CN105206040A - Bus bunching predication method based on IC card data - Google Patents
Bus bunching predication method based on IC card data Download PDFInfo
- Publication number
- CN105206040A CN105206040A CN201510483302.3A CN201510483302A CN105206040A CN 105206040 A CN105206040 A CN 105206040A CN 201510483302 A CN201510483302 A CN 201510483302A CN 105206040 A CN105206040 A CN 105206040A
- Authority
- CN
- China
- Prior art keywords
- bus
- bunching
- train number
- public transport
- website
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a bus bunching prediction method based on IC card data, and belongs to the technical field of public transport information processing. The prediction method comprises the steps of bus IC card data collection, data processing, practical bus bunching state detection, data training and learning and bus bunching prediction, wherein bus bunching prediction uses a least square support vector machine (LS-SVM) algorithm. IC card data of buses is combined, a lot of passenger information is extracted from multiple buses, a vehicle-mounted GPS system is not needed, operation is convenient and rapid, and the data processing cost is reduced; the LS-SVM algorithm can be used to realize bus bunching prediction more rapidly and more effectively, passengers can better understand operation state of buses and regulate travel time reasonably, and a public transport operation department can adjust the departure interval of buses timely and improve the service level of public transport; and data processing is simple, the cost is low, and the prediction precision is higher.
Description
Technical field
The present invention relates to public traffic information processing technology field, specifically a kind of public transport bunching Forecasting Methodology based on IC-card data.
Background technology
In the bus operation process of reality, due to the factor such as the change impact of traffic congestion, website berthing time and number of getting on or off the bus, public transit vehicle arrive at a station and irregular.Particularly peak period, passenger usually had a bus in upper ten minutes such as bus platform or more of a specified duration loseing, and once send a car settle the next not just car of discovery, but some cars arrive simultaneously, and the handling capacity of passengers of vehicle is often uneven.Reduce the service level of public transport, cause safety hazard.
In fact, certain bus is in the delay of certain website, and the time that it may be caused to arrive next website increases, and causes next website ridership and the increase of stand-by period simultaneously, further increases the delay time at stop of this bus.On the other hand, the ridership of the bus carrying of next train number will reduce, and decreases the website delay time at stop simultaneously, shorten the time interval with front truck, this is as snowball effect, and in same route walking afterwards, there is a strong possibility meets at a certain website for these two buses.This phenomenon is public transport bunching phenomenon.Therefore predict that public transport bunching can reduce passenger waiting time, improves the service level of public transport, promote public transport share rate.
In recent years, in the bus station of some big cities (as Nanjing, Zhejiang Hangzhou etc.), occurred the prediction that public transit vehicle is arrived at a station, and the document carrying out predicting for public transport bunching situation is considerably less.But current public transit vehicle arrives at a station, prediction is all in conjunction with vehicle GPS, and is only directed to a car, provides the distance of its distance website and estimates arrival time.Although this can give bus passenger certain reference, but in fact, in peak period, congestion in road situation is serious, causing public transport bunching phenomenon, causing subsequent vehicle prior to front pulling in, the public transport arrival time that dopes and passenger are not inconsistent the actual stand-by period, and vehicle GPS requires large storage space, positioning precision is low, and we need to seek better method and solve the problems referred to above.
Summary of the invention
For the problems referred to above, the invention provides and a kind ofly take into full account each correlative factor that a certain train number arrives downstream website, have real time and dynamic can the public transport bunching high-precision forecasting method based on IC-card data.The present invention is based on Based on Bus IC Card Data, from passenger's angle, predict arrive at a station interval and the public transport bunching of adjacent two cars, public transport operation situation can be understood better, the Reasonable Regulation And Control travel time, improve and line efficiency; Simultaneously for bus operation department, also can adjust bus departure interval in time, avoid public transport bunching situation to occur, better lifting bus service level.
Described a kind of public transport bunching high-precision forecasting method based on IC-card data, extracts train number mark, line identification, site identity, arrival time and the information such as the volume of the flow of passengers of getting on or off the bus to many train numbers of two adjacent sites of same public bus network.First the abnormity point that the train number mark of two websites is not corresponding is rejected, obtain the data that train number mark is completely corresponding consistent, calculate second website and sequentially arrange according to the train number of first website the time headway obtained, by analyzing the positive and negative public transport bunching situation detecting arrival second website reality of time headway.If just, illustrating and bunching is not occurring, on the contrary, if negative, illustrating and there occurs bunching.Then to predict that some train numbers arrive the public transport bunching situation of second website, according to the line identification of said extracted, train number identifies, arrival time and the data such as the volume of the flow of passengers of getting on or off the bus, extract the Small Sample Database of every day in training study, comprise the hourage of two websites, some train numbers are at the time headway of first website, a certain train number and an adjacent upper train number are respectively in the number of getting on or off the bus of the first website, and an adjacent upper train number is in the information such as number of getting on or off the bus of second website, the Small Sample Database of these every day forms a big-sample data, forecast model is set up according to described big-sample data, the public transport bunching situation of second website is arrived in conjunction with a certain train number of least square method supporting vector machine algorithm predicts.
The invention has the advantages that:
1, the present invention is in conjunction with Based on Bus IC Card Data, for many train numbers, extracts a large amount of Customer informations, does not need vehicle GPS, convenient and swift, reduces data processing cost;
2, the present invention adopts least square method supporting vector machine method can realize the prediction of public transport bunching better more quickly and effectively, enables passenger understand public transport operation situation better, the Reasonable Regulation And Control travel time; Make bus operation department also can adjust bus departure interval in time simultaneously, promote bus service level;
3, contemplated by the invention multiple factor such as time headway of the hourage between the number of getting on or off the bus, arrival time, two websites, two adjacent train numbers, process data are simple, and cost is low, and has higher forecasting precision.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of the public transport bunching Forecasting Methodology based on IC-card data of the present invention;
Fig. 2 is the process flow diagram of the public transport bunching Forecasting Methodology based on IC-card data of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail, can implement according to this with reference to instructions word to make those skilled in the art.
The invention provides a kind of public transport bunching Forecasting Methodology based on IC-card data, comprise the following steps:
The first step, bus IC-card data acquisition: by 3G transmission network Real-time Obtaining bus IC-card card using information, set up public transport operation circuit and vehicle operating information database.Described bus IC-card data comprise train number mark, line identification, site identity, arrival time, date and the information such as the volume of the flow of passengers of getting on or off the bus.The public bus network that one bunching easily occurs is obtained from the above-mentioned the whole network IC-card data collected, the basis of this public bus network is looked for adjacent two targeted sites, and the onestep extraction every day of going forward side by side arrives the arrival time of these two targeted sites, number of getting on or off the bus through the bus train number of above-mentioned two targeted sites and each train number.
Because traffic every day differs, so the bus number of times that public transport company provides is not quite similar, according to different vehicle number or train number interval, the train number mark of every day can be extracted.
Second step, data processing: because the bus station number of getting on or off the bus every day has randomness and uneven, and also there is exception in passenger's card using information, need to carry out train number marking matched, two not corresponding data of targeted sites train number mark are rejected as misdata, identify corresponding site identity, arrival time and the information such as the volume of the flow of passengers also corresponding rejecting of getting on or off the bus to train number simultaneously, only retain the data that two targeted sites have identical train number mark.
3rd step, actual public transport bunching situation detects: the public transport bunching situation of bus station is divided into binary condition by the present invention, and what have bunching situation is 1, and what do not have bunching situation is 0.According to second step, when two targeted sites have identical train number mark, second target website sequentially arranges the time headway (i.e. Headway) of the two adjacent train numbers obtained according to the train number of first aim website, actual public transport bunching situation can be obtained, if the time headway of trying to achieve just is, then illustrate there is no bunching situation, be designated as 0; If the time headway of trying to achieve for bearing or being 0, then illustrates and there occurs bunching situation, be designated as 1.
Described first aim site definitions is the website first arrived in two adjacent targeted sites, described second target site definitions be in two adjacent targeted sites after the website that arrives.
The time headway (i.e. Headway) of described two adjacent train numbers is exactly current train number some targeted sites arrival time and adjacent on a train number in the difference of the arrival time of same targeted sites.
4th step, training study data: the real-time current train number of prediction to arrive the public transport bunching situation of second target website, correlative factor just comprises an adjacent upper train number in the arrival time of first aim website and number of getting on or off the bus, in the arrival time of second target website and number of getting on or off the bus, and current train number is in the arrival time of first aim website and number of getting on or off the bus.As the input factor in training study comprise hourage of two targeted sites, the time headway of two adjacent train numbers between first aim website, adjacent on a train number and current train number respectively first aim website number of getting on or off the bus and adjacent on train number in the number of getting on or off the bus of second target website.Factor as output variable only has 1, i.e. public transport bunching situation.First extract the Small Sample Database of every day in the present invention, then form a big-sample data in chronological order, select training set according to the sample data ratio of training set and test set 3:1.
The hourage of two described targeted sites, when train number mark is corresponding, hourage of two targeted sites is exactly current train number in the difference of the arrival time of second target website and the arrival time of first aim website.Because two targeted sites exist station spacing, according to the bus max. speed of national regulation, hourage between two targeted sites be one on the occasion of and be greater than some definite values, so data hourage against regulation will be rejected, simultaneously corresponding train number mark, site identity, arrival time and the information such as the volume of the flow of passengers also corresponding rejecting of getting on or off the bus.
5th step, public transport bunching is predicted: the present invention adopts least square method supporting vector machine algorithm predicts public transport bunching situation, set up forecast model according to the training set chosen in the 4th step to predict the public transport bunching situation that current train number arrives second target website, obtain predicted value.
Described least square method supporting vector machine (LS-SVM) algorithm is a kind of kernel function Learning machine following structural risk minimization, and LS-SVM is applied to the regression algorithm that the prediction of public transport bunching mainly uses it.Utilize adjacent historical data to set up LS-SVM model, after training model, obtain a regression function, bring prediction input vector into regression function, the output valve obtained is data to be predicted.
LS-SVM described in employing is applied to the prediction of public transport bunching, comprises training model and forecast and assesses two processes.
Wherein, in training process, for training sample
ask equation
Solution, in equation, y is 1 dimensional vector, by the output y of training sample
i(i=1 ... l) form;
be 1 dimensional vector, the number of 1 is l; γ is the hyper parameter determined, b and α is the unknown number needing to solve, and b is real number, and α is 1 dimensional vector (being called Lagrange multiplier), and the process solving b and α is exactly modeling process, and Ω is kernel matrix, has the input x of input amendment
icalculated by kernel function and obtain, formula is
Ω
ij＝K(x
i,x
j)，
Radial basis (RBF) function is selected as kernel function, to be expressed as in formula
the center of each radial basis function corresponds to a support vector, and the support vector machine now obtained is radial basis function classifiers;
The key of (1) of solving an equation asks the inverse matrix of A, A=Ω+γ
-1i, after obtaining the inverse matrix of A, both can obtain parameter b is:
Also can obtain parameter alpha is:
After obtaining b and α, training process terminates, and obtains model as follows:
According to the model that formula (3) describes, calculate it to new input X and export f (X), this process is called forecasting process.
In a particular application, the calculated amount of training process is larger, above-mentioned computation process is carried out refinement, obtains following process:
The forming process of kernel matrix:
The formation of kernel matrix mainly calculates the kernel function of different input vector, and kernel function adopts RBF function, and its concrete form is:
Wherein parameter σ is the hyper parameter determined before training, and take K cross validation mode to determine, detailed process is:
Step a, selected σ initial value, σ=0.01;
Step b, is divided into the subset that k part is equal by training set, at every turn will wherein k-1 number according to as training data, and using other a data as test data.Such repetition k time, estimates to expect extensive error according to the MSE mean value obtained after k iteration, finally selects the parameter of one group of optimum, and as kernel function K (x, x
i) parameter σ.
The calculating of RBF function relates to 2 norm calculation of vector and the calculating of exponential function, according to Ω
ij=K (x
i, x
j) definition, for l training sample, Ω
ijfor l × l tie up matrix, namely in l sample any two carry out kernel function calculating and obtain kernel matrix.
Kernel matrix inversion process:
Obtain Ω
ijafter, can matrix A be formed, from Ω
ijcomputation process known, A is symmetric positive definite matrix.If obtain the inverse matrix A of matrix A
-1, then b and α can be obtained according to formula (2).The process of the inverse matrix of matrix A is asked to be the key link of training process.
embodiment
As shown in Figure 1, two adjacent train number bus V1 and V2 are divided into two kinds of situations in the process of same link travel: situation 1: the perfect condition not having public transport bunching: first in 9: 02, and bus V1 and V2 is respectively at the 1st website and the 4th website; In 9: 18, bus V1 and V2 reaches the 5th website and the 8th website respectively; Then in 9: 24, V1 reaches the 7th website, and V2 reaches the 10th website.Two bus V1 and V2 remain the distance about three stations always, and the passengers quantity waited at each website is also substantially relatively average, and situation of not meeting, bunching situation does not occur.
Situation 2: public transport bunching state: first in 9: 02, bus V1 and V2 is respectively at the first website and the 4th website, and the passenger that each website is waited for is substantially average; In 9: 10, V1 arrives the 3rd website, and V2 arrives between the 5th website and the 6th website, and two row bus distances start to further, and V2 travels slow, arrives website more late, and the passengers quantity that website is waited for after the 6th website increases; When 9: 13, V1 arrives the 4th website, and V2 arrives the 6th website at once; Then in 9: 19, V1 arrives the 6th website, and V2 has just rolled the 7th website away from, and two row bus distances closely; Last in 9: 34, V1 and V2 meets at the 10th website, and the passengers quantity that the 11st station is waited in the next stop is very large, there occurs public transport bunching situation.This just illustrates a snowball effect, and a row bus V2 postpones the quantity increasing next stop passenger, too increases the stop delay time, obviously, which increases the delay of bus.On the other hand, the passenger of next column bus V1 will reduce, and decreases the stop delay time, does not postpone.
The evaluation index of prediction is defined as follows:
Public transport bunching is had like this to the classification problem of two classifications, sample is divided into bunching situation, represents with 1, and not bunching situation, represent with 0.Concerning a bunching two points of problems, if sample is bunching 1 and also predicted one-tenth bunching 1, this sample is exactly a correct bunching quantity; Correspondingly, sample is the not predicted one-tenth of bunching 0 not bunching 0, and this sample is exactly a correct not bunching quantity;
Prediction index below, usually for the performance of classification of assessment algorithm:
(1) accuracy rate: calculating be in all sample, correct sample (comprising correct bunching sample and the correct not bunching sample) proportion of prediction.
(2) correct bunching rate: calculating be the ratio that correct bunching sample accounts for all bunching samples.
In the present embodiment, conveniently parameter of the present invention is understood and algorithm embodiment, is specifically described the concrete basic data in six steps.
Based on Bus IC Card Data has XX company of Beijing to provide, and Based on Bus IC Card Data comprises train number mark, line identification, site identity, arrival time and the volume of the flow of passengers of getting on or off the bus, recording mechanism, type of transaction, transaction sequence number, trade date, exchange hour, SAM card number, city number, card issue number, Card Type, line number, vehicle number, bus loading zone, debarkation stop, the information such as driver number and card number.Arrive certain two targeted sites SA, SB for example with XX company XX road, Beijing bus, train number mark, site identity, the arrival time of four months and the volume of the flow of passengers basic data that gets on and off are as table 1 and table 2:
Table 1: XX company XX road, Beijing bus arrives the basic data of first aim website SA
Table 2: XX company XX road, Beijing bus arrives the basic data of second target website SB
Data processing mainly comprises the following steps:
1, abnormity point is removed.
First process data to screen according to a day data, such as extract the basic data of some day, train number mark, arrival time and the volume of the flow of passengers of getting on or off the bus of second website will according to the train number order arrangements of first website, try to achieve the hourage of two websites, according to the station spacing of two websites, and know the bus max. speed of national regulation, can draw hourage be one on the occasion of and be greater than some definite values, so reject undesirable data, comprise train number mark, arrival time and the information such as the volume of the flow of passengers of getting on or off the bus;
Then calculate the time headway of adjacent two train numbers, i.e. Headway, owing to eliminating undesirable data in the first step, so there are some train numbers non-conterminous, that can only calculate a Headway and next Headway;
2, input variable.
The real-time current train number of prediction is wanted to arrive the public transport bunching situation of next targeted sites SB, correlative factor just comprises an adjacent upper train number in the arrival time of website SA and number of getting on or off the bus, next website SB arrival time and to get on or off the bus number, and this train number is in the arrival time of a upper website SA and number of getting on or off the bus.
As input variable because have 8, comprise the hourage of two targeted sites, the time headway of current train number between adjacent two train numbers of first object website, a upper train number and current train number are respectively in the number of getting on or off the bus of first object website, and a upper train number is in the number of getting on or off the bus of the second targeted sites.
3, output variable.
The present invention is based on IC-card data prediction public transport bunching situation, as output variable because have 1, i.e. public transport bunching situation, if this train number next website SB occur bunching, be designated as 1, if not there is bunching, be designated as 0.
Arrive certain two targeted sites SA, SB for example with XX company XX road, Beijing bus, the basic data after process in four months, comprises 8 input variables and 1 output variable, also has the date as shown in table 3 below:
Table 3
The present invention is based on Based on Bus IC Card Data prediction public transport bunching situation, the algorithm adopted is least square method supporting vector machine (LeastSquaresSupportVectorMachines, LS-SVM), the instrument adopted is MATLAB2013b, choose the data of first trimester (20120702-20120930) as training data, the data of latter one month (20121001-20121029) as test data, pass budgets finally draw predict the outcome as shown in table 4 below:
Table 4 predicts the outcome
| Public transport bunching predicts the outcome | Accuracy rate (%) | Correct bunching rate (%) |
| Precision of prediction | 93.77％ | 85.54％ |
The present invention is based on the public transport bunching Forecasting Methodology of IC-card data, precision of prediction is high, rate of accuracy reached 93.77%.This train number of prediction that can be real-time, in the public transport bunching situation of next targeted sites, makes bus passenger understand public transport operation present situation in time, the reasonable arrangement travel time, improves and line efficiency; Simultaneously bus operation department also can predict the outcome by this scheduling bus suitable, the adjustment departure interval, avoids public transport bunching situation to occur, improves service level and the service quality of public transport.
Claims (6)
1., based on a public transport bunching Forecasting Methodology for IC-card data, it is characterized in that: comprise the following steps,
The first step, bus IC-card data acquisition: by 3G transmission network Real-time Obtaining bus IC-card card using information, described bus IC-card data comprise train number mark, line identification, site identity, arrival time, date and volume of the flow of passengers information of getting on or off the bus; The public bus network that one bunching easily occurs is chosen from the above-mentioned IC-card data collected, the basis of this public bus network is looked for adjacent two targeted sites, and the onestep extraction every day of going forward side by side arrives the arrival time of these two targeted sites and number of getting on or off the bus through the bus train number of above-mentioned two targeted sites and each train number;
Second step, data processing: need the coupling doing train number mark, two not corresponding data of targeted sites train number mark are rejected as misdata, identify corresponding site identity, arrival time and volume of the flow of passengers information also corresponding rejecting of getting on or off the bus to train number simultaneously, only retain the data that two targeted sites have identical train number mark;
3rd step, actual public transport bunching situation detects: when two targeted sites have identical train number mark, second target website obtains the time headway of two adjacent train numbers according to the train number order arrangement of first aim website, if the time headway of trying to achieve just is, then illustrate there is no bunching situation, be designated as 0; If the time headway of trying to achieve for bearing or being 0, then illustrates and there occurs bunching situation, be designated as 1;
4th step, training study data: the real-time current train number of prediction to arrive the public transport bunching situation of second target website, correlative factor just comprises an adjacent upper train number in the arrival time of first aim website and number of getting on or off the bus, in the arrival time of second target website and number of getting on or off the bus, and current train number is in the arrival time of first aim website and number of getting on or off the bus; As the input factor in training study comprise the hourage of two targeted sites, the time headway of adjacent two train numbers between first aim website, adjacent on a train number and current train number respectively first aim website number of getting on or off the bus and adjacent on train number in the number of getting on or off the bus of second target website; Factor as output variable only has 1, i.e. public transport bunching situation; First extract the Small Sample Database of every day, then form a big-sample data in chronological order, select training set according to the sample data ratio of training set and test set 3:1;
5th step, public transport bunching is predicted: adopt least square method supporting vector machine algorithm predicts public transport bunching situation, set up forecast model according to the training set chosen in the 4th step to predict the public transport bunching situation that current train number arrives second target website, obtain predicted value.
2. a kind of public transport bunching Forecasting Methodology based on IC-card data according to claim 1, it is characterized in that, first aim site definitions described in 3rd step is the website first arrived in two adjacent targeted sites, described second target site definitions be in two adjacent targeted sites after the website that arrives.
3. a kind of public transport bunching Forecasting Methodology based on IC-card data according to claim 1, it is characterized in that, the time headway of two adjacent train numbers described in the 3rd step is exactly current train number some targeted sites arrival time and adjacent on a train number in the difference of the arrival time of same targeted sites.
4. a kind of public transport bunching Forecasting Methodology based on IC-card data according to claim 1, it is characterized in that, the hourage of two targeted sites described in the 4th step, be exactly when train number mark is corresponding, current train number is in the difference of the arrival time of second target website and the arrival time of first aim website.
5. a kind of public transport bunching Forecasting Methodology based on IC-card data according to claim 1, it is characterized in that, the forecast model described in the 5th step is expressed as
wherein select radial basis function as kernel function, be expressed as
α
ifor the array element of Lagrange multiplier α,
And
Side-play amount
Wherein matrix
kernel matrix Ω=K (x
i, x
j).
6. Radial basis kernel function K (x, x according to claim 5
i) in parameter σ take K cross validation mode to determine, detailed process is:
Step a, selected σ initial value, σ=0.01;
Step b, sets up LS-SVM model;
Step c, is divided into the equal subset of k part by the training set selected, at every turn will wherein k-1 number according to as training data, and using other a data as test data; Such repetition k time, estimates to expect extensive error according to the MSE mean value obtained after k iteration, finally selects the parameter value of one group of optimum, and as kernel function K (x, x
i) parameter σ.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510483302.3A CN105206040B (en) | 2015-08-07 | 2015-08-07 | A kind of public transport bunching Forecasting Methodology based on IC-card data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510483302.3A CN105206040B (en) | 2015-08-07 | 2015-08-07 | A kind of public transport bunching Forecasting Methodology based on IC-card data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105206040A true CN105206040A (en) | 2015-12-30 |
| CN105206040B CN105206040B (en) | 2017-06-23 |
Family
ID=54953682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510483302.3A Active CN105206040B (en) | 2015-08-07 | 2015-08-07 | A kind of public transport bunching Forecasting Methodology based on IC-card data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105206040B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327867A (en) * | 2016-08-30 | 2017-01-11 | 北京航空航天大学 | Bus punctuality prediction method based on GPS data |
| CN106448139A (en) * | 2016-11-18 | 2017-02-22 | 山东浪潮云服务信息科技有限公司 | Intelligent bus scheduling method and intelligent bus scheduling device |
| CN107220724A (en) * | 2017-04-21 | 2017-09-29 | 北京航空航天大学 | Passenger flow forecast method and device |
| CN111341096A (en) * | 2020-02-06 | 2020-06-26 | 长安大学 | Bus running state evaluation method based on GPS data |
| CN112269930A (en) * | 2020-10-26 | 2021-01-26 | 北京百度网讯科技有限公司 | Method and device for establishing regional heat prediction model and regional heat prediction |
| CN112347596A (en) * | 2020-11-05 | 2021-02-09 | 浙江非线数联科技有限公司 | Urban public transport network optimization method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7394404B2 (en) * | 2004-09-17 | 2008-07-01 | Jae-ho Kim | System and method for controlling public transportation |
| CN101615340A (en) * | 2009-07-24 | 2009-12-30 | 北京工业大学 | Real-time information processing method in the bus dynamic dispatching |
| CN102063791A (en) * | 2010-12-17 | 2011-05-18 | 北京公共交通控股（集团）有限公司 | Public transport travelling control method by combining signal control with positioning monitoring |
| CN102737503A (en) * | 2012-06-20 | 2012-10-17 | 东南大学 | Communication connectivity analysis method for bus dynamic scheduling under internet of vehicles environment |
| CN102737500A (en) * | 2012-06-05 | 2012-10-17 | 东南大学 | Method for acquiring arrival interval reliability of urban bus |
| WO2014108265A1 (en) * | 2013-01-11 | 2014-07-17 | Here Global B.V. | Real-time vehicle spacing control |
| CN104408908A (en) * | 2014-11-05 | 2015-03-11 | 东南大学 | Public transportation vehicle station-skipping scheduling method and system |
-
2015
- 2015-08-07 CN CN201510483302.3A patent/CN105206040B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7394404B2 (en) * | 2004-09-17 | 2008-07-01 | Jae-ho Kim | System and method for controlling public transportation |
| CN101615340A (en) * | 2009-07-24 | 2009-12-30 | 北京工业大学 | Real-time information processing method in the bus dynamic dispatching |
| CN102063791A (en) * | 2010-12-17 | 2011-05-18 | 北京公共交通控股（集团）有限公司 | Public transport travelling control method by combining signal control with positioning monitoring |
| CN102737500A (en) * | 2012-06-05 | 2012-10-17 | 东南大学 | Method for acquiring arrival interval reliability of urban bus |
| CN102737503A (en) * | 2012-06-20 | 2012-10-17 | 东南大学 | Communication connectivity analysis method for bus dynamic scheduling under internet of vehicles environment |
| WO2014108265A1 (en) * | 2013-01-11 | 2014-07-17 | Here Global B.V. | Real-time vehicle spacing control |
| CN104408908A (en) * | 2014-11-05 | 2015-03-11 | 东南大学 | Public transportation vehicle station-skipping scheduling method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327867A (en) * | 2016-08-30 | 2017-01-11 | 北京航空航天大学 | Bus punctuality prediction method based on GPS data |
| CN106327867B (en) * | 2016-08-30 | 2020-02-11 | 北京航空航天大学 | Bus punctuation prediction method based on GPS data |
| CN106448139A (en) * | 2016-11-18 | 2017-02-22 | 山东浪潮云服务信息科技有限公司 | Intelligent bus scheduling method and intelligent bus scheduling device |
| CN106448139B (en) * | 2016-11-18 | 2018-10-26 | 山东浪潮云服务信息科技有限公司 | A kind of intelligent public transportation dispatching method and apparatus |
| CN107220724A (en) * | 2017-04-21 | 2017-09-29 | 北京航空航天大学 | Passenger flow forecast method and device |
| CN107220724B (en) * | 2017-04-21 | 2020-12-08 | 北京航空航天大学 | Passenger flow volume prediction method and device |
| CN111341096A (en) * | 2020-02-06 | 2020-06-26 | 长安大学 | Bus running state evaluation method based on GPS data |
| CN111341096B (en) * | 2020-02-06 | 2020-12-18 | 长安大学 | Bus running state evaluation method based on GPS data |
| CN112269930A (en) * | 2020-10-26 | 2021-01-26 | 北京百度网讯科技有限公司 | Method and device for establishing regional heat prediction model and regional heat prediction |
| CN112269930B (en) * | 2020-10-26 | 2023-10-24 | 北京百度网讯科技有限公司 | Regional heat prediction model and regional heat prediction method and device |
| CN112347596A (en) * | 2020-11-05 | 2021-02-09 | 浙江非线数联科技有限公司 | Urban public transport network optimization method |
| CN112347596B (en) * | 2020-11-05 | 2021-08-13 | 浙江非线数联科技股份有限公司 | Urban public transport network optimization method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105206040B (en) | 2017-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105206040A (en) | Bus bunching predication method based on IC card data | |
| CN104064028B (en) | Based on public transport arrival time Forecasting Methodology and the system of multiple information data | |
| CN103310287B (en) | Predict that passenger goes on a journey the track traffic for passenger flow Forecasting Methodology of probability based on SVM | |
| CN106781468B (en) | Link Travel Time Estimation method based on built environment and low frequency floating car data | |
| CN105469602A (en) | Method for predicting bus passenger waiting time range based on IC card data | |
| CN104318757B (en) | Bus bus or train route section Forecasting Methodology working time on a kind of public transportation lane | |
| CN105868865A (en) | Electric vehicle parc prediction method based on multivariate linear regression method and proportional substitution method | |
| CN105243868B (en) | A kind of public transit vehicle arrival time Forecasting Methodology and device | |
| CN105868861A (en) | Bus passenger flow evolution analysis method based on time-space data fusion | |
| Ram et al. | SMARTBUS: A web application for smart urban mobility and transportation | |
| CN105354638A (en) | Prediction method and system for repair and maintenance costs of automobile | |
| CN105678036A (en) | Measurement and calculation method and system of stopping time of bus at bus stop | |
| CN103606272B (en) | A kind of bus rapid transit arrival time Forecasting Methodology based on the volume of the flow of passengers | |
| CN104298832A (en) | Road network traffic flow analytical method based on RFID technology | |
| CN106898142A (en) | A kind of path forms time reliability degree calculation method of consideration section correlation | |
| CN103854475A (en) | Novel urban public transportation system improvement method | |
| CN114912689B (en) | Overrun vehicle destination prediction method and system based on map grid index and XGBOOST | |
| CN106251628A (en) | A kind of method and device of the traffic trip amount determining motor vehicles | |
| CN105046958A (en) | Highway traffic information acquisition node nonequidistance optimized layout method | |
| Bhuiyan et al. | Investigating the impact of access-timing-sizing regulations on urban logistics | |
| CN105608315A (en) | Quantitative evaluation method and system of safety service level of bus stop | |
| CN112836996B (en) | Method for identifying potential ticket buying demand of passenger | |
| CN111489552B (en) | Method, device, equipment and storage medium for predicting headway | |
| CN101866549A (en) | Micro indicator and evaluation method of regional transportation service level | |
| CN103700264A (en) | Computation method of expressway section travel speed based on ETC (Electronic Toll Collection) data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |