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

Artificial intelligence (AI) based downlink channel state information (CSI)prediction for frequency division duplexing (FDD) massive multiple-inputmultiple-output (MIMO) systems has attracted growing attention recently.However, existing works focus on the downlink CSI prediction for the usersunder a given environment and is hard to adapt to users in new environmentespecially when labeled data is limited. To address this issue, we formulatethe downlink channel prediction as a deep transfer learning (DTL) problem,where each learning task aims to predict the downlink CSI from the uplink CSIfor one single environment. Specifically, we develop the direct-transferalgorithm based on the fully-connected neural network architecture, where thenetwork is trained on the data from all previous environments in the manner ofclassical deep learning and is then fine-tuned for new environments. To furtherimprove the transfer efficiency, we propose the meta-learning algorithm thattrains the network by alternating inner-task and across-task updates and thenadapts to a new environment with a small number of labeled data. Simulationresults show that the direct-transfer algorithm achieves better performancethan the deep learning algorithm, which implies that the transfer learningbenefits the downlink channel prediction in new environments. Moreover, themeta-learning algorithm significantly outperforms the direct-transfer algorithmin terms of both prediction accuracy and stability, which validates itseffectiveness and superiority.

Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO Systems