Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing

Spectral dimensionality reduction is a crucial step for hyperspectral image classification in practical applications. Dimensionality reduction has a strong influence on image classification performance with the problems of strong coupling features and high band correlation. To solve these issues, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Liu, Yulong Qiao
Format: Article
Language:English
Published: Wiley 2020-11-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/1550147720968467
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849473171303956480
author Jing Liu
Yulong Qiao
author_facet Jing Liu
Yulong Qiao
author_sort Jing Liu
collection DOAJ
description Spectral dimensionality reduction is a crucial step for hyperspectral image classification in practical applications. Dimensionality reduction has a strong influence on image classification performance with the problems of strong coupling features and high band correlation. To solve these issues, we propose the Mahalanobis distance–based kernel supervised machine learning framework for spectral dimensionality reduction. With Mahalanobis distance matrix–based dimensional reduction, the coupling relationship between features and the elimination of the scale effect are removed in low-dimensional feature space, which benefits the image classification. The experimental results show that compared with other methods, the proposed algorithm demonstrates the best accuracy and efficiency. The Mahalanobis distance–based multiples kernel learning achieves higher classification accuracy than the Euclidean distance kernel function. Accordingly, the proposed Mahalanobis distance–based kernel supervised machine learning method performs well with respect to the spectral dimensionality reduction in hyperspectral imaging remote sensing.
format Article
id doaj-art-d856e6422e3f42f9942e790b2509ca9c
institution Kabale University
issn 1550-1477
language English
publishDate 2020-11-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-d856e6422e3f42f9942e790b2509ca9c2025-08-20T03:24:15ZengWileyInternational Journal of Distributed Sensor Networks1550-14772020-11-011610.1177/1550147720968467Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensingJing LiuYulong QiaoSpectral dimensionality reduction is a crucial step for hyperspectral image classification in practical applications. Dimensionality reduction has a strong influence on image classification performance with the problems of strong coupling features and high band correlation. To solve these issues, we propose the Mahalanobis distance–based kernel supervised machine learning framework for spectral dimensionality reduction. With Mahalanobis distance matrix–based dimensional reduction, the coupling relationship between features and the elimination of the scale effect are removed in low-dimensional feature space, which benefits the image classification. The experimental results show that compared with other methods, the proposed algorithm demonstrates the best accuracy and efficiency. The Mahalanobis distance–based multiples kernel learning achieves higher classification accuracy than the Euclidean distance kernel function. Accordingly, the proposed Mahalanobis distance–based kernel supervised machine learning method performs well with respect to the spectral dimensionality reduction in hyperspectral imaging remote sensing.https://doi.org/10.1177/1550147720968467
spellingShingle Jing Liu
Yulong Qiao
Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
International Journal of Distributed Sensor Networks
title Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
title_full Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
title_fullStr Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
title_full_unstemmed Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
title_short Mahalanobis distance–based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
title_sort mahalanobis distance based kernel supervised machine learning in spectral dimensionality reduction for hyperspectral imaging remote sensing
url https://doi.org/10.1177/1550147720968467
work_keys_str_mv AT jingliu mahalanobisdistancebasedkernelsupervisedmachinelearninginspectraldimensionalityreductionforhyperspectralimagingremotesensing
AT yulongqiao mahalanobisdistancebasedkernelsupervisedmachinelearninginspectraldimensionalityreductionforhyperspectralimagingremotesensing