论文部分内容阅读
应用支持向量机(SVM)的算法进行中国大豆产量的预测研究,用1991-2008年中国大豆数据组成样本集,建立影响因素与大豆产量之间的SVM模型.利用SVM对输入和输出数据进行训练学习,逼近历史数据所隐含的函数关系,完成对新数据序列的映射关系,从而完成对未来年份大豆的预测,并与其它几种方法的预测效果进行比较.结果表明,SVM预测模型预测大豆产量的精度优于其它预测方法.
The SVM algorithm was used to predict the soybean production in China, and the SVM model was established to establish the SVM model between the influencing factors and the soybean yield using the sample data of Chinese soybean from 1991 to 2008. The input and output data were trained by SVM Learning and approximating the functional relations implied by the historical data and completing the mapping relationship with the new data series so as to complete the prediction of the future year soybean and comparing with the prediction results of several other methods.The results show that the SVM prediction model predicts the soybean The accuracy of the output is better than the other forecast methods.