The Metamer Number Prediction Based on Improved SVM
WANG DeJi1,2, XIONG FanLun1, WANG RuJing1, ZHA ShiHong1,2
1.Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031 2.Department of Automation, University of Science and Technology of China, Hefei 230026
Abstract：The relation between the temperature and the metamer is very important for the virtual plant growth model. However, it is difficult to predict it just by SVM because there are too many noises in the raw data. In this paper, a new kernel function based on the information geometry is established to overcome the high noise and nonlinear data. The relation between number of metamer and temperature can thus be gotten precisely. The method is applied to the cotton growth model. Compared with the methods of least square and SVM, the improved SVM can predict the number of metamer more precisely.
王德吉，熊范纶，王儒敬，查世红. 基于改进SVM的叶元数目预测[J]. 模式识别与人工智能, 2006, 19(4): 557-560.
WANG DeJi, XIONG FanLun, WANG RuJing, ZHA ShiHong. The Metamer Number Prediction Based on Improved SVM. , 2006, 19(4): 557-560.
[1] Hu B G, Zhao X, et al. Plant Growth Modeling and Visualization -Review and Perspective. Acta Automatica Sinica, 2001, 27(6): 816-835 (in Chinese) (胡包钢,赵 星,等.植物生长建造模型与可视化——回顾与展望.自动化学报, 2001, 27(6): 816-835) [2] Guo Y, Li B G. Research Summary about Virtual Plant. Chinese Science Bulletin, 2001, 46(4): 273-280 (in Chinese) (郭 炎,李保国.虚拟植物的研究进展.科学通报, 2001, 46(4): 273-280) [3] Ding W L.Research of the Agricultural Expert System Based on Artificial Plant Growth Model.Journal of Zhejiang University of Technology, 2005, 33(5): 525-533 (in Chinese) (丁维龙.基于虚拟植物生长模型的农业专家系统研究.浙江工业大学学报, 2005, 33(5): 525-533) [4] McKinion J M, Baker D N, Whisler F D, Lambert J R. Application of Gossym/Comax System to Cotton Crop Management. Agricultural Systems, 1989, 31: 55-65 [5] de Reffye P, Edelin C , Francon J, et al. Plant Models Faithful to Botanical Structure and Development. ACM Computer Graphics, 1988, 22(4): 151-158 [6] Ma Y, Huang D X, Jin Y H. Soft-Sensor Modeling Method Based on Support Vector Machine. Information and Control, 2004, 33(4): 417-421 (in Chinese) (马 勇,黄德先,金以慧.基于支持向量机的软测量建模方法.信息与控制, 2004, 33(4): 417-421) [7] Sun Y F, Liang Y C. An Improved Method for Kernel Function with Data-Dependent Type of Support Vector Machine. Journal of Jilin University (Science Edition), 2003, 41(3): 329-333 (in Chinese) (孙延风,梁艳春.支持向量机的数据依赖型核函数改进算法.吉林大学学报(理学版), 2003, 41(3): 329-333) [8] Vapnik V N. Statistical Learning Theory. New York, USA: Wiley, 1998 [9] Boser B E, Guyon I M, Vapnik V N. A Training Algorithm for Optimal Margin Classifiers. In: Proc of the 5th Annual Workshop on Computational Learning Theory. Pittsburgh, USA, 1992 [10] Cortes C, Vapnik V N. Support Vector Networks. Machine Learning, 1995, 20(3): 273-297 [11] Bishop C M. Training with Noise is Equivalent to Tikohonov Regularization. Neural Computation, 1995, 7: 108-116 [12] Vapnik V N, Chervonenkis A Y. Necessary and Sufficient Conditions for the Uniform Convergence of Means to Their Expectations. Theory of Probability and Its Applications, 1981, 26(3): 532-553
2006, Vol. 19 
