Neural networks applications for CDMA systems in non-Gaussian multi-path channels

Hilal, Hasan Abu

doi:10.1016/j.aeue.2017.01.006

Cited by 11 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the performance of the system is not still well enough for practical use and there is a need for a more sophisticated method. In this manner, neural networks and deep learning algorithms are evaluated to improve the performance of the IN filters [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Decoder with an Adaptive Fuzzy Logic Filter for Single-User Millimeter Wave Systems Under Impulsive Noise

Mulla

Rızaner

Ulusoy

2021

Preprint

View full text Add to dashboard Cite

The conventional millimeter wave systems are mostly designed to operate only for the Gaussian noise model. Although this model simplifies the noise removal problem, recent research findings state that a mixture noise model with additive impulsive noise is a more realistic approximation for millimeter wave channels. In this paper, we propose a novel approach to eliminate the impulsive noise effects on single-user millimeter wave massive multiple-input-multiple-output system using an adaptive fuzzy logic filter. Hence, a fuzzy median filter is applied to the system and it is aimed to minimize the effects of the impulsive noise by ordering samples based on fuzzy rank. Simulation results show that the proposed filter successfully eliminates the impulsive noise effects and achieves a better bit error rate and spectral efficiency performance than the competing methods in the literature while also working efficiently in Gaussian noise.

show abstract

Section: Introductionmentioning

confidence: 99%