内容简介：

In this talk, we present a data-driven method for identification of high-dimensional additive nonlinear dynamical systems with little a priori information. In particular, we develop a two-step method for variable selection to determine contributing additive functions and to remove non-contributing ones from the underlying nonlinear system. At the first step, we estimate each additive function by kernel-based nonparametric identification approaches without suffering from the curse of dimensionality. At the second step, we utilize a nonnegative garrote estimator to identify which additive functions are nonzero by use of the obtained nonparametric estimates of each function. We show that the proposed variable selection method can find the correct variables with probability one under weak conditions. We present simulation examples to demonstrate the efficiency of the proposed data-driven identification method.

报告人简介：

Wei Xing Zheng received the B.Sc. degree in Applied Mathematics in 1982, the M.Sc. degree in Control Theory and Applications in 1984, and the PhD degree in Control Theory and Applications in 1989, all from Southeast University, Nanjing, China. Currently he holds the rank of Full Professor at Western Sydney University, Australia. Dr. Zheng is a Fellow of IEEE and was thrice named as a Thomson Reuters ISI Highly Cited Researcher in 2015, 2016 and 2017. Currently, he serves as Associate Editor for Automatica, IEEE Transactions on Automatic Control, IEEE Transactions on Cybernetics, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Control of Network Systems, and other scholarly journals.
 
欢迎广大师生光临