Robust regression and outlier detection
Robust regression and outlier detection
Adaptive filter theory (2nd ed.)
Adaptive filter theory (2nd ed.)
Systolic block Householder transformation for RLS algorithm withtwo-level pipelined implementation
IEEE Transactions on Signal Processing
Incremental Adaptive Strategies Over Distributed Networks
IEEE Transactions on Signal Processing
Diffusion Recursive Least-Squares for Distributed Estimation Over Adaptive Networks
IEEE Transactions on Signal Processing
Preliminary Study on Wilcoxon Learning Machines
IEEE Transactions on Neural Networks
Hi-index | 0.08 |
When outliers are present in the desired data, the conventional distributed adaptive estimation algorithms exhibit poor performance. To alleviate this shortcoming a novel distributed robust incremental strategy based on QR decomposition and the Wilcoxon score is proposed which convergence speed is faster than the other previous techniques. To demonstrate the potential of this algorithm simulation study is carried out for the distributed estimation of parameters in the presence of weak to strong outliers in the desired data. The results show that the performance of the new algorithm is robust against outliers compared to conventional incremental RLS algorithm. Further to achieve low communication overhead, a new scheme is introduced and its performance has been assessed through simulation study. It is observed that the proposed scheme even though exhibits slightly inferior performance but offers substantially reduction in terms of communication overhead.