Comparison of adaptive algorithms for single-trial event-related potentials extraction
Mahmoud Boudiaf, Moncef Benkherrat, Khaled Mansouri · 2017 Intelligent Systems Conference (IntelliSys) · 2017
In this paper, the Recursive Least Square, the Least Mean Square and a Variable Step Size Least Mean Square algorithms, used with adaptive linear combiner based on the Hermite functions, are compared for single-trials event-related potential extraction. The performances of the algorithms are evaluated and compared in term of rate of convergence, steady-state error and tracking ability. The simulation results show that the Variable Step Size Least Mean Square algorithm outperforms the two other algorithms in terms of convergence rate and tracking ability.