Reduced-rank filtering on L1-norm subspaces
Panos P. Markopoulos · 2016
Recent studies in signal processing have unveiled the remarkable outlier-resistance properties of L1-norm subspaces, calculated by means of L1-norm principal component analysis (L1-PCA). In this work, we present for the first time reduced-rank interference-suppressive filtering on L1-norm subspaces of the received signal vectors. Our simulation studies illustrate that the proposed filtering framework allows for successful suppression of coherent interference while, at the same time, it offers sturdy protection against outliers that appear among the training samples.