Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
A Fast Deep-Learning Signal Detection Architecture for the Short-wave Band
Ist Teil von
Journal of physics. Conference series, 2020-09, Vol.1646 (1), p.12003
Ort / Verlag
IOP Publishing
Erscheinungsjahr
2020
Link zum Volltext
Quelle
EZB Electronic Journals Library
Beschreibungen/Notizen
Wideband signal detection plays an important role in wireless communication systems. In recent years, deep learning (DL) has been introduced, and many trial efforts have been posed. In this paper, a fast deep-learning signal detection architecture is proposed for the short-wave band, which consists of the GPU-based Down Digital Converter (DDC), the DL-based signal detector, and the signal data viewer & recorder. Wideband signal data are taken directly as the input, and detected signals are automatically recorded as the output of the architecture. Experimental results suggest that our architecture is capable of detecting signals in the whole short-wave band in quasi-real-time, and specifically, with single GPU device.