Distributed nonlinear regression using in-network processing with multiple Gaussian kernels

In this paper, we propose the use of multiple Gaussian kernels for distributed nonlinear regression or system identification tasks by a network of nodes. By employing multiple kernels in the estimation process we increase the degree of freedom and thus, the ability to reconstruct nonlinear functions. For this, we extend the so-called KDiCE algorithm, which allows a distributed regression of nonlinear functions but uses a single kernel only, to multiple kernels. We corroborate our proposed scheme by numerical evaluations for the reconstruction of nonlinear functions both static and time-varying. We achieve performance gains for both cases, in particular for the tracking of a time-varying nonlinear function.