Dempster–Shafer theory-based robust least squares support vector machine for stochastic modelling

Noise can be produced from various types of sources with different spectral distributions. This often causes the least squares support vector machine (LS-SVM) to be less effective since the LS-SVM is sensitive to noisy data. In this work, a Dempster–Shafer (D–S) theory-based robust LS-SVM is proposed, which has a more reliable modelling performance under various noise regimes. A distributed LS-SVM is first developed to construct the evidence data set. Fuzzy clustering is then used to construct an evidence base from the data. D–S theory is further used to fuse different pieces of evidence to derive the parameters for the construction of a robust LS-SVM. This robust model can represent the original system well even in the presence of different types of random noise. Case studies are presented to demonstrate the effectiveness of the proposed LS-SVM approach.