Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves
<i>Sclerotinia</i> stem rot (SSR) is one of the most destructive diseases in the world caused by <i>Sclerotinia sclerotiorum</i> (<i>S. sclerotiorum</i>), resulting in significant yield loss. Early and high-throughput detection would be critical to prevent SSR fro...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/10/2092 |
| _version_ | 1811227997156409344 |
|---|---|
| author | Jing Liang Xiaoli Li Panpan Zhu Ning Xu Yong He |
| author_facet | Jing Liang Xiaoli Li Panpan Zhu Ning Xu Yong He |
| author_sort | Jing Liang |
| collection | DOAJ |
| description | <i>Sclerotinia</i> stem rot (SSR) is one of the most destructive diseases in the world caused by <i>Sclerotinia sclerotiorum</i> (<i>S. sclerotiorum</i>), resulting in significant yield loss. Early and high-throughput detection would be critical to prevent SSR from spreading. This study aimed to propose a feasible method for SSR detection based on the hyperspectral imaging coupled with multivariate analysis. The performance of different detecting algorithms were compared by combining the extreme learning machine (ELM), K-nearest neighbor algorithm (KNN), linear discriminant analysis (LDA), naïve Bayes classifier (NB) and the support vector machine (SVM) with the random frog (RF), successive projection algorithm (SPA) and sequential forward selection (SFS). The similarity of selected optimal wavelengths by three different feature selection methods indicated a high correlation between selected wavelengths and SSR. Compared with KNN, LDA, NB, and SVM, three wavelengths (455, 671 and 747 nm) selected by SFS-CA combined with ELM could achieve relatively better results with the overall accuracy of 93.7% and the lowest false negative rate of 2.4%. These results demonstrated the potential of the presented method using hyperspectral reflectance imaging combined with multivariate analysis for SSR diagnosis. |
| first_indexed | 2024-04-12T09:51:05Z |
| format | Article |
| id | doaj.art-8c2fcb360697474f85ddc524df52cfe3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-12T09:51:05Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-8c2fcb360697474f85ddc524df52cfe32022-12-22T03:37:49ZengMDPI AGApplied Sciences2076-34172019-05-01910209210.3390/app9102092app9102092Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> LeavesJing Liang0Xiaoli Li1Panpan Zhu2Ning Xu3Yong He4Institute of Drug Development & Chemical Biology, College of Pharmaceutical Science, Zhejiang University of Technology, Hangzhou 311122, Zhejiang, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, ChinaInstitute of Drug Development & Chemical Biology, College of Pharmaceutical Science, Zhejiang University of Technology, Hangzhou 311122, Zhejiang, ChinaInstitute of Drug Development & Chemical Biology, College of Pharmaceutical Science, Zhejiang University of Technology, Hangzhou 311122, Zhejiang, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China<i>Sclerotinia</i> stem rot (SSR) is one of the most destructive diseases in the world caused by <i>Sclerotinia sclerotiorum</i> (<i>S. sclerotiorum</i>), resulting in significant yield loss. Early and high-throughput detection would be critical to prevent SSR from spreading. This study aimed to propose a feasible method for SSR detection based on the hyperspectral imaging coupled with multivariate analysis. The performance of different detecting algorithms were compared by combining the extreme learning machine (ELM), K-nearest neighbor algorithm (KNN), linear discriminant analysis (LDA), naïve Bayes classifier (NB) and the support vector machine (SVM) with the random frog (RF), successive projection algorithm (SPA) and sequential forward selection (SFS). The similarity of selected optimal wavelengths by three different feature selection methods indicated a high correlation between selected wavelengths and SSR. Compared with KNN, LDA, NB, and SVM, three wavelengths (455, 671 and 747 nm) selected by SFS-CA combined with ELM could achieve relatively better results with the overall accuracy of 93.7% and the lowest false negative rate of 2.4%. These results demonstrated the potential of the presented method using hyperspectral reflectance imaging combined with multivariate analysis for SSR diagnosis.https://www.mdpi.com/2076-3417/9/10/2092<i>Arabidopsis thaliana</i><i>Sclerotinia sclerotiorum</i><i>Sclerotinia</i> stem rot (SSR)hyperspectral reflectance imaging |
| spellingShingle | Jing Liang Xiaoli Li Panpan Zhu Ning Xu Yong He Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves Applied Sciences <i>Arabidopsis thaliana</i> <i>Sclerotinia sclerotiorum</i> <i>Sclerotinia</i> stem rot (SSR) hyperspectral reflectance imaging |
| title | Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves |
| title_full | Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves |
| title_fullStr | Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves |
| title_full_unstemmed | Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves |
| title_short | Hyperspectral Reflectance Imaging Combined with Multivariate Analysis for Diagnosis of <i>Sclerotinia</i> Stem Rot on <i>Arabidopsis Thaliana</i> Leaves |
| title_sort | hyperspectral reflectance imaging combined with multivariate analysis for diagnosis of i sclerotinia i stem rot on i arabidopsis thaliana i leaves |
| topic | <i>Arabidopsis thaliana</i> <i>Sclerotinia sclerotiorum</i> <i>Sclerotinia</i> stem rot (SSR) hyperspectral reflectance imaging |
| url | https://www.mdpi.com/2076-3417/9/10/2092 |
| work_keys_str_mv | AT jingliang hyperspectralreflectanceimagingcombinedwithmultivariateanalysisfordiagnosisofisclerotiniaistemrotoniarabidopsisthalianaileaves AT xiaolili hyperspectralreflectanceimagingcombinedwithmultivariateanalysisfordiagnosisofisclerotiniaistemrotoniarabidopsisthalianaileaves AT panpanzhu hyperspectralreflectanceimagingcombinedwithmultivariateanalysisfordiagnosisofisclerotiniaistemrotoniarabidopsisthalianaileaves AT ningxu hyperspectralreflectanceimagingcombinedwithmultivariateanalysisfordiagnosisofisclerotiniaistemrotoniarabidopsisthalianaileaves AT yonghe hyperspectralreflectanceimagingcombinedwithmultivariateanalysisfordiagnosisofisclerotiniaistemrotoniarabidopsisthalianaileaves |