Academic Journals Database
Disseminating quality controlled scientific knowledge

Application of Artificial Neural Networks for Airline Number of Passenger Estimation in Time Series State

Author(s): M. Zandieh | A. Azadeh | B. Hadadi | M. Saberi

Journal: Journal of Applied Sciences
ISSN 1812-5654

Volume: 9;
Issue: 6;
Start page: 1001;
Date: 2009;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: pre-processed data | airline number of passenger | data envelopment analysis | artificial neural network | Prediction

This study presents an integrated Artificial Neural Networks (ANN) to estimate and predict airline number of passenger in Iran. All type of ANN-Multi Layer Perceptron (MLP) is examined to this estimation. The ANN models are implemented on MATLAB software. Auto-Correlation Function (ACF) is utilized to define input variables. Finally, the best type of ANN-MLP is determined with Data Envelopment Analysis (DEA). Kruskal-Wallis test is used for asses the impact of raw data, preprocessed data and post process method on ANN performance. Monthly airline number of passenger of Iran airline from 1993 to 2005 is considered as the case of this study.

Tango Rapperswil
Tango Rapperswil

     Save time & money - Smart Internet Solutions