Byungjun Kim, Sathyanarayanan, V., Mecklenbräuker, C., & Gerstoft, P. (2023). Deep Learning based OFDM Modulation Classification without Symbol-level Synchronization. In Proceedings of the 2023 International Conference on Acoustics, Speech and Signal Processing. ICASSP 2023, Rhodos, Greece. IEEE. http://hdl.handle.net/20.500.12708/187133
E389-02 - Forschungsbereich Wireless Communications E389 - Institute of Telecommunications
-
Erschienen in:
Proceedings of the 2023 International Conference on Acoustics, Speech and Signal Processing
-
ISBN:
979-8-3503-0261-5
-
Datum (veröffentlicht):
4-Jun-2023
-
Veranstaltungsname:
ICASSP 2023
en
Veranstaltungszeitraum:
4-Jun-2023 - 10-Jun-2023
-
Veranstaltungsort:
Rhodos, Griechenland
-
Umfang:
5
-
Verlag:
IEEE, Piscataway
-
Peer Reviewed:
Ja
-
Keywords:
Modulation Classification
en
Abstract:
Deep learning (DL)-based modulation classification of incoherently received orthogonal frequency division multiplexing (OFDM) signals is studied. We propose a novel preprocess- ing algorithm to build features characterizing the modulation of OFDM signals, which are insensitive to synchronization error. With obtained features, pilot subcarrier indices used for CFO correction may also be estimated. The features obtained with the proposed algorithm are classified with a convolutional neural network (CNN)-based classifier. We have evaluated classification performance with simulated and hardware- generated data. Using these features, the modulation classi- fier outperforms existing DL-based classifiers which assume symbol-level synchronization with up to 25% classification accuracy performance gain.
en
Forschungsschwerpunkte:
Telecommunication: 50% Information Systems Engineering: 50%
