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

To support the modern machine-type communications, a crucial task during therandom access phase is device activity detection, which is to detect the activedevices from a large number of potential devices based on the received signalat the access point. By utilizing the statistical properties of the channel,state-of-the-art covariance based methods have been demonstrated to achievebetter activity detection performance than compressed sensing based methods.However, covariance based methods require to solve a high dimensional nonconvexoptimization problem by updating the estimate of the activity status of eachdevice sequentially. Since the number of updates is proportional to the devicenumber, the computational complexity and delay make the iterative updatesdifficult for real-time implementation especially when the device number scalesup. Inspired by the success of deep learning for real-time inference, thispaper proposes a learning based method with a customized heterogeneoustransformer architecture for device activity detection. By adopting anattention mechanism in the architecture design, the proposed method is able toextract the relevance between device pilots and received signal, is permutationequivariant with respect to devices, and is scale adaptable to differentnumbers of devices. Simulation results demonstrate that the proposed methodachieves better activity detection performance with much shorter computationtime than state-of-the-art covariance approach, and generalizes well todifferent numbers of devices, BS-antennas, and different signal-to-noiseratios.

Heterogeneous Transformer: A Scale Adaptable Neural Network Architecture for Device Activity Detection