为了建立基于光谱的实时监测模型，本文给出了一种基于移动窗口策略的的偏最小二乘算法。
In order to establish real - time model of spectral measurement, a algorithm called Moving Windows Partial Least Squares algorithm is proposed.
将主成分回归(PCR)和偏最小二乘回归(PLSR)的方法引入RBF网络中，提出了分别采用这两种方法确定网络权重的算法。
The Principal Component Regression (PCR) and Partial Least Square Regression (PLSR) methods are applied to determine the weight of the RBF networks with certain good results.
为进一步提高回归算法的色彩校正精度，提出一个基于核偏最小二乘回归的局部迭代算法。
To further improve the calibration precision of the previous regression algorithms, an iterative local algorithm of color calibration based on kernel partial least squares regression is proposed.
应用推荐