The classification of wheat grain varieties is of great value because its high purity is the yield and quality guarantee. In this study, hyperspectral imaging combined with the chemometric methods was applied to explore and implement the varieties classification of wheat seeds. The hyperspectral images of all the samples covering 874–1734 nm bands were collected. Exploratory analysis was first carried out while using principal component analysis (PCA) and linear discrimination analysis (LDA). Spectral preprocessing methods including standard normal variate (SNV), multiplicative scatter correction (MSC), and wavelet transform (WT) were introduced, and their effects on discriminant models were studied to eliminate the interference of instrumental and environmental factors. PCA loading, successive projections algorithm (SPA), and random frog (RF) were applied to extract feature wavelengths for redundancy elimination owing to the possibility of existing redundant spectral information. Classification models were developed based on full wavelengths and feature wavelengths using LDA, support vector machine (SVM), and extreme learning machine (ELM). This optimal model was finally utilized to generate visualization map to observe the classification performance intuitively. When comparing with other models, ELM based on full wavelengths achieved the best accuracy up to 91.3%. The overall results suggested that hyperspectral imaging was a potential tool for the rapid and accurate identification of wheat varieties, which could be conducted in large-scale seeds classification and quality detection in modern seed industry.

Rapid determination of chlorophyll content is significant for evaluating cottons nutritional and physiological status. Hyperspectral technology equipped with multivariate analysis methods has been widely used for chlorophyll content detection. However, the model developed on one batch or variety cannot produce the same effect for another due to variations, such as samples and measurement conditions. Considering that it is costly to establish models for each batch or variety, the feasibility of using spectral preprocessing combined with deep transfer learning for model transfer was explored. Seven different spectral preprocessing methods were discussed, and a self-designed convolutional neural network (CNN) was developed to build models and conduct transfer tasks by fine-tuning. The approach combined first-derivative (FD) and standard normal variate transformation (SNV) was chosen as the best pretreatment. For the dataset of the target domain, fine-tuned CNN based on spectra processed by FD+SNV outperformed conventional partial least squares (PLS) and squares-support vector machine regression (SVR). Although the performance of fine-tuned CNN with a smaller dataset was slightly lower, it was still better than conventional models and achieved satisfactory results. Ensemble preprocessing combined with deep transfer learning could be an effective approach to estimate the chlorophyll content between different cotton varieties, offering a new possibility for evaluating the nutritional status of cotton in the field.

Rapid and accurate discrimination of Chrysanthemum varieties is very important for producers, consumers and market regulators. The feasibility of using hyperspectral imaging combined with deep convolutional neural network (DCNN) algorithm to identify Chrysanthemum varieties was studied in this paper. Hyperspectral images in the spectral range of 874–1734 nm were collected for 11,038 samples of seven varieties. Principal component analysis (PCA) was introduced for qualitative analysis. Score images of the first five PCs were used to explore the differences between different varieties. Second derivative (2nd derivative) method was employed to select optimal wavelengths. Support vector machine (SVM), logistic regression (LR), and DCNN were used to construct discriminant models using full wavelengths and optimal wavelengths. The results showed that all models based on full wavelengths achieved better performance than those based on optimal wavelengths. DCNN based on full wavelengths obtained the best results with an accuracy close to 100% on both training set and testing set. This optimal model was utilized to visualize the classification results. The overall results indicated that hyperspectral imaging combined with DCNN was a very powerful tool for rapid and accurate discrimination of Chrysanthemum varieties. The proposed method exhibited important potential for developing an online Chrysanthemum evaluation system.

The excellent representation ability of deep spectral features enables hyperspectral imaging combined with deep convolutional neural network to be a powerful tool for large-scale seeds detection in modern seed industry.

Fusarium species are important seedborne pathogens that cause rice bakanae disease (RBD). In this study, 421 strains were isolated from 25 rice samples collected from Zhejiang, Anhui, and Jiangxi provinces of China. Furthermore, 407 isolates were identified as F. fujikuroi (80.05% isolation frequency), F. proliferatum (8.31%), F. equiseti (5.94%), F. incarnatum (2.61%), F. andiyazi (0.95%), and F. asiaticum (0.48%) based on morphology and translation elongation factor 1-alpha (TEF1-α) gene. Phylogenetic analysis of combined sequences of the RNA polymerase II largest subunit (RPB1), RNA polymerase II second largest subunit (RPB2), TEF1-α gene, and ribosomal DNA (rDNA) internal transcribed spacer (ITS) showed that 17 representative strains were attributed to six species. Pathogenicity tests showed that representative isolates possessed varying ability to cause symptoms of bakanae on rice seedlings. Moreover, the seed germination assay revealed that six isolates had different effects, such as inhibition of seed germination, as well as seed and bud rot. The loop mediated isothermal amplification (LAMP)-based assay were developed for the detection of F. fujikuroi. According to sequences of desaturase-coding gene promoter, a species-specific marker desM231 was developed for the detection of F. fujikuroi. The LAMP assay using seeds collected from field was validated, and diagnostics developed are efficient, rapid, and sensitive.