CN109272169A - Traffic flow forecasting method, device, computer equipment and storage medium - Google Patents
Traffic flow forecasting method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109272169A CN109272169A CN201811177980.7A CN201811177980A CN109272169A CN 109272169 A CN109272169 A CN 109272169A CN 201811177980 A CN201811177980 A CN 201811177980A CN 109272169 A CN109272169 A CN 109272169A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- space
- traffic
- sample
- temporal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The present invention relates to traffic flow forecasting method, device, computer equipment and storage medium, this method includes obtaining traffic flow data；Traffic flow data is pre-processed, to form traffic flow sample；Temporal and spatial correlations coefficient is calculated according to traffic flow sample；Prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient；Using the road conditions of prediction model prediction current road segment next period, to obtain road condition predicting information.The present invention takes into account time-space relationship, influence using temporal and spatial correlations coefficient analysis adjacent segments to prediction road section traffic volume flow, have the space road section traffic volume flow data of highest related coefficient as independent variable for prediction road traffic delay, independent variable is mapped in high-dimensional feature space by support vector machines, and construct linear decision function within this space to predict road section traffic volume flow, short-time traffic flow forecast precision is improved, provides relatively reliable volume forecasting data for traffic control and induction.
Description
Technical field
The present invention relates to traffic flow forecasting methods, more specifically refer to traffic flow forecasting method, device, computer
Equipment and storage medium.
Background technique
With the fast development of China's economic society, the trip requirements of private car ownership and numerous residents are growing day by day,
Many traffic problems such as traffic congestion and traffic accident increasingly highlight, and become the problem that everybody pays close attention to jointly.It is quasi- in real time
True traffic flow forecasting is the key that intellectual traffic control and induction, helps to improve utilization efficiency and the people of means of transportation
Trip quality.
Traffic flow data is a kind of observation value set being sequentially arranged, and there are dependences between observation
And correlation, in the selection of predictive factor, not stringent theoretical foundation only only accounts for pre- existing short-term prediction algorithm
Sequencing column itself trend and continuity that are embodied in time, and have ignored between adjacent each sequence in space-time institute's body on the whole
Existing regularity is based on single section traffic flow temporal change characteristic, only focuses on changing rule of the traffic flow on historical time,
Lack the global analysis to city road network traffic flow, and has ignored influence of the adjacent segments traffic flow variation to prediction result；City
Section in city's road network be not it is isolated existing, predict road section traffic flow parameter in addition to following its own on time dimension
Outside changing rule, while being influenced by Spatial Dimensions traffic conditions such as adjacent segments, upstream and downstream sections, upstream road traffic delay
Downstream road section can be passed to similar distribution characteristics by road carrier, the traffic behavior of downstream road can also react on
Road is swum, therefore, the precision of current prediction algorithm is low, and volume forecasting data are unreliable.
Therefore, it is necessary to design a kind of new method, realization improves short-time traffic flow forecast precision, be traffic control and
Induction provides relatively reliable volume forecasting data.
Summary of the invention
It is an object of the invention to overcome the deficiencies of existing technologies, traffic flow forecasting method, device, computer are provided and set
Standby and storage medium.
To achieve the above object, the invention adopts the following technical scheme: traffic flow forecasting method, comprising:
Obtain traffic flow data；
Traffic flow data is pre-processed, to form traffic flow sample；
Temporal and spatial correlations coefficient is calculated according to traffic flow sample；
Prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient；
Using the road conditions of prediction model prediction current road segment next period, to obtain road condition predicting information.
Its further technical solution are as follows: it is described that traffic flow data is pre-processed, to form traffic flow sample, packet
It includes:
Remove exceptional value, trend term and the season in traffic flow data；
Stationarity is examined using Dickey-fowler to the traffic flow data after removal, to form traffic flow sample.
Its further technical solution are as follows: described that temporal and spatial correlations coefficient is calculated according to traffic flow sample, comprising:
The space-time relationship between traffic flow sample is determined based on space weight matrix and time delay；
The related coefficient of space adjacent segments different time lag value and traffic flow sample is calculated according to space-time relationship, with
Form temporal and spatial correlations coefficient.
Its further technical solution are as follows: it is described according to space-time relationship calculate space adjacent segments different time lag value with
The related coefficient of traffic flow sample, to form temporal and spatial correlations coefficient, comprising:
Several traffic flow samples of each section are combined to form column vector li=[x1,x2,...,xi]T(i=1,2,
3 ..., n), wherein xiFor traffic flow sample；
All traffic flow samples of section each in set period of time are constituted into matrix L=[l1,l2,...,li], (i=1,
2,3,…,n)；
UsingWherein, cov (LAi,LBi) it is with space-time relationship
Section A, B covariance of the traffic flow sample about time series；D(LAi) and D (LBi) it is respectively section A, B traffic flow sample
This parameter time series variance；ρABFor temporal and spatial correlations coefficient.
Its further technical solution are as follows: the traffic flow sample in the space section of the higher temporal and spatial correlations coefficient of basis constructs
Prediction model, comprising:
The traffic flow sample in the space section of higher temporal and spatial correlations coefficient is mapped into high-dimensional feature space as input quantity
In；
Construct the model mapped function relation between input quantity and output quantity；
Model mapped function relation is optimized, to obtain prediction model.
Its further technical solution are as follows: the road conditions using the prediction model prediction current road segment next period, with
To road condition predicting information, comprising:
Use the accuracy of the coefficient of determination and prediction Error Absolute Value mean measures model checking road condition predicting information.
The present invention also provides traffic flow forecasting devices, comprising:
Data capture unit, for obtaining traffic flow data；
Pretreatment unit, for being pre-processed to traffic flow data, to form traffic flow sample；
Coefficient calculation unit, for calculating temporal and spatial correlations coefficient according to traffic flow sample；
Mould is predicted in model construction unit, the traffic flow sample building for the space section according to higher temporal and spatial correlations coefficient
Type；
Predicting unit, for the road conditions using the prediction model prediction current road segment next period, to obtain road condition predicting
Information.
Its further technical solution are as follows: the pretreatment unit includes:
Subelement is handled, for removing the exceptional value in traffic flow data, trend term and season；
Subelement is examined, for examining stationarity using Dickey-fowler to the traffic flow data after removal, is handed over being formed
Through-flow sample.
The present invention also provides a kind of computer equipment, the computer equipment includes memory and processor, described to deposit
Computer program is stored on reservoir, the processor realizes above-mentioned method when executing the computer program.
The present invention also provides a kind of storage medium, the storage medium is stored with computer program, the computer journey
Sequence can realize above-mentioned method when being executed by processor.
Compared with the prior art, the invention has the advantages that: the present invention is by calculating temporal and spatial correlations according to traffic flow sample
Coefficient；Prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient；It is predicted using prediction model
The road conditions of current road segment next period are taken into account time-space relationship with obtaining road condition predicting information, using temporal and spatial correlations system
Influence of the number analysis adjacent segments to prediction road section traffic volume flow will have the sky of higher related coefficient with prediction road traffic delay
Between road section traffic volume flow data independent variable is mapped in high-dimensional feature space by support vector machines as independent variable, and at this
Linear decision function is constructed in space to predict road section traffic volume flow, improves short-time traffic flow forecast precision, is traffic control
Relatively reliable volume forecasting data are provided with induction.
The invention will be further described in the following with reference to the drawings and specific embodiments.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of traffic flow forecasting method provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of traffic flow forecasting method provided in an embodiment of the present invention；
Fig. 3 is the sub-process schematic diagram of traffic flow forecasting method provided in an embodiment of the present invention；
Fig. 4 is the sub-process schematic diagram of traffic flow forecasting method provided in an embodiment of the present invention；
Fig. 5 is the sub-process schematic diagram of traffic flow forecasting method provided in an embodiment of the present invention；
Fig. 6 is intersection link flow topology schematic diagram provided in an embodiment of the present invention；
Fig. 7 is upstream and downstream link flow contrast schematic diagram provided in an embodiment of the present invention；
Fig. 8 is volume forecasting algorithm effect schematic diagram provided in an embodiment of the present invention
Fig. 9 be another embodiment of the present invention provides traffic flow forecasting method flow diagram；
Figure 10 is the schematic block diagram of traffic flow forecasting device provided in an embodiment of the present invention；
Figure 11 be another embodiment of the present invention provides traffic flow forecasting device schematic block diagram；
Figure 12 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is that the application scenarios of traffic flow forecasting method provided in an embodiment of the present invention are illustrated
Figure.Fig. 2 is the schematic flow chart of traffic flow forecasting method provided in an embodiment of the present invention.The traffic flow forecasting method is answered
For in server.The server can be a server in Distributed Services platform, be deployed with traffic in the server
Volume forecasting platform, the traffic flow data that Vehicle Detection equipment will acquire are sent in server, so that server can be with
The prediction of road conditions is carried out to the traffic flow data of Vehicle Detection equipment, and the result of prediction is transmitted to terminal and is shown,
The prediction result specifically refers to the load conditions in prediction section.
It should be noted that only illustrating a Vehicle Detection equipment, in the actual operation process, server in Fig. 2
The traffic flow data of multiple Vehicle Detection equipment can be predicted.
Fig. 2 is the flow diagram of traffic flow forecasting method provided in an embodiment of the present invention.As shown in Fig. 2, this method
Include the following steps S110 to S150.
S110, traffic flow data is obtained.
In the present embodiment, traffic flow data refers to the wagon flow about time series got by traffic detector
The traffic datas such as amount.
The section predicted as needed determines approach way, and collects the flow system of the traffic detector of each approach way
It counts.
S120, traffic flow data is pre-processed, to form traffic flow sample.
In the present embodiment, traffic flow sample refers to the traffic flow after removing abnormal, trend term and season and examining
Measure data.The traffic flow sample of acquisition can make the former sequence of traffic flow data meet steady reversible precondition.
In one embodiment, as shown in figure 3, above-mentioned step S120 may include step S121~S122.
Exceptional value, trend term and season in S121, removal traffic flow data；
S122, stationarity is examined using Dickey-fowler to the traffic flow data after removal, to form traffic flow sample.
In the present embodiment, the magnitude of traffic flow is provided with tendency and periodicity, and trend term refers to the friendship for having tendency
Through-current capacity data, season refer to having periodic traffic flow data；Above-mentioned trend term and season pass through difference
Divide operation so that uneven stability data are steady；It is gone by pretreatment modes such as data smoothing, zero averaging, difference and seasonal differences
Except exceptional value, trend term and the season in traffic flow data, treated, and traffic flow data uses Dickey-Fuller
Stationarity is examined, so that former traffic flow data meets steady reversible precondition.
In other embodiments, the above-mentioned traffic flow data to after removal can also be using augmentation Dickey-fowler inspection
Stationarity is tested, to exclude autocorrelative influence.
S130, temporal and spatial correlations coefficient is calculated according to traffic flow sample.
In the present embodiment, temporal and spatial correlations coefficient refers to that measures a statistical correlation between two or more stochastic variable
Index.
Since the working time of people and daily schedule have obviously periodically, thus, the magnitude of traffic flow number for generation of going on a journey
According to similarly there is the periodic regularity as unit of day, week etc., i.e., adjacent several days or different weeks but same " what day "
Traffic flow there is similitude to a certain extent, space-time relationship analysis studies what it was changed over time based on spatial object
Rule, the relevance of reflecting time sequence data over time and space.In city road network, the friendship in each section in the road network of space
It interacts between through-current capacity, be richly stored with space time information.
In city road network, traffic flow has very strong space-time relationship.In time, traffic flow follows certain variation
Rule, subsequent period traffic flow parameter value are considered as continuity of the period traffic flow parameter value in this rule；In sky
Between on, traffic flow is influenced by adjacent segments, upstream and downstream road section traffic volume state and shows certain correlation, and certain
Decay in spatial dimension with the increase of section spacing.Therefore, the traffic flow for comprehensively considering adjacent segments temporal correlation is pre-
Survey method can effectively improve the accuracy rate and reliability of traffic flow forecasting.
In one embodiment, as shown in figure 4, above-mentioned step S130 may include step S131~S132.
S131, the space-time relationship between traffic flow sample is determined based on space weight matrix and time delay.
Two reachable road traffic delay of space have spatial coherence, and space weight matrix is the quantification of spatial neighbors
Measurement, by statistical theory it is found that spatial coherence reflects the linear correlation degree between different groups of data, spatial coherence
It is bigger, it more can mutual linear expression.
Assuming that space section i, j are any two section or crossing in survey region, it is no if it is 1 that space is reachable
It is then 0, space weighted value is expressed as
Time delay self-explanatory characters' part a occur to event b occur two moment time interval, reflect two pieces thing occur when
Between on difference relationship.
The generation of magnitude of traffic flow sequence in short-term depends on the accessibility of road, the flow sequence between each road there is also
Time difference relationship is based on statistics related coefficient, and space and time order extension is carried out to it, introduces Spatial weight matrix and the time prolongs
The space-time relationship between each flow sequence is expressed late, is convenient for using temporal and spatial correlations coefficient as judgment basis, fast selecting and future position
Relevant predictive factor eliminates the subjectivity that predictive factor is chosen, to improve short-time traffic flow forecast precision.
S132, the phase relation that space adjacent segments different time lag value and traffic flow sample are calculated according to space-time relationship
Number, to form temporal and spatial correlations coefficient.
In one embodiment, above-mentioned step S132 may include step S1321~S1323.
S1321, several traffic flow samples of each section are combined to form column vector li=[x1,x2,...,xi]T(i=
1,2,3 ..., n), wherein xiFor traffic flow sample；
S1322, all traffic flow samples of section each in set period of time are constituted into matrix L=[l1,l2,...,li],
(i=1,2,3 ..., n)；
S1323, useWherein, cov (LAi,LBi) be with when
Covariance of the traffic flow sample of section A, B of null Context about time series；D(LAi) and D (LBi) it is respectively section A, B
The parameter time series variance of traffic flow sample；ρABFor temporal and spatial correlations coefficient.
For example: assuming that as unit of day, using daily k traffic flow data as a column vector li=[x1,
x2,...,xi]T(i=1,2,3 ..., n)；Then n days all data constitute matrix L=[l1,l2,...,li], (i=1,2,
3,…,n)；Assuming that for two road section A, B with neighbouring relations, xAi,xBiTwo sections are respectively indicated in the friendship of the i-th period
Through-flow parameter value, then temporal and spatial correlations coefficient both are Wherein, cov
(LAi,LBi) it is covariance of the traffic flow sample of section A, B with space-time relationship about time series；D(LAi) and D
(LBi) be respectively section A, B traffic flow sample parameter time series variance；ρABFor temporal and spatial correlations coefficient, ρABValue it is bigger, table
Correlation is bigger between bright section.
Since vehicle has mobility on city road network, the vehicle in upstream section can drive to downstream road by certain time
Section, the traffic behavior of downstream road section can also have an impact upstream traffic after the regular hour, and therefore, traffic fluid space is mutual
Closing property introduces time lag value when comparing, the setting section A is in the section B downstream, the time lag value of two road traffic delay variation
For τ, then related coefficient at this time is represented byWhen considering adjacent segments
The traffic flow forecasting method of empty correlation can effectively improve the accuracy rate and reliability of traffic flow forecasting
S140, prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient.
In the present embodiment, prediction model refers to the model for predicting the road conditions in certain section, inputs the traffic in the section
Data on flows can export the road condition predicting information.
In one embodiment, as shown in figure 5, above-mentioned step S140 may include step S1431~S1433.
S1431, higher-dimension spy is mapped to using the traffic flow sample in the space section of higher temporal and spatial correlations coefficient as input quantity
It levies in space；
Model mapped function relation between S1432, building input quantity and output quantity.
S1433, model mapped function relation is optimized, to obtain prediction model.
The traffic flow sample in the space section of higher temporal and spatial correlations coefficient refers to that temporal and spatial correlations coefficient is greater than or equal to and sets
The traffic flow sample in the space section of definite value；Using temporal and spatial correlations coefficient analysis adjacent segments to the shadow of prediction road traffic delay
Ring, by temporal and spatial correlations coefficient can effective Selection Model predictive factor, but the interaction between each predictive factor is
Non-linear relation.By the traffic flow sample in the space section with the road traffic delay for needing to predict with higher temporal and spatial correlations coefficient
As independent variable, it is mapped in high-dimensional feature space H by support vector machines by independent variable is inputted, constructs input quantity and output quantity
Between model mapped function relation.And construct linear decision function within this space to predict road section traffic volume flow, it improves
Short-time traffic flow forecast precision provides relatively reliable volume forecasting data for traffic control and inducible system.
According to the extensive minimax risk criterion of SRM, optional negated Linear Estimation function, that is, kernel function isM indicates sample number, and w is weight vector, and b is known as threshold value,It indicates n dimension independent variable to be mapped to
Feature space.
In order to improve model prediction accuracy, needs to choose suitable parameter, in order to which the real risk of formula is minimum, construct excellent
Change objective functionModel mapped function relation is optimized, to obtain prediction model；Constraint
Condition isWherein, δiFor two slack variables, C
It can be obtained for penalty factor therefore, it is possible to convert lagrange duality problem for above formula to solveWherein, αiFor Lagrange multiplier, K (xi, x) and it is kernel function, and meet
Operation dimension and complexity can be reduced by introducing kernel function, establish the corresponding relationship between input quantity and output quantity
Afterwards, corresponding output quantity can be obtained according to new input quantity.
Various possible kernel functions and model parameter are attempted to value based on grid search, carry out cross validation, i.e., data
Collection is divided into s group, randomly selects s-1 group every time as training set, and remaining one group is used as test set, randomly selects n times, obtains
N model finds out the optimal kernel function of cross validation accuracy and model parameter to value, to form prediction model, to improve
The accuracy and reliability of prediction.
S150, the road conditions that the current road segment next period is predicted using prediction model, to obtain road condition predicting information.
Obtained road condition predicting information provides effective information in real time, is docked to Traffic flux detection and inducible system, helps
Traveler preferably carries out Path selection, shortens the travel time, reduces congested in traffic；Accurately traffic flow forecasting is to hand in real time
The premise and key of logical control and Traffic flow guidance can provide effective information in real time to traveler, help traveler more preferable
Ground carries out Path selection, shortens the travel time, reduces congested in traffic.
Traffic flow forecasting method based on temporal correlation, the generation of magnitude of traffic flow sequence in short-term is dependent on road
Accessibility, there is also time difference relationships for the flow sequence between each road, are based on statistics related coefficient, carry out space-time to it
Semantic extension, introduces Spatial weight matrix and time delay expresses the space-time relationship between each flow sequence, and with temporal and spatial correlations
Coefficient is judgment basis, and fast selecting predictive factor relevant to future position eliminates the subjectivity that predictive factor is chosen.Will with it is pre-
Surveying road traffic delay has the space road section traffic volume flow data of higher related coefficient as independent variable, will by support vector machines
The argument data of the input space is mapped in high-dimensional feature space, and constructs decision function in this feature space to predict road
The section magnitude of traffic flow, to improve the accuracy and reliability of prediction.
Above-mentioned traffic flow forecasting method, by calculating temporal and spatial correlations coefficient according to traffic flow sample；According to it is higher when
The traffic flow sample in the space section of empty related coefficient constructs prediction model；The current road segment next time is predicted using prediction model
The road conditions of section are taken into account time-space relationship with obtaining road condition predicting information, using temporal and spatial correlations coefficient analysis adjacent segments pair
The influence for predicting road section traffic volume flow will have the space road section traffic volume flow data of higher related coefficient with prediction road traffic delay
As independent variable, independent variable is mapped in high-dimensional feature space by support vector machines, and construction is linear certainly within this space
Plan function predicts road section traffic volume flow, improves short-time traffic flow forecast precision, provides and more may be used for traffic control and induction
The volume forecasting data leaned on.
Fig. 9 be another embodiment of the present invention provides a kind of traffic flow forecasting method flow diagram.Such as Fig. 9 institute
Show, the traffic flow forecasting method of the present embodiment includes step S210-S260.Wherein step S210-S250 and above-described embodiment
In step S110-S150 it is similar, details are not described herein.The following detailed description of in the present embodiment increase step S260.
S260, using the coefficient of determination and prediction Error Absolute Value mean measures model checking road condition predicting information it is accurate
Property.
It is predicted using road conditions of the prediction model to the current road segment next period to obtain predicting road conditions information, and is made
With coefficient of determination R2With prediction Error Absolute Value mean value (MAE) measurement model prediction effect, the accuracy of prediction effect is examined.R2→ 1 effect is better, R2→ 0 effect is poorer.MAE value is smaller
Effect is better, whereinFor model predication value, yiFor true observation,For desired value, n is the sample total of prediction.
For example, referring to Fig. 6, can be seen that the flow of section A by adjacent segments, upstream and downstream road from topological diagram
The influence of section traffic condition, it is not only related to current time t, it is also related with its historical traffic flows t-1 and t-2, while with
The B of adjacent segments, C, D are related.As seen from Figure 7, Wulin tomb road, people road downstream road section current capacity contrast are it is found that for upstream and downstream
Road section traffic volume flow distribution characteristics is similar, by analyzing a large amount of traffic detector data, finds traffic flow when longer
Between there is in scale periodicity and similitude, there is time variation, chaotic property and correlation in the short time.Traffic for the previous period
Stream can have an impact the traffic flow of rear a period of time, the influence of this related receptor traffic behavior, and traffic flow time sequence
Column variation tendency is positively correlated with historical time sequence variation trend.
The magnitude of traffic flow and road of the prediction model based on historical traffic data and adjacent segments data on flows to the next period
Condition is predicted.The following table 1 present temporal correlation model and ARIMA model (autoregression integrates moving average model,
Autoregressive Integrated Moving Average Model) to the data of 2018-8-25~2018-8-26 into
The accuracy of row prediction.
1. prediction model prediction effect Measure Indexes data of table
| Prediction technique | MAE | R2 |
| Temporal correlation algorithm | 7.36 | 0.856 |
| Arima algorithm | 9.02 | 0.803 |
As shown in figure 8, the R2 of temporal correlation algorithm is scored at 0.856, MAE average value 7.36, the score of ARIMA algorithm
0.813, MAE average value 9.02, from figure it is found that temporal correlation algorithm effect is better than ARIMA algorithm.Model can not only be immediately following friendship
Through-flow variation tendency, and can preferably reflect the variation characteristic of the magnitude of traffic flow, it will be realized with relatively small error to future
The magnitude of traffic flow approach, the judgement for road network road section traffic volume state provides reliable data supporting.
Figure 10 is a kind of schematic block diagram of traffic flow forecasting device 300 provided in an embodiment of the present invention.Such as Figure 10 institute
Show, corresponds to the above traffic flow forecasting method, the present invention also provides a kind of traffic flow forecasting devices 300.The magnitude of traffic flow
Prediction meanss 300 include the unit for executing above-mentioned traffic flow forecasting method, which can be configured in server.
Specifically, referring to Fig. 10, the traffic flow forecasting device 300 includes:
Data capture unit 301, for obtaining traffic flow data；
Pretreatment unit 302, for being pre-processed to traffic flow data, to form traffic flow sample；
Coefficient calculation unit 303, for calculating temporal and spatial correlations coefficient according to traffic flow sample；
Model construction unit 304, the traffic flow sample building for the space section according to higher temporal and spatial correlations coefficient are pre-
Survey model；
Predicting unit 305, it is pre- to obtain road conditions for the road conditions using the prediction model prediction current road segment next period
Measurement information.
In one embodiment, the pretreatment unit 302 includes:
Subelement is handled, for removing the exceptional value in traffic flow data, trend term and season；
Subelement is examined, for examining stationarity using Dickey-fowler to the traffic flow data after removal, is handed over being formed
Through-flow sample.
In one embodiment, the coefficient calculation unit 303 includes:
Relevance determines subelement, for based on space weight matrix and time delay determine between traffic flow sample when
Null Context；
Coefficient forms subelement, for calculating space adjacent segments different time lag value and traffic according to space-time relationship
The related coefficient of sample is flowed, to form temporal and spatial correlations coefficient.
In one embodiment, the coefficient formation subelement includes:
Column vector forms module, for combining to form column vector l by several traffic flow samples of each sectioni=[x1,
x2,...,xi]T(i=1,2,3 ..., n), wherein xiFor traffic flow sample；
Matrix constitutes module, for by all traffic flow samples of section each in set period of time constitute matrix L=
[l1,l2,...,li], (i=1,2,3 ..., n)；
Computing module, for usingWherein, cov (LAi,LBi) be
Covariance of the traffic flow sample of section A, B with space-time relationship about time series；D(LAi) and D (LBi) it is respectively disconnected
The parameter time series variance of face A, B traffic flow sample；ρABFor temporal and spatial correlations coefficient.
In one embodiment, the model construction unit 304 includes:
Subelement is mapped, for mapping the traffic flow sample in the space section of higher temporal and spatial correlations coefficient as input quantity
Into high-dimensional feature space；
Relationship constructs subelement, for constructing the model mapped function relation between input quantity and output quantity；
Optimize subelement, for optimizing to model mapped function relation, to obtain prediction model.
Figure 11 be another embodiment of the present invention provides a kind of traffic flow forecasting device 300 schematic block diagram.Such as figure
Shown in 11, the traffic flow forecasting device 300 of the present embodiment is to increase accuracy verification unit on the basis of above-described embodiment
306。
Accuracy verification unit 306, for using the coefficient of determination and prediction Error Absolute Value mean measures model checking road
The accuracy of condition predictive information.
It should be noted that it is apparent to those skilled in the art that, above-mentioned traffic flow forecasting device
300 and each unit specific implementation process, can with reference to the corresponding description in preceding method embodiment, for convenience of description and
Succinctly, details are not described herein.
Above-mentioned traffic flow forecasting device 300 can be implemented as a kind of form of computer program, which can
To be run in computer equipment as shown in figure 12.
Figure 12 is please referred to, Figure 12 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.The calculating
Machine equipment 500 is server, and server can be independent server, is also possible to the server set of multiple server compositions
Group.
Refering to fig. 12, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 include program instruction, which is performed, and processor 502 may make to execute a kind of traffic flow forecasting method.
The processor 502 is for providing calculating and control ability, to support the operation of entire computer equipment 500.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute a kind of traffic flow forecasting method.
The network interface 505 is used to carry out network communication with other equipment.It will be understood by those skilled in the art that in Figure 12
The structure shown, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied to application scheme
The restriction of computer equipment 500 thereon, specific computer equipment 500 may include more more or fewer than as shown in the figure
Component perhaps combines certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following step
It is rapid:
Obtain traffic flow data；
Traffic flow data is pre-processed, to form traffic flow sample；
Temporal and spatial correlations coefficient is calculated according to traffic flow sample；
Prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient；
Using the road conditions of prediction model prediction current road segment next period, to obtain road condition predicting information.
In one embodiment, processor 502 realize it is described traffic flow data is pre-processed, to form traffic flow
When sample step, it is implemented as follows step:
Remove exceptional value, trend term and the season in traffic flow data；
Stationarity is examined using Dickey-fowler to the traffic flow data after removal, to form traffic flow sample.
In one embodiment, processor 502 realize it is described according to traffic flow sample calculate temporal and spatial correlations coefficient step when,
It is implemented as follows step:
The space-time relationship between traffic flow sample is determined based on space weight matrix and time delay；
The related coefficient of space adjacent segments different time lag value and traffic flow sample is calculated according to space-time relationship, with
Form temporal and spatial correlations coefficient.
In one embodiment, processor 502 is when realizing the calculating space adjacent segments difference according to space-time relationship
Between the related coefficient of lagged value and traffic flow sample be implemented as follows step when forming temporal and spatial correlations coefficient step:
Several traffic flow samples of each section are combined to form column vector li=[x1,x2,...,xi]T(i=1,2,
3 ..., n), wherein xiFor traffic flow sample；
All traffic flow samples of section each in set period of time are constituted into matrix L=[l1,l2,...,li], (i=1,
2,3,…,n)；
UsingWherein, cov (LAi,LBi) it is with space-time relationship
Section A, B covariance of the traffic flow sample about time series；D(LAi) and D (LBi) it is respectively section A, B traffic flow sample
This parameter time series variance；ρABFor temporal and spatial correlations coefficient.
In one embodiment, traffic of the processor 502 in the space section for realizing the higher temporal and spatial correlations coefficient of basis
When flowing sample building prediction model step, it is implemented as follows step:
The traffic flow sample in the space section of higher temporal and spatial correlations coefficient is mapped into high-dimensional feature space as input quantity
In；
Construct the model mapped function relation between input quantity and output quantity；
Model mapped function relation is optimized, to obtain prediction model.
In one embodiment, processor 502 described utilizes prediction model prediction current road segment next period realizing
Road conditions also realize following steps after obtaining road condition predicting information Step:
Use the accuracy of the coefficient of determination and prediction Error Absolute Value mean measures model checking road condition predicting information.
It should be appreciated that in the embodiment of the present application, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
Person's processor is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that relevant hardware can be instructed to complete by computer program.The computer program includes program instruction, computer journey
Sequence can be stored in a storage medium, which is computer readable storage medium.The program instruction is by the department of computer science
At least one processor in system executes, to realize the process step of the embodiment of the above method.
Therefore, the present invention also provides a kind of storage mediums.The storage medium can be computer readable storage medium.This is deposited
Storage media is stored with computer program, and processor is made to execute following steps when wherein the computer program is executed by processor:
Obtain traffic flow data；
Traffic flow data is pre-processed, to form traffic flow sample；
Temporal and spatial correlations coefficient is calculated according to traffic flow sample；
Prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient；
Using the road conditions of prediction model prediction current road segment next period, to obtain road condition predicting information.
In one embodiment, the processor execute the computer program and realize it is described to traffic flow data into
Row pretreatment, when forming traffic flow sample step, is implemented as follows step:
Remove exceptional value, trend term and the season in traffic flow data；
Stationarity is examined using Dickey-fowler to the traffic flow data after removal, to form traffic flow sample.
In one embodiment, the processor is realized described according to traffic flow sample meter in the execution computer program
When calculating temporal and spatial correlations coefficient step, it is implemented as follows step:
The space-time relationship between traffic flow sample is determined based on space weight matrix and time delay；
The related coefficient of space adjacent segments different time lag value and traffic flow sample is calculated according to space-time relationship, with
Form temporal and spatial correlations coefficient.
In one embodiment, the processor is realized described according to space-time relationship meter in the execution computer program
The related coefficient for calculating space adjacent segments different time lag value and traffic flow sample, when forming temporal and spatial correlations coefficient step,
It is implemented as follows step:
Several traffic flow samples of each section are combined to form column vector li=[x1,x2,...,xi]T(i=1,2,
3 ..., n), wherein xiFor traffic flow sample；
All traffic flow samples of section each in set period of time are constituted into matrix L=[l1,l2,...,li], (i=1,
2,3,…,n)；
UsingWherein, cov (LAi,LBi) it is with space-time relationship
Section A, B covariance of the traffic flow sample about time series；D(LAi) and D (LBi) it is respectively section A, B traffic flow sample
This parameter time series variance；ρABFor temporal and spatial correlations coefficient.
In one embodiment, the processor realizes the higher temporal and spatial correlations of the basis executing the computer program
When the traffic flow sample in the space section of coefficient constructs prediction model step, it is implemented as follows step:
The traffic flow sample in the space section of higher temporal and spatial correlations coefficient is mapped into high-dimensional feature space as input quantity
In；
Construct the model mapped function relation between input quantity and output quantity；
Model mapped function relation is optimized, to obtain prediction model.
In one embodiment, the processor is realized the utilization prediction model and is predicted in the execution computer program
The road conditions of current road segment next period also realize following steps after obtaining road condition predicting information Step:
Use the accuracy of the coefficient of determination and prediction Error Absolute Value mean measures model checking road condition predicting information.
The storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), magnetic disk
Or the various computer readable storage mediums that can store program code such as CD.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary.For example, the division of each unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the present invention
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.
If the integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing skill
The all or part of part or the technical solution that art contributes can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, terminal or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. traffic flow forecasting method characterized by comprising
Obtain traffic flow data；
Traffic flow data is pre-processed, to form traffic flow sample；
Temporal and spatial correlations coefficient is calculated according to traffic flow sample；
Prediction model is constructed according to the traffic flow sample in the space section of higher temporal and spatial correlations coefficient；
Using the road conditions of prediction model prediction current road segment next period, to obtain road condition predicting information.
2. traffic flow forecasting method according to claim 1, which is characterized in that described to be carried out in advance to traffic flow data
Processing, to form traffic flow sample, comprising:
Remove exceptional value, trend term and the season in traffic flow data；
Stationarity is examined using Dickey-fowler to the traffic flow data after removal, to form traffic flow sample.
3. traffic flow forecasting method according to claim 1, which is characterized in that when the calculating according to traffic flow sample
Empty related coefficient, comprising:
The space-time relationship between traffic flow sample is determined based on space weight matrix and time delay；
The related coefficient of space adjacent segments different time lag value and traffic flow sample is calculated, according to space-time relationship to be formed
Temporal and spatial correlations coefficient.
4. traffic flow forecasting method according to claim 3, which is characterized in that described to calculate sky according to space-time relationship
Between adjacent segments different time lag value and traffic flow sample related coefficient, to form temporal and spatial correlations coefficient, comprising:
Several traffic flow samples of each section are combined to form column vector li=[x1,x2,...,xi]T(i=1,2,3 ...,
N), wherein xiFor traffic flow sample；
All traffic flow samples of section each in set period of time are constituted into matrix L=[l1,l2,...,li], (i=1,2,
3,…,n)；
UsingWherein, cov (LAi,LBi) it is disconnected with space-time relationship
Covariance of the traffic flow sample of face A, B about time series；D(LAi) and D (LBi) it is respectively section A, B traffic flow sample
Parameter time series variance；ρABFor temporal and spatial correlations coefficient.
5. traffic flow forecasting method according to claim 4, which is characterized in that the higher temporal and spatial correlations coefficient of basis
Space section traffic flow sample construct prediction model, comprising:
The traffic flow sample in the space section of higher temporal and spatial correlations coefficient is mapped in high-dimensional feature space as input quantity；
Construct the model mapped function relation between input quantity and output quantity；
Model mapped function relation is optimized, to obtain prediction model.
6. traffic flow forecasting method according to any one of claims 1 to 5, which is characterized in that described to utilize prediction mould
Type predicts the road conditions of current road segment next period, to obtain road condition predicting information, comprising:
Use the accuracy of the coefficient of determination and prediction Error Absolute Value mean measures model checking road condition predicting information.
7. traffic flow forecasting device characterized by comprising
Data capture unit, for obtaining traffic flow data；
Pretreatment unit, for being pre-processed to traffic flow data, to form traffic flow sample；
Coefficient calculation unit, for calculating temporal and spatial correlations coefficient according to traffic flow sample；
Model construction unit, the traffic flow sample for the space section according to higher temporal and spatial correlations coefficient construct prediction model；
Predicting unit, for the road conditions using the prediction model prediction current road segment next period, to obtain road condition predicting information.
8. traffic flow forecasting device according to claim 7, which is characterized in that the pretreatment unit includes:
Subelement is handled, for removing the exceptional value in traffic flow data, trend term and season；
Subelement is examined, for examining stationarity using Dickey-fowler to the traffic flow data after removal, to form traffic flow
Sample.
9. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, on the memory
It is stored with computer program, the processor is realized as described in any one of claims 1 to 6 when executing the computer program
Method.
10. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, the computer program quilt
Processor can be realized when executing such as method described in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811177980.7A CN109272169A (en) | 2018-10-10 | 2018-10-10 | Traffic flow forecasting method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811177980.7A CN109272169A (en) | 2018-10-10 | 2018-10-10 | Traffic flow forecasting method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109272169A true CN109272169A (en) | 2019-01-25 |
Family
ID=65196206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811177980.7A Pending CN109272169A (en) | 2018-10-10 | 2018-10-10 | Traffic flow forecasting method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109272169A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263996A (en) * | 2019-06-18 | 2019-09-20 | 重庆大学 | A kind of traffic flow character parameter spatio-temporal correlation analysis method |
| CN110276955A (en) * | 2019-07-18 | 2019-09-24 | 中南大学 | A kind of traffic congestion state evaluation method towards traveler individual perception |
| CN110517488A (en) * | 2019-08-19 | 2019-11-29 | 南京理工大学 | The Short-time Traffic Flow Forecasting Methods with Recognition with Recurrent Neural Network are decomposed based on timing |
| CN111627210A (en) * | 2020-06-05 | 2020-09-04 | 腾讯科技（深圳）有限公司 | Traffic flow prediction method, device, equipment and medium |
| 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 |
| CN111915878A (en) * | 2019-05-09 | 2020-11-10 | 奥迪股份公司 | Method and device for predicting road traffic state, computer device and storage medium |
| CN112183868A (en) * | 2020-09-30 | 2021-01-05 | 青岛海信网络科技股份有限公司 | Construction method of traffic flow prediction model and electronic equipment |
| CN113160563A (en) * | 2021-03-31 | 2021-07-23 | 西安交通大学 | Short-time road condition prediction method, system and equipment based on historical road conditions |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730006A (en) * | 2014-01-26 | 2014-04-16 | 吉林大学 | Short-time traffic flow combined forecasting method |
| CN104064023A (en) * | 2014-06-18 | 2014-09-24 | 银江股份有限公司 | Dynamic traffic flow prediction method based on space-time correlation |
| CN105913664A (en) * | 2016-06-29 | 2016-08-31 | 肖锐 | Traffic flow monitoring and predicting system |
| CN106157616A (en) * | 2016-06-29 | 2016-11-23 | 肖锐 | A kind of magnitude of traffic flow short-term prediction device |
| CN106940829A (en) * | 2017-04-28 | 2017-07-11 | 兰州交通大学 | Recommend method in a kind of personalized path under car networking environment |
-
2018
- 2018-10-10 CN CN201811177980.7A patent/CN109272169A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730006A (en) * | 2014-01-26 | 2014-04-16 | 吉林大学 | Short-time traffic flow combined forecasting method |
| CN104064023A (en) * | 2014-06-18 | 2014-09-24 | 银江股份有限公司 | Dynamic traffic flow prediction method based on space-time correlation |
| CN105913664A (en) * | 2016-06-29 | 2016-08-31 | 肖锐 | Traffic flow monitoring and predicting system |
| CN106157616A (en) * | 2016-06-29 | 2016-11-23 | 肖锐 | A kind of magnitude of traffic flow short-term prediction device |
| CN106940829A (en) * | 2017-04-28 | 2017-07-11 | 兰州交通大学 | Recommend method in a kind of personalized path under car networking environment |
Non-Patent Citations (5)
| Title |
|---|
| 夏英 等: "基于时空分析的短时交通流量预测模型", 《南京大学学报（自然科学）》 * |
| 杨东援 等: "《连续数据环境下的交通规划与管理》", 31 January 2014, 同济大学出版社 * |
| 梁礼明 等: "《优化方法导论》", 30 September 2017, 北京理工大学出版社 * |
| 赵婷婷 等: "城市路网交通流的空间互相关性", 《清华大学学报（自然科学版）》 * |
| 韩卫国 等: "区域交通流的时空预测与分析", 《公路交通科技》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915878A (en) * | 2019-05-09 | 2020-11-10 | 奥迪股份公司 | Method and device for predicting road traffic state, computer device and storage medium |
| CN110263996A (en) * | 2019-06-18 | 2019-09-20 | 重庆大学 | A kind of traffic flow character parameter spatio-temporal correlation analysis method |
| CN110263996B (en) * | 2019-06-18 | 2022-12-02 | 重庆大学 | Traffic flow characteristic parameter space-time correlation analysis method |
| CN110276955A (en) * | 2019-07-18 | 2019-09-24 | 中南大学 | A kind of traffic congestion state evaluation method towards traveler individual perception |
| CN110517488A (en) * | 2019-08-19 | 2019-11-29 | 南京理工大学 | The Short-time Traffic Flow Forecasting Methods with Recognition with Recurrent Neural Network are decomposed based on timing |
| CN111627210A (en) * | 2020-06-05 | 2020-09-04 | 腾讯科技（深圳）有限公司 | Traffic flow prediction method, device, equipment and medium |
| 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 |
| CN112183868A (en) * | 2020-09-30 | 2021-01-05 | 青岛海信网络科技股份有限公司 | Construction method of traffic flow prediction model and electronic equipment |
| CN112183868B (en) * | 2020-09-30 | 2023-05-12 | 青岛海信网络科技股份有限公司 | Traffic flow prediction model construction method and electronic equipment |
| CN113160563A (en) * | 2021-03-31 | 2021-07-23 | 西安交通大学 | Short-time road condition prediction method, system and equipment based on historical road conditions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272169A (en) | Traffic flow forecasting method, device, computer equipment and storage medium | |
| Yu et al. | k-Nearest neighbor model for multiple-time-step prediction of short-term traffic condition | |
| Liu et al. | Bus stop-skipping scheme with random travel time | |
| Zheng et al. | A dynamic cordon pricing scheme combining the macroscopic fundamental diagram and an agent-based traffic model | |
| Huang et al. | A static bike repositioning model in a hub-and-spoke network framework | |
| CN102693633B (en) | Short-term traffic flow weighted combination prediction method | |
| Yu et al. | Real-time partway deadheading strategy based on transit service reliability assessment | |
| Yang et al. | Sensitivity-based uncertainty analysis of a combined travel demand model | |
| Negahban | Simulation-based estimation of the real demand in bike-sharing systems in the presence of censoring | |
| CN102346964A (en) | Real-time jam prediction and intelligent management system for road traffic network area | |
| Djuric et al. | Travel speed forecasting by means of continuous conditional random fields | |
| CN104183119A (en) | Real-time traffic flow distribution prediction system based on road section OD backstepping | |
| Zheng et al. | A stochastic simulation-based optimization method for equitable and efficient network-wide signal timing under uncertainties | |
| Yao et al. | An optimization model for arterial coordination control based on sampled vehicle trajectories: The STREAM model | |
| CN105787858A (en) | Situation deduction method for expressway network | |
| Deb Nath et al. | Modified K-means clustering for travel time prediction based on historical traffic data | |
| Kim et al. | Determining optimal sensor locations in freeway using genetic algorithm-based optimization | |
| Liang et al. | City traffic prediction based on real-time traffic information for intelligent transport systems | |
| Chandra et al. | Cross-correlation analysis and multivariate prediction of spatial time series of freeway traffic speeds | |
| Li et al. | Short-term traffic flow forecasting: A component-wise gradient boosting approach with hierarchical reconciliation | |
| Hosseini et al. | Traffic flow prediction using MI algorithm and considering noisy and data loss conditions: An application to Minnesota traffic flow prediction | |
| Duan et al. | A unified STARIMA based model for short-term traffic flow prediction | |
| Osorio et al. | Reducing gridlock probabilities via simulation-based signal control | |
| Shuvo et al. | Traffic forecasting using time-series analysis | |
| CN106157616A (en) | A kind of magnitude of traffic flow short-term prediction device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |
|
| RJ01 | Rejection of invention patent application after publication |