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

Simple item page
dc.contributor.authorTschannerl, Julius
dc.contributor.authorRen, Jinchang
dc.contributor.authorYuen, Peter W. T.
dc.contributor.authorSun, Genyun
dc.contributor.authorZhao, Huimin
dc.contributor.authorYang, Zhijing
dc.contributor.authorWang, Zheng
dc.contributor.authorMarshall, Stephen
dc.date.accessioned2019-02-26T15:39:06Z
dc.date.available2019-02-26T15:39:06Z
dc.date.issued2019-02-15
dc.description.abstractBand 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.en_UK
dc.identifier.citationTschannerl J, Ren J, Yuen P, et al., (2019) MIMR-DGSA: unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm. Information Fusion, Volume 51, November 2019, pp. 189-200en_UK
dc.identifier.cris23135937
dc.identifier.issn1566-2535
dc.identifier.urihttp://doi.org/10.1016/j.inffus.2019.02.005
dc.identifier.urihttp://dspace.lib.cranfield.ac.uk/handle/1826/13944
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectBand selectionen_UK
dc.subjectDiscrete optimisationen_UK
dc.subjectEntropyen_UK
dc.subjectEvolutionary computationen_UK
dc.subjectFeature selectionen_UK
dc.subjectGravitational search algorithmen_UK
dc.subjectHyperspectral imagingen_UK
dc.subjectMaximum-Information-Minimum-Redundancyen_UK
dc.subjectMutual informationen_UK
dc.titleMIMR-DGSA: unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithmen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
MIMR-DGSA_Unsupervised_Hyperspectral_Band_Selection-2019.pdf
Size:
883.65 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (CDS)