Estimation of passengers alighting at a bus stop based on smart card data using bayesian networks and neural networks as machine learning.
Project/Area Number |
26820211
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Civil engineering project/Traffic engineering
|
Research Institution | Kyoto University |
Principal Investigator |
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
|
Keywords | スマートカード / 公共交通 / バス / ニューラルネットワーク / ベイジアンネットワーク / 機会学習 / IC card data / Public Transportation / Trip Destination / Bayesian network |
Outline of Final Research Achievements |
Smart card systems are widely introduced as payment (electric fare collection) systems to bus and railway operators. Electronic fare collection data such as smart card records offer new opportunities though. Smart cards have now been available in many cities since several years so that records of public transport usage frequency records over prolonged periods of time can be obtained. The Aim of this research is to utilize such transportation smart cards, to develop a model for estimating OD demand of public transportation using Bayesian network, neural network. Both methods suggested that prediction with a certain precision is guaranteed by doing by number of passengers, but it is possible to grasp the influential factors when using this research result at the time of formulating the traffic plan. It was clarified through interviews with transportation companies that it is beneficial to use BNN.
|
Report
(4 results)
Research Products
(7 results)