Novel grey models for the trend forecast of Taiwan waste gas apparatus
by Chen-Fang Tsai; Shin-Li Lu
International Journal of Environmental Technology and Management (IJETM), Vol. 18, No. 2, 2015

Abstract: This paper proposes a novel optimiser to refine the prediction accuracy of grey models (GM). This design consists of a dynamic genetic algorithm (GA) controller that uses a weighting optimiser with the exponentially weighted moving average (EWMA) method to search for an optimal background value of GM optimisation (EGM). The contributions of our research are that these two new EWMA-GM models can formulate a dynamic prediction sequence using a novel GA mechanism, which can then be used to effectively predict Taiwan's industry pollution. Finally, a case study is provided to illustrate the proposed approach. Our simulations are designed by four different GM models (GM, EGM, RGM, and REGM). Comparisons for predicting the greenhouse outputs of Taiwan were performed. The simulation outcomes show that EGM and REGM models perform better than GM and RGM models. The REGM model performed the best and efficiently improved the accuracy of the GM(1,1) model. This study can reveal Taiwan's pollution management status and provide a beneficial option for the presentation of environmental strategies.

Online publication date: Wed, 06-May-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Environmental Technology and Management (IJETM):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email