Full Length Research Paper
Abstract
As the production values in the integrated circuit (IC) industry are inherently nonlinear and non-stationary, it is regarded as one of the most challenging tasks for practitioners and academics. This study proposed a hybrid methodology by combining empirical mode decomposition (EMD) and support vector regression (SVR) in production values forecasting. The proposed approach first uses EMD, which can adaptively decompose the complicated raw data into a finite set of intrinsic mode functions (IMFs) and a residue. After identifying the IMF components, residue are then modeled and forecasted using SVR. Thefinal forecasting value can be obtained by the sum of these prediction results. Experimental results show that the proposed approach outperforms the SVR model without EMD preprocessing.
Key words: Integrated circuit (IC) industry, production values forecasting, empirical mode decomposition, support vector regression.
Copyright © 2024 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0