| 基于支持向量机非线性筛选水稻苗期抗旱性指标 |
| |
| 引用本文： | 袁哲明,谭显胜.基于支持向量机非线性筛选水稻苗期抗旱性指标[J].作物学报,2010,36(7):1176-1182. |
| |
| 作者姓名： | 袁哲明 谭显胜 |
| |
| 作者单位： | 湖南农业大学生物安全科学技术学院 / 湖南省作物种质创新与资源利用重点实验室，湖南长沙410128 |
| |
| 基金项目： | 教育部新世纪优秀人才支持计划项，高等学校博士学科点专项科研基金项目，湖南省教育厅青年基金项目，湖南省研究生科研创新项目 |
| |
| 摘 要： | 作物抗旱性指标筛选具小样本、多指标和非线性等特点，传统的基于经验风险最小原则经线性筛选获得的综合指标及在此基础上建立的线性回归模型的合理性受到质疑；基于结构风险最小原则的支持向量机具适于小样本、非线性、泛化推广能力优异等诸多优点，但可解释性差。本文以15个水稻品种苗期反复干旱存活率为因变量，从24个形态生理指标中经支持向量回归(SVR)非线性筛选得苗高、脯氨酸、丙二醛、叶龄、心叶下倒一叶面积、抗坏血酸等6个综合指标，以此建立的SVR模型拟合精度与留一法预测精度均明显优于参比线性模型；如考虑指标测量的简易性，仅以地上部干重、心叶下倒二叶面积、根冠比、叶龄、叶鲜重、心叶下倒一叶面积等6个形态指标进行评估同样可行。为增强SVR的解释能力，基于F测验对SVR模型建立了非线性回归显著性与单因子重要性显著性的测验方法。
|
| 关 键 词： | 水稻 苗期 抗旱性指标 支持向量机 非线性筛选 |
| 收稿时间： | 2009-12-31 |
Nonlinear Screening Indexes of Drought Resistance at Rice Seedling Stage Based on Support Vector Machine |
| |
| YUAN Zhe-Ming,TAN Xian-Sheng.Nonlinear Screening Indexes of Drought Resistance at Rice Seedling Stage Based on Support Vector Machine[J].Acta Agronomica Sinica,2010,36(7):1176-1182. |
| |
| Authors: | YUAN Zhe-Ming TAN Xian-Sheng |
| |
| Institution: | College of Bio-safety Science and Technology / Hunan Provincial Key Laboratory of Crop Germplasm Innovation and Utilization, Hunan Agricultural University, Changsha 410128, China |
| |
| Abstract: | Screening indexes of drought resistance in crops is a puzzler with a few samples, multi-index and non-linear characteristics. Rationality of linear regression model and the indexes obtained by linear screening based on empirical risk minimization are debated. On the contrary, support vector machine based on structural risk minimization has the advantages of non-linear characteristics, fitting for a few samples, avoiding the over-fit, strong generalization ability and high prediction precision, etc. In this paper, setting the survival percentage under repeated drought condition as the target and support vector regression as the nonlinear screen tool, six integrated indicators including plant height, proline, malondialdehyde, leaf age, area of the first leaf under the central leaf and ascorbic acid, were highlighted from 24 morphological and physiological indicators in 15 paddy rice cultivars. The results showed that support vector regression model with the six integrated indicators had a more distinct improvementin fitting and prediction precision than the linear reference models. Considering the simplicity of indicators measurement, the support vector regression model with the only six morphological indicators including shoot dry weight, area of the second leaf under the central leaf, root shoot ratio, leaf age, leaf fresh weight and area of the first leaf under the central leaf was also feasible. Furthermore, an explanatory system including the significance of regression model and the importance of single indicator was established based on support vector regression and F-test. |
| |
| Keywords: | Rice Seedling stage Drought resistance index Support vector machine Non-linear screening |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《作物学报》浏览原始摘要信息 |
| 点击此处可从《作物学报》下载免费的PDF全文 |
|
