CN106128098B  A kind of multidisplay apparatus that can carry out traffic flow forecasting  Google Patents
A kind of multidisplay apparatus that can carry out traffic flow forecasting Download PDFInfo
 Publication number
 CN106128098B CN106128098B CN201610513353.0A CN201610513353A CN106128098B CN 106128098 B CN106128098 B CN 106128098B CN 201610513353 A CN201610513353 A CN 201610513353A CN 106128098 B CN106128098 B CN 106128098B
 Authority
 CN
 China
 Prior art keywords
 traffic flow
 data
 module
 τ
 magnitude
 Prior art date
Links
Abstract
Description
Technical field
The present invention relates to intelligent transportation fields, and in particular to a kind of multihead display dress that can carry out traffic flow forecasting It sets.
Background technology
The magnitude of traffic flow refers to the actual vehicle number by a certain section of road in the unit interval, is the weight for describing traffic behavior Want characteristic parameter.The magnitude of traffic flow variation again be one in real time, higherdimension, nonlinear, nonstationary random process, correlative factor Variation may all influence the magnitude of traffic flow of subsequent time.In the related technology, strong about prediction meanss limitation in shortterm, prediction essence To spend relatively low, prediction in real time fails to achieve satisfactory results, and fails to provide the selection of the Realtime Road of people and effectively suggest, from And traffic flow forecasting largely rests on the medium and longterm forecasting of the magnitude of traffic flow.
Invention content
In view of the abovementioned problems, the present invention provides a kind of multidisplay apparatus that can carry out traffic flow forecasting.
The purpose of the present invention is realized using following technical scheme：
A kind of multidisplay apparatus that can carry out traffic flow forecasting, including multidisplay apparatus and with multihead display fill Connected prediction meanss are set, the multidisplay apparatus includes：
First display device, first display device include an at least display screen, which shows smaller User interface, it is characterised in that：The multidisplay apparatus further includes the second display device, and second display device is first aobvious with this Showing device is rotatablely connected, which includes an at least display screen, when first display device and second display fill When setting in same plane, an at least display screen for first display device and an at least display screen for second display device without Seam docking is to show larger user interface.
Preferably, the first display device includes first shell, which includes the first main body, which has One first face and one adjacent to first face first side, on the direction of the both ends of the first side along the vertical first side Protrude out the first driveconnecting shaft and the second driveconnecting shaft, first driveconnecting shaft and second driveconnecting shaft it is coaxial, first driveconnecting shaft and should One first container is formed between main body, one second container is formed between second driveconnecting shaft and the main body, this is second aobvious Showing device includes second shell, which includes the second main body, which has one opposite with first face the Two faces and one adjacent to second face second side, the both ends of the second side are protruded out along the direction perpendicular to the second side Go out third driveconnecting shaft and the 4th driveconnecting shaft, the third driveconnecting shaft and the 4th driveconnecting shaft are coaxial, and the third driveconnecting shaft is contained in First container, the 4th driveconnecting shaft are contained in second container.
Preferably, first shell includes that the master control key being located on first face and volume port, first driveconnecting shaft are separate It is provided with an earphone interface on the side of second driveconnecting shaft, is arranged on the side of second driveconnecting shaft far from first driveconnecting shaft There is a power port.
Preferably, characterized in that prediction meanss include sequentially connected acquisition module, data preprocessing module, data point Generic module, stationary test module, related coefficient computing module, threshold setting module, temporal and spatial correlations coefficient matrix generation module, History correlation matrix generation module, predictive factor choose module and forecast model construction module：
(1) acquisition module observes section S for acquiring in road network S_{i}, prediction section S_{j}The magnitude of traffic flow of corresponding each period Data and passage situation；
(2) data preprocessing module for carrying out data prediction to the traffic flow data, and is rejected and is not met friendship The data of logical actual conditions；
(3) data categorization module, for carrying out classification of type, the class by the traffic flow data of data prediction Type includes festivals or holidays traffic flow data, weekend traffic flow data and working day traffic flow data；
(4) stationary test module, for being in same type of observation section S_{i}Magnitude of traffic flow sequence X_{i}With prediction Section S_{j}Magnitude of traffic flow sequence X_{j}Stationary test is carried out respectively, examines the autocorrelation function of stationarity to be：
Wherein, X_{x}Indicate magnitude of traffic flow sequence to be tested, ν_{i}Indicate the mean value of magnitude of traffic flow sequence to be tested, X_{x+τ}Indicate X_{x} Magnitude of traffic flow sequence after time delay τ, ν_{x+τ}For X_{x+τ}Mean value, σ^{2}For X_{x}With X_{x+τ}Between variance；
When autocorrelation function P (τ) can rapid decay level off to and 0 or fluctuate near 0, then the magnitude of traffic flow sequence to be tested Row pass through stationary test；When autocorrelation function P (τ) is unable to rapid decay and levels off to 0 or fluctuate near 0, then wait for described Continue stationary test after examining magnitude of traffic flow sequence to carry out calm disposing；
(5) related coefficient computing module, for calculating the observation section S by stationary test_{i}Magnitude of traffic flow sequence X_{i} With prediction section S_{j}Magnitude of traffic flow sequence X_{j}Time correlation coefficient ρ at time delay τ_{ij}(τ) and space correlation coefficient ρ_{ij} (w), if there is N number of section in road network S, magnitude of traffic flow sequence X_{i}=[x_{i}(1),x_{i}(2),...,x_{i}(n)], magnitude of traffic flow sequencex_{i}(t) observation section S is indicated_{i}In the flow of t moment, x_{j}(t) prediction section S is indicated_{j}In t The flow at quarter, t=1,2 ... n, time correlation coefficient ρ_{ij}The calculation formula of (τ) is：
Space correlation coefficient ρ_{ij}(w) calculation formula is：
Preferably, characterized in that prediction meanss further include：
(6) threshold setting module, for setting time delay maximum value L, temporal and spatial correlations coefficient threshold between each section T_{1}With history correlation coefficient threshold T_{2}；
(7) temporal and spatial correlations coefficient matrix generation module, for the time correlation coefficient ρ according to each section_{ij}(τ) and space phase Relationship number ρ_{ij}(w) each observation section S is built_{i}With prediction section S_{j}Postpone the temporal and spatial correlations coefficient matrix ρ under τ in different time (τ) ', and calculate the temporal and spatial correlations coefficient ρ in each section_{ij}(τ) ', the wherein value range of i ∈ [1, N] and τ ∈ [0, L], L be [8, 12], the calculation formula of temporal and spatial correlations coefficient matrix ρ (τ) ' is：
Temporal and spatial correlations coefficient ρ_{ij}The calculation formula of (τ) ' is：
ρ_{ij}(τ) '=ρ_{ij}(τ)ρ_{ij}(w)；
(8) history correlation matrix generation module, for generating prediction section S_{j}History correlation matrix ρ (t)：
Wherein, it chooses the nearly M weeks same period and same type of historical traffic is as magnitude of traffic flow sequence X_{j}History it is related Sequence is denoted as X_{jm} M=1,2 ... the value range of M, M are [3,5], the history phase Relationship number ρ_{jm}(t) calculation formula is：
(9) predictive factor chooses module, for according to the temporal and spatial correlations coefficient threshold T_{1}With history correlation coefficient threshold T_{2} It chooses and predicts the relevant predictive factor of target point, and matrix reconstruction is carried out according to its selected spatial position j and time delay τ, Selection principle is：
If ρ_{ij}(τ) ' ＞ T_{1}, then section S will be observed_{i}Magnitude of traffic flow sequence X_{i}The middle magnitude of traffic flow composition for meeting condition is new Sequence and as the first predictive factor, be denoted as X', X'=(x1', x_{2}',...,x_{p}'), wherein p is the friendship for meeting condition Throughcurrent capacity number, if L_{1}For the maximum value of time delay in the first predictive factor, L_{1}=max τ  τ ∈ [0, L] and ρ_{ij}(τ) ' ＞ T_{1}, then the first predictive factor X' can state following matrix form as：
If ρ_{jm}(t) ＞ T_{2}, then by all history correlated series X for meeting condition_{jm}(t) it is used as the second predictive factor, is denoted as Y', Y'={ y_{1}',y_{2}',...,y_{q}', wherein q is the historical traffic number for the condition that meets, and the second predictive factor Y' can be stated as Following matrix form：
(10) forecast model construction module, by by the first predictive factor and the second predictive factor be used as training sample come Prediction model of the predictable section of construction in the magnitude of traffic flow of subsequent time.
Wherein, in the data preprocessing module, the rule that the data of traffic actual conditions are not met described in rejecting is： In one data update cycle, the threshold range of total traffic flow data in each section is set separately, if certain collected section Total traffic flow data fall in corresponding threshold range, then show that this group of data are reliable, retain this group of data；If collecting Total traffic flow data in certain section fall not in corresponding threshold range, then show that this group of data are unreliable, and picked It removes.
Wherein, the stationary test module includes following submodule：
(1) submodule is examined, for in the same type of magnitude of traffic flow sequence for observing section and prediction section Magnitude of traffic flow sequence carries out stationary test respectively；
(2) continuity check submodule is connect with submodule is examined, for not passing through the friendship to be tested of stationary test Throughcurrent capacity sequence carries out continuity check, if not meeting continuity, the continuity check submodule uses average interpolation method pair Data carry out polishing；
(3) misarrangement submodule is connect with continuity check submodule, and the data for deleting apparent error use simultaneously Average interpolation method carries out polishing to data；
(4) difference processing submodule, connection misarrangement submodule and inspection submodule, it is poor for being carried out to the data after polishing Point processing, and by the data transmission after difference processing to inspection submodule.
Beneficial effects of the present invention are：
1, data categorization module and stationarity inspection module are set, increase the accuracy of data, and make the prediction of construction Model is more targeted；
2, setting related coefficient computing module, temporal and spatial correlations coefficient matrix generation module, history correlation matrix generate Module, predictive factor choose module and forecast model construction module, wherein predictive factor directly affect precision of prediction, related coefficient It is the index for measuring stochastic variable correlation, can helps to choose instruction of the variable closely related with future position as prediction model Practice sample, chooses multiple related coefficients as predictive factor, eliminate the subjectivity that initial predictive factor is chosen, can increase pre Precision is surveyed, keeps forecast model construction module more stable and accurate；
3, the space correlation coefficient in related coefficient computing module reflects influence of the accessibility to prediction model of road network, Time correlation coefficient can express the time sequencing of flow sequence, reflect the causality on two sequence times, pre to improve Survey the efficiency of predictor selection；Due to the Weekly similarity of the magnitude of traffic flow, the history phase of history correlation matrix generation module is introduced Relationship number, is used cooperatively with time correlation coefficient and space correlation coefficient, and providing more data for Accurate Prediction supports.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings Other attached drawings.
Fig. 1 is the connection diagram of each module of prediction meanss of the present invention.
Fig. 2 is multidisplay apparatus dimensional structure diagram of the present invention.
Specific implementation mode
The invention will be further described with the following Examples.
Embodiment 1
Referring to Fig. 1, Fig. 2, a kind of multidisplay apparatus that can carry out traffic flow forecasting of the present embodiment, including multiscreen are aobvious Showing device and the prediction meanss being connected with multidisplay apparatus, the multidisplay apparatus include：
First display device, first display device include an at least display screen, which shows smaller User interface, it is characterised in that：The multidisplay apparatus further includes the second display device, and second display device is first aobvious with this Showing device is rotatablely connected, which includes an at least display screen, when first display device and second display fill When setting in same plane, an at least display screen for first display device and an at least display screen for second display device without Seam docking is to show larger user interface.
Preferably, the first display device includes first shell, which includes the first main body, which has One first face and one adjacent to first face first side, on the direction of the both ends of the first side along the vertical first side Protrude out the first driveconnecting shaft and the second driveconnecting shaft, first driveconnecting shaft and second driveconnecting shaft it is coaxial, first driveconnecting shaft and should One first container is formed between main body, one second container is formed between second driveconnecting shaft and the main body, this is second aobvious Showing device includes second shell, which includes the second main body, which has one opposite with first face the Two faces and one adjacent to second face second side, the both ends of the second side are protruded out along the direction perpendicular to the second side Go out third driveconnecting shaft and the 4th driveconnecting shaft, the third driveconnecting shaft and the 4th driveconnecting shaft are coaxial, and the third driveconnecting shaft is contained in First container, the 4th driveconnecting shaft are contained in second container.
Preferably, first shell includes that the master control key being located on first face and volume port, first driveconnecting shaft are separate It is provided with an earphone interface on the side of second driveconnecting shaft, is arranged on the side of second driveconnecting shaft far from first driveconnecting shaft There is a power port.
Preferably, characterized in that prediction meanss include sequentially connected acquisition module, data preprocessing module, data point Generic module, stationary test module, related coefficient computing module, threshold setting module, temporal and spatial correlations coefficient matrix generation module, History correlation matrix generation module, predictive factor choose module and forecast model construction module：
(1) acquisition module observes section S for acquiring in road network S_{i}, prediction section S_{j}The magnitude of traffic flow of corresponding each period Data and passage situation；
(2) data preprocessing module for carrying out data prediction to the traffic flow data, and is rejected and is not met friendship The data of logical actual conditions；
(3) data categorization module, for carrying out classification of type, the class by the traffic flow data of data prediction Type includes festivals or holidays traffic flow data, weekend traffic flow data and working day traffic flow data；
(4) stationary test module, for being in same type of observation section S_{i}Magnitude of traffic flow sequence X_{i}With prediction Section S_{j}Magnitude of traffic flow sequence X_{j}Stationary test is carried out respectively, examines the autocorrelation function of stationarity to be：
Wherein, X_{x}Indicate magnitude of traffic flow sequence to be tested, ν_{i}Indicate the mean value of magnitude of traffic flow sequence to be tested, X_{x+τ}Indicate X_{x} Magnitude of traffic flow sequence after time delay τ, ν_{x+τ}For X_{x+τ}Mean value, σ^{2}For X_{x}With X_{x+τ}Between variance；
When autocorrelation function P (τ) can rapid decay level off to and 0 or fluctuate near 0, then the magnitude of traffic flow sequence to be tested Row pass through stationary test；When autocorrelation function P (τ) is unable to rapid decay and levels off to 0 or fluctuate near 0, then wait for described Continue stationary test after examining magnitude of traffic flow sequence to carry out calm disposing；
(5) related coefficient computing module, for calculating the observation section S by stationary test_{i}Magnitude of traffic flow sequence X_{i} With prediction section S_{j}Magnitude of traffic flow sequence X_{j}Time correlation coefficient ρ at time delay τ_{ij}(τ) and space correlation coefficient ρ_{ij} (w), if there is N number of section in road network S, magnitude of traffic flow sequence X_{i}=[x_{i}(1),x_{i}(2),...,x_{i}(n)], magnitude of traffic flow sequencex_{i}(t) observation section S is indicated_{i}In the flow of t moment, x_{j}(t) prediction section S is indicated_{j}In t The flow at quarter, t=1,2 ... n, time correlation coefficient ρ_{ij}The calculation formula of (τ) is：
Space correlation coefficient ρ_{ij}(w) calculation formula is：
Preferably, characterized in that prediction meanss further include：
(6) threshold setting module, for setting time delay maximum value L, temporal and spatial correlations coefficient threshold between each section T_{1}With history correlation coefficient threshold T_{2}；
(7) temporal and spatial correlations coefficient matrix generation module, for the time correlation coefficient ρ according to each section_{ij}(τ) and space phase Relationship number ρ_{ij}(w) each observation section S is built_{i}With prediction section S_{j}Postpone the temporal and spatial correlations coefficient matrix ρ under τ in different time (τ) ', and calculate the temporal and spatial correlations coefficient ρ in each section_{ij}(τ) ', the wherein value range of i ∈ [1, N] and τ ∈ [0, L], L be [8, 12], the calculation formula of temporal and spatial correlations coefficient matrix ρ (τ) ' is：
Temporal and spatial correlations coefficient ρ_{ij}The calculation formula of (τ) ' is：
ρ_{ij}(τ) '=ρ_{ij}(τ)ρ_{ij}(w)；
(8) history correlation matrix generation module, for generating prediction section S_{j}History correlation matrix ρ (t)：
Wherein, it chooses the nearly M weeks same period and same type of historical traffic is as magnitude of traffic flow sequence X_{j}History it is related Sequence is denoted asM=1,2 ... the value range of M, M are [3,5], the history phase Relationship number ρ_{jm}(t) calculation formula is：
(9) predictive factor chooses module, for according to the temporal and spatial correlations coefficient threshold T_{1}With history correlation coefficient threshold T_{2} It chooses and predicts the relevant predictive factor of target point, and matrix reconstruction is carried out according to its selected spatial position j and time delay τ, Selection principle is：
If ρ_{ij}(τ) ' ＞ T_{1}, then section S will be observed_{i}Magnitude of traffic flow sequence X_{i}The middle magnitude of traffic flow composition for meeting condition is new Sequence and as the first predictive factor, be denoted as X', X'=(x_{1}',x_{2}',...,x_{p}'), wherein p is the friendship for meeting condition Throughcurrent capacity number, if L_{1}For the maximum value of time delay in the first predictive factor, L_{1}=max τ  τ ∈ [0, L] and ρ_{ij}(τ) ' ＞ T_{1}, then the first predictive factor X' can state following matrix form as：
If ρ_{jm}(t) ＞ T_{2}, then by all history correlated series X for meeting condition_{jm}(t) it is used as the second predictive factor, is denoted as Y', Y'={ y_{1}',y_{2}',...,y_{q}', wherein q is the historical traffic number for the condition that meets, and the second predictive factor Y' can be stated as Following matrix form：
(10) forecast model construction module, by by the first predictive factor and the second predictive factor be used as training sample come Prediction model of the predictable section of construction in the magnitude of traffic flow of subsequent time.
Wherein, in the data preprocessing module, the rule that the data of traffic actual conditions are not met described in rejecting is： In one data update cycle, the threshold range of total traffic flow data in each section is set separately, if certain collected section Total traffic flow data fall in corresponding threshold range, then show that this group of data are reliable, retain this group of data；If collecting Total traffic flow data in certain section fall not in corresponding threshold range, then show that this group of data are unreliable, and picked It removes.
Wherein, the stationary test module includes following submodule：
(1) submodule is examined, for in the same type of magnitude of traffic flow sequence for observing section and prediction section Magnitude of traffic flow sequence carries out stationary test respectively；
(2) continuity check submodule is connect with submodule is examined, for not passing through the friendship to be tested of stationary test Throughcurrent capacity sequence carries out continuity check, if not meeting continuity, the continuity check submodule uses average interpolation method pair Data carry out polishing；
(3) misarrangement submodule is connect with continuity check submodule, and the data for deleting apparent error use simultaneously Average interpolation method carries out polishing to data；
(4) difference processing submodule, connection misarrangement submodule and inspection submodule, it is poor for being carried out to the data after polishing Point processing, and by the data transmission after difference processing to inspection submodule.
Data categorization module and stationarity inspection module is arranged in the present embodiment, increases the accuracy of data, and make construction Prediction model it is more targeted；Related coefficient computing module, temporal and spatial correlations coefficient matrix generation module, history phase relation are set Matrix number generation module, predictive factor choose module and forecast model construction module, eliminate the master that initial predictive factor is chosen The property seen, can increase precision of prediction, keep forecast model construction module more stable and accurate；The present embodiment value L=8, M=3, Precision of prediction improves 1.5% relative to the relevant technologies.
Embodiment 2
Referring to Fig. 1, Fig. 2, a kind of multidisplay apparatus that can carry out traffic flow forecasting of the present embodiment, including multiscreen are aobvious Showing device and the prediction meanss being connected with multidisplay apparatus, the multidisplay apparatus include：
First display device, first display device include an at least display screen, which shows smaller User interface, it is characterised in that：The multidisplay apparatus further includes the second display device, and second display device is first aobvious with this Showing device is rotatablely connected, which includes an at least display screen, when first display device and second display fill When setting in same plane, an at least display screen for first display device and an at least display screen for second display device without Seam docking is to show larger user interface.
Preferably, the first display device includes first shell, which includes the first main body, which has One first face and one adjacent to first face first side, on the direction of the both ends of the first side along the vertical first side Protrude out the first driveconnecting shaft and the second driveconnecting shaft, first driveconnecting shaft and second driveconnecting shaft it is coaxial, first driveconnecting shaft and should One first container is formed between main body, one second container is formed between second driveconnecting shaft and the main body, this is second aobvious Showing device includes second shell, which includes the second main body, which has one opposite with first face the Two faces and one adjacent to second face second side, the both ends of the second side are protruded out along the direction perpendicular to the second side Go out third driveconnecting shaft and the 4th driveconnecting shaft, the third driveconnecting shaft and the 4th driveconnecting shaft are coaxial, and the third driveconnecting shaft is contained in First container, the 4th driveconnecting shaft are contained in second container.
Preferably, first shell includes that the master control key being located on first face and volume port, first driveconnecting shaft are separate It is provided with an earphone interface on the side of second driveconnecting shaft, is arranged on the side of second driveconnecting shaft far from first driveconnecting shaft There is a power port.
Preferably, characterized in that prediction meanss include sequentially connected acquisition module, data preprocessing module, data point Generic module, stationary test module, related coefficient computing module, threshold setting module, temporal and spatial correlations coefficient matrix generation module, History correlation matrix generation module, predictive factor choose module and forecast model construction module：
(1) acquisition module observes section S for acquiring in road network S_{i}, prediction section S_{j}The magnitude of traffic flow of corresponding each period Data and passage situation；
(2) data preprocessing module for carrying out data prediction to the traffic flow data, and is rejected and is not met friendship The data of logical actual conditions；
(3) data categorization module, for carrying out classification of type, the class by the traffic flow data of data prediction Type includes festivals or holidays traffic flow data, weekend traffic flow data and working day traffic flow data；
(4) stationary test module, for being in same type of observation section S_{i}Magnitude of traffic flow sequence X_{i}With prediction Section S_{j}Magnitude of traffic flow sequence X_{j}Stationary test is carried out respectively, examines the autocorrelation function of stationarity to be：
Wherein, X_{x}Indicate magnitude of traffic flow sequence to be tested, ν_{i}Indicate the mean value of magnitude of traffic flow sequence to be tested, X_{x+τ}Indicate X_{x} Magnitude of traffic flow sequence after time delay τ, ν_{x+τ}For X_{x+τ}Mean value, σ^{2}For X_{x}With X_{x+τ}Between variance；
When autocorrelation function P (τ) can rapid decay level off to and 0 or fluctuate near 0, then the magnitude of traffic flow sequence to be tested Row pass through stationary test；When autocorrelation function P (τ) is unable to rapid decay and levels off to 0 or fluctuate near 0, then wait for described Continue stationary test after examining magnitude of traffic flow sequence to carry out calm disposing；
(5) related coefficient computing module, for calculating the observation section S by stationary test_{i}Magnitude of traffic flow sequence X_{i} With prediction section S_{j}Magnitude of traffic flow sequence X_{j}Time correlation coefficient ρ at time delay τ_{ij}(τ) and space correlation coefficient ρ_{ij} (w), if there is N number of section in road network S, magnitude of traffic flow sequence X_{i}=[x_{i}(1),x_{i}(2),...,x_{i}(n)], magnitude of traffic flow sequencex_{i}(t) observation section S is indicated_{i}In the flow of t moment, x_{j}(t) prediction section S is indicated_{j}In t The flow at quarter, t=1,2 ... n, time correlation coefficient ρ_{ij}The calculation formula of (τ) is：
Space correlation coefficient ρ_{ij}(w) calculation formula is：
Preferably, characterized in that prediction meanss further include：
(6) threshold setting module, for setting time delay maximum value L, temporal and spatial correlations coefficient threshold between each section T_{1}With history correlation coefficient threshold T_{2}；
(7) temporal and spatial correlations coefficient matrix generation module, for the time correlation coefficient ρ according to each section_{ij}(τ) and space phase Relationship number ρ_{ij}(w) each observation section S is built_{i}With prediction section S_{j}Postpone the temporal and spatial correlations coefficient matrix ρ under τ in different time (τ) ', and calculate the temporal and spatial correlations coefficient ρ in each section_{ij}(τ) ', the wherein value range of i ∈ [1, N] and τ ∈ [0, L], L be [8, 12], the calculation formula of temporal and spatial correlations coefficient matrix ρ (τ) ' is：
Temporal and spatial correlations coefficient ρ_{ij}The calculation formula of (τ) ' is：
ρ_{ij}(τ) '=ρ_{ij}(τ)ρ_{ij}(w)；
(8) history correlation matrix generation module, for generating prediction section S_{j}History correlation matrix ρ (t)：
Wherein, it chooses the nearly M weeks same period and same type of historical traffic is as magnitude of traffic flow sequence X_{j}History it is related Sequence is denoted asM=1,2 ... the value range of M, M are [3,5], the history phase Relationship number ρ_{jm}(t) calculation formula is：
(9) predictive factor chooses module, for according to the temporal and spatial correlations coefficient threshold T_{1}With history correlation coefficient threshold T_{2} It chooses and predicts the relevant predictive factor of target point, and matrix reconstruction is carried out according to its selected spatial position j and time delay τ, Selection principle is：
If ρ_{ij}(τ) ' ＞ T_{1}, then section S will be observed_{i}Magnitude of traffic flow sequence X_{i}The middle magnitude of traffic flow composition for meeting condition is new Sequence and as the first predictive factor, be denoted as X', X'=(x_{1}',x_{2}',...,x_{p}'), wherein p is the friendship for meeting condition Throughcurrent capacity number, if L_{1}For the maximum value of time delay in the first predictive factor, L_{1}=max τ  τ ∈ [0, L] and ρ_{ij}(τ) ' ＞ T_{1}, then the first predictive factor X' can state following matrix form as：
If ρ_{jm}(t) ＞ T_{2}, then by all history correlated series X for meeting condition_{jm}(t) it is used as the second predictive factor, is denoted as Y', Y'={ y_{1}',y_{2}',...,y_{q}', wherein q is the historical traffic number for the condition that meets, and the second predictive factor Y' can be stated as Following matrix form：
(10) forecast model construction module, by by the first predictive factor and the second predictive factor be used as training sample come Prediction model of the predictable section of construction in the magnitude of traffic flow of subsequent time.
Wherein, in the data preprocessing module, the rule that the data of traffic actual conditions are not met described in rejecting is： In one data update cycle, the threshold range of total traffic flow data in each section is set separately, if certain collected section Total traffic flow data fall in corresponding threshold range, then show that this group of data are reliable, retain this group of data；If collecting Total traffic flow data in certain section fall not in corresponding threshold range, then show that this group of data are unreliable, and picked It removes.
Wherein, the stationary test module includes following submodule：
(1) submodule is examined, for in the same type of magnitude of traffic flow sequence for observing section and prediction section Magnitude of traffic flow sequence carries out stationary test respectively；
(2) continuity check submodule is connect with submodule is examined, for not passing through the friendship to be tested of stationary test Throughcurrent capacity sequence carries out continuity check, if not meeting continuity, the continuity check submodule uses average interpolation method pair Data carry out polishing；
(3) misarrangement submodule is connect with continuity check submodule, and the data for deleting apparent error use simultaneously Average interpolation method carries out polishing to data；
(4) difference processing submodule, connection misarrangement submodule and inspection submodule, it is poor for being carried out to the data after polishing Point processing, and by the data transmission after difference processing to inspection submodule.
Data categorization module and stationarity inspection module is arranged in the present embodiment, increases the accuracy of data, and make construction Prediction model it is more targeted；Related coefficient computing module, temporal and spatial correlations coefficient matrix generation module, history phase relation are set Matrix number generation module, predictive factor choose module and forecast model construction module, eliminate the master that initial predictive factor is chosen The property seen, can increase precision of prediction, keep forecast model construction module more stable and accurate；The present embodiment value L=9, M=3, Precision of prediction improves 2% relative to the relevant technologies.
Embodiment 3
Referring to Fig. 1, Fig. 2, a kind of multidisplay apparatus that can carry out traffic flow forecasting of the present embodiment, including multiscreen are aobvious Showing device and the prediction meanss being connected with multidisplay apparatus, the multidisplay apparatus include：
First display device, first display device include an at least display screen, which shows smaller User interface, it is characterised in that：The multidisplay apparatus further includes the second display device, and second display device is first aobvious with this Showing device is rotatablely connected, which includes an at least display screen, when first display device and second display fill When setting in same plane, an at least display screen for first display device and an at least display screen for second display device without Seam docking is to show larger user interface.
Preferably, the first display device includes first shell, which includes the first main body, which has One first face and one adjacent to first face first side, on the direction of the both ends of the first side along the vertical first side Protrude out the first driveconnecting shaft and the second driveconnecting shaft, first driveconnecting shaft and second driveconnecting shaft it is coaxial, first driveconnecting shaft and should One first container is formed between main body, one second container is formed between second driveconnecting shaft and the main body, this is second aobvious Showing device includes second shell, which includes the second main body, which has one opposite with first face the Two faces and one adjacent to second face second side, the both ends of the second side are protruded out along the direction perpendicular to the second side Go out third driveconnecting shaft and the 4th driveconnecting shaft, the third driveconnecting shaft and the 4th driveconnecting shaft are coaxial, and the third driveconnecting shaft is contained in First container, the 4th driveconnecting shaft are contained in second container.
Preferably, first shell includes that the master control key being located on first face and volume port, first driveconnecting shaft are separate It is provided with an earphone interface on the side of second driveconnecting shaft, is arranged on the side of second driveconnecting shaft far from first driveconnecting shaft There is a power port.
Preferably, characterized in that prediction meanss include sequentially connected acquisition module, data preprocessing module, data point Generic module, stationary test module, related coefficient computing module, threshold setting module, temporal and spatial correlations coefficient matrix generation module, History correlation matrix generation module, predictive factor choose module and forecast model construction module：
(1) acquisition module observes section S for acquiring in road network S_{i}, prediction section S_{j}The magnitude of traffic flow of corresponding each period Data and passage situation；
(2) data preprocessing module for carrying out data prediction to the traffic flow data, and is rejected and is not met friendship The data of logical actual conditions；
(3) data categorization module, for carrying out classification of type, the class by the traffic flow data of data prediction Type includes festivals or holidays traffic flow data, weekend traffic flow data and working day traffic flow data；
(4) stationary test module, for being in same type of observation section S_{i}Magnitude of traffic flow sequence X_{i}With prediction Section S_{j}Magnitude of traffic flow sequence X_{j}Stationary test is carried out respectively, examines the autocorrelation function of stationarity to be：
Wherein, X_{x}Indicate magnitude of traffic flow sequence to be tested, ν_{i}Indicate the mean value of magnitude of traffic flow sequence to be tested, X_{x+τ}Indicate X_{x} Magnitude of traffic flow sequence after time delay τ, ν_{x+τ}For X_{x+τ}Mean value, σ^{2}For X_{x}With X_{x+τ}Between variance；
When autocorrelation function P (τ) can rapid decay level off to and 0 or fluctuate near 0, then the magnitude of traffic flow sequence to be tested Row pass through stationary test；When autocorrelation function P (τ) is unable to rapid decay and levels off to 0 or fluctuate near 0, then wait for described Continue stationary test after examining magnitude of traffic flow sequence to carry out calm disposing；
(5) related coefficient computing module, for calculating the observation section S by stationary test_{i}Magnitude of traffic flow sequence X_{i} With prediction section S_{j}Magnitude of traffic flow sequence X_{j}Time correlation coefficient ρ at time delay τ_{ij}(τ) and space correlation coefficient ρ_{ij} (w), if there is N number of section in road network S, magnitude of traffic flow sequence X_{i}=[x_{i}(1),x_{i}(2),...,x_{i}(n)], magnitude of traffic flow sequencex_{i}(t) observation section S is indicated_{i}In the flow of t moment, x_{j}(t) prediction section S is indicated_{j}In t The flow at quarter, t=1,2 ... n, time correlation coefficient ρ_{ij}The calculation formula of (τ) is：
Space correlation coefficient ρ_{ij}(w) calculation formula is：
Preferably, characterized in that prediction meanss further include：
(6) threshold setting module, for setting time delay maximum value L, temporal and spatial correlations coefficient threshold between each section T_{1}With history correlation coefficient threshold T_{2}；
(7) temporal and spatial correlations coefficient matrix generation module, for the time correlation coefficient ρ according to each section_{ij}(τ) and space phase Relationship number ρ_{ij}(w) each observation section S is built_{i}With prediction section S_{j}Postpone the temporal and spatial correlations coefficient matrix ρ under τ in different time (τ) ', and calculate the temporal and spatial correlations coefficient ρ in each section_{ij}(τ) ', the wherein value range of i ∈ [1, N] and τ ∈ [0, L], L be [8, 12], the calculation formula of temporal and spatial correlations coefficient matrix ρ (τ) ' is：
Temporal and spatial correlations coefficient ρ_{ij}The calculation formula of (τ) ' is：
ρ_{ij}(τ) '=ρ_{ij}(τ)ρ_{ij}(w)；
(8) history correlation matrix generation module, for generating prediction section S_{j}History correlation matrix ρ (t)：
Wherein, it chooses the nearly M weeks same period and same type of historical traffic is as magnitude of traffic flow sequence X_{j}History it is related Sequence is denoted asM=1,2 ... the value range of M, M are [3,5], the history phase Relationship number ρ_{jm}(t) calculation formula is：
(9) predictive factor chooses module, for according to the temporal and spatial correlations coefficient threshold T_{1}With history correlation coefficient threshold T_{2} It chooses and predicts the relevant predictive factor of target point, and matrix reconstruction is carried out according to its selected spatial position j and time delay τ, Selection principle is：
If ρ_{ij}(τ) ' ＞ T_{1}, then section S will be observed_{i}Magnitude of traffic flow sequence X_{i}The middle magnitude of traffic flow composition for meeting condition is new Sequence and as the first predictive factor, be denoted as X', X'=(x_{1}',x_{2}',...,x_{p}'), wherein p is the friendship for meeting condition Throughcurrent capacity number, if L_{1}For the maximum value of time delay in the first predictive factor, L_{1}=max τ  τ ∈ [0, L] and ρ_{ij}(τ) ' ＞ T_{1}, then the first predictive factor X' can state following matrix form as：
If ρ_{jm}(t) ＞ T_{2}, then by all history correlated series X for meeting condition_{jm}(t) it is used as the second predictive factor, is denoted as Y', Y'={ y_{1}',y_{2}',...,y_{q}', wherein q is the historical traffic number for the condition that meets, and the second predictive factor Y' can be stated as Following matrix form：
(10) forecast model construction module, by by the first predictive factor and the second predictive factor be used as training sample come Prediction model of the predictable section of construction in the magnitude of traffic flow of subsequent time.
Wherein, in the data preprocessing module, the rule that the data of traffic actual conditions are not met described in rejecting is： In one data update cycle, the threshold range of total traffic flow data in each section is set separately, if certain collected section Total traffic flow data fall in corresponding threshold range, then show that this group of data are reliable, retain this group of data；If collecting Total traffic flow data in certain section fall not in corresponding threshold range, then show that this group of data are unreliable, and picked It removes.
Wherein, the stationary test module includes following submodule：
(1) submodule is examined, for in the same type of magnitude of traffic flow sequence for observing section and prediction section Magnitude of traffic flow sequence carries out stationary test respectively；
(2) continuity check submodule is connect with submodule is examined, for not passing through the friendship to be tested of stationary test Throughcurrent capacity sequence carries out continuity check, if not meeting continuity, the continuity check submodule uses average interpolation method pair Data carry out polishing；
(3) misarrangement submodule is connect with continuity check submodule, and the data for deleting apparent error use simultaneously Average interpolation method carries out polishing to data；
(4) difference processing submodule, connection misarrangement submodule and inspection submodule, it is poor for being carried out to the data after polishing Point processing, and by the data transmission after difference processing to inspection submodule.
Data categorization module and stationarity inspection module is arranged in the present embodiment, increases the accuracy of data, and make construction Prediction model it is more targeted；Related coefficient computing module, temporal and spatial correlations coefficient matrix generation module, history phase relation are set Matrix number generation module, predictive factor choose module and forecast model construction module, eliminate the master that initial predictive factor is chosen The property seen, can increase precision of prediction, keep forecast model construction module more stable and accurate；The present embodiment value L=10, M= 4, precision of prediction improves 2.6% relative to the relevant technologies.
Embodiment 4
Referring to Fig. 1, Fig. 2, a kind of multidisplay apparatus that can carry out traffic flow forecasting of the present embodiment, including multiscreen are aobvious Showing device and the prediction meanss being connected with multidisplay apparatus, the multidisplay apparatus include：
First display device, first display device include an at least display screen, which shows smaller User interface, it is characterised in that：The multidisplay apparatus further includes the second display device, and second display device is first aobvious with this Showing device is rotatablely connected, which includes an at least display screen, when first display device and second display fill When setting in same plane, an at least display screen for first display device and an at least display screen for second display device without Seam docking is to show larger user interface.
Preferably, the first display device includes first shell, which includes the first main body, which has One first face and one adjacent to first face first side, on the direction of the both ends of the first side along the vertical first side Protrude out the first driveconnecting shaft and the second driveconnecting shaft, first driveconnecting shaft and second driveconnecting shaft it is coaxial, first driveconnecting shaft and should One first container is formed between main body, one second container is formed between second driveconnecting shaft and the main body, this is second aobvious Showing device includes second shell, which includes the second main body, which has one opposite with first face the Two faces and one adjacent to second face second side, the both ends of the second side are protruded out along the direction perpendicular to the second side Go out third driveconnecting shaft and the 4th driveconnecting shaft, the third driveconnecting shaft and the 4th driveconnecting shaft are coaxial, and the third driveconnecting shaft is contained in First container, the 4th driveconnecting shaft are contained in second container.
Preferably, first shell includes that the master control key being located on first face and volume port, first driveconnecting shaft are separate It is provided with an earphone interface on the side of second driveconnecting shaft, is arranged on the side of second driveconnecting shaft far from first driveconnecting shaft There is a power port.
Preferably, characterized in that prediction meanss include sequentially connected acquisition module, data preprocessing module, data point Generic module, stationary test module, related coefficient computing module, threshold setting module, temporal and spatial correlations coefficient matrix generation module, History correlation matrix generation module, predictive factor choose module and forecast model construction module：
(1) acquisition module observes section S for acquiring in road network S_{i}, prediction section S_{j}The magnitude of traffic flow of corresponding each period Data and passage situation；
(2) data preprocessing module for carrying out data prediction to the traffic flow data, and is rejected and is not met friendship The data of logical actual conditions；
(3) data categorization module, for carrying out classification of type, the class by the traffic flow data of data prediction Type includes festivals or holidays traffic flow data, weekend traffic flow data and working day traffic flow data；
(4) stationary test module, for being in same type of observation section S_{i}Magnitude of traffic flow sequence X_{i}With prediction Section S_{j}Magnitude of traffic flow sequence X_{j}Stationary test is carried out respectively, examines the autocorrelation function of stationarity to be：
Wherein, X_{x}Indicate magnitude of traffic flow sequence to be tested, ν_{i}Indicate the mean value of magnitude of traffic flow sequence to be tested, X_{x+τ}Indicate X_{x} Magnitude of traffic flow sequence after time delay τ, ν_{x+τ}For X_{x+τ}Mean value, σ^{2}For X_{x}With X_{x+τ}Between variance；
When autocorrelation function P (τ) can rapid decay level off to and 0 or fluctuate near 0, then the magnitude of traffic flow sequence to be tested Row pass through stationary test；When autocorrelation function P (τ) is unable to rapid decay and levels off to 0 or fluctuate near 0, then wait for described Continue stationary test after examining magnitude of traffic flow sequence to carry out calm disposing；
(5) related coefficient computing module, for calculating the observation section S by stationary test_{i}Magnitude of traffic flow sequence X_{i} With prediction section S_{j}Magnitude of traffic flow sequence X_{j}Time correlation coefficient ρ at time delay τ_{ij}(τ) and space correlation coefficient ρ_{ij} (w), if there is N number of section in road network S, magnitude of traffic flow sequence X_{i}=[x_{i}(1),x_{i}(2),...,x_{i}(n)], magnitude of traffic flow sequencex_{i}(t) observation section S is indicated_{i}In the flow of t moment, x_{j}(t) prediction section S is indicated_{j}In t The flow at quarter, t=1,2 ... n, time correlation coefficient ρ_{ij}The calculation formula of (τ) is：
Space correlation coefficient ρ_{ij}(w) calculation formula is：
Preferably, characterized in that prediction meanss further include：
(6) threshold setting module, for setting time delay maximum value L, temporal and spatial correlations coefficient threshold between each section T_{1}With history correlation coefficient threshold T_{2}；
(7) temporal and spatial correlations coefficient matrix generation module, for the time correlation coefficient ρ according to each section_{ij}(τ) and space phase Relationship number ρ_{ij}(w) each observation section S is built_{i}With prediction section S_{j}Postpone the temporal and spatial correlations coefficient matrix ρ under τ in different time (τ) ', and calculate the temporal and spatial correlations coefficient ρ in each section_{ij}(τ) ', the wherein value range of i ∈ [1, N] and τ ∈ [0, L], L be [8, 12], the calculation formula of temporal and spatial correlations coefficient matrix ρ (τ) ' is：
Temporal and spatial correlations coefficient ρ_{ij}The calculation formula of (τ) ' is：
ρ_{ij}(τ) '=ρ_{ij}(τ)ρ_{ij}(w)；
(8) history correlation matrix generation module, for generating prediction section S_{j}History correlation matrix ρ (t)：
Wherein, it chooses the nearly M weeks same period and same type of historical traffic is as magnitude of traffic flow sequence X_{j}History it is related Sequence is denoted asM=1,2 ... the value range of M, M are [3,5], the history phase Relationship number ρ_{jm}(t) calculation formula is：
(9) predictive factor chooses module, for according to the temporal and spatial correlations coefficient threshold T_{1}With history correlation coefficient threshold T_{2} It chooses and predicts the relevant predictive factor of target point, and matrix reconstruction is carried out according to its selected spatial position j and time delay τ, Selection principle is：
If ρ_{ij}(τ) ' ＞ T_{1}, then section S will be observed_{i}Magnitude of traffic flow sequence X_{i}The middle magnitude of traffic flow composition for meeting condition is new Sequence and as the first predictive factor, be denoted as X', X'=(x_{1}',x_{2}',...,x_{p}'), wherein p is the friendship for meeting condition Throughcurrent capacity number, if L_{1}For the maximum value of time delay in the first predictive factor, L_{1}=max τ  τ ∈ [0, L] and ρ_{ij}(τ) ' ＞ T_{1}, then the first predictive factor X' can state following matrix form as：
If ρ_{jm}(t) ＞ T_{2}, then by all history correlated series X for meeting condition_{jm}(t) it is used as the second predictive factor, is denoted as Y', Y'={ y_{1}',y_{2}',...,y_{q}', wherein q is the historical traffic number for the condition that meets, and the second predictive factor Y' can be stated as Following matrix form：
(10) forecast model construction module, by by the first predictive factor and the second predictive factor be used as training sample come Prediction model of the predictable section of construction in the magnitude of traffic flow of subsequent time.
Wherein, in the data preprocessing module, the rule that the data of traffic actual conditions are not met described in rejecting is： In one data update cycle, the threshold range of total traffic flow data in each section is set separately, if certain collected section Total traffic flow data fall in corresponding threshold range, then show that this group of data are reliable, retain this group of data；If collecting Total traffic flow data in certain section fall not in corresponding threshold range, then show that this group of data are unreliable, and picked It removes.
Wherein, the stationary test module includes following submodule：
(1) submodule is examined, for in the same type of magnitude of traffic flow sequence for observing section and prediction section Magnitude of traffic flow sequence carries out stationary test respectively；
(2) continuity check submodule is connect with submodule is examined, for not passing through the friendship to be tested of stationary test Throughcurrent capacity sequence carries out continuity check, if not meeting continuity, the continuity check submodule uses average interpolation method pair Data carry out polishing；
(3) misarrangement submodule is connect with continuity check submodule, and the data for deleting apparent error use simultaneously Average interpolation method carries out polishing to data；
(4) difference processing submodule, connection misarrangement submodule and inspection submodule, it is poor for being carried out to the data after polishing Point processing, and by the data transmission after difference processing to inspection submodule.
Data categorization module and stationarity inspection module is arranged in the present embodiment, increases the accuracy of data, and make construction Prediction model it is more targeted；Related coefficient computing module, temporal and spatial correlations coefficient matrix generation module, history phase relation are set Matrix number generation module, predictive factor choose module and forecast model construction module, eliminate the master that initial predictive factor is chosen The property seen, can increase precision of prediction, keep forecast model construction module more stable and accurate；The present embodiment value L=11, M= 5, precision of prediction improves 3.2% relative to the relevant technologies.
Embodiment 5
Referring to Fig. 1, Fig. 2, a kind of multidisplay apparatus that can carry out traffic flow forecasting of the present embodiment, including multiscreen are aobvious Showing device and the prediction meanss being connected with multidisplay apparatus, the multidisplay apparatus include：
First display device, first display device include an at least display screen, which shows smaller User interface, it is characterised in that：The multidisplay apparatus further includes the second display device, and second display device is first aobvious with this Showing device is rotatablely connected, which includes an at least display screen, when first display device and second display fill When setting in same plane, an at least display screen for first display device and an at least display screen for second display device without Seam docking is to show larger user interface.
Preferably, the first display device includes first shell, which includes the first main body, which has One first face and one adjacent to first face first side, on the direction of the both ends of the first side along the vertical first side Protrude out the first driveconnecting shaft and the second driveconnecting shaft, first driveconnecting shaft and second driveconnecting shaft it is coaxial, first driveconnecting shaft and should One first container is formed between main body, one second container is formed between second driveconnecting shaft and the main body, this is second aobvious Showing device includes second shell, which includes the second main body, which has one opposite with first face the Two faces and one adjacent to second face second side, the both ends of the second side are protruded out along the direction perpendicular to the second side Go out third driveconnecting shaft and the 4th driveconnecting shaft, the third driveconnecting shaft and the 4th driveconnecting shaft are coaxial, and the third driveconnecting shaft is contained in First container, the 4th driveconnecting shaft are contained in second container.
Preferably, first shell includes that the master control key being located on first face and volume port, first driveconnecting shaft are separate It is provided with an earphone interface on the side of second driveconnecting shaft, is arranged on the side of second driveconnecting shaft far from first driveconnecting shaft There is a power port.
Preferably, characterized in that prediction meanss include sequentially connected acquisition module, data preprocessing module, data point Generic module, stationary test module, related coefficient computing module, threshold setting module, temporal and spatial correlations coefficient matrix generation module, History correlation matrix generation module, predictive factor choose module and forecast model construction module：
(1) acquisition module observes section S for acquiring in road network S_{i}, prediction section S_{j}The magnitude of traffic flow of corresponding each period Data and passage situation；
(2) data preprocessing module for carrying out data prediction to the traffic flow data, and is rejected and is not met friendship The data of logical actual conditions；
(3) data categorization module, for carrying out classification of type, the class by the traffic flow data of data prediction Type includes festivals or holidays traffic flow data, weekend traffic flow data and working day traffic flow data；
(4) stationary test module, for being in same type of observation section S_{i}Magnitude of traffic flow sequence X_{i}With prediction Section S_{j}Magnitude of traffic flow sequence X_{j}Stationary test is carried out respectively, examines the autocorrelation function of stationarity to be：
Wherein, X_{x}Indicate magnitude of traffic flow sequence to be tested, ν_{i}Indicate the mean value of magnitude of traffic flow sequence to be tested, X_{x+τ}Indicate X_{x} Magnitude of traffic flow sequence after time delay τ, ν_{x+τ}For X_{x+τ}Mean value, σ^{2}For X_{x}With X_{x+τ}Between variance；
When autocorrelation function P (τ) can rapid decay level off to and 0 or fluctuate near 0, then the magnitude of traffic flow sequence to be tested Row pass through stationary test；When autocorrelation function P (τ) is unable to rapid decay and levels off to 0 or fluctuate near 0, then wait for described Continue stationary test after examining magnitude of traffic flow sequence to carry out calm disposing；
(5) related coefficient computing module, for calculating the observation section S by stationary test_{i}Magnitude of traffic flow sequence X_{i} With prediction section S_{j}Magnitude of traffic flow sequence X_{j}Time correlation coefficient ρ at time delay τ_{ij}(τ) and space correlation coefficient ρ_{ij} (w), if there is N number of section in road network S, magnitude of traffic flow sequence X_{i}=[x_{i}(1),x_{i}(2),...,x_{i}(n)], magnitude of traffic flow sequencex_{i}(t) observation section S is indicated_{i}In the flow of t moment, x_{j}(t) prediction section S is indicated_{j}In t The flow at quarter, t=1,2 ... n, time correlation coefficient ρ_{ij}The calculation formula of (τ) is：
Space correlation coefficient ρ_{ij}(w) calculation formula is：
Preferably, characterized in that prediction meanss further include：
(6) threshold setting module, for setting time delay maximum value L, temporal and spatial correlations coefficient threshold between each section T_{1}With history correlation coefficient threshold T_{2}；
(7) temporal and spatial correlations coefficient matrix generation module, for the time correlation coefficient ρ according to each section_{ij}(τ) and space phase Relationship number ρ_{ij}(w) each observation section S is built_{i}With prediction section S_{j}Postpone the temporal and spatial correlations coefficient matrix ρ under τ in different time (τ) ', and calculate the temporal and spatial correlations coefficient ρ in each section_{ij}(τ) ', the wherein value range of i ∈ [1, N] and τ ∈ [0, L], L be [8, 12], the calculation formula of temporal and spatial correlations coefficient matrix ρ (τ) ' is：
Temporal and spatial correlations coefficient ρ_{ij}The calculation formula of (τ) ' is：
ρ_{ij}(τ) '=ρ_{ij}(τ)ρ_{ij}(w)；
(8) history correlation matrix generation module, for generating prediction section S_{j}History correlation matrix ρ (t)：
Wherein, it chooses the nearly M weeks same period and same type of historical traffic is as magnitude of traffic flow sequence X_{j}History it is related Sequence is denoted asM=1,2 ... the value range of M, M are [3,5], the history phase Relationship number ρ_{jm}(t) calculation formula is：
(9) predictive factor chooses module, for according to the temporal and spatial correlations coefficient threshold T_{1}With history correlation coefficient threshold T_{2} It chooses and predicts the relevant predictive factor of target point, and matrix reconstruction is carried out according to its selected spatial position j and time delay τ, Selection principle is：
If ρ_{ij}(τ) ' ＞ T_{1}, then section S will be observed_{i}Magnitude of traffic flow sequence X_{i}The middle magnitude of traffic flow composition for meeting condition is new Sequence and as the first predictive factor, be denoted as X', X'=(x_{1}',x_{2}',...,x_{p}'), wherein p is the friendship for meeting condition Throughcurrent capacity number, if L_{1}For the maximum value of time delay in the first predictive factor, L_{1}=max τ  and τ ∈ [0, L]  and ρ_{ij}(τ)' ＞ T_{1}, then the first predictive factor X' can state following matrix form as：
If ρ_{jm}(t) ＞ T_{2}, then by all history correlated series X for meeting condition_{jm}(t) it is used as the second predictive factor, is denoted as Y', Y'={ y_{1}',y_{2}',...,y_{q}', wherein q is the historical traffic number for the condition that meets, and the second predictive factor Y' can be stated as Following matrix form：
(10) forecast model construction module, by by the first predictive factor and the second predictive factor be used as training sample come Prediction model of the predictable section of construction in the magnitude of traffic flow of subsequent time.
Wherein, in the data preprocessing module, the rule that the data of traffic actual conditions are not met described in rejecting is： In one data update cycle, the threshold range of total traffic flow data in each section is set separately, if certain collected section Total traffic flow data fall in corresponding threshold range, then show that this group of data are reliable, retain this group of data；If collecting Total traffic flow data in certain section fall not in corresponding threshold range, then show that this group of data are unreliable, and picked It removes.
Wherein, the stationary test module includes following submodule：
(1) submodule is examined, for in the same type of magnitude of traffic flow sequence for observing section and prediction section Magnitude of traffic flow sequence carries out stationary test respectively；
(2) continuity check submodule is connect with submodule is examined, for not passing through the friendship to be tested of stationary test Throughcurrent capacity sequence carries out continuity check, if not meeting continuity, the continuity check submodule uses average interpolation method pair Data carry out polishing；
(3) misarrangement submodule is connect with continuity check submodule, and the data for deleting apparent error use simultaneously Average interpolation method carries out polishing to data；
(4) difference processing submodule, connection misarrangement submodule and inspection submodule, it is poor for being carried out to the data after polishing Point processing, and by the data transmission after difference processing to inspection submodule.
Data categorization module and stationarity inspection module is arranged in the present embodiment, increases the accuracy of data, and make construction Prediction model it is more targeted；Related coefficient computing module, temporal and spatial correlations coefficient matrix generation module, history phase relation are set Matrix number generation module, predictive factor choose module and forecast model construction module, eliminate the master that initial predictive factor is chosen The property seen, can increase precision of prediction, keep forecast model construction module more stable and accurate；The present embodiment value L=12, M= 5, precision of prediction improves 3.5% relative to the relevant technologies.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention Matter and range.
Claims (5)
Priority Applications (1)
Application Number  Priority Date  Filing Date  Title 

CN201610513353.0A CN106128098B (en)  20160629  20160629  A kind of multidisplay apparatus that can carry out traffic flow forecasting 
Applications Claiming Priority (1)
Application Number  Priority Date  Filing Date  Title 

CN201610513353.0A CN106128098B (en)  20160629  20160629  A kind of multidisplay apparatus that can carry out traffic flow forecasting 
Publications (2)
Publication Number  Publication Date 

CN106128098A CN106128098A (en)  20161116 
CN106128098B true CN106128098B (en)  20180803 
Family
ID=57468672
Family Applications (1)
Application Number  Title  Priority Date  Filing Date 

CN201610513353.0A CN106128098B (en)  20160629  20160629  A kind of multidisplay apparatus that can carry out traffic flow forecasting 
Country Status (1)
Country  Link 

CN (1)  CN106128098B (en) 
Citations (4)
Publication number  Priority date  Publication date  Assignee  Title 

CN103620967A (en) *  20110503  20140305  艾科星科技公司  Communications device with extendable screen 
CN103632542A (en) *  20120827  20140312  国际商业机器公司  Traffic information processing method, device and corresponding equipment 
CN104506378A (en) *  20141203  20150408  上海华为技术有限公司  Data flow prediction device and method 
TW201610831A (en) *  20140902  20160316  Hon Hai Prec Ind Co Ltd  Multiscreen display device 
Family Cites Families (4)
Publication number  Priority date  Publication date  Assignee  Title 

CN101673463B (en) *  20090917  20111214  北京世纪高通科技有限公司  A traffic information prediction method and apparatus based on the time series 
EP2622443A4 (en) *  20101001  20140813  Z124  Drag move gesture in user interface 
WO2015170289A1 (en) *  20140509  20151112  Vodafone Omnitel B.V.  Method and system for vehicular traffic prediction 
CN104899663B (en) *  20150617  20190226  北京奇虎科技有限公司  A kind of data predication method and device 

2016
 20160629 CN CN201610513353.0A patent/CN106128098B/en active IP Right Grant
Patent Citations (4)
Publication number  Priority date  Publication date  Assignee  Title 

CN103620967A (en) *  20110503  20140305  艾科星科技公司  Communications device with extendable screen 
CN103632542A (en) *  20120827  20140312  国际商业机器公司  Traffic information processing method, device and corresponding equipment 
TW201610831A (en) *  20140902  20160316  Hon Hai Prec Ind Co Ltd  Multiscreen display device 
CN104506378A (en) *  20141203  20150408  上海华为技术有限公司  Data flow prediction device and method 
Also Published As
Publication number  Publication date 

CN106128098A (en)  20161116 
Similar Documents
Publication  Publication Date  Title 

Olea  Geostatistics for engineers and earth scientists  
Wittenbrink et al.  Glyphs for visualizing uncertainty in vector fields  
Fernández et al.  Modelling spatially correlated data via mixtures: a Bayesian approach  
Wakelin  The role of innovation in bilateral OECD trade performance  
Magalhaes et al.  Online automatic identification of the modal parameters of a long span arch bridge  
Bode  Neural networks for cost estimation: simulations and pilot application  
Stern  Neural networks in applied statistics  
Brix et al.  Spatiotemporal prediction for log‐Gaussian Cox processes  
Devi et al.  A multicriteria intuitionistic fuzzy group decision making for plant location selection with ELECTRE method  
Genton  Separable approximations of space‐time covariance matrices  
Feick et al.  A method for examining the spatial dimension of multicriteria weight sensitivity  
Grecu et al.  An efficient methodology for detection of anomalous propagation echoes in radar reflectivity data using neural networks  
US5126978A (en)  Undersea data collection, analysis, and display system  
Kell et al.  An evaluation of the implicit management procedure used for some ICES roundfish stocks  
JP2003516863A (en)  Welding evaluation  
AghaKouchak et al.  Modeling radar rainfall estimation uncertainties: Random error model  
Assuncao et al.  A Bayesian space varying parameter model applied to estimating fertility schedules  
Chen et al.  Identification of λfuzzy measures using sampling design and genetic algorithms  
Xie et al.  Ecological risk assessment of land use change in the Poyang Lake ecoeconomic zone, China  
Mendoza  GISbased multicriteria approaches to land use suitability assessment and allocation  
Bodri  A neuralnetwork model for earthquake occurrence  
Canizares et al.  Developments in operational shelf sea modelling in Danish waters  
Mulder et al.  Multidimensional adaptive testing with Kullback–Leibler information item selection  
Mentis  Hypotheticodeductive and inductive approaches in ecology  
CN107111794A (en)  Prediction and the changeability using the travel time in Map Services 
Legal Events
Date  Code  Title  Description 

C06  Publication  
PB01  Publication  
C10  Entry into substantive examination  
SE01  Entry into force of request for substantive examination  
TA01  Transfer of patent application right  
TA01  Transfer of patent application right 
Effective date of registration: 20180621 Address after: 030012 Taiyuan, Shanxi Xiaodian District, 91 West Road, B, office building, 6 floor, North Tower. Applicant after: Shanxi unobstructed engineering survey and Design Consulting Co., Ltd. Address before: No. 372, Zhenhai District, Ningbo, Zhejiang, Zhejiang Applicant before: Xiao Rui 

GR01  Patent grant  
GR01  Patent grant 