English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Wireless links using massive MIMO transceivers are vital for next generationwireless communications networks networks. Precoding in Massive MIMOtransmission requires accurate downlink channel state information (CSI). Manyrecent works have effectively applied deep learning (DL) to jointly trainUE-side compression networks for delay domain CSI and a BS-side decodingscheme. Vitally, these works assume that the full delay domain CSI is availableat the UE, but in reality, the UE must estimate the delay domain based on alimited number of frequency domain pilots. In this work, we propose a linearpilot-to-delay (P2D) estimator that transforms sparse frequency pilots to thetruncated delay CSI. We show that the P2D estimator is accurate under frequencydownsampling, and we demonstrate that the P2D estimate can be effectivelyutilized with existing autoencoder-based CSI estimation networks. In additionto accounting for pilot-based estimates of downlink CSI, we apply unrolledoptimization networks to emulate iterative solutions to compressed sensing(CS), and we demonstrate better estimation performance than priorautoencoder-based DL networks. Finally, we investigate the efficacy oftrainable CS networks for in a differential encoding network for time-varyingCSI estimation, and we propose a new network, MarkovNet-ISTA-ENet, comprised ofboth a CS network for initial CSI estimation and multiple autoencoders toestimate the error terms. We demonstrate that this heterogeneous network hasbetter asymptotic performance than networks comprised of only one type ofnetwork.

Learning-Based MIMO Channel Estimation under Spectrum Efficient Pilot Allocation and Feedback