of the coefficient reconstruct disappearance section time point training.Linear programming can realize with the linprog function of matlab.
Empty matrix while utilizing the good traffic flow data of pre-service to build traffic flow data.Taking the traffic flow data of [2013-9-5] 10:35 on the same day as test sample book, in [2013-8-7] to [2013-9-4] continuous 29 days, 10:00 is training sample set to 10:30 and [2013-9-5] 10:00 on the same day to the data of 10:25, there are 209 time point data, each time point has 330 section microwave points, there are 330 data, the array that test sample book is 330*1, the time empty matrix that training sample is 330*209.
During to traffic flow data, empty matrix carries out training based on the reconstruct of neighbour's local linear.
First find neighbour.Calculate test sample book with time empty matrix in the Euclidean distance of 209 training samples, find out K apart from minimum training sample K the neighbour as test sample book, in the present invention, K gets 20.In like manner, the data on flows of putting front 209 time points taking the test duration when traffic flow data of [2013-9-5] 10:35 on the same day and 10:40 is test sample book is as training set.
Secondly calculate weight matrix W.Set up error minimize function:
Wherein, wherein, X
ifor test sample book, N is total sample number, X
ijfor test sample book X
ij neighbour, neighbour adds up to K=20, w
ij' be sample X
ij neighbour's weights.The local covariance matrix of sample is: C
jk(i)=(X
i-X '
ij)
t(X
i-X
ik) (5), be the matrix of a KxK, it is carried out to Regularization and obtain C
jk(i)=C
jk(i)+rI (6), the unit matrix that wherein I is KxK, r is regularization coefficient, the mark that in the present invention, r value is C is multiplied by 0.001, asks mark computing to try to achieve with the trace function of Matlab; Can obtain weights according to local covariance matrix:
Step 5: weight matrix is carried out to non-negative correction, set up the weight matrix of the linear positive weighting of neighbour:
Each weight, after non-negative correction, meets w
j> > 0 and
wherein k ' is non-negative revised positive weights number.
Calculate predicted value according to non-negative revised weight matrix and 20 test sample book neighbours, predicted value is the traffic flow of next 5 minutes of test sample book time point, uses the training result of [2013-9-5] 10:30 on the same day to predict the magnitude of traffic flow of [2013-9-5] 10:35 on the same day.Computing formula is as follows:
Wherein X
ijit is the item that weights corresponding in neighbour are greater than 0.
Calculate the error of predicted value and actual value:
Wherein, Z
i' be the predicted value actual value in corresponding moment.
Complete after above-mentioned prediction, in order to reduce data stochastic error, increase forecasting accuracy, during to traffic flow data, empty matrix increment upgrades.Empty matrix when this moment, traffic flow data added by the predicted value of [2013-9-5] 10:35 on the same day and in first 29 days, and remove the flow value of 10:00 in 30 days, be combined to form new time empty matrix, repeat said process, the traffic flow of prediction [2013-9-5] 10:40 on the same day, so repeatedly, carry out multi-step prediction.
As shown in Figures 2 to 5, be respectively prediction [2013-9-5] 10:45 on the same day, 10:50,10:55, the volume forecasting result of 11:00 and the fitting effect of actual value contrast schematic diagram, in figure, 330 section microwave points on fitting result chart are divided into 3 parts, (a) figure is the volume forecasting fitting result chart of front 1 to No. 110 microwave point, (b) figure is the fitting result chart of 111 to No. 220 microwave points, and (c) figure is the fitting result chart of 221 to No. 330 microwave points.Can see, for the larger section of magnitude of traffic flow fluctuation, the inventive method can obtain predicting the outcome more accurately.
As shown in Figure 6, the inventive method and the historical method of average are compared, show that historical method of average precision of prediction is 78%, the inventive method precision of prediction reaches 85%, has greatly improved the accuracy of prediction, meets the accuracy requirement of traffic flow forecasting.In addition, for the multi-step prediction on fundamentals of forecasting, the inventive method precision of prediction remains on 83% left and right, and precision of prediction and stability are all higher.
Described in above, be specific embodiments of the invention and the know-why used, if the change of doing according to conception of the present invention, when its function producing does not exceed spiritual that instructions and accompanying drawing contain yet, must belong to protection scope of the present invention.
Claims (4)
1. the Dynamic Traffic Flow Prediction method based on spacetime correlation, is characterized in that comprising:
1) by layout, the data acquisition equipment on microwave section gathers historical traffic flows data, predicts the traffic flow data that be T interval time on the same day;
2) traffic flow data carries out pre-service, cleans extraneous data, and missing data is carried out to data interpolation according to threshold value is set;
3) taking data acquisition time as the longitudinal axis, microwave section is transverse axis, empty matrix while building traffic flow data;
4) while carrying out the traffic flow data based on the reconstruct of neighbour's local linear, empty matrix training, finds the weight matrix and the test sample book neighbour that predict use;
5) weight matrix is carried out to non-negative correction, set up the weight matrix of the linear positive weighting of neighbour;
6) carry out traffic flow forecasting according to weight matrix and test sample book neighbour, predictor formula is:
wherein: X
ijfor test sample book X
ij neighbour, w
ijfor sample X
ij neighbour's weights, K ' is weight matrix length, K ' is less than test sample book neighbour number;
7) traffic flow data of prediction and True Data are contrasted, obtain predicated error;
8) empty matrix while predicted value being added to traffic flow data, and remove the flow value in moment the earliest, empty matrix while being combined to form new traffic flow data, repeating step 4).
2. a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation according to claim 1, is characterized in that, described traffic flow data pre-service comprises the following steps:
2.1) it is the mean value of this time point data on flows in history that data cleansing: T minute inside lane flow is greater than 300 data replacement;
2.2) missing values interpolation: for the disappearance of T minutes groove data on certain microwave section, utilize linear programming method:
min||x||
1st. Ax=y (2)
Wherein, the each microwave link flow in complete T minutes groove is shown in history in the list of matrix A, vector y represents the non-disappearance part of the each link flow of T time slot that has disappearance, and x represents the coefficient vector of each column vector in the time of linear reconstruct y in A, and solving the x obtaining is sparse vector.
3. a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation according to claim 1, is characterized in that described step 4) in empty matrix training when traffic flow data based on the reconstruct of neighbour's local linear, specifically comprise the following steps:
4.1) taking predicted time point traffic flow data as test sample book, before this time point, the traffic flow data of moment and historical time is training sample, taking different microwaves section data as basis, calculation training sample and the test sample book Euclidean distance under spacetime correlation, finds out K the neighbour of K the minimum training sample of distance as test sample book; Euclidean distance between two vectors is as follows:
Wherein n is vector length, X
ifor test sample book, x
iand y
ibe respectively the element in vectorial X and Y;
4.2) calculate weight matrix:
Set up error minimize function:
wherein, X
ifor test sample book, N is total sample number, X
ijfor test sample book X
ij neighbour, neighbour adds up to K, w
ijfor sample X
ij neighbour's weights.The local covariance matrix of sample is: C
jk(i)=(X
i-X
ij)
t(X
i-X
ik) (5), be the matrix of a KxK, it is carried out to Regularization and obtain C
jk(i)=C
jk(i)+rI (6), the unit matrix that wherein I is KxK, r is regularization coefficient; Can obtain weights according to local covariance matrix:
4. a kind of Dynamic Traffic Flow Prediction method based on spacetime correlation according to claim 1, is characterized in that, described interval time, T was 5 minutes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410272800.9A CN104064023B (en) | 2014-06-18 | 2014-06-18 | A kind of Dynamic Traffic Flow Prediction method based on space time correlation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410272800.9A CN104064023B (en) | 2014-06-18 | 2014-06-18 | A kind of Dynamic Traffic Flow Prediction method based on space time correlation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104064023A true CN104064023A (en) | 2014-09-24 |
CN104064023B CN104064023B (en) | 2016-12-07 |
Family
ID=51551709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410272800.9A Active CN104064023B (en) | 2014-06-18 | 2014-06-18 | A kind of Dynamic Traffic Flow Prediction method based on space time correlation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104064023B (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105006147A (en) * | 2015-06-19 | 2015-10-28 | 武汉大学 | Road segment travel time deducing method based on road space-time incidence relation |
CN105046956A (en) * | 2015-06-24 | 2015-11-11 | 银江股份有限公司 | Traffic flow simulating and predicting method based on turning probability |
CN105632193A (en) * | 2015-12-25 | 2016-06-01 | 银江股份有限公司 | Data missing road speed calculation method based on time-space relevance |
CN105679021A (en) * | 2016-02-02 | 2016-06-15 | 重庆云途交通科技有限公司 | Travel time fusion prediction and query method based on traffic big data |
CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
CN107944605A (en) * | 2017-11-10 | 2018-04-20 | 河海大学常州校区 | A kind of dynamic traffic paths planning method based on data prediction |
CN108492568A (en) * | 2018-04-25 | 2018-09-04 | 南京邮电大学 | A kind of Short-time Traffic Flow Forecasting Methods based on space-time characterisation analysis |
CN109034905A (en) * | 2018-08-03 | 2018-12-18 | 四川长虹电器股份有限公司 | The method for promoting sales volume prediction result robustness |
CN109272169A (en) * | 2018-10-10 | 2019-01-25 | 深圳市赛为智能股份有限公司 | Traffic flow forecasting method, device, computer equipment and storage medium |
CN109979195A (en) * | 2019-03-22 | 2019-07-05 | 浙江大学城市学院 | A kind of short-term traffic flow forecast method of the fusion Spatio-temporal factors based on sparse regression |
CN110113226A (en) * | 2019-04-16 | 2019-08-09 | 新华三信息安全技术有限公司 | A kind of method and device of detection device exception |
CN110444010A (en) * | 2018-05-02 | 2019-11-12 | 芝麻开门网络信息股份有限公司 | A kind of expressway wagon flow prediction technique based on Internet of Things |
CN110474815A (en) * | 2019-09-23 | 2019-11-19 | 北京达佳互联信息技术有限公司 | Bandwidth prediction method, apparatus, electronic equipment and storage medium |
CN110517479A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视系统技术有限公司 | A kind of urban highway traffic prediction technique, device and electronic equipment |
CN111444467A (en) * | 2020-04-21 | 2020-07-24 | 南京大学 | Method for local linear interpolation and prediction based on real-time positioning track data |
CN111583648A (en) * | 2020-05-14 | 2020-08-25 | 公安部交通管理科学研究所 | Urban traffic flow prediction method fusing GPS data and checkpoint flow data |
CN111724601A (en) * | 2020-06-30 | 2020-09-29 | 西安电子科技大学 | Motor vehicle traffic flow prediction method suitable for data loss |
CN113420414A (en) * | 2021-05-27 | 2021-09-21 | 四川大学 | Short-term traffic flow prediction model based on dynamic space-time analysis |
CN113761020A (en) * | 2021-07-30 | 2021-12-07 | 北京交通大学 | Real-time prediction method for abnormal large passenger flow of urban rail transit |
CN114255591A (en) * | 2021-12-17 | 2022-03-29 | 重庆中信科信息技术有限公司 | Short-term traffic flow prediction method and device considering space-time correlation and storage medium |
CN114566046A (en) * | 2022-03-01 | 2022-05-31 | 海南大学 | Short-time traffic condition prediction system and method thereof |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080033630A1 (en) * | 2006-07-26 | 2008-02-07 | Eun-Mi Lee | System and method of predicting traffic speed based on speed of neighboring link |
CN103247177A (en) * | 2013-05-21 | 2013-08-14 | 清华大学 | Large-scale road network traffic flow real-time dynamic prediction system |
CN103700255A (en) * | 2013-12-30 | 2014-04-02 | 复旦大学 | Time and space related data mining-based traffic flow prediction method |
-
2014
- 2014-06-18 CN CN201410272800.9A patent/CN104064023B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080033630A1 (en) * | 2006-07-26 | 2008-02-07 | Eun-Mi Lee | System and method of predicting traffic speed based on speed of neighboring link |
CN103247177A (en) * | 2013-05-21 | 2013-08-14 | 清华大学 | Large-scale road network traffic flow real-time dynamic prediction system |
CN103700255A (en) * | 2013-12-30 | 2014-04-02 | 复旦大学 | Time and space related data mining-based traffic flow prediction method |
Non-Patent Citations (1)
Title |
---|
张涛等: "基于K近邻非参数回归的短时交通流预测方法", 《系统工程理论与实践》 * |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105006147A (en) * | 2015-06-19 | 2015-10-28 | 武汉大学 | Road segment travel time deducing method based on road space-time incidence relation |
CN105046956A (en) * | 2015-06-24 | 2015-11-11 | 银江股份有限公司 | Traffic flow simulating and predicting method based on turning probability |
CN105632193A (en) * | 2015-12-25 | 2016-06-01 | 银江股份有限公司 | Data missing road speed calculation method based on time-space relevance |
CN105632193B (en) * | 2015-12-25 | 2017-12-22 | 银江股份有限公司 | A kind of shortage of data section speed calculation method based on space-time relationship |
CN105679021A (en) * | 2016-02-02 | 2016-06-15 | 重庆云途交通科技有限公司 | Travel time fusion prediction and query method based on traffic big data |
CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
CN106781457B (en) * | 2016-11-29 | 2019-04-30 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
CN107944605A (en) * | 2017-11-10 | 2018-04-20 | 河海大学常州校区 | A kind of dynamic traffic paths planning method based on data prediction |
CN107944605B (en) * | 2017-11-10 | 2021-07-30 | 河海大学常州校区 | Dynamic traffic path planning method based on data prediction |
CN108492568A (en) * | 2018-04-25 | 2018-09-04 | 南京邮电大学 | A kind of Short-time Traffic Flow Forecasting Methods based on space-time characterisation analysis |
CN108492568B (en) * | 2018-04-25 | 2020-06-12 | 南京邮电大学 | Short-term traffic flow prediction method based on time-space characteristic analysis |
CN110444010A (en) * | 2018-05-02 | 2019-11-12 | 芝麻开门网络信息股份有限公司 | A kind of expressway wagon flow prediction technique based on Internet of Things |
CN110517479A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视系统技术有限公司 | A kind of urban highway traffic prediction technique, device and electronic equipment |
CN110517479B (en) * | 2018-05-22 | 2020-11-03 | 杭州海康威视系统技术有限公司 | Urban road traffic prediction method and device and electronic equipment |
CN109034905A (en) * | 2018-08-03 | 2018-12-18 | 四川长虹电器股份有限公司 | The method for promoting sales volume prediction result robustness |
CN109272169A (en) * | 2018-10-10 | 2019-01-25 | 深圳市赛为智能股份有限公司 | Traffic flow forecasting method, device, computer equipment and storage medium |
CN109979195A (en) * | 2019-03-22 | 2019-07-05 | 浙江大学城市学院 | A kind of short-term traffic flow forecast method of the fusion Spatio-temporal factors based on sparse regression |
CN110113226A (en) * | 2019-04-16 | 2019-08-09 | 新华三信息安全技术有限公司 | A kind of method and device of detection device exception |
CN110113226B (en) * | 2019-04-16 | 2021-03-12 | 新华三信息安全技术有限公司 | Method and device for detecting equipment abnormity |
CN110474815A (en) * | 2019-09-23 | 2019-11-19 | 北京达佳互联信息技术有限公司 | Bandwidth prediction method, apparatus, electronic equipment and storage medium |
CN110474815B (en) * | 2019-09-23 | 2021-08-13 | 北京达佳互联信息技术有限公司 | Bandwidth prediction method and device, electronic equipment and storage medium |
US11374825B2 (en) | 2019-09-23 | 2022-06-28 | Beijing Daijia Internet Information Technology Co., Ltd. | Method and apparatus for predicting bandwidth |
CN111444467B (en) * | 2020-04-21 | 2022-03-15 | 南京大学 | Method for local linear interpolation and prediction based on real-time positioning track data |
CN111444467A (en) * | 2020-04-21 | 2020-07-24 | 南京大学 | Method for local linear interpolation and prediction based on real-time positioning track data |
CN111583648A (en) * | 2020-05-14 | 2020-08-25 | 公安部交通管理科学研究所 | Urban traffic flow prediction method fusing GPS data and checkpoint flow data |
CN111724601A (en) * | 2020-06-30 | 2020-09-29 | 西安电子科技大学 | Motor vehicle traffic flow prediction method suitable for data loss |
CN113420414A (en) * | 2021-05-27 | 2021-09-21 | 四川大学 | Short-term traffic flow prediction model based on dynamic space-time analysis |
CN113420414B (en) * | 2021-05-27 | 2022-08-30 | 四川大学 | Short-term traffic flow prediction model based on dynamic space-time analysis |
CN113761020A (en) * | 2021-07-30 | 2021-12-07 | 北京交通大学 | Real-time prediction method for abnormal large passenger flow of urban rail transit |
CN113761020B (en) * | 2021-07-30 | 2023-06-13 | 北京交通大学 | Urban rail transit abnormal large passenger flow real-time prediction method |
CN114255591A (en) * | 2021-12-17 | 2022-03-29 | 重庆中信科信息技术有限公司 | Short-term traffic flow prediction method and device considering space-time correlation and storage medium |
CN114566046A (en) * | 2022-03-01 | 2022-05-31 | 海南大学 | Short-time traffic condition prediction system and method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN104064023B (en) | 2016-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104064023A (en) | Dynamic traffic flow prediction method based on space-time correlation | |
Chacon-Hurtado et al. | Rainfall and streamflow sensor network design: a review of applications, classification, and a proposed framework | |
Wang et al. | Sequence transfer correction algorithm for numerical weather prediction wind speed and its application in a wind power forecasting system | |
CN109902801B (en) | Flood collective forecasting method based on variational reasoning Bayesian neural network | |
Ahmed et al. | An intelligent framework for short-term multi-step wind speed forecasting based on Functional Networks | |
CN111653088B (en) | Vehicle driving quantity prediction model construction method, prediction method and system | |
CN102568205A (en) | Traffic parameter short-time prediction method based on empirical mode decomposition and classification combination prediction in abnormal state | |
CN105243502B (en) | A kind of power station schedule risk appraisal procedure based on runoff interval prediction and system | |
CN111582551B (en) | Wind power plant short-term wind speed prediction method and system and electronic equipment | |
CN103632546B (en) | A kind of Urban Road Traffic Accidents impact prediction method based on floating car data | |
CN103942461A (en) | Water quality parameter prediction method based on online sequential extreme learning machine | |
CN105376097A (en) | Hybrid prediction method for network traffic | |
CN105046953A (en) | Short-time traffic-flow combination prediction method | |
CN106875033A (en) | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting | |
CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
Choudhury et al. | Optimal location selection for installation of surface water treatment plant by Gini coefficient-based analytical hierarchy process | |
CN105243428A (en) | Bus arrival time prediction method through optimizing support vector machine based on bat algorithm | |
CN105023071A (en) | Water quality prediction method based on Gaussian cloud transformation and fuzzy time sequence | |
CN104240520A (en) | GSO (glowworm swarm optimization) based highway traffic prediction method | |
CN103886223B (en) | Power forecasting method and system | |
CN107481523A (en) | A kind of traffic flow speed Forecasting Methodology and system | |
CN105303835B (en) | A kind of Forecasting Approach for Short-term of road traffic stream mode | |
Li et al. | Short-term passenger flow prediction of a passageway in a subway station using time space correlations between multi sites | |
Hou et al. | Road network state estimation using random forest ensemble learning | |
Zha et al. | Selection of time window for wind power ramp prediction based on risk model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee after: Yinjiang Technology Co.,Ltd. Address before: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee before: ENJOYOR Co.,Ltd. |