Research on optimal predicting model for the grading detection of rice blast
- 7 Downloads
Rice blast is a worldwide disease of rice that is an important reason for the reduction of rice yield. In this paper, “Lingliangyou 268” was selected as the research object. The spectral data were measured by a Landmark Spectrum instrument. The spectral characteristics of the original spectrum, derivative spectrum and logarithmic spectrum of different grades of rice blast were studied. A new method for rice blast grading based on sensitive bands was proposed. Then, the method of system clustering method, BP neural network and probabilistic neural network were used to establish the rice blast classification prediction model, respectively. Comparing the three models, the classification effect based on probabilistic neural network is the best. In the training samples, the logarithmic spectral classification accuracy is 97.8%. In the test samples, the logarithmic spectral classification accuracy is 75.5%.
KeywordsRice blast High spectral Grading-detection
This paper is supported by the Foundation Item: Technology plan of Hunan Province (2016NK2117).
Compliance with ethical standards
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
- 1.Yang, Y., He, Y.: Early prediction of antioxidant enzyme value of rice blast based on hyper-spectral image[J].Trans Chin Soc Agric Eng (Trans CSAE) 29(20), 135–141 (in Chinese) Google Scholar
- 3.Shi, C., Chen, W.L., Wang, J., et al.: Evaluation of the resistance spectrum of three important rice cultivars against blast disease caused by Magnaporthe oryzae and correlation analysis among evaluation indexes[J]. Acta Phytophylacica Sin 41(4), 390–394 (2014) (in Chinese)Google Scholar
- 4.Yang, X.H., Wu, Y.P., Huang, J.F., et al.: Estimation of rice biophysical parameters by remote sensing using support vector machine. Sci China Ser C: Life Sci 39(11), 1080–1091 (2009)Google Scholar
- 6.Wang, X.Z., Li, D.P.: Spectrum detection of rice planthopper populations from canopy reflectance based on principal component regression[J]. Plant Dis Pests 1(4), 20–21, 24 (2010)Google Scholar
- 7.Zheng, Z.X., Qi, L., Ma, X., et al.: Grading method of rice leaf blast using hyperspectral imaging technology[J]. Trans Chin Soc Agric Eng 29(19), 138–144 (2013) (in Chinese) Google Scholar
- 8.Huang, S.P., Qi, L., Ma, X., et al.: Grading method of rice panicle blast severity based on hyperspectral image[J]. Trans Chin Soc Agric Eng 31(1), 212–219 (2015) (in Chinese) Google Scholar
- 9.Li, B., Liu, Z.Y., Wu, H.F., et al.: Differentiation of rice panicles blast by hyperspectral remote sensing based on probabilistic neural network[J]. Bull Sci Technol 25(6):812–815 (2009) (in Chinese) Google Scholar