Mean Mixed-norm Algorithm Research Articles

Nonnegative least mean mixed-norm algorithm: Analysis and performance

Adaptive filter has been successfully considered for the system identifications. Under some circumstances, due to the unknown system's intrinsic characteristics, nonnegativity is an desired constraint imposed on the parameters to be estimated, which will affect the performance of devised adaptive filtering. This paper studies a nonnegative least mean mixed-norm algorithm (NNLMMN) with fourth-order moment error and square-order error, which are jointly considered and devised to design a new cost function for dealing with the system identification problems with a nonnegativity constraint in mixed Gaussian noise environment. We also provide the theoretical behavior prediction of the mean weight, the transient analysis and steady-state excess mean square error (EMSE) of the NNLMMN algorithm. Experiment results show that the superior performance of the NNLMMN algorithm and verify the effectiveness of the presented theory analysis.

Transform Domain Based Multi-Channel Noise Cancellation Based on Adaptive Decorrelation and Least Mean Mixed-Norm Algorithm

Transform Domain Based Multi-Channel Noise Cancellation Based on Adaptive Decorrelation and Least Mean Mixed-Norm Algorithm

Adaptive echo cancellation using least mean mixed-norm algorithm

A novel algorithm for echo cancellation is presented in this work. The algorithm consists of simultaneously applying the least mean square (LMS) algorithm to the near-end section of the echo canceller and the least mean fourth (LMF) algorithm to the far-end section. This new scheme results in a substantial performance improvement over the LMS algorithm and other algorithms.