A neural network for predicting decoder error in turbo decoders

It is shown that a neural network can be trained to predict the presence of errors in turbo-decoded data. The inputs to the network are samples of the cross entropy of the component decoder outputs at two or more time instants. Such a neural network can be used as a trigger for retransmission reques...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE communications letters 1999-05, Vol.3 (5), p.145-147
Hauptverfasser:	Buckley, M.E., Wicker, S.B.
Format:	Artikel
Sprache:	eng
Schlagworte:	Applied sciences AWGN Complexity Computational complexity Convergence Cyclic redundancy check Decoders Decoding Detection, estimation, filtering, equalization, prediction Electric, optical and optoelectronic circuits Electronics Entropy Error detection Errors Exact sciences and technology Information, signal and communications theory Intelligent networks Iterative decoding Multidimensional systems Networks Neural networks Signal and communications theory Signal, noise Telecommunications and information theory Turbo codes
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	It is shown that a neural network can be trained to predict the presence of errors in turbo-decoded data. The inputs to the network are samples of the cross entropy of the component decoder outputs at two or more time instants. Such a neural network can be used as a trigger for retransmission requests at either the beginning or at the conclusion of the decoding process, providing improved reliability performance and lower average decoding complexity than turbo decoding with CRC error detection.
ISSN:	1089-7798 1558-2558
DOI:	10.1109/4234.766850