A neural network for predicting decoder error in turbo decoders

Author

Buckley, M. Eoin ; Wicker, Stephen B.

Author_Institution

Sch. of Electr. Eng., Cornell Univ., Ithaca, NY, USA

Volume

3

Issue

5

fYear

1999

fDate

5/1/1999 12:00:00 AM

Firstpage

145

Lastpage

147

Abstract

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.

Keywords

automatic repeat request; coding errors; computational complexity; decoding; entropy; learning (artificial intelligence); neural nets; protocols; turbo codes; ARQ protocols; CRC error detection; average decoding complexity; component decoder outputs; cross entropy; decoder error prediction; neural network; reliability performance; retransmission requests; training; turbo decoders; turbo-decoded data; AWGN; Computational complexity; Convergence; Cyclic redundancy check; Entropy; Intelligent networks; Iterative decoding; Multidimensional systems; Neural networks; Turbo codes;

fLanguage

English

Journal_Title

Communications Letters, IEEE

Publisher

ieee

ISSN

1089-7798

Type

jour

DOI

10.1109/4234.766850

Filename

766850