CN107180278A - A kind of real-time passenger flow forecasting of track traffic - Google Patents
A kind of real-time passenger flow forecasting of track traffic Download PDFInfo
- Publication number
- CN107180278A CN107180278A CN201710387638.9A CN201710387638A CN107180278A CN 107180278 A CN107180278 A CN 107180278A CN 201710387638 A CN201710387638 A CN 201710387638A CN 107180278 A CN107180278 A CN 107180278A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- passenger flow
- function
- real
- 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
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 54
- 230000000694 effects Effects 0.000 description 10
- 238000012417 linear regression Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000007306 turnover Effects 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000010903 husk Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000010181 polygamy Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of real-time passenger flow forecasting of track traffic, low, the computationally intensive technical problem of predictablity rate present in prior art is mainly solved, the present invention includes by using method:N historical data is gathered as original sample from AFC system, and original sample progress is pre-processed and obtains pre-processing sample;Sample is pre-processed according in, the Passenger flow forecast model in short-term based on support vector regression is set up according to kernel function and fitting regression function, the kernel function is RBF;Anticipation function is fitted using time series vector X and with time series to the corresponding passenger flow vector Y of X amounts as input, the input is fitted anticipation function input step Passenger flow forecast model, passenger flow forecast vector Y in short-termn+1;Technical scheme, the problem is preferably resolved, available in the real-time passenger flow estimation of track traffic.
Description
Technical field
Field is predicted the present invention relates to track traffic for passenger flow, a kind of real-time passenger flow estimation side of track traffic is related specifically to
Method.
Background technology
With the fast development of urbanization process, conflicting between the trip requirements and urban transportation carrying capacity of urban population
More protrude.Urban track traffic takes off grain husk with advantages such as its distinctive high speed, high power capacity and environmental protection from multiple transportation modes
And go out, as the main means of transport for solving traffic congestion.Each city puts into construction one after another, makes urban track traffic be transported from single line
Seek to gauze operation and make the transition, while its scale and complexity lifting, the also network management to track traffic and development is proposed
Challenge.It is also the weight of real-time adjustment operation plan and fast and accurately passenger flow estimation is both the basis that science formulates route plan
Will foundation, it contribute to traffic operation and management more comprehensively high-quality performance its effect.SVMs, i.e. SVM, it is convex as one
Quadratic programming problem, it is ensured that obtained minimax solution is exactly globally optimal solution.These characteristics make SVM enough turn into it is outstanding based on
The machine learning method of data.SVM has outstanding behaviours, and energy in the problems such as solving to recognize for small sample and high dimensional pattern
By in the correlation machine Learning Studies such as application to Function Fitting.Different from traditional machine learning algorithm, SVM is by original sample
This space reflection arrives high-dimensional feature space, and tries to achieve in new space optimum linearity classifying face.This Mapping and Converting is non-linear
Conversion is realized using appropriate interior Product function.SVM successfully solves the problems, such as local minimum and higher-dimension problem.It is different by defining
Interior Product function can realize a variety of learning algorithms such as Bayes classifier, radial basis functions, multi-Layer Perceptron Neural Network.SVM
The training process learnt using the large-spacing factor come control machine, makes its only maximum Optimal Separating Hyperplane in selection sort interval.SVM
Algorithm possesses more complete theoretical foundation, and extraordinary Generalization Capability is presented in the application in some fields, in consideration of it, it
Original effect is obtained in classification, recurrence and density function estimation is solved, and has successfully been applied to regression estimates, pattern
In terms of identification.Such as text classification, speech recognition.SVM is designed and is used widely for classification problem earliest.In recent years
Come, it also shows extraordinary performance in terms of regression problem.
The existing real-time passenger flow forecasting of track traffic includes Roos J and proposes that a dynamic bayesian network method is used
Short-term passenger flow in prediction Paris railway network, the infull situation of the data that this method is caused to the system failure has preferable processing
Effect.The existing real-time passenger flow forecasting of track traffic has that predictablity rate is low, computationally intensive technical problem.Therefore,
There is provided the real-time passenger flow forecasting of track traffic that a kind of predictablity rate is high, amount of calculation is small just necessary.
The content of the invention
The technical problems to be solved by the invention are that predictablity rate present in prior art is low, computationally intensive problem.
A kind of real-time passenger flow forecasting of new track traffic is provided, the real-time passenger flow forecasting of the track traffic has predictablity rate
It is high, the characteristics of amount of calculation is small.
In order to solve the above technical problems, the technical scheme used is as follows:
A kind of real-time passenger flow forecasting of track traffic, methods described includes:
(1) n historical data is gathered as original sample from AFC system, original sample is carried out to pre-process
To pretreatment sample, the pretreatment sample includes time series vector X and passenger flow corresponding with time series vector X vector Y;
(2) according to pretreatment sample in step (1), set up and returned based on supporting vector according to kernel function and fitting regression function
Return the Passenger flow forecast model in short-term of machine, the kernel function is RBF;
(3) it is used as input fitting prediction letter using time series vector X and with time series to the corresponding passenger flow vector Y of X amounts
Number, is fitted the Passenger flow forecast model in short-term based on support vector regression in anticipation function input step (2), in advance by the input
Survey passenger flow vector Yn+1;
Wherein, X={ t1,t2,...,tn, Y={ y1,y2,...,yn}。
The operation principle of the present invention:Time series is the Serial No. according to time-sequencing.Analysis to time series
Journey be the time series data that arrives statistical process as sample, set up the generation that model is used to predicting future event.Including two
Point:One, recognize the continuity of event development;Two, it is considered to the randomness that event occurs.Prediction for time series mainly can be with
Reflect three kinds of changing rules based on cyclically-varying, Long-term change trend, randomness change.Passenger flow data then possesses this in short-term
Changing rule, for the prediction of passenger flow in short-term, final purpose is to aid in rail transportation operation safe operation, improve efficiency of service with
And service quality.Accurate passenger flow forecast trend, it is necessary to realized by setting up high-precision forecast model.Passenger flow data has multiple
Polygamy and mutability, thus be excluded that linear prediction method, selection uses Non-linear.
Because original sample is the mass data that is collected from real world, and reality production and real life and science
There is diversity, uncertain and complexity between research, cause the initial data collected more at random, meet prediction algorithm
The standard degree for carrying out knowledge acquisition research is low.Therefore, before being predicted, initial data must be handled, changed first.
The present invention gathers n historical data as original sample using from AFC system, and original sample is carried out
Pretreatment is obtained pre-processing sample, and the passenger flow in short-term based on support vector regression is set up according to kernel function and fitting regression function
Forecast model, the kernel function is RBF;According to the prediction of Passenger flow forecast model in short-term based on support vector regression
Following passenger flow.Support vector regression model only has a class sample point, and sought optimal hyperlane is to make all sample points
It is minimum apart from hyperplane total deviation value.This moment, between sample point is all contained in two borders, ask optimum regression hyperplane just with
It is of equal value to seek largest interval.Non-linear support vector regression mainly using pre-determined Nonlinear Mapping will input to
Amount maps to some high-dimensional feature space, and linear regression is carried out in higher dimensional space, is obtained and is returned with former Space Nonlinear with this
Identical effect.In several kernel functions, linear kernel function can not be handled input value, higher-dimension core in Radial basis kernel function
Number of parameters be less than Polynomial kernel function, but in support vector regression training process, Polynomial kernel function is tested
The required training time is much larger than Radial basis kernel function, and when using Sigmoid kernel functions, the value in some parameters is mistake
's.Therefore, the present invention uses Radial basis kernel function.
In above-mentioned technical proposal, for optimization, further, the in short-term passenger flow of the foundation based on support vector regression is pre-
Surveying model includes:
(A) it regard pretreatment sample as given training set T={ (x1,y1),…,(xn,yn)}∈(R×y)n;
(B) according to kernel function K (x, x'), computational accuracy ε > 0 and penalty C > 0 are constructed and are solved convex quadratic programming
Object function;
K(xi,xj)=Φ (xi) Φ (xj);
(C) decision function is calculated according to quadratic programming object function and nonlinear fitting function:
The nonlinear fitting function is:
The decision function calculated is:
(D) according to decision function, using n historical data as training set, progress returns pre- on the hyperplane that n+1 is tieed up
Survey, calculating the Passenger flow forecast model in short-term is:
F (x+1)=β1f(x)+β2f(x-1)+...+βnf(x-n+1);
Wherein, K (x, x') is kernel function, xi∈Rn,yi∈ y=R, i=1 ..., n, f (x+1) represent the visitor at the x+1 moment
Flow, βiRepresent weight coefficient, i=1,2 ..., n.
Further, the RBF is gaussian kernel function:
Further, the passenger flow vector Yn+1Predicted including passenger flow estimation in short-term and peak.
Further, the peak prediction includes morning peak prediction and evening peak prediction.
Further, the pretreatment includes key message extraction, data preparation and minute level discrepancy guest flow statistics.
Further, the key message, which is extracted, includes parameter conduct in extraction charge time, platform and traffic Card Type 3
Key message.
Further, the statistic frequency of minute level discrepancy guest flow statistics is not less than every 5 minutes statistics once.
Support vector regression, i.e. support vector regression, are generally divided into linear regression and nonlinear regression.Returned for linear
Return, sample data is estimated using linear regression function.For nonlinear regression, mapped the data into by a Nonlinear Mapping
High-dimensional feature space simultaneously carries out linear regression in this space, and nonlinear regression the step of rise dimension, enter in higher dimensional space
Row linear regression replaces the nonlinear regression of lower dimensional space, to save dot-product operation complicated in higher dimensional space.Supporting vector is returned
Reduction method switchs to the solution to convex quadratic programming problem, and its scale is twice of svm classifier problem under same sample size.
Support vector regression mainly includes two kinds of situations of linear processes.
In Linear Support Vector Regression, training set is set
The parameter found in regression function f (x, α)=ω x+b is calculated using ε-insensitive loss functionWithI.e.:
(ω·xi+b)-yi≤ε+ξi, i=1 ..., l
Wherein, ξiWithIt is slack variable, introduces Lagrange functions
Wherein, Lagrange multipliers are met
If L is to b, w, ξ(*)Partial derivative be 0, on α(*)Maximum:
In nonlinear regression machine, Nonlinear Mapping is first usedCorresponding data is mapped to some high-dimensional feature space, and
Linear regression is done in higher dimensional space.Due to only accounting for feature space inner product operation in optimization process, thus with kernel function k (x,
Y) replaceNonlinear regression can be realized.Nonlinear regression is:
Wherein,
Obtain α(*)Value, it is mostIt is worth for 0, not the α for 0(*)Correspondence sample is supporting vector.F (x) table
It is up to formula:
Wherein, b is:
Any supporting vector can calculate b values.
The present invention verify support vector regression forecast model validity while, compared for gaussian kernel function with
The fitting effect of RBF kernel functions.Realize that effect shows that the Passenger flow forecast model based on support vector regression possesses certain prediction
Ability, its prediction conclusion is effective.In two kinds of kernel functions, gaussian kernel function prediction effect is substantially better than RBF kernel functions, excellent
Selection of land, behavior optimal selection is entered by selection gaussian kernel function.Original sample is obtained from practical application AFC system (AFC)
Take, because experimental data amount is bigger, any time passenger turnover information of acquisition, information is more mixed and disorderly.Therefore need to huge
Data set carry out one integrate with key message extract.In the selection of key message, the present invention have chosen in 7 kinds of labels
Three kinds as key message, they include charge time, platform and traffic Card Type.The present invention has traveled through all experimental datas,
All the elements of key message are arranged.Because raw data form is mixed and disorderly, it is unfavorable for carrying out experiment prediction.Therefore, by data
The progress for being conducive to subsequent experimental is arranged according to certain rules.The present invention is predicted to the travelling traffic amount of different websites, by before
Website number in the site list that one step is arranged is remembered as tag along sort to the discrepancy of Metro Network within a certain period of time
Record is classified.The numerous information of initial data of the present invention, and every information only have recorded certain passenger's moment go out state of entering a profession.
Passenger flow forecast is carried out to set up forecast model, then initial data must be counted.Therefore, travel through after each arrange
Platform data file, the inbound number and outbound number for counting once the website in every 5 minutes.
Beneficial effects of the present invention:
Effect one, improves prediction accuracy;
Effect two, improves forecasting efficiency;
Data are pre-processed by effect three, reduce the diversity of prediction, uncertain and complexity.
Brief description of the drawings
The present invention is further described with reference to the accompanying drawings and examples.
Fig. 1, data prediction schematic flow sheet.
Fig. 2, No. 0321 platform, which enters the station, predicts support vector regression model.
Fig. 3, the outbound prediction support vector regression model of No. 0321 platform.
Fig. 4, No. 0212 platform, which enters the station, predicts support vector regression model.
Fig. 5, the outbound prediction support vector regression model of No. 0212 platform.
Fig. 6, No. 0315 platform, which enters the station, predicts support vector regression model.
Fig. 7, the outbound prediction support vector regression model of No. 0315 platform.
Fig. 8, No. 0613 platform morning peak predicts support vector regression model.
Fig. 9, No. 0210 platform morning peak predicts support vector regression model.
Figure 10, No. 0613 platform evening peak predicts support vector regression model.
Figure 11, No. 0210 platform evening peak predicts support vector regression model.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Embodiment 1
The present embodiment provides a kind of real-time passenger flow forecasting of track traffic, and methods described includes:
(1) n historical data is gathered as original sample from AFC system, original sample is carried out to pre-process
To pretreatment sample, the pretreatment sample includes time series vector X and passenger flow corresponding with time series vector X vector Y;
(2) according to pretreatment sample in step (1), set up and returned based on supporting vector according to kernel function and fitting regression function
Return the Passenger flow forecast model in short-term of machine, the kernel function is RBF;
(3) it is used as input fitting prediction letter using time series vector X and with time series to the corresponding passenger flow vector Y of X amounts
Number, is fitted the Passenger flow forecast model in short-term based on support vector regression in anticipation function input step (2), in advance by the input
Survey passenger flow vector Yn+1;
Wherein, X={ t1,t2,...,tn, Y={ y1,y2,...,yn}。
Specifically, the in short-term Passenger flow forecast model of the foundation based on support vector regression includes:
(A) it regard pretreatment sample as given training set T={ (x1,y1),…,(xn,yn)}∈(R×y)n;
(B) according to kernel function K (x, x'), computational accuracy ε > 0 and penalty C > 0 are constructed and are solved convex quadratic programming
Object function;
K(xi,xj)=Φ (xi)·Φ(xj);
(C) decision function is calculated according to quadratic programming object function and nonlinear fitting function:
The nonlinear fitting function is:
The decision function calculated is:
(D) according to decision function, using n historical data as training set, progress returns pre- on the hyperplane that n+1 is tieed up
Survey, calculating the Passenger flow forecast model in short-term is:
F (x+1)=β1f(x)+β2f(x-1)+...+βnf(x-n+1);
Wherein, K (x, x') is kernel function, xi∈Rn,yi∈ y=R, i=1 ..., n, f (x+1) represent the visitor at the x+1 moment
Flow, βiRepresent weight coefficient, i=1,2 ..., n.
Preferably, further, the RBF is gaussian kernel function:
Specifically, the passenger flow vector Yn+1Predicted including passenger flow estimation in short-term and peak.
More specifically, the peak prediction includes morning peak prediction and evening peak prediction.
Because original sample is the mass data that is collected from real world, and reality production and real life and science
There is diversity, uncertain and complexity between research, cause the initial data collected more at random, meet prediction algorithm
The degree for carrying out knowledge acquisition research is low.
Preferably, such as Fig. 1, the pretreatment includes key message extraction, data preparation and minute level discrepancy volume of the flow of passengers system
Meter.Specifically, key message described in the present embodiment, which is extracted, includes parameter in extraction charge time, platform and traffic Card Type 3
It is used as key message.
Original sample is obtained from practical application AFC system, and because data volume is big, any time of acquisition multiplies
Visitor's turnover information clutter.Extracted accordingly, it would be desirable to carry out one to huge data set and integrate with key message.In key message
In selection, the present embodiment have chosen three kinds of more researching value as key message in 7 kinds of labels, when they include swiping the card
Between, platform and traffic Card Type.The present embodiment has traveled through all experimental datas in experimentation, has arranged the institute of key message
There is content.Arrange result:Table 1 is data sample keyword time list, and table 2 is data sample keyword platform list, and table 3 is
Data sample keyword card class-mark list.
Time | Time |
20140101 | 20140117 |
20140102 | 20140118 |
20140103 | 20140119 |
20140104 | 20140120 |
20140105 | 20140121 |
20140106 | 20140122 |
20140107 | 20140123 |
20140108 | 20140124 |
20140109 | 20140125 |
20140110 | 20140126 |
20140111 | 20140127 |
20140112 | 20140128 |
20140113 | 20140129 |
20140114 | 20140130 |
20140115 | 20140131 |
20140116 |
Table 1
Platform number | Platform number | Platform number | Platform number |
0102 | 0201 | 0301 | 0609 |
0103 | 0202 | 0302 | 0610 |
0104 | 0203 | 0303 | 0611 |
0105 | 0204 | 0304 | 0613 |
0106 | 0205 | 0305 | 0614 |
… | … | … | … |
0120 | 0215 | 0336 | 0623 |
0121 | 0216 | 0337 | 0625 |
0122 | 0217 | 0338 | 0626 |
0123 | 0218 | 0339 | 0628 |
Table 2
Card class-mark | Card Type | Card class-mark | Card Type |
00 | Livable generic card | 05 | Livable monthly ticket |
14 | Livable free card | 77 | Livable free numbered card |
15 | Livable employee job card | 82 | Business class |
20 | Love promotional card | 88 | Employee's ticket |
03 | Livable student card | 89 | One way commemorates ticket |
44 | Rail warns card on duty | 94 | Fixed ticket of track |
48 | Track service card | 98 | One-way ticket |
Table 3
It is on January 31,1 day to 2014 January in 2014 that data acquisition time scope is confirmed shown in table 1.Can from table 2
Go out, the platform of statistics, front two represents rail line name, rear two expression platforms number and from first to last once passs
Increase.Wherein, missing platform number represents that the platform is not also open-minded on the circuit.Transportation card type statistics are in table 3, and number is corresponding
Card Type name is also accordingly shown.
Because raw data form is mixed and disorderly, it is unfavorable for carrying out experiment prediction.Therefore, data are arranged to favourable according to certain rules
In the progress of subsequent experimental.Plan to be predicted the travelling traffic amount of different websites, in consideration of it, the station that previous step is arranged
Website number in point list is classified as tag along sort to discrepancy record of the Metro Network in one month.It is each
Individual site file contains passenger flow discrepancy record of the website in January, 2014.Initial data is more, and every information is only recorded
Certain passenger's moment goes out state of entering a profession.Passenger flow forecast is carried out to set up forecast model, first initial data is united
Meter can reduce amount of calculation.Therefore, the platform data file after each arrange is traveled through.
Preferably, the inbound number and outbound number for counting once the website in every 5 minutes, statistical result such as table 4.
Count the time started | Count deadline | Inbound number | Outbound number |
20140112-070000 | 20140112-070500 | 29 | 63 |
20140112-070500 | 20140112-071000 | 18 | 67 |
20140112-071000 | 20140112-071500 | 23 | 25 |
20140112-071500 | 20140112-072000 | 18 | 86 |
20140112-072000 | 20140112-072500 | 21 | 143 |
20140112-072500 | 20140112-073000 | 24 | 112 |
20140112-073000 | 20140112-073500 | 25 | 36 |
20140112-073500 | 20140112-074000 | 43 | 142 |
20140112-074000 | 20140112-074500 | 30 | 135 |
Table 4
The present embodiment predicts the outcome:
Passenger flow estimation in short-term:This No. 0321 platform of selection, No. 0212 platform, No. 0315 platform are right as prediction object
The website on January 6th, 2014, daily 15 entering the station when 21/outbound data was trained into January 21, and to 2014
The identical period on the 22nd enters the station/and the outbound volume of the flow of passengers is predicted, and every 15 minutes statistics of training data are once.Its experimental result such as Fig. 2-
Fig. 7.Wherein, Fig. 2 and Fig. 3 are respectively No. 0321 platform entry/exit station prediction support vector regression model;Fig. 4 and Fig. 5 are respectively
Predict support vector regression model in No. 0212 platform entry/exit station;Fig. 6 and Fig. 7 are respectively No. 0315 platform entry/exit station prediction branch
Hold vector regression model.
Wherein, abscissa is every 5 minutes scales in the period, and each protrusion represents the business hours in one day
Volume of the flow of passengers situation, last protrusion is the data being predicted.
Predict on peak:
Morning peak is predicted:This No. 0613 platform of selection and No. 0210 platform were as prediction object, to the website 2014 1
30 points to 30 points when 9 of the data that enter the station are trained when the moon 6 is into January 21 daily 6, and to the identical period on the 22nd in 2014
The volume of the flow of passengers that enters the station is predicted, and every 15 minutes statistics of training data are once.Its experimental result such as Fig. 8 and Fig. 9, Fig. 8 are No. 0613
The morning peak prediction support vector regression model of platform, Fig. 9 is No. 0210 platform morning peak prediction support vector regression mould
Type.Wherein, abscissa is every 20 minutes scales in the period.
Evening peak is predicted:This No. 0613 platform of selection and No. 0210 platform were as prediction object, to the website 2014 1
Months 6 days into January 21 daily 17 data that enter the station when 20 be trained, and standee was entered to the identical period on the 22nd in 2014
Flow is predicted, and every 15 minutes statistics of training data are once.Experimental result such as Figure 10 and Figure 11, Figure 10 are No. 0613 platform evening
Support vector regression model is predicted on peak, and Figure 11 is No. 0210 platform evening peak prediction support vector regression model.
Wherein, abscissa is every 20 minutes scales in the period.
Although illustrative embodiment of the invention is described above, in order to the technology of the art
Personnel are it will be appreciated that the present invention, but the present invention is not limited only to the scope of embodiment, to the common skill of the art
For art personnel, as long as long as various change is in the spirit and scope of the invention that appended claim is limited and is determined, one
The innovation and creation using present inventive concept are cut in the row of protection.
Claims (8)
1. a kind of real-time passenger flow forecasting of track traffic, it is characterised in that:Methods described includes:
(1) n historical data is gathered as original sample from AFC system, original sample pre-process to obtain pre-
Sample is handled, the pretreatment sample includes time series vector X and passenger flow corresponding with time series vector X vector Y;
(2) according to pretreatment sample in step (1), set up according to kernel function and fitting regression function and be based on support vector regression
Passenger flow forecast model in short-term, the kernel function be RBF;
(3) input fitting anticipation function is used as using time series vector X and with time series to the corresponding passenger flow vector Y of X amounts, will
Passenger flow forecast model in short-term based on support vector regression in the input fitting anticipation function input step (2), prediction visitor
Flow vector Yn+1;
Wherein, X={ t1,t2,...,tn, Y={ y1,y2,...,yn}。
2. the real-time passenger flow forecasting of track traffic according to claim 1, it is characterised in that:It is described to set up based on support
The Passenger flow forecast model in short-term of vector regression includes:
(A) it regard pretreatment sample as given training set T={ (x1,y1),…,(xn,yn)}∈(R×y)n;
(B) according to kernel function K (x, x'), computational accuracy ε > 0 and penalty C > 0 are constructed and are solved convex quadratic programming target
Function;
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>W</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>a</mi>
<mo>,</mo>
<msup>
<mi>a</mi>
<mo>*</mo>
</msup>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>a</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>a</mi>
<mi>j</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mo>&CenterDot;</mo>
<mi>K</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>+</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>a</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>+</mo>
<msubsup>
<mi>a</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mi>&epsiv;</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
K(xi,xj)=Φ (xi)·Φ(xj);
(C) decision function is calculated according to quadratic programming object function and nonlinear fitting function:
The nonlinear fitting function is:
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&omega;</mi>
<mo>&CenterDot;</mo>
<mi>&Phi;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>b</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>a</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
<mo>)</mo>
</mrow>
<mi>K</mi>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>)</mo>
<mo>+</mo>
<mi>b</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
The decision function calculated is:
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mrow>
<mo>(</mo>
<msubsup>
<mover>
<mi>&alpha;</mi>
<mo>&OverBar;</mo>
</mover>
<mi>i</mi>
<mo>*</mo>
</msubsup>
<mo>-</mo>
<msub>
<mover>
<mi>&alpha;</mi>
<mo>&OverBar;</mo>
</mover>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mi>K</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mover>
<mi>b</mi>
<mo>&OverBar;</mo>
</mover>
<mo>;</mo>
</mrow>
(D) according to decision function, using n historical data as training set, regression forecasting is carried out on the hyperplane that n+1 is tieed up, is counted
Calculation show that the Passenger flow forecast model in short-term is:
F (x+1)=β1f(x)+β2f(x-1)+...+βnf(x-n+1);
Wherein, K (x, x') is kernel function, xi∈Rn,yi∈ y=R, i=1 ..., n, f (x+1) represent the passenger flow at the x+1 moment
Amount, βiRepresent weight coefficient, i=1,2 ..., n.
3. the real-time passenger flow forecasting of track traffic according to claim 2, it is characterised in that:The RBF is
Gaussian kernel function:
<mrow>
<mi>k</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<mn>2</mn>
<msup>
<mi>&sigma;</mi>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
4. the real-time passenger flow forecasting of track traffic according to claim 1, it is characterised in that:The passenger flow vector Yn+1
Predicted including passenger flow estimation in short-term and peak.
5. the real-time passenger flow forecasting of track traffic according to claim 4, it is characterised in that:The peak prediction includes
Morning peak is predicted and evening peak prediction.
6. the real-time passenger flow forecasting of track traffic according to claim 1, it is characterised in that:The pretreatment includes closing
Key information extraction, data preparation and minute level discrepancy guest flow statistics.
7. the real-time passenger flow forecasting of track traffic according to claim 6, it is characterised in that:The key message is extracted
Key message is used as including parameter in extraction charge time, platform and traffic Card Type 3.
8. the real-time passenger flow forecasting of track traffic according to claim 6, it is characterised in that:The minute level comes in and goes out objective
The statistic frequency of flow is not less than 5 minutes statistics once.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710387638.9A CN107180278A (en) | 2017-05-27 | 2017-05-27 | A kind of real-time passenger flow forecasting of track traffic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710387638.9A CN107180278A (en) | 2017-05-27 | 2017-05-27 | A kind of real-time passenger flow forecasting of track traffic |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107180278A true CN107180278A (en) | 2017-09-19 |
Family
ID=59835094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710387638.9A Pending CN107180278A (en) | 2017-05-27 | 2017-05-27 | A kind of real-time passenger flow forecasting of track traffic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107180278A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109754115A (en) * | 2018-12-04 | 2019-05-14 | 东软集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment of data prediction |
CN109993341A (en) * | 2018-09-29 | 2019-07-09 | 上海电科智能系统股份有限公司 | A kind of passenger flow forecast method based on radial basis function neural network |
CN110119845A (en) * | 2019-05-11 | 2019-08-13 | 北京京投亿雅捷交通科技有限公司 | A kind of application method of track traffic for passenger flow prediction |
CN110134088A (en) * | 2019-05-21 | 2019-08-16 | 浙江大学 | A kind of adaptive quality forecasting procedure based on increment support vector regression |
CN111414719A (en) * | 2020-04-28 | 2020-07-14 | 中南大学 | Method and device for extracting peripheral features of subway station and estimating traffic demand |
CN113781693A (en) * | 2020-06-28 | 2021-12-10 | 朱俊达 | Block chain identity information authentication system based on big data |
CN114091579A (en) * | 2021-11-03 | 2022-02-25 | 深圳技术大学 | Urban rail transit passenger flow early warning system and method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102819768A (en) * | 2011-11-07 | 2012-12-12 | 金蝶软件(中国)有限公司 | Method and system for analyzing passenger flow data |
CN103150609A (en) * | 2013-02-18 | 2013-06-12 | 健雄职业技术学院 | Modeling method for short time traffic flow predicting model |
CN103310287A (en) * | 2013-07-02 | 2013-09-18 | 北京航空航天大学 | Rail transit passenger flow predicting method for predicting passenger travel probability and based on support vector machine (SVM) |
-
2017
- 2017-05-27 CN CN201710387638.9A patent/CN107180278A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102819768A (en) * | 2011-11-07 | 2012-12-12 | 金蝶软件(中国)有限公司 | Method and system for analyzing passenger flow data |
CN103150609A (en) * | 2013-02-18 | 2013-06-12 | 健雄职业技术学院 | Modeling method for short time traffic flow predicting model |
CN103310287A (en) * | 2013-07-02 | 2013-09-18 | 北京航空航天大学 | Rail transit passenger flow predicting method for predicting passenger travel probability and based on support vector machine (SVM) |
Non-Patent Citations (1)
Title |
---|
赵钰棠等: "基于支持向量机的地铁客流量预测", 《都市快轨交通》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109993341A (en) * | 2018-09-29 | 2019-07-09 | 上海电科智能系统股份有限公司 | A kind of passenger flow forecast method based on radial basis function neural network |
CN109754115A (en) * | 2018-12-04 | 2019-05-14 | 东软集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment of data prediction |
CN109754115B (en) * | 2018-12-04 | 2021-03-26 | 东软集团股份有限公司 | Data prediction method and device, storage medium and electronic equipment |
CN110119845A (en) * | 2019-05-11 | 2019-08-13 | 北京京投亿雅捷交通科技有限公司 | A kind of application method of track traffic for passenger flow prediction |
CN110134088A (en) * | 2019-05-21 | 2019-08-16 | 浙江大学 | A kind of adaptive quality forecasting procedure based on increment support vector regression |
CN111414719A (en) * | 2020-04-28 | 2020-07-14 | 中南大学 | Method and device for extracting peripheral features of subway station and estimating traffic demand |
CN113781693A (en) * | 2020-06-28 | 2021-12-10 | 朱俊达 | Block chain identity information authentication system based on big data |
CN113781693B (en) * | 2020-06-28 | 2023-05-23 | 江苏人加信息科技有限公司 | Block chain identity information authentication system based on big data |
CN114091579A (en) * | 2021-11-03 | 2022-02-25 | 深圳技术大学 | Urban rail transit passenger flow early warning system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107180278A (en) | A kind of real-time passenger flow forecasting of track traffic | |
Zhang et al. | Deep learning architecture for short-term passenger flow forecasting in urban rail transit | |
Barhoom et al. | Predicting Titanic Survivors using Artificial Neural Network | |
Wu et al. | Adversarial sparse transformer for time series forecasting | |
Swathi et al. | An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis | |
Sarkar et al. | LSTM response models for direct marketing analytics: Replacing feature engineering with deep learning | |
CN107067076A (en) | A kind of passenger flow forecasting based on time lag NARX neutral nets | |
Bin et al. | Bus arrival time prediction using support vector machines | |
CN103310287A (en) | Rail transit passenger flow predicting method for predicting passenger travel probability and based on support vector machine (SVM) | |
CN106919953A (en) | A kind of abnormal trip Stock discrimination method based on track traffic data analysis | |
CN110458337B (en) | C-GRU-based network appointment vehicle supply and demand prediction method | |
Raza et al. | Hybrid artificial neural network and locally weighted regression models for lane-based short-term urban traffic flow forecasting | |
CN108492561B (en) | Road network traffic state space-time characteristic analysis method based on matrix decomposition | |
CN105469602A (en) | Method for predicting bus passenger waiting time range based on IC card data | |
Shi et al. | Short-term metro passenger flow forecasting using ensemble-chaos support vector regression | |
CN113380043B (en) | Bus arrival time prediction method based on deep neural network calculation | |
Zhang et al. | A hybrid spatiotemporal deep learning model for short-term metro passenger flow prediction | |
Zhang et al. | Short‐Term Passenger Flow Forecast of Rail Transit Station Based on MIC Feature Selection and ST‐LightGBM considering Transfer Passenger Flow | |
Mei et al. | Identifying commuters based on random forest of smartcard data | |
Wang et al. | Deep learning of spatiotemporal patterns for urban mobility prediction using big data | |
CN113706291A (en) | Fraud risk prediction method, device, equipment and storage medium | |
Ruiz-Aguilar et al. | A two-stage procedure for forecasting freight inspections at Border Inspection Posts using SOMs and support vector regression | |
Bao et al. | Forecasting network-wide multi-step metro ridership with an attention-weighted multi-view graph to sequence learning approach | |
Petrović et al. | Controlling highway toll stations using deep learning, queuing theory, and differential evolution | |
Dong et al. | A method for short-term passenger flow prediction in urban rail transit based on deep learning |
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: 20170919 |
|
RJ01 | Rejection of invention patent application after publication |