Classification noise detection based SMO algorithm

SMO (Sequential Minimal Optimization) is an outstanding SVM algorithm in efficiency and memory requirements. But it need cross validation to optimize parameters in the mathematical model to avoid the overfitting, which produces too much median classifiers, resulting in the decrease of the stability of algorithm and the increase of training time considerably. In this paper, by introducing the concept of “classification noise”, CNSMO (Classification Noise Detection based SMO algorithm) is proposed. In the CNSMO, an inseparable problem can be converted into a separable problem so that overfitting is not required to be taken into consideration. This makes cross validation can be avoided in the whole algorithm and the stability of the algorithm can be improved. The training time can be saved considerably. The penalty parameter in the CNSMO algorithm can be eliminated so that the model of the CNSMO is much simpler than other SMO algorithms. This paper presents that the proposed algorithm can reduce training time considerably without decreasing prediction accuracy. The effectiveness and efficiency of the CNSMO are demonstrated through experiments on public data sets.