Subband adaptive filtering with \(l_1\)-norm constraint for sparse system identification (Q474425)

Summary: This paper presents a new approach of the normalized subband adaptive filter (NSAF) which directly exploits the sparsity condition of an underlying system for sparse system identification. The proposed NSAF integrates a weighted \(l_1\)-norm constraint into the cost function of the NSAF algorithm. To get the optimum solution of the weighted \(l_1\)-norm regularized cost function, a subgradient calculus is employed, resulting in a stochastic gradient based update recursion of the weighted \(l_1\)-norm regularized NSAF. The choice of distinct weighted \(l_1\)-norm regularization leads to two versions of the \(l_1\)-norm regularized NSAF. Numerical results clearly indicate the superior convergence of the \(l_1\)-norm regularized NSAFs over the classical NSAF especially when identifying a sparse system.