Pests and diseases seriously affect the yield and economic benefits of growing rice, and the key to inhibiting rice’s pathogenesis is to find early identification of rice infection. The characteristic Raman spectrum of healthy leaves, and leaves infected with rice blast, paddy rice bakanae and infected by Chilo suppressalis (Walker) were tested by TriVista555CRS laser Raman spectrometer (900cm−1–1700cm−1). At the same integration time, compared with healthy plants, the Raman peak of infected plants not only changed significantly, but also the signal intensity decreased. The results show that there are clear Raman peaks at the three characteristic wavenumbers of 1002.87cm−1, 1156.5cm−1 and 1522.36cm−1. Especially in the leaves of rice blast, it was found that the degree of fungal infection affects the peak width at half height of the characteristic peak. The research shows that Raman spectroscopy provides an effective method for the early detection of rice pests and diseases which may have economic benefits.
Combined laser-induced breakdown spectroscopy (LIBS) and hyperspectral imaging (HSI) with machine learning algorithms can be used to identify rice quality and the place of origin of rice production rapidly and accurately.
In this paper, the ginsengs from five ginseng origins are discriminated by using laser-induced breakdown spectrum (LIBS) combined with random forestsupport vector machine (RF-SVM) and random forest-multilayer perception (RF-MLP) machine learning algorithms. The raw LIBS of ginseng is pretreated by using the wavelet threshold method, denoise the background information and normalazation to improve the signal-to-background ratio and the experimental reliability. The RF algorithm is used to select 10 characteristic spectral lines as the input vectors of the MLP and the SVM models to identify the ginseng orgin. The experimental results show that the discrimination accuracy rates of RF-MLP and RF-SVM models are 99.75% and 99.5%, respectively. The disrimination accuracy of ginseng origin used in the RF-MLP machine algorithm model is slightly higher than that of the RF-SVM model, and then calculated the speed of the RF-MLP model is faster than the RF-SVM model. The results show that LIBS combined with machine algorithms are both promising rapid discrimination methods for ginseng origin.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.