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

Modulation classification, an intermediate process between signal detectionand demodulation in a physical layer, is now attracting more interest to thecognitive radio field, wherein the performance is powered by artificialintelligence algorithms. However, most existing conventional approaches posethe obstacle of effectively learning weakly discriminative modulation patterns.This paper proposes a robust modulation classification method by takingadvantage of deep learning to capture the meaningful information of modulationsignal at multi-scale feature representations. To this end, a novelarchitecture of convolutional neural network, namely Chain-Net, is developedwith various asymmetric kernels organized in two processing flows andassociated via depth-wise concatenation and element-wise addition foroptimizing feature utilization. The network is evaluated on a big dataset of 14challenging modulation formats, including analog and high-order digitaltechniques. The simulation results demonstrate that Chain-Net robustlyclassifies the modulation of radio signals suffering from a synthetic channeldeterioration and further performs better than other deep networks.

Chain-Net: Learning Deep Model for Modulation Classification Under Synthetic Channel Impairment