Detection of cucumber green mottle mosaic virus-infected watermelon seeds using a near-infrared (NIR) hyperspectral imaging system: Application to seeds of the “Sambok Honey” cultivar
详细信息 查看全文
- 作者：Hoonsoo Leea ; hoonsoolee83@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Moon S. Kimb ; moon.kim@ars.usda.gov" class="auth_mail" title="E-mail the corresponding author ; Hyoun-Sub Limc ; hyounlim@cnu.ac.kr" class="auth_mail" title="E-mail the corresponding author ; Eunsoo Parka ; besoo0407@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Wang-Hee Leea ; wanghee@cnu.ac.kr" class="auth_mail" title="E-mail the corresponding author ; Byoung-Kwan Choa ; chobk@cnu.ac.kr" class="auth_mail" title="E-mail the corresponding author
- 关键词：Cucumber green mottle mosaic virus (CGMMV) ; Watermelon seeds ; Near-infrared (NIR) hyperspectral imaging ; Partial least square discriminant analysis (PLS-DA) ; Least square support vector machine (LS-SVM)
- 刊名：Biosystems Engineering
- 出版年：2016
- 出版时间：August 2016
- 年：2016
- 卷：148
- 期：Complete
- 页码：138-147
- 全文大小：1647 K
文摘
- •
Hyperspectral imaging system distinguished CGMMV-infected “Sambok Honey” watermelon seeds with an accuracy of 83.3%.
- •
Spectral bands of 1411, 1456, 1792, and 1867 nm were significant for detecting virus-infected watermelon seeds.
- •
Better prediction accuracy was achieved with PLS-DA rather than LS-SVM model.