摘要
城市生活用水量受到多重因素的影响,这些因素之间的相关性都较大.将偏最小二乘回归与神经网络耦合,建立了城市生活用水量预测模型.将自变量利用偏最小二乘回归处理,提取对因变量影响强的成分,既可以克服变量之间的相关性问题,又可以降低神经网络的输入维数;利用神经网络建模可以较好地解决非线性问题.实例表明本预测模型的拟合和预测精度均较好.
The urban life-water quantity is influenced by many correlative factors. The paper establishes the model for the urban life-water quantity prediction by means of combining neural network with the partial least squares method. Dealt with independent variables by the partial least squares method, it can not only solve the relationship between independent variables but also reduce the input dimensions in neural network model which can solve the non-linear problem better. The result of an example shows that the prediction and forecasting orecision are preferable.
出处
《华中科技大学学报（城市科学版）》
CAS
2006年第3期20-22,27,共4页
Journal of Huazhong University of Science and Technology
基金
国家863计划资助项目(2002AA2Z4291)
河南省高校杰出科研人才创新工程资助项目(HAIPURT)(2005KYCX015)
关键词
偏最小二乘回归
神经网络
预测模型
城市生活用水量
partial least squares method
neural network
forecasting model
urban life-water quantity
