Variable individual step-size subband adaptive filtering algorithm

• Published in: Electronics letters Vol. 50; no. 3; pp. 177 - 178
• Main Authors: Seo, Ji-Hye, Park, PooGyeon
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 30.01.2014; Institution of Engineering and Technology; John Wiley & Sons, Inc
• Subjects: Adaptive filters; Algorithms; Applied sciences; Coding, codes; Convergence; convergence rate; Derivation; Detection, estimation, filtering, equalization, prediction; Deviation; Exact sciences and technology; excited input signals; Information and communications; Information, signal and communications theory; input vector; Mathematical analysis; mean‐square deviation; minimisation; MSD minimisation; Norms; regularisation effect; Signal and communications theory; Signal, noise; steady‐state estimation error; Telecommunications and information theory; variable individual step‐size subband adaptive filtering algorithm; Vectors (mathematics); MSD minimisation; mean-square deviation; regularisation effect; adaptive filters; variable individual step-size subband adaptive filtering algorithm; input vector; excited input signals; minimisation; convergence rate; steady-state estimation error; Estimation error; Subband decomposition; Convergence rate; Subband; Adaptive filter; State estimation; Steady state; Numerical convergence
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2013.3508

A subband adaptive filtering algorithm is proposed which improves its performance by adjusting step sizes. The proposed algorithm derives the individual step sizes for each subband instead of using a common step size for multiple subbands. The derivation of the step sizes is based on the mean-square deviation minimisation in order to achieve the fastest convergence at the instant. Furthermore, the individual step sizes contain the squared norm of the input vector, hence it leads to the regularisation effect that helps the algorithm work well in the case of badly excited input signals. The simulation results show that the proposed algorithm achieves a faster convergence rate and a smaller steady-state estimation error than the existing algorithms.