Optimized multivariate analysis for the discrimination of cucumber green mosaic mottle virus-infected watermelon seeds based on spectral imaging

Authors: SEO, YOUNGWOOK - Chungnam National University; LEE, HOONSOO - Chungbuk National University; BAE, HYUNG-JIN - Chungnam National University; PARK, EUNSOO - Chungnam National University; LIM, HYUN-SUB - Chungnam National University; Kim, Moon; CHO, BYOUNG-KWAN - Chungnam National University

Submitted to: Journal of Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/6/2019
Publication Date: N/A
Citation: N/A

Interpretive Summary: The cucumber green mottle mosaic virus (CGMMV) is the cause of a common disease affecting cucurbit crops such as cucumber, squash, and melons, and is very easily spread through the planting of infected seeds. Existing biological and molecular methods are effective for detecting infected seeds—to prevent their sale/distribution for planting--but are also time-consuming and labor-intensive. This study investigated non-destructive sorting of watermelon seeds to detect CGMMV-infected seeds using a short-wave infrared hyperspectral imaging technique (SWIR-HIT). Multiple methods of spectral data preprocessing and multiple types of classification models were investigated, targeting both two-class sorting (infected vs sound seeds) and three-class sorting (infected, infection suspected, and sound). The highest classification accuracies achieved were 93% for two-class sorting and 80% for three-class sorting. The results demonstrated that SWIR-HIT can be a valuable nondestructive method for rapidly inspecting seeds for CGMMV-infection. Cucurbit farmers and seed production companies stand to benefit from the potential implementation of the technique and methodology presented in this paper for the prevention and containment of CGMMV.

Technical Abstract: This study proposes a nondestructive sorting method based on the short-wave infrared hyperspectral imaging technique (SWIR-HIT) to detect and classify watermelon seeds infected with the cucumber green mosaic mottle virus (CGMMV). Virus-infected watermelon seeds were collected from virus-infected watermelon plants. Five plates each with 81 seeds were scanned. A total of 304 mean reflectance spectra were used to develop and evaluate virus-infected seed classification models with multivariate analysis methods such as partial least squares discriminant analysis (PLS-DA), support vector machine (SVM), and least squares support vector machine (LS-SVM). To determine the optimal preprocessing method, three preprocessing methods were employed: multivariate scatter correct (MSC) as well as first- and second-derivative preprocessing with the Savitzky–Golay algorithm. Among these methods, second-derivative preprocessing with the LS-SVM method showed an approximately 75% accuracy with a 0.57 kappa coefficient for all three classification classes (infected, infection suspected, and sound seeds). Binary classification between infected and sound seeds by LS-SVM with second-derivative preprocessing showed an approximately 92% accuracy with a 0.75 kappa coefficient. To improve the classification accuracy, the genetic algorithm was implemented, and 9 bands were selected. The selected wavelengths were applied to develop and compare classification models with full wavelengths. The three-class classification with the selected bands showed an approximately 80% accuracy, whereas binary classification in infected and sound seeds showed a more than 93% accuracy with a 0.78 kappa coefficient. These results indicate that SWIR-HIT is a valuable nondestructive tool for rapidly classifying CGMMV-infected watermelon seeds using LS-SVM with raw spectra.