Blind Identification Of Full-Sized Volterra Sysytems In SOS Domain

For a single-input single-output (SISO) Volterra system with finite order and memory, excited by unobservable i.i.d. stationary random sequences, it is known that subclasses of sparse Volterra systems are identifiable blindly in the second-order statistics (SOS) or higher-order statistics (HOS) domain under some conditions. In this paper, we show that, given sufficient conditions, a full-sized single-input multi-output (SIMO) Volterra system, structured by temporally or spatially oversampling its SISO counterpart, can be fully blindly identified in the SOS domain. Numerical simulations demonstrate the validity and usefulness of the proposed method