Support vector machine for ultraviolet spectroscopic water quality analyzers

How to describe the correlation between the water quality parameter such as chemical oxygen demand (COD), biochemical oxygen demand (BOD), total organic carbon (TOC) and the ultraviolet (UV) spectroscopy is important for the UV water quality analyzers. A novel modeling method based on support vector machine (SVM) is proposed for UV water spectroscopic water quality analyzers in this paper. The estimating model obtained by this method shows obvious improvement in predicting ability and measurement accuracy. The experimental results show the proposed method has obvious advantage over the classical method such as partial least square.