Parallel deflation with alphabet-based criteria for blind source extraction

Abstract

Blind source extraction aims at estimating the source signals which appear mixed at the output of a sensor array. A novel approach to blind source extraction is presented in this contribution, which exploits the discrete character (finite alphabet property) of digital modulations in the case where sources with different alphabet exist. An alphabet polynomial fitting (APF) criterion matched to the specific signal constellation is employed to extract, through deflation, the sources with the same modulation. Using the appropriate APF criteria, the sources with different modulations can be extracted in parallel. This new concept, referred to as parallel deflation, presents the potential of reducing both the signal estimation errors that typically accumulate in the conventional deflationary approach and the spatiotemporal diversity required for a satisfactory source extraction. In addition, APF criteria can be optimized through a cost-effective optimal step-size technique that can escape local extrema.

Deterministic Blind Separation of Sources Having Different Symbol Rates Using Tensor-Based Parallel Deflation

“…more sources than sensors). According to condition (11), if M j ≥ P and L ≥ P , then I = 2 sensors are enough to blindly separate P sources.…”

“…By applying successive canonical decompositions (CanD) [9] of these tensors, we obtain successive estimates of the related sources along with a mixture estimate. This approach can be connected to the parallel deflation method proposed in [10,11]. This paper is organized as follows.…”