Control of chaotic system based on least squares support vector machine modeling
基于最小二乘支持向量机建模的混沌系统控制

A new approach to control chaotic systems is presented. This control approach is based on least squares support vector machines (LS_SVMs) modeling. Compared wit h the feed_forward neural networks, the LS_SVM possesses prominent advantages: o ver fitting is unlikely to occur by employing structural risk minimization crite rion, the global optimal solution can be uniquely obtained owing to the fact tha t its training is performed through the solution of a set of linear equations. A lso, the LS_SVM need not determine its topology in advance, which can be automat ically obtained when the training process ends. Thus the effectiveness and feasi bility of this method are found to be better than those of the feed_forward neur al networks. The method does not needs an analytic model, and it is still effect ive when there are measurement noises. The chaotic systems with one_and two_ dim ensional nonlinear maps are used as examples for demonstration.