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

Channel estimation is one of the key issues in practical massivemultiple-input multiple-output (MIMO) systems. Compared with conventionalestimation algorithms, deep learning (DL) based ones have exhibited greatpotential in terms of performance and complexity. In this paper, an attentionmechanism, exploiting the channel distribution characteristics, is proposed toimprove the estimation accuracy of highly separable channels with narrowangular spread by realizing the "divide-and-conquer" policy. Specifically, weintroduce a novel attention-aided DL channel estimation framework forconventional massive MIMO systems and devise an embedding method to effectivelyintegrate the attention mechanism into the fully connected neural network forthe hybrid analog-digital (HAD) architecture. Simulation results show that inboth scenarios, the channel estimation performance is significantly improvedwith the aid of attention at the cost of small complexity overhead.Furthermore, strong robustness under different system and channel parameterscan be achieved by the proposed approach, which further strengthens itspractical value. We also investigate the distributions of learned attentionmaps to reveal the role of attention, which endows the proposed approach with acertain degree of interpretability.

An Attention-Aided Deep Learning Framework for Massive MIMO Channel Estimation