Self-adaptive Differential Evolution Extreme Learning Machine for the Classification of Hyperspectral Images
- DOI
- 10.2991/mce-14.2014.144How to use a DOI?
- Keywords
- Differential Evolution; Self-adaptive; Extreme Learning Machine; Hyperspectral Images;Machine Learning
- Abstract
In this paper, we propose an efficient classification method for hyperspectral images based on the extreme learning machine (ELM) and self-adaptive differential evolution (jDE).The approach of ELM is characterized by a unified formulation for regression, binary, and multiclass classification problems, and the related solution is given in an analytical compact form. In order to address the selection issue that is associated with the ELM, we have developed an automatic method to solve the model selection issue that is associated with this classifier based on the jDE optimization. The self-adaptive control mechanism is used to change control parameters, i.e. select weighting factor F and crossover constant CR, during the run. This simple yet powerful evolutionary optimization algorithm uses cross-validation accuracy as a performance indicator for determining the optimal ELM parameters. Experimental results obtained from hyperspectral data set confirm the attractive properties of the proposed jDE-ELM method in terms of classification accuracy and computation time.
- Copyright
- © 2014, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Junhua Ku AU - Zhihua Cai AU - Xiuying Yang PY - 2014/03 DA - 2014/03 TI - Self-adaptive Differential Evolution Extreme Learning Machine for the Classification of Hyperspectral Images BT - Proceedings of the 2014 International Conference on Mechatronics, Control and Electronic Engineering PB - Atlantis Press SP - 645 EP - 649 SN - 1951-6851 UR - https://doi.org/10.2991/mce-14.2014.144 DO - 10.2991/mce-14.2014.144 ID - Ku2014/03 ER -