Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers

Abstract We investigated the feasibility and potentiality of presymptomatic detection of tobacco disease using hyperspectral imaging, combined with the variable selection method and machine-learning classifiers. Images from healthy and TMV-infected leaves with 2, 4, and 6 days post infection were ac...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongyan Zhu, Bingquan Chu, Chu Zhang, Fei Liu, Linjun Jiang, Yong He
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/3623b88b79654fcf87be710ee2e68d46
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3623b88b79654fcf87be710ee2e68d46
record_format	dspace
spelling	oai:doaj.org-article:3623b88b79654fcf87be710ee2e68d462021-12-02T15:04:56ZHyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers10.1038/s41598-017-04501-22045-2322https://doaj.org/article/3623b88b79654fcf87be710ee2e68d462017-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-04501-2https://doaj.org/toc/2045-2322Abstract We investigated the feasibility and potentiality of presymptomatic detection of tobacco disease using hyperspectral imaging, combined with the variable selection method and machine-learning classifiers. Images from healthy and TMV-infected leaves with 2, 4, and 6 days post infection were acquired by a pushbroom hyperspectral reflectance imaging system covering the spectral range of 380–1023 nm. Successive projections algorithm was evaluated for effective wavelengths (EWs) selection. Four texture features, including contrast, correlation, entropy, and homogeneity were extracted according to grey-level co-occurrence matrix (GLCM). Additionally, different machine-learning algorithms were developed and compared to detect and classify disease stages with EWs, texture features and data fusion respectively. The performance of chemometric models with data fusion manifested better results with classification accuracies of calibration and prediction all above 80% than those only using EWs or texture features; the accuracies were up to 95% employing back propagation neural network (BPNN), extreme learning machine (ELM), and least squares support vector machine (LS-SVM) models. Hence, hyperspectral imaging has the potential as a fast and non-invasive method to identify infected leaves in a short period of time (i.e. 48 h) in comparison to the reference images (5 days for visible symptoms of infection, 11 days for typical symptoms).Hongyan ZhuBingquan ChuChu ZhangFei LiuLinjun JiangYong HeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-12 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Hongyan Zhu Bingquan Chu Chu Zhang Fei Liu Linjun Jiang Yong He Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers
description	Abstract We investigated the feasibility and potentiality of presymptomatic detection of tobacco disease using hyperspectral imaging, combined with the variable selection method and machine-learning classifiers. Images from healthy and TMV-infected leaves with 2, 4, and 6 days post infection were acquired by a pushbroom hyperspectral reflectance imaging system covering the spectral range of 380–1023 nm. Successive projections algorithm was evaluated for effective wavelengths (EWs) selection. Four texture features, including contrast, correlation, entropy, and homogeneity were extracted according to grey-level co-occurrence matrix (GLCM). Additionally, different machine-learning algorithms were developed and compared to detect and classify disease stages with EWs, texture features and data fusion respectively. The performance of chemometric models with data fusion manifested better results with classification accuracies of calibration and prediction all above 80% than those only using EWs or texture features; the accuracies were up to 95% employing back propagation neural network (BPNN), extreme learning machine (ELM), and least squares support vector machine (LS-SVM) models. Hence, hyperspectral imaging has the potential as a fast and non-invasive method to identify infected leaves in a short period of time (i.e. 48 h) in comparison to the reference images (5 days for visible symptoms of infection, 11 days for typical symptoms).
format	article
author	Hongyan Zhu Bingquan Chu Chu Zhang Fei Liu Linjun Jiang Yong He
author_facet	Hongyan Zhu Bingquan Chu Chu Zhang Fei Liu Linjun Jiang Yong He
author_sort	Hongyan Zhu
title	Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers
title_short	Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers
title_full	Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers
title_fullStr	Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers
title_full_unstemmed	Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers
title_sort	hyperspectral imaging for presymptomatic detection of tobacco disease with successive projections algorithm and machine-learning classifiers
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/3623b88b79654fcf87be710ee2e68d46
work_keys_str_mv	AT hongyanzhu hyperspectralimagingforpresymptomaticdetectionoftobaccodiseasewithsuccessiveprojectionsalgorithmandmachinelearningclassifiers AT bingquanchu hyperspectralimagingforpresymptomaticdetectionoftobaccodiseasewithsuccessiveprojectionsalgorithmandmachinelearningclassifiers AT chuzhang hyperspectralimagingforpresymptomaticdetectionoftobaccodiseasewithsuccessiveprojectionsalgorithmandmachinelearningclassifiers AT feiliu hyperspectralimagingforpresymptomaticdetectionoftobaccodiseasewithsuccessiveprojectionsalgorithmandmachinelearningclassifiers AT linjunjiang hyperspectralimagingforpresymptomaticdetectionoftobaccodiseasewithsuccessiveprojectionsalgorithmandmachinelearningclassifiers AT yonghe hyperspectralimagingforpresymptomaticdetectionoftobaccodiseasewithsuccessiveprojectionsalgorithmandmachinelearningclassifiers
_version_	1718388946683035648

Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers

Ejemplares similares