Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (5): 1425-1430.DOI: 10.11772/j.issn.1001-9081.2019101769

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Hyperspectral band selection based on multi-kernelized fuzzy rough set and grasshopper optimization algorithm

ZHANG Wu, CHEN Hongmei   

  1. School of Information Science and Technology, Southwest Jiaotong University, Chengdu Sichuan 611756, China
  • Received:2019-10-18 Revised:2019-12-15 Online:2020-05-10 Published:2020-05-15
  • Contact: CHEN Hongmei, born in 1971, Ph. D., professor. Her research interests include intelligent information processing, data mining.
  • About author:ZHANG Wu, born in 1994, M. S. candidate. His research interests include data mining.CHEN Hongmei, born in 1971, Ph. D., professor. Her research interests include intelligent information processing, data mining.
  • Supported by:

    This work is partially supported by the National Natural Science Foundation of China (61572406, 61976182), the Key Program for International Technical Innovation Cooperation of Sichuan Province (2019YFH0097).


张伍, 陈红梅   

  1. 西南交通大学 信息科学与技术学院,成都 611756
  • 通讯作者: 陈红梅(1971—)
  • 作者简介:张伍(1994—),男,四川成都人,硕士研究生,CCF会员,主要研究方向:数据挖掘; 陈红梅(1971—),女,四川成都人,教授,博士,CCF会员,主要研究方向:智能信息处理、数据挖掘。
  • 基金资助:



Band selection can effectively reduce the spatial redundancy of hyperspectral data and provide effective support for subsequent classification. Multi-kernel fuzzy rough set model is able to analyze numerical data containing uncertainty and approximate description, and grasshopper optimization algorithm can solve optimization problem with strong exploration and development capabilities. Multi-kernelized fuzzy rough set model was introduced into hyperspectral uncertainty analysis modeling, grasshopper optimization algorithm was used to select the subset of bands, then a hyperspectral band selection algorithm based on multi-kernel fuzzy rough set and grasshopper optimization algorithm was proposed. Firstly, the multi-kernel operator was used to measure the similarity in order to improve the adaptability of the model to data distribution. The correlation measure of bands based on the kernel fuzzy rough set was determined, and the correlation between bands was measured by the lower approximate distribution of ground objects at different pixel points in fuzzy rough set. Then, the band dependence, band information entropy and band correlation were considered comprehensively to define the fitness function of band subset. Finally, with J48 and K-Nearest Neighbor (KNN) adopted as the classifier algorithms, the proposed algorithm was compared with Band Correlation Analysis (BCA) and Normalized Mutual Information (NMI) algorithms in the classification performance on a common hyperspectral dataset Indiana Pines agricultural area. The experimental results show that the proposed algorithm has the overall average classification accuracy increased by 2.46 and 1.54 percentage points respectively when fewer bands are selected.

Key words: hyperspectral remote sensing image, band selection, fuzzy rough set, multi-kernel operator, grasshopper optimization algorithm, information entropy


波段选择能有效减少高光谱数据的空间冗余,为后续分类提供有效的支持。多核模糊粗糙集模型能够对包含不确定性的数值数据进行分析和近似描述,而蝗虫优化算法对优化问题求解具有较强的探索和开发能力,因而将多核模糊粗糙集模型引入高光谱的不确定性分析建模中,采用蝗虫优化算法对波段子集进行选择,提出了一种基于多核模糊粗糙集与蝗虫优化算法的高光谱波段选择算法。首先,使用多核算子来进行相似性度量,提高模型对数据分布的适应性。定义基于核模糊粗糙集的波段相关性度量,通过模糊粗糙集中不同像素点地物上的下近似分布来度量波段之间的相关性。然后,综合考虑波段依赖度、波段信息熵、波段间相关性来定义波段子集的适应度函数。最后,在常用高光谱数据集Indiana Pines农业区上,采用J48和K近邻(KNN)作为分类算法,把所提算法与波段相关性分析(BCA)、标准化互信息(NMI)算法进行分类性能比较。实验结果表明,在选取较少波段个数时,所提算法的总体平均分类精度提高了2.46和1.54个百分点。

关键词: 高光谱遥感图像, 波段选择, 模糊粗糙集, 多核算子, 蝗虫优化算法, 信息熵

CLC Number: