Rapid detection of chemical oxygen demand using least square support vector machines

A novel method to rapidly detect COD (Chemical Oxygen Demand) in polluted water with UV (ultra-violet) spectroanalysis is proposed in this paper. This method utilizes an on-line adaptive algorithm based upon LS-SVM (least square support vector machine), which can build adaptive models to predict the COD values of unknown water samples quickly and accurately. Practical application shows that this adaptive algorithm can build better estimation models than the traditional modeling techniques, such as MLR (multivariate linear regression), PLS (partial least square regression) and BPNN (back-propagation neural network) in terms of various statistical performance indices. Meanwhile, the new COD model shows a good correlation between COD estimated values and COD analysis values.