An optimization-based ensemble EMD for classification of hyperspectral images

• Published in: 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) pp. 1045 - 1050
• Main Authors: Yi Shen, Zhi He, Xiaoshuai Li, Qiang Wang, Miao Zhang, Yan Wang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2013
• Subjects: Accuracy; classification; Empirical mode decomposition; ensemble empirical mode decomposition (EEMD); Feature extraction; hyperspectral images; Hyperspectral imaging; Roads; support vector machine (SVM); Support vector machines
• ISBN: 9781467346214; 1467346217
• ISSN: 1091-5281
• DOI: 10.1109/I2MTC.2013.6555574

Extraction of the essential features from massive bands is a key issue in hyperspectral images classification. Plenty of feature extraction techniques can be found in the literature but most of these methods rely on the linear/stationary assumptions. The aim of this paper is to propose an alternative methodology based on the ensemble empirical mode decomposition (EEMD) and utilize the versatile support vector machine (SVM) as a classifier. An optimization problem, which minimizes a smooth function subjected to inequality constraints associated with the extrema, is formulated in each iteration step to enhance the benefits of the EEMD. Additionally, the intrinsic mode functions (IMFs) extracted by the optimization-based EEMD are taken as features of the hyperspectral dataset and classified by the SVM. Simulations on the Washington D.C. mall hyperspectral dataset confirm the promising performance of our approach.