Forecast of civil aviation freight volume using unbiased grey-fuzzy-Markov chain method

Abstract

This paper presented an unbiased grey-Markov chain method to forecast civil aviation freight volume. It combines the unbiased grey system theory and fuzzy classification. When forecasting freight volumes, uncertainty factors often cause deviation in estimations derived from traditional grey model. Therefor fuzzy classification is a good tool to integrate with unbiased grey analysis to reduce the residual resulted from these uncertain factors. This method can take advantage of the prediction power of conventional Grey-Markov forecasting method and simultaneously eliminate grey bias and improve anti-jamming performance. Finally, this method is applied in forecasting the Chinese civil aviation fright volume. Our experimental result shows that the model not only discovers the trend of the freight volumes but also overcomes the random fluctuation of data affecting precision.

Railway freight volume forecast using an ensemble model with optimised deep belief network

“…Wang and Chen [3] proposed a combined model with optimal weights which combined elasticity coefficient method with GM(1,1) and forecasted passenger and freight traffic volumes from 2011 to 2015 of all provinces in China. Ma and Chen [4] and Lu and Song [5] used Markov model improved by gray model and other methods to build predicting models for forecasting civil aviation freight volume and railway freight volume, respectively. The gray system theory is simple and has fast operating speed, which can give a good performance for short-term forecasting, but it is not ideal for the changing system.…”

Adaptive combination forecasting model for China’s logistics freight volume based on an improved PSO-BP neural network

“…The researchers applied various methods to develop logistics freight volume forecasting models such as: Delphi method, triple exponential smoothing model (TESM), polynomial trend extrapolation model (PTEM), linear regression model (LR), auto regression model (AR), support vector machine (SVM), computable general equilibrium method (CGE), BP neural network, grey model (GM), Markov model, scenario analysis, combination method, and so on. Ma et al (2013) proposed an unbiased grey-Markov chain method to forecast civil aviation freight volume. Zhang and Shi (2005) constructed a grey stochastic model to forecast passenger and freight volume.…”