2015/09/04 by Rangeet Mitra, Vimal Bhatia, Mitra, Rangeet +1
Computer Science · Engineering · #Advanced Adaptive Filtering Techniques #Direction-of-Arrival Estimation Techniques #Distributed #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #Machine Learning (cs.LG) #Parallel #Speech and Audio Processing #Systems and Control (eess.SY) #and Cluster Computing (cs.DC) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1509.01352
openalex publication_date 2015/09/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In a distributed network environment, the diffusion-least mean squares (LMS)\nalgorithm gives faster convergence than the original LMS algorithm. It has also\nbeen observed that, the diffusion-LMS generally outperforms other distributed\nLMS algorithms like spatial LMS and incremental LMS. However, both the original\nLMS and diffusion-LMS are not applicable in non-linear environments where data\nmay not be linearly separable. A variant of LMS called kernel-LMS (KLMS) has\nbeen proposed in the literature for such non-linearities. In this paper, we\npropose kernelised version of diffusion-LMS for non-linear distributed\nenvironments. Simulations show that the proposed approach has superior\nconvergence as compared to algorithms of the same genre. We also introduce a\ntechnique to predict the transient and steady-state behaviour of the proposed\nalgorithm. The techniques proposed in this work (or algorithms of same genre)\ncan be easily extended to distributed parameter estimation applications like\ncooperative spectrum sensing and massive multiple input multiple output (MIMO)\nreceiver design which are potential components for 5G communication systems.\n