2015/07/23 by Wael M. Bazzi, Bazzi, Wael M., Amir Rastegarnia +3
Computer Science · Engineering · #Advanced Adaptive Filtering Techniques #Distributed Sensor Networks and Detection Algorithms #FOS: Electrical engineering #Systems and Control (eess.SY) #Target Tracking and Data Fusion in Sensor Networks #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1507.06672
openalex publication_date 2015/07/23 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28
In this paper we consider the issue of reliability of measurements in\ndistributed adaptive estimation problem. To this aim, we assume a sensor\nnetwork with different observation noise variance among the sensors and propose\nnew estimation method based on incremental distributed least mean-square\n(IDLMS) algorithm. The proposed method contains two phases: I) Estimation of\neach sensors observation noise variance, and II) Estimation of the desired\nparameter using the estimated observation variances. To deal with the\nreliability of measurements, in the second phase of the proposed algorithm, the\nstep-size parameter is adjusted for each sensor according to its observation\nnoise variance. As our simulation results show, the proposed algorithm\nconsiderably improves the performance of the IDLMS algorithm in the same\ncondition.\n