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

Reliable and fast channel estimation is crucial for next-generation wirelessnetworks supporting a wide range of vehicular and low-latency services.Recently, deep learning (DL) based channel estimation has been explored as anefficient alternative to conventional least-square (LS) and linear minimum meansquare error (LMMSE) approaches. Most of these DL approaches have not beenrealized on system-on-chip (SoC), and preliminary study shows that theircomplexity exceeds the complexity of the entire physical layer (PHY). The highlatency of DL is another concern. This paper considers the design andimplementation of deep neural network (DNN) augmented LS-based channelestimation (LSDNN) for preamble-based orthogonal frequency-divisionmultiplexing (OFDM) physical layer (PHY) on SoC. We demonstrate the gain inperformance compared to the conventional LS and LMMSE approaches. Viasoftware-hardware co-design, word-length optimization, and reconfigurablearchitectures, we demonstrate the superiority of the LSDNN over the LS andLMMSE for a wide range of signal-to-noise ratio (SNR), number of pilots,preamble types, and wireless channels. Further, we evaluate the performance,power, and area (PPA) of the LS and LSDNN application-specific integratedcircuit (ASIC) implementations in 45 nm technology. We demonstrate thatword-length optimization can substantially improve PPA for the proposedarchitecture in ASIC implementations.

Deep Neural Network Augmented Wireless Channel Estimation for Preamble-based OFDM PHY on Zynq System on Chip