Sewage COD measurement by ultraviolet scanning instrument using partial least squares
Partial least squares (PLS) regression is one of the most popular multivariate calibration methods in chemometrics which were widely used in environment detection field like water quality monitoring in recent years. In this paper, we used self-fabricated instrument to detect water samples. PLS is employed to model the relationship between the ultraviolet absorbance and the chemical oxygen demand (COD). We use the predicted residual errors sum of squares of the leave-one-out cross-validation (PRESS_(CV)) as the criterion to select the optimal number of PLS factors. Then the prediction has been compared with that of the common multiple linear regression (MLR) and artificial neural network (ANN). The results show that PLS has the best accuracy of prediction.
Chemical Oxygen Demand (COD) Partial Least Squares (PLS) Chemometric
Xiangdong Zhou Xiaoping Wang
State Key Laboratory of Modern Optical Instrument Zhejiang University Hangzhou, China
国际会议
2010 International Conference on Measurement and Control Engineering(2010年IEEE测量与控制工程国际会议 ICMCE2010)
成都
英文
749-752
2010-11-16（万方平台首次上网日期，不代表论文的发表时间）