Title :
Equally constrained affine projection algorithm
Author :
Jo, SungEun ; Kim, Sang Woo ; Park, Tae Joon
Author_Institution :
Dept. of Electron. & Electr. Eng., Pohang Univ. of Sci. & Technol., South Korea
Abstract :
A novel version of the constrained affine projection (CAP) algorithm, referred to as the equally constrained affine projection (ECAP) algorithm is derived simultaneously to satisfy both the linear constraints and the residual conditions by means of the Lagrange method. In a geometrical view, the ECAP algorithm is interpreted to show a one-step optimization even with the parameter perturbation that is orthogonal to the constraint hyperplane, while the CAP algorithm yields two steps to reach at the optimal point. An adaptive filtering simulation with linear constraints depicts its behavior.
Keywords :
adaptive filters; array signal processing; filtering theory; optimisation; ECAP algorithm; Lagrange method; adaptive filtering; equally constrained affine projection; linear constraint; one-step optimization; Adaptive arrays; Adaptive filters; Array signal processing; Constraint optimization; Convergence; Interference cancellation; Interference constraints; Lagrangian functions; Projection algorithms; Vectors;
Conference_Titel :
Signals, Systems and Computers, 2004. Conference Record of the Thirty-Eighth Asilomar Conference on
Print_ISBN :
0-7803-8622-1
DOI :
10.1109/ACSSC.2004.1399280