A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts

Moldy peanuts are often found in harvested and stored peanuts. Aflatoxins in moldy peanuts pose a potential risk to food safety. Hyperspectral imaging techniques is often used for rapid nondestructive testing of food. However, the information redundancy of hyperspectral data has a negative effect on...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ziwei Liu, Jinbao Jiang, Ying Du, Zhifang Xu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Hyperspectral image band selection band influence algorithm classification moldy peanuts Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/546f98f2ec3243c9b702e39bb3d22e25
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:546f98f2ec3243c9b702e39bb3d22e25
record_format	dspace
spelling	oai:doaj.org-article:546f98f2ec3243c9b702e39bb3d22e252021-11-18T00:04:27ZA Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts2169-353610.1109/ACCESS.2021.3123172https://doaj.org/article/546f98f2ec3243c9b702e39bb3d22e252021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9590516/https://doaj.org/toc/2169-3536Moldy peanuts are often found in harvested and stored peanuts. Aflatoxins in moldy peanuts pose a potential risk to food safety. Hyperspectral imaging techniques is often used for rapid nondestructive testing of food. However, the information redundancy of hyperspectral data has a negative effect on the processing speed and classification accuracy. In this study, a novel band selection method, namely the band influence algorithm (BIA), was proposed to extract key features and remove redundancy for the classification of moldy peanuts. Firstly, hyperspectral images of moldy, healthy and damaged peanuts were collected with 128 bands ranging from 400 nm to 1000nm. Secondly, the BIA method was used to extract feature bands according to the influence of each band subset on the accuracy of the classification model. The effectiveness of BIA method was compared with five representative band selection methods on four classification models: decision tree (DT), k-nearest neighbor (KNN), support vector machine (SVM), and ShuffleNet V2. The experimental results show that the BIA method performs superior effect and stability than other methods on all classification models. The integration of BIA and ShuffleNet V2 achieved the best classification effect. Especially when using 10 feature bands on ShuffleNet V2, the average accuracy, F1 score, and kappa coefficient of BIA reached 97.66%, 0.977, and 0.963 respectively.Ziwei LiuJinbao JiangYing DuZhifang XuIEEEarticleHyperspectral imageband selectionband influence algorithmclassificationmoldy peanutsElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 147527-147536 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hyperspectral image band selection band influence algorithm classification moldy peanuts Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Hyperspectral image band selection band influence algorithm classification moldy peanuts Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ziwei Liu Jinbao Jiang Ying Du Zhifang Xu A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts
description	Moldy peanuts are often found in harvested and stored peanuts. Aflatoxins in moldy peanuts pose a potential risk to food safety. Hyperspectral imaging techniques is often used for rapid nondestructive testing of food. However, the information redundancy of hyperspectral data has a negative effect on the processing speed and classification accuracy. In this study, a novel band selection method, namely the band influence algorithm (BIA), was proposed to extract key features and remove redundancy for the classification of moldy peanuts. Firstly, hyperspectral images of moldy, healthy and damaged peanuts were collected with 128 bands ranging from 400 nm to 1000nm. Secondly, the BIA method was used to extract feature bands according to the influence of each band subset on the accuracy of the classification model. The effectiveness of BIA method was compared with five representative band selection methods on four classification models: decision tree (DT), k-nearest neighbor (KNN), support vector machine (SVM), and ShuffleNet V2. The experimental results show that the BIA method performs superior effect and stability than other methods on all classification models. The integration of BIA and ShuffleNet V2 achieved the best classification effect. Especially when using 10 feature bands on ShuffleNet V2, the average accuracy, F1 score, and kappa coefficient of BIA reached 97.66%, 0.977, and 0.963 respectively.
format	article
author	Ziwei Liu Jinbao Jiang Ying Du Zhifang Xu
author_facet	Ziwei Liu Jinbao Jiang Ying Du Zhifang Xu
author_sort	Ziwei Liu
title	A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts
title_short	A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts
title_full	A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts
title_fullStr	A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts
title_full_unstemmed	A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts
title_sort	band influence algorithm for hyperspectral band selection to classify moldy peanuts
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/546f98f2ec3243c9b702e39bb3d22e25
work_keys_str_mv	AT ziweiliu abandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT jinbaojiang abandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT yingdu abandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT zhifangxu abandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT ziweiliu bandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT jinbaojiang bandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT yingdu bandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts AT zhifangxu bandinfluencealgorithmforhyperspectralbandselectiontoclassifymoldypeanuts
_version_	1718425225003008000

A Band Influence Algorithm for Hyperspectral Band Selection to Classify Moldy Peanuts

Ejemplares similares