文献类型：会议论文

英文题名：A Framework of Multiple Kernel Ensemble Learning for Hyperspectral Classification

作者：Qi, Chengming[1,2];Zhou, ZhangBing[1,3];Hu, Lishuan[1,2];Wang, Qun[1]

第一作者：Qi, Chengming;亓呈明

通讯作者：Zhou, ZB[1];Zhou, ZB[2]

机构：[1]China Univ Geosci, Sch Informat Engn, Beijing 100083, Peoples R China;[2]Beijing Union Univ, Sch Automat, Beijing 100044, Peoples R China;[3]TELECOM Sud Paris, Dept Comp Sci, F-91001 Evry, France

第一机构：China Univ Geosci, Sch Informat Engn, Beijing 100083, Peoples R China

通讯机构：[1]corresponding author), China Univ Geosci, Sch Informat Engn, Beijing 100083, Peoples R China;[2]corresponding author), TELECOM Sud Paris, Dept Comp Sci, F-91001 Evry, France.

会议论文集：Conference on UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld

会议日期：JUL 18-21, 2016

会议地点：Toulouse, FRANCE

语种：英文

外文关键词：Ensemble; Hyperspectral image; Stochastic Multiple Kernel Boosting

摘要：Hyperspectral image classification has been a very active area of research in recent years. Multiple kernel learning (MKL) and ensemble learning are promising family of machine learning algorithms and have been applied extensively in hyperspectral image classification. However, many MKL methods often formulate the problem as an optimization task. Due to the high computational cost of solving the complicated optimization problem and improve the efficiency of MKL, in this paper, an ensemble learning framework, SMKB (Stochastic Multiple Kernel Boosting), which applies Adaptive Boosting (AdaBoost) and stochastic approach to learning multiple kernel-based classifier for multi-class classification problem, is presented. We examine empirical performance of proposed approach on benchmark hyperspectral classification data set in comparison with various state-of-the-art algorithms. Experimental results show that SMKB is more effective and efficient than traditional MKL techniques.