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

Blind modulation identification is essential for 6G's RAN-agnosticcommunications, which identifies the modulation type of an incompatiblewireless signal without any prior knowledge. Nowadays, research on blindmodulation identification relies on deep convolutional networks that deal witha received signal's raw I/Q samples, but they mostly are limited tosingle-carrier signal recognition thus not pragmatic for identifyingspectro-temporal OFDM/OFDMA signals whose modulation varies with time andfrequency. Therefore, this paper proposes RiSi, a semantic segmentation neuralnetwork designed to work on OFDMA's spectrograms, by replacing vanillaDeepLabV3+'s 2D convolutions with 'flattened' convolutions to enforce thetime-frequency orthogonality constraint and to achieve the grid-like pattern ofOFDMA's resource blocks, and by introducing three-channel inputs consisting ofI/Q/amplitude. Then, we synthesized a realistic and effective datasetconsisting of OFDMA signals with various channel impairments to train theproposed network. Moreover, we treated varying communication parameters asdifferent domains to apply domain generalization methods, to enhance ourmodel's adaptability to diverse communication environments. Extensiveevaluation shows that RiSi's modulation identification accuracy reaches 86%averaged over four modulation types (BPSK, QPSK, 16-QAM, 64-QAM), while itsdomain generalization performance for unseen data has been also shown to bereliable.

RiSi: Spectro-temporal RAN-agnostic Modulation Identification for OFDMA Signals