Noise-immune SVM classifier with uneven class sizes in wastewater treatment process

A classification algorithm named PCA-SVM is presented, where support vector machine (SVM) theory is combined with principal component analysis (PCA) techniques, which is good at eliminating noise. When training sets with uneven class sizes are used, the result is undesirably biased towards the larger class. The cause and the compensation method are shown in the paper. The numerical experiments for classifying the operational state of the wastewater treatment processes show that the proposed algorithm is effective and has less predicted error.