CN104916134A - Regional highway main channel traffic demand forecasting method based on multiple-factor regression - Google Patents
Regional highway main channel traffic demand forecasting method based on multiple-factor regression Download PDFInfo
- Publication number
- CN104916134A CN104916134A CN201510313078.3A CN201510313078A CN104916134A CN 104916134 A CN104916134 A CN 104916134A CN 201510313078 A CN201510313078 A CN 201510313078A CN 104916134 A CN104916134 A CN 104916134A
- Authority
- CN
- China
- Prior art keywords
- main channel
- path
- factor
- represent
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a regional highway main channel traffic demand forecasting method based on multiple-factor regression. The method comprises the following steps: determining influencing factors of regional highway main channel traffic demand forecasting; determining at least one selectable path which is same with the starting point and end point of a main channel path; constructing a multiple-factor regression model according to the determined influencing factors and the selectable path; and forecasting the traffic demand y1 of the main channel by adopting the established regression model. The method improves an existing regional highway main channel traffic demand forecasting method which carries out regression forecasting only on a single path without considering the influence of other adjacent paths, the trends of which are roughly same with the trend of the path; the traffic demand forecasting of some path in the channel is carried out by utilizing the multiple-factor united regression; and the method improves existing demand forecasting precision and can provide more accurate demand forecasting result for the follow-up jobs in engineering practice.
Description
Technical field
The invention belongs to demand forecast technical field, relate in Regional Road main channel the impact of other adjacent path moving towards roughly the same with predicted path, is one high-precision Regional Road main channel Forecast of Traffic Demand.
Background technology
To when transport need is predicted in regional traffic main channel, usually adopt unidirectional prediction respectively or the four-stage predict method based on OD survey data.Unidirectional prognosis traffic volume is respectively by after on the road intending project study, the basic traffic capacity in distant view time, diverted traffic and induced traffic carry out quantitative forecast respectively, gather the prospect traffic volume predicted value obtaining this circuit, during unidirectional prediction respectively, do not consider influencing each other of mulitpath in main channel.Four-stage predict method is a kind of Forecasting Methodology grown up in the process of research Urban Traffic Planning, it is widely applied in Urban Traffic Planning, but urban transportation and the traffic of regional traffic main channel exist very large different: the traffic flow of urban transportation flows to complexity, have diversity, the traffic flow in passage has very strong directivity; Circuit in Traffic Systems from O to D has a lot, and traveler has right to choose relatively freely, and the circuit in passage from O to D is generally fixing, selects limited.Therefore be not suitable for adopting Four-stage Method prediction channel traffic demand.
At present in existing research, after taking into full account the influence factor of transport need, a part studies the correlativity for transport need and the influence factor such as social activities, economic development, according to the transport need total amount of related coefficient prediction passage, and then feasible path is adopted to attract power apportion design to obtain the magnitude of traffic flow of feasible path; Another part research, by the emulative analysis in path each in passage, establishes betting model and model of fuzzy synthetic evaluation, but these algorithm operatings are complicated and subjective factor is larger.In view of at present when carrying out the linear regression forecasting of certain paths transport need in Regional Road main channel, usually only launch to analyze separately for this paths, and directly consider to move towards that other roughly the same paths produce this path affects this present situation, the present invention proposes a kind of Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor.
Summary of the invention
The technical problem to be solved in the present invention is: for when in Regional Road main channel, certain paths carries out demand forecast, consider to move towards with it the impact of roughly the same adjacent path, carry out the prediction of multivariate response joint regression, but at present also not based on the Forecast of Traffic Demand that multiple-factor returns.
Technical scheme of the present invention is:
Based on the Regional Road main channel Forecast of Traffic Demand that multiple-factor returns, it is characterized in that, comprise the following steps:
1) influence factor of Regional Road main channel Traffic Demand Forecasting is determined;
2) at least one feasible path identical with terminal with path, main channel starting point is determined;
3) according to step 1) influence factor determined and step 2) feasible path determined, build multiple-factor regression model:
Y=XB+ε+θ (1)
Wherein Y=(y
1, y
2..., y
n)
trepresent the link traffic flow in path, T is transposition, y
1represent the link traffic flow of predicted path, y
2~ y
nrepresent the link traffic flow of (n-1) bar feasible path, y
irepresent the link traffic flow of the i-th paths; X=(1, x
1, x
2..., x
j..., x
m) influence factor for determining, x
jrepresent a jth influence factor, total m influence factor;
Represent the unknown parameter of corresponding each influence factor, b
jirepresent that a jth influence factor is to the regression coefficient of the i-th paths; ε=(ε
1, ε
2..., ε
i..., ε
n) ' represent error term, ε
irepresent the stochastic variable that the i-th paths is returned, and Normal Distribution N (0, σ
2); θ=(θ)
n × 1, θ represents affects y
1with y
2~ y
nbetween other known variables of correlativity, different values may be got with regional change, and
4) step 3 is adopted) the transport need y of forecast of regression model main channel that sets up
1.
Described step 4) predict that main channel transport need adopts Markov Monte Carlo simulation method to carry out program calculation.
Described influence factor comprises: traffic flow of section, region, region permanent resident population's total amount, region GDP total value, category of roads, track quantity and section are apart from intown distance.
Wherein traffic flow of section is the annual average daily traffic of selected section between every two gateways on path; Region is the city at investigation section place; Region permanent resident population's total amount is the statistical value at per end of the year; Region GDP total value is the annual annual GDP total value in city, section place; Number of track-lines is the unidirectional number of track-lines of investigation section; Section adopts investigation section apart from the air line distance at administrative region of a city center, city apart from intown distance.
Step 2) described in feasible path be path more than 80% the region of process identical or adjacent through region with predicted path institute.
The invention provides a kind of Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor, by the analysis to channel traffic influencing factors for demand, and find in passage and move towards at least one roughly the same feasible path, build influence factor to the multiple-factor multiple linear regression equations of feasible path, Markov Monte Carlo simulation method is adopted to carry out model parameter demarcation by historical data, when adopting calibrated multiple-factor regression model to carry out Regional Road main channel Traffic Demand Forecasting, precision of prediction can be improved.Originality of the present invention is when in passage, certain paths carries out demand forecast, the prediction of multiple-factor joint regression is carried out in the impact directly considering the adjacent path moving towards with it roughly the same, by with predicted path is carried out to predicting the outcome of independent multiple linear regression and carries out contrasting the improvement value that can obtain precision of prediction, it is more that feasible path is chosen, and main channel Traffic Demand Forecasting is then more accurate.
The present invention proposes high-precision Regional Road main channel Forecast of Traffic Demand from the angle that multiple-factor returns, and the computation process of the method is simple, can obtain the transport need of predicted path in Regional Road main channel in engineering practice fast.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the inventive method.
Fig. 2 is path schematic diagram selected by the example of the inventive method.
Fig. 3 is multiple-factor regression forecasting result figure in the example of the inventive method.
Fig. 4 is independent regression forecasting result figure in the example of the inventive method.
Embodiment
Below in conjunction with accompanying drawing and example, the embodiment to the inventive method is further described.
Be illustrated in figure 1 the overview flow chart of the Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor, the concrete steps below in conjunction with Fig. 1 and the inventive method carry out detailed exemplary application introduction:
1) influence factor of Regional Road main channel Traffic Demand Forecasting is determined, comprise region, region permanent resident population's total amount, region GDP total value, category of roads, track quantity and section apart from intown distance, and other known variables that can have an impact to Regional Road main channel Traffic Demand Forecasting;
This example is Beijing-Harbin Traffic Demand Forecasting at a high speed in regional traffic main channel, Shenyang to the Shanhai Pass, consider the feature of passage in this example itself, carry out that regretional analysis chooses because have: region, region permanent resident population's total amount, region GDP total value, category of roads, track quantity and section are apart from intown distance totally six.
2) roughly the same adjacent path is moved towards with predicted path in searching main channel;
In this example, Beijing-Harbin high speed Shen Shan section has 380km, is followed successively by Shenyang, Anshan, Panjin, Jinzhou and Huludao City in the Shanhai Pass to terminal from starting point Shenyang through region; The total 434km of national highway Beijing-Harbin line (G102) in passage, from starting point Shenyang, the Shanhai Pass is followed successively by Shenyang, Jinzhou, Huludao City through region to terminal, is satisfied with the condition that predicted path moves towards roughly the same.Move towards roughly the same path in this example in Shen Shan passage with Beijing-Harbin high speed Shen Shan section and have national highway Beijing-Harbin line (G102), move towards figure as shown in Figure 2.
3) obtain the historical data of these path Correlative Influence Factors and traffic flow of section, wherein traffic flow of section is the annual average daily traffic (pcu/d) of selected section between every two large-scale gateways on path; Region is sorting parameter, the city at representative investigation section place; Region permanent resident population's total amount is the statistical value (ten thousand people) at per end of the year; Region GDP total value is the annual annual GDP total value (ten thousand yuan) in city, section place; Category of roads is sorting parameter; Number of track-lines is the unidirectional number of track-lines of investigation section; Section adopts investigation section apart from the air line distance (km) at administrative region of a city center, city apart from intown distance;
The G1 highway that have chosen 2006 ~ 2013 in this example is in the annual average daily traffic (referring to table 1) of 22 measuring frequency sections and the G102 national highway of 2002 ~ 2013 the average daily traffic volume data (referring to table 2) at 16 measuring frequency sections, correspondence obtains year permanent resident population total amount (referring to table 3) and the year GDP total value (referring to table 4) of selected time measuring frequency section region, obtain simultaneously measuring frequency section unidirectional number of track-lines and apart from intown distance, in table 1 and table 2.Category of roads adopts classified variable, and highway gets 0, and Class I highway gets 1, and Class II highway gets 2.
Table 1 2006 ~ 2013 G1 highways are at the annual average daily traffic (pcu/d) of 22 measuring frequency sections
Table 2 2002 ~ 2013 G102 national highways are in the average daily traffic volume data (pcu/d) of 16 measuring frequency sections
The each region of table 3 permanent resident population's total amount over the years (unit: ten thousand people)
Time | Shenyang | Anshan | Panjin | Jinzhou | Huludao City | Yingkou | Dalian |
2002 | 689 | 283 | 123 | 307 | 270 | 191 | 531 |
2003 | 689 | 283 | 124 | 307 | 271 | 201 | 533 |
2004 | 691 | 346 | 127 | 313 | 272 | 207 | 539 |
2005 | 696 | 347 | 128 | 308 | 273 | 220 | 551 |
2006 | 701 | 348 | 130 | 309 | 281 | 225 | 560 |
2007 | 707 | 351 | 128 | 309 | 281 | 228 | 566 |
2008 | 712 | 351 | 132 | 310 | 282 | 228 | 580 |
2009 | 717 | 351 | 130 | 307 | 281 | 230 | 583 |
2010 | 825 | 351 | 130 | 310 | 281 | 234 | 586 |
2011 | 827 | 351 | 131 | 312 | 282 | 235 | 589 |
2012 | 829 | 351 | 132 | 313 | 282 | 235 | 590 |
2013 | 727 | 350 | 129 | 306 | 280 | 233 | 591 |
The each region of table 4 GDP total value over the years (unit: hundred million yuan)
Time | Shenyang | Anshan | Panjin | Jinzhou | Huludao City | Yingkou | Dalian |
2002 | 1400.0 | 572.0 | 302.0 | 242.9 | 197.8 | 217.6 | 1406.1 |
2003 | 1602.0 | 648.0 | 330.8 | 281.7 | 225.5 | 253.4 | 1632.6 |
2004 | 1900.7 | 849.0 | 369.4 | 343.1 | 262.0 | 318.3 | 1961.8 |
2005 | 2084.1 | 1018.0 | 441.3 | 381.9 | 299.5 | 380.9 | 2152.2 |
2006 | 2519.6 | 1136.0 | 509.2 | 460.2 | 335.4 | 457.7 | 2569.7 |
2007 | 3221.1 | 1350.0 | 562.9 | 551.1 | 379.4 | 570.1 | 3130.7 |
2008 | 3860.5 | 1608.0 | 675.0 | 690.4 | 414.6 | 703.6 | 3858.2 |
2009 | 4268.5 | 1730.5 | 685.3 | 790.1 | 445.6 | 799.5 | 4417.7 |
2010 | 5107.5 | 2125.0 | 926.5 | 912.6 | 531.5 | 1002.4 | 5158.1 |
2011 | 5914.9 | 2398.8 | 1119.9 | 1115.9 | 650.1 | 1222.5 | 6150.1 |
2012 | 6606.8 | 2429.3 | 1245.0 | 1248.5 | 719.3 | 1381.2 | 7002.8 |
2013 | 7158.6 | 2623.3 | 1400.0 | 1344.9 | 784.0 | 1513.1 | 7650.8 |
4) according to step 1) influence factor determined and step 2) the optional adjacent path determined, build multiple-factor regression model, as shown in the formula:
Y=XB+ε+θ (1)
Wherein Y=(y
1, y
2..., y
n)
trepresent the link traffic flow in path, y
1represent the link traffic flow of predicted path, y
2~ y
nrepresent the link traffic flow moving towards roughly the same (n-1) paths with predicted path, y
irepresent the link traffic flow of the i-th paths; X=(1, x
1, x
2..., x
j..., x
m) represent influence factor, x
jrepresent a jth influence factor, total m influence factor;
Represent the unknown parameter of corresponding each influence factor, b
jirepresent that a jth influence factor is to the regression coefficient of the i-th paths; ε=(ε
1, ε
2..., ε
i..., ε
n) ' represent error term, ε
irepresent the stochastic variable that the i-th paths is returned, and Normal Distribution N (0, σ
2); θ=(θ)
n × 1, θ represents affects y
1with y
2~ y
nbetween other of correlativity are unknown becomes 2), wherein σ and σ
θvalue be 0 ~ 1000000;
In the present embodiment, step 2) feasible path determined is 1, step 2) the optional influence factor determined is 5, the multiple-factor regression model of structure is:
Wherein y
1represent the section annual average daily traffic of G1; y
2represent the section annual average daily traffic of G102; x
1~ x
5represent measuring frequency section category of roads, number of track-lines, region permanent resident population sum, region GDP total value respectively, apart from intown distance; b
10~ b
15, b
20~ b
25for undetermined coefficient; ε
1, ε
2for stochastic error and ε
1, 2), ε
1with ε
2not separate; θ represents affects y
1with y
2between other known variables of correlativity, with district 2), in the present embodiment, σ and σ
θvalue be 1000000.
5) utilize step 3) in the data that obtain to step 4) in model carry out parameter calibration, adopt Markov Monte Carlo simulation method to carry out program calculation.
According to the measured data over the years of this example, respectively by the volume of traffic of two paths and category of roads, number of track-lines, region permanent resident population sum, region GDP total value with carry out returning factor linear apart from intown distance, return result of calculation in table 1, level of significance gets 0.05.Can obtain the Regional Road main channel Traffic Demand Forecasting regression equation returned based on multiple-factor in this example is:
Table 1 multiple-factor equation of linear regression parameter estimation result
coefficients | mean | variance | 2.50% | median | 97.50% |
b 10 | 1819 | 978 | -88.55 | 1810 | 3685 |
b 20 | -1657 | 965.7 | -3631 | -1627 | 187.3 |
b 11 | 1757 | 970.3 | -150.9 | 1727 | 3741 |
b 21 | 6.195 | 1003 | -1930 | -2.237 | 1986 |
b 12 | 10230 | 465.1 | 9273 | 10240 | 11080 |
b 13 | -107.4 | 22.85 | -139.3 | -113.6 | -56.55 |
b 23 | -41.92 | 20.59 | -74.45 | -46.26 | 0.2759 |
b 14 | 6.202 | 0.9095 | 4.314 | 6.245 | 7.817 |
b 24 | 6.129 | 0.8559 | 4.548 | 6.093 | 7.929 |
b 15 | -27.69 | 23.48 | -71.77 | -27.96 | 18.71 |
b 25 | -51.26 | 15.21 | -82.03 | -51.29 | -21.14 |
correlation | 0.8628 | 0.1099 | 0.5644 | 0.8967 | 0.9822 |
2 | 5.64E+07 | 4.23E+06 | 4.87E+07 | 5.62E+07 | 6.51E+07 |
2 | 7.63E+08 | 1.24E+09 | 7.51E+07 | 4.88E+08 | 3.06E+09 |
The present invention can carry out precision of prediction contrast by carrying out independent multiple linear regression to predicted path, wherein identical all with multiple-factor regression model of influence factor and each parameter value of predicted path.
Carry out independent multiple linear regression to two paths in this example below, regression equation is as follows:
y
1=b
10+b
11x
1+b
12x
2+b
13x
3+b
14x
4+b
15x
5+ε
1(3)
y
2=b
20+b
21x
1+b
22x
2+b
23x
3+b
24x
4+b
25x
5+ε
2(4)
Wherein ε
1with ε
2separate, all the other parameter meanings are the same.
Adopt parameter estimation result that identical data and parameter calibration method obtain in table 2.The regression equation obtained is:
y
1=1544+1594x
1+9354x
2-0.2246x
3-3.201x
4-48.37x
5
y
2=1135+12.87x
1+18.95x
3+1.655x
4-4.892x
5
Table 2 is multiple linear regression equations parameter estimation result separately
coefficients | mean | variance | 2.50% | median | 97.50% |
b 10 | 1544 | 994.6 | -389.2 | 1559 | 3460 |
b 20 | 1135 | 941.5 | -672.5 | 1142 | 2970 |
b 11 | 1594 | 989.7 | -326.8 | 1587 | 3526 |
b 21 | 12.87 | 994.7 | -1934 | -13.28 | 1977 |
b 12 | 9354 | 388.7 | 8576 | 9352 | 10120 |
b 13 | -0.2246 | 8.094 | -16.21 | 0.1211 | 14.8 |
b 23 | 18.95 | 5.603 | 7.953 | 18.83 | 30 |
b 14 | -3.201 | 0.9354 | -4.965 | -3.24 | -1.368 |
b 24 | 1.655 | 0.8918 | -0.1064 | 1.659 | 3.355 |
b 15 | -48.37 | 27.96 | -104.2 | -48.24 | 4.998 |
b 25 | -4.892 | 17.79 | -41.11 | -4.88 | 29.53 |
Utilize the multiple-factor equation of linear regression calculated in table 1 to carry out Traffic Demand Forecasting, predicted value and actual value are analyzed, result as shown in Figure 3; Utilize the independent multiple linear regression equations calculated in table 2 to carry out Traffic Demand Forecasting, predicted value and actual value are analyzed, result as shown in Figure 4.Can find out: joint regression equation predict the outcome and related coefficient between measured value square be R
2=0.9095, be comparatively close to 1, and separately multiple regression equation predict the outcome and related coefficient between measured value square be R
2=0.8368, prediction effect is relatively poor.This example uses the inventive method to carry out multiple-factor and returns Traffic Demand Forecasting, and precision of prediction is improve 5.7%.
Claims (5)
1., based on the Regional Road main channel Forecast of Traffic Demand that multiple-factor returns, it is characterized in that, comprise the following steps:
1) influence factor of Regional Road main channel Traffic Demand Forecasting is determined;
2) at least one feasible path identical with terminal with path, main channel starting point is determined;
3) according to step 1) influence factor determined and step 2) feasible path determined, build multiple-factor regression model:
Y=XB+ε+θ (1)
Wherein Y=(y
1, y
2..., y
n)
trepresent the link traffic flow in path, T is transposition, y
1represent the link traffic flow of predicted path, y
2~ y
nrepresent the link traffic flow of (n-1) bar feasible path, y
irepresent the link traffic flow of the i-th paths; X=(1, x
1, x
2..., x
j..., x
m) influence factor for determining, x
jrepresent a jth influence factor, total m influence factor;
Represent the unknown parameter of corresponding each influence factor, b
jirepresent that a jth influence factor is to the regression coefficient of the i-th paths; ε=(ε
1, ε
2..., ε
i..., ε
n) ' represent error term, ε
irepresent the stochastic variable that the i-th paths is returned, and Normal Distribution N (0, σ
2); θ=(θ)
n × 1, θ represents affects y
1with y
2~ y
nbetween other known variables of correlativity, different values may be got with regional change, and
4) step 3 is adopted) the transport need y of forecast of regression model main channel that sets up
1.
2. the Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor according to claim 1, is characterized in that: described step 4) predict that main channel transport need adopts Markov Monte Carlo simulation method to carry out program calculation.
3. the Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor according to claim 1, is characterized in that: described influence factor comprises: traffic flow of section, region, region permanent resident population's total amount, region GDP total value, category of roads, track quantity and section are apart from intown distance.
4. the Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor according to claim 3, is characterized in that: wherein traffic flow of section is the annual average daily traffic of selected section between every two gateways on path; Region is the city at investigation section place; Region permanent resident population's total amount is the statistical value at per end of the year; Region GDP total value is the annual annual GDP total value in city, section place; Number of track-lines is the unidirectional number of track-lines of investigation section; Section adopts investigation section apart from the air line distance at administrative region of a city center, city apart from intown distance.
5. the Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor according to claim 1, is characterized in that: step 2) described in feasible path be path more than 80% process region and predicted path identical or adjacent through region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510313078.3A CN104916134B (en) | 2015-06-09 | 2015-06-09 | A kind of Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510313078.3A CN104916134B (en) | 2015-06-09 | 2015-06-09 | A kind of Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104916134A true CN104916134A (en) | 2015-09-16 |
CN104916134B CN104916134B (en) | 2016-04-13 |
Family
ID=54085168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510313078.3A Active CN104916134B (en) | 2015-06-09 | 2015-06-09 | A kind of Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104916134B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409573A (en) * | 2018-09-26 | 2019-03-01 | 北京交通大学 | Roadside assistance needing forecasting method based on linear regression model (LRM) |
CN109543872A (en) * | 2018-09-19 | 2019-03-29 | 北京科技大学 | Multirobot is without parking maneuver method and system |
JP2020035091A (en) * | 2018-08-28 | 2020-03-05 | 株式会社Nttドコモ | Traffic situation prediction device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101127040A (en) * | 2007-09-14 | 2008-02-20 | 东南大学 | Highway origin-destination traffic flow character extraction method |
CN101436345A (en) * | 2008-12-19 | 2009-05-20 | 天津市市政工程设计研究院 | System for forecasting harbor district road traffic requirement based on TransCAD macroscopic artificial platform |
US20140309977A1 (en) * | 2013-04-16 | 2014-10-16 | International Business Machines Corporation | Performing-time-series based predictions with projection thresholds using secondary time-series-based information stream |
KR101473103B1 (en) * | 2013-05-29 | 2014-12-15 | 서울시립대학교 산학협력단 | traffic demand forecast system based on agents |
-
2015
- 2015-06-09 CN CN201510313078.3A patent/CN104916134B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101127040A (en) * | 2007-09-14 | 2008-02-20 | 东南大学 | Highway origin-destination traffic flow character extraction method |
CN101436345A (en) * | 2008-12-19 | 2009-05-20 | 天津市市政工程设计研究院 | System for forecasting harbor district road traffic requirement based on TransCAD macroscopic artificial platform |
US20140309977A1 (en) * | 2013-04-16 | 2014-10-16 | International Business Machines Corporation | Performing-time-series based predictions with projection thresholds using secondary time-series-based information stream |
KR101473103B1 (en) * | 2013-05-29 | 2014-12-15 | 서울시립대학교 산학협력단 | traffic demand forecast system based on agents |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020035091A (en) * | 2018-08-28 | 2020-03-05 | 株式会社Nttドコモ | Traffic situation prediction device |
JP7033515B2 (en) | 2018-08-28 | 2022-03-10 | 株式会社Nttドコモ | Traffic condition prediction device |
CN109543872A (en) * | 2018-09-19 | 2019-03-29 | 北京科技大学 | Multirobot is without parking maneuver method and system |
CN109543872B (en) * | 2018-09-19 | 2021-08-31 | 北京科技大学 | Multi-robot parking-free scheduling method and system |
CN109409573A (en) * | 2018-09-26 | 2019-03-01 | 北京交通大学 | Roadside assistance needing forecasting method based on linear regression model (LRM) |
CN109409573B (en) * | 2018-09-26 | 2022-04-12 | 北京交通大学 | Road rescue demand prediction method based on linear regression model |
Also Published As
Publication number | Publication date |
---|---|
CN104916134B (en) | 2016-04-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111653088B (en) | Vehicle driving quantity prediction model construction method, prediction method and system | |
Yang et al. | Origin‐destination estimation using probe vehicle trajectory and link counts | |
Deng et al. | Traffic state estimation and uncertainty quantification based on heterogeneous data sources: A three detector approach | |
Willems | A spatial rainfall generator for small spatial scales | |
CN105513359B (en) | A kind of urban expressway traffic method for estimating state based on smart mobile phone movement detection | |
CN108564790A (en) | A kind of urban short-term traffic flow prediction technique based on traffic flow space-time similitude | |
CN102693633A (en) | Short-term traffic flow weighted combination prediction method | |
CN102521989B (en) | Dynamic-data-driven highway-exit flow-quantity predicting method | |
CN105741549B (en) | A kind of traffic flow forecasting method theoretical based on space copula | |
CN107103392A (en) | A kind of identification of bus passenger flow influence factor and Forecasting Methodology based on space-time Geographical Weighted Regression | |
CN108009972A (en) | A kind of multimode trip O-D needs estimate methods checked based on multi-source data | |
CN104574967A (en) | City large-area road network traffic sensing method based on plough satellite | |
CN106488405A (en) | A kind of position predicting method merging individuality and neighbour's movement law | |
CN107705558A (en) | A kind of Bayes OD matrix estimation methods of more data types | |
KR20150072471A (en) | Traffic flow prediction system using spatiotemporal stochastic model | |
CN109272169A (en) | Traffic flow forecasting method, device, computer equipment and storage medium | |
CN103870890A (en) | Prediction method for traffic flow distribution of expressway network | |
CN104916134B (en) | A kind of Regional Road main channel Forecast of Traffic Demand returned based on multiple-factor | |
CN103093643A (en) | Public parking lot berth quantity confirming method | |
Dantsuji et al. | A novel metamodel-based framework for large-scale dynamic origin–destination demand calibration | |
CN105389631A (en) | Transportation accessibility analysis method for area with multiple cross-sea channels | |
CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
Niu et al. | Road extraction using smart phones GPS | |
Susilawati et al. | Modelling urban travel time variability with the Burr regression technique | |
CN109741597A (en) | A kind of bus section runing time prediction technique based on improvement depth forest |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address |
Address after: 110166 No. 42 Li Dao Road, Heping District, Liaoning, Shenyang Co-patentee after: Nanjing Quan Sida transport science and techonologies company limited Patentee after: Liaoning communication planning and Design Institute Co., Ltd. Address before: 110166 No. 42-2 Li Dao Road, Heping District, Liaoning, Shenyang Co-patentee before: Nanjing Quan Sida transport science and techonologies company limited Patentee before: Liaoning Provincial Communication Planning & Design Institute |
|
CP03 | Change of name, title or address |