ARMA-GRNN for passenger demand forecasting

Author

Gong, Weiwei

Author_Institution

Transp. & Economic Res. Inst., China Acad. of Railway Sci., Beijing, China

Volume

3

fYear

2010

fDate

10-12 Aug. 2010

Firstpage

1577

Lastpage

1581

Abstract

Passenger transport demand analysis is strategically important in mastering ever-changing market for each transport mode. In order to improve the predict accuracy in complex reality situation, the ARMA-GRNN technique is proposed to capture both the linear and nonlinear perspectives of the intercity passenger demand forecast problem. Taking flight demand from 1991 to 2008 in Beijing-Shanghai corridor as an example, the numerical experiment results demonstrate that after subtract from the linear part by AR, the GRNN network based on principal component analysis can effectively fit the non-linear section with maximum error 1.08%.

Keywords

autoregressive moving average processes; demand forecasting; neural nets; principal component analysis; regression analysis; transportation; ARMA-GRNN technique; GRNN network; flight demand; general regression neural network; passenger demand forecasting; passenger transport demand analysis; predict accuracy; principal component analysis; transport mode; Artificial neural networks; Biological system modeling; Computational modeling; Economics; Mathematical model; Time series analysis; Transportation; ARMA; Beijing-Shanghai corridor; GRNN; intercity passenger demand forecast;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation (ICNC), 2010 Sixth International Conference on

Conference_Location

Yantai, Shandong

Print_ISBN

978-1-4244-5958-2

Type

conf

DOI

10.1109/ICNC.2010.5583711

Filename

5583711