Title :
The design and performance of a neural network for predicting turbo decoding error with application to hybrid ARQ protocols
Author :
Buckley, Michael E. ; Wicker, Stephen B.
Author_Institution :
Sch. of Electr. Eng., Cornell Univ., Ithaca, NY, USA
fDate :
4/1/2000 12:00:00 AM
Abstract :
It is shown that a neural network can be trained to observe the cross entropy of the outputs of component decoders in a turbo error control system and to accurately predict the presence of errors in the decoded data. The neural network can be used as a trigger for retransmission requests at either the beginning or the conclusion of the decoding process, providing improved reliability and throughput performance at a lower average decoding complexity than turbo decoding with cyclic redundancy check error detection
Keywords :
automatic repeat request; coding errors; entropy; feedforward neural nets; iterative decoding; learning (artificial intelligence); turbo codes; average decoding complexity; component decoder output; correlation; cross entropy; cyclic redundancy check error detection; decoded data errors; decoder iterations; feedforward hidden-layer neural networks; hybrid ARQ protocols; neural network design; neural network performance; reliability; retransmission requests; simulation results; throughput performance; turbo decoding error prediction; turbo error control system; AWGN; Automatic repeat request; Concatenated codes; Convergence; Entropy; Error correction; Iterative decoding; Maximum likelihood decoding; Neural networks; Protocols;
Journal_Title :
Communications, IEEE Transactions on
