基于主成分分析和径向基网络的水稻胡麻斑病严重度估测

doi:10.3964/j.issn.1000-0593(2008)09-2156-05

Abstract
References
Related Citation (15)

Download: PDF (1343 KB)
Export: BibTeX | EndNote (RIS)

Abstract An ASD Field Spec Pro Full Range spectrometer was used here to acquire the spectral reflectance of healthy and disease leaves cut from rice plants in the field. The leaf disease severity of rice brown spot was determined by estimating the percentage of infected surface area of rice leaves in the laboratory through phytopathologist’s observation. Three steps were taken to estimate leaf disease severity of rice brown spot. The first step was that different spectra transforming methods, namely, resampling spectrum (10 nm interval), the first- and second-order derivative spectrum based on raw hyperspectral reflectance, were conducted. The second step was that the principal component analysis (PCA) was examined to obtain the principal components (PCs) from the above transformed spectra to reduce the spectra dimensions of hyperspectral reflectance and simplify the data structure of hyperspectra. The last step was that the resampling and PCs spectra entered the Radial Basis Function neural network (RBFN) as the input vectors, and the disease severity of rice brown spot entered RBFN as the target vectors. RBFN is an effective feed forward propagation neural network, which is based on the linear combinations of corresponding radial basis functions. In general RBFN can be used to solve the problems such as regression or classification with high operation rate and efficient extrapolation capability, and quickly designed with zero error to approximate functions. The total dataset (n=262) was divided into two subsets, in which three quarters (n=210) was the training subset to train the neural network, and the remaining quarter (n=52) was the testing dataset to conduct the performance analysis of neural network. The spread constants of RBFN and various data processing methods were investigated in detail. The best prediction result was obtained by PCs spectra based on the first-order derivative using RBFN model, the root mean square of prediction error（RMSE）was small (7.73%) in the testing dataset, and the next was the resampling spectra with RMSE of 8.75%. This research demonstrated that it was feasible and reliable to estimate the disease severity of rice brown spot based on PCA-RBFN and hyperspectral reflectance at the leaf level.

Key words：Disease severity;Rice brown spot;Principal component analysis (PCA);Neural network

Received: 2007-05-28 Accepted: 2007-09-02

ZTFLH:	TP29
	S127

Corresponding Authors: HUANG Jing-feng E-mail: hjf@zju.edu.cn

Cite this article:

LIU Zhan-yu,HUANG Jing-feng,TAO Rong-xiang, et al. Estimating Rice Brown Spot Disease Severity Based on Principal Component Analysis and Radial Basis Function Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(09): 2156-2160.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2008)09-2156-05 OR https://www.gpxygpfx.com/EN/Y2008/V28/I09/2156

[1] Brenchley G H. Annual Review of Phytopathology, 1968, 6: 1.
[2] West J S, Bravo C, Oberit R, et al. Annual Review of Phytopathology, 2003, 41: 593.
[3] Jackson R D. Annual Review of Phytopathology, 1986, 24: 265.
[4] Penuelas J, Filella L. Trends in Plant Science, 1998, 3(4): 151.
[5] Nilsson H E. Annual Review of Phytopathology, 1995, 33: 489.
[6] GAO Ning, SHAO Lu-shou(高宁，邵陆寿). Computers and Agriculture(计算机与农业), 2003, (7): 16.
[7] Adams M L, Philpot W D, Norvell W A. International Journal of Remote Sensing, 1999, 20(18): 3363.
[8] Riedell W E. and Blackmer T M. Crop Science, 1999, 39: 1835.
[9] Kobayashi T, Kanda E, Kitada K, et al. Pytopathology, 2001, 91(3): 316.
[10] HUANG Mu-yi, WANG Ji-hua, HUANG Wen-jiang, et al(黄木易, 王纪华, 黄文江, 等). Transactions of the CSAE(农业工程学报), 2003, 19(6): 154.
[11] Vigier B J, Elizabeth P, Strachan Ian B. IEEE Geosciences and Remote Sensing Letters, 2004, 1(4): 255.
[12] Malthus T J, Madeira A C. Remote Sensing of Environment, 1993, 45: 107.
[13] TANG Jian, YE Gong-yin, YANG Bao-jun, et al(唐健, 叶恭银, 杨保军，等). Chinese Journal of Rice Science(中国水稻科学), 2001, 15(4): 317.
[14] Haykin S. Neural Networks: A Comprehensive Foundation, Second Edition(神经网络原理，第2版). Beijing: China Machine Press(北京: 机械工业出版社), 2004, 183.
[15] Ingebritsen S E, Lyon R J P. International Journal of Remote Sensing, 1985, 6(5): 687.
[16] HE Yong, LI Xiao-li, SHAO Yong-ni(何勇, 李晓丽, 邵咏妮). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(5): 850.
[17] Cloutis E A. International Journal of Remote Sensing, 1996, 17(12): 2215.
[18] Rundquist D, Han L, Schalles J, et al. Photogramme Engineering Remote Sensing, 1996, 62: 195.
[19] Center for the Research and Development of FeiSi Technology(飞思科技产品研发中心编). The Theory Artificial of Neutral Networks and Its Realization in Matlab7(神经网络理论与Matlab7实现). Beijing: Electronics Industry Press(北京: 电子工业出版社), 2006. 116.
[20] Carter G A. International Journal of Remote Sensing, 1994, 15(3): 697.