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

Dynamic spectrum access (DSA) benefits from detection and classification ofinterference sources including in-network users, out-network users, and jammersthat may all coexist in a wireless network. We present a deep learning basedsignal (modulation) classification solution in a realistic wireless networksetting, where 1) signal types may change over time; 2) some signal types maybe unknown for which there is no training data; 3) signals may be spoofed suchas the smart jammers replaying other signal types; and 4) different signaltypes may be superimposed due to the interference from concurrenttransmissions. For case 1, we apply continual learning and train aConvolutional Neural Network (CNN) using an Elastic Weight Consolidation (EWC)based loss. For case 2, we detect unknown signals via outlier detection appliedto the outputs of convolutional layers using Minimum Covariance Determinant(MCD) and k-means clustering methods. For case 3, we extend the CNN structureto capture phase shifts due to radio hardware effects to identify the spoofingsignal sources. For case 4, we apply blind source separation using IndependentComponent Analysis (ICA) to separate interfering signals. We utilize the signalclassification results in a distributed scheduling protocol, where in-network(secondary) users employ signal classification scores to make channel accessdecisions and share the spectrum with each other while avoiding interferencewith out-network (primary) users and jammers. Compared with benchmarkTDMA-based schemes, we show that distributed scheduling constructed upon signalclassification results provides major improvements to in-network userthroughput and out-network user success ratio.

Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments