Year: 2023
Type: conference-paper
Abstract: In response to the shortcomings of manually adjusting parameters in the variable step size LMS algorithm and the contradiction between convergence speed and steady-state error performance, a variable step size LMS algorithm based on improved Particle Swarm Optimization (PSO) is proposed, namely the GPSO-LMS algorithm. This algorithm first improves the traditional PSO algorithm by constructing a fitness function based on the error between the filter output and the expected signal, and constructing a nonlinear decreasing inertia weight using the population extremum of each iteration; Secondly, the GPSO algorithm is used to automatically optimize the step size of each iteration of the LMS algorithm, so that the optimal step size can be used for each iteration of the LMS algorithm, effectively balancing the contradiction between convergence speed and steady-state error performance. Simulation experiments have shown that the proposed algorithm has faster convergence speed and smaller steady-state error compared with traditional LMS algorithm, Sigmoid function based variable step LMS algorithm (SVS-LMS) and its improved algorithms.
Authors: Yanling Li, Jianwei Zhan, Hui Zhang, Dong Wang
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4392084624
