MIMR-DGSA : unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm

Tschannerl, Julius and Ren, Jinchang and Yuen, Peter and Sun, Genyun and Zhao, Huimin and Yang, Zhijing and Wang, Zheng and Marshall, Stephen (2019) MIMR-DGSA : unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm. Information Fusion, 51. pp. 189-200. ISSN 1566-2535 (https://doi.org/10.1016/j.inffus.2019.02.005)

[thumbnail of Tschannerl-etal-IF2019-MIMR-DGSA-unsupervised-hyperspectral-band-selection-based]
Preview
 Text. Filename: Tschannerl_etal_IF2019_MIMR_DGSA_unsupervised_hyperspectral_band_selection_based.pdf
Accepted Author Manuscript
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (1MB)| Preview

Abstract

Band selection plays an important role in hyperspectral data analysis as it can improve the performance of data analysis without losing information about the constitution of the underlying data. We propose a MIMR-DGSA algorithm for band selection by following the Maximum-Information-Minimum-Redundancy (MIMR) criterion that maximises the information carried by individual features of a subset and minimises redundant information between them. Subsets are generated with a modified Discrete Gravitational Search Algorithm (DGSA) where we definine a neighbourhood concept for feature subsets. A fast algorithm for pairwise mutual information calculation that incorporates variable bandwidths of hyperspectral bands called VarBWFastMI is also developed. Classification results on three hyperspectral remote sensing datasets show that the proposed MIMR-DGSA performs similar to the original MIMR with Clonal Selection Algorithm (CSA) but is computationally more efficient and easier to handle as it has fewer parameters for tuning.

CORE (COnnecting REpositories)