Neural convolutional decoders in the satellite channel

Cheolwoo You, Daesik Hong

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

The Neural Convolutional Decoders (NCD) have been used as an alternative for decoding convolutional codes. The motivation of the NCD is to reduce the hardware complexity of the conventional convolutional decoders and maintain the performance. To show the role of the nonlinearity of the neural networks, simulations are performed under the satellite channel that has the nonlinear distortion. We restrict our attention to the case of coherent QPSK modulation. In this case, the neural networks can learn the nonlinear distortion of the satellite channel including the filtering effects and the nonlinear effects of the traveling-wave tube (TWT) amplifiers. In result, the performance of the NCD with a simple structure is almost equal to that of the soft decision Viterbi decoder for the systematic code with 32-bit paths which need 128-bit memory storage. And, the performance difference between the NCD for the systematic code and the soft decision Viterbi decoder for the nonsystematic code is about 1.0 dB and nearly identical to that caused by the dissimilarity of the error-correcting ability in two codes. Therefore, if we could efficiently train the NCD for the nonsystematic codes, the NCD would perform as well as the soft decision Viterbi decoder for the nonsystematic code.

Original languageEnglish
Pages443-448
Number of pages6
Publication statusPublished - 1995 Dec 1
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: 1995 Nov 271995 Dec 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95/11/2795/12/1

Fingerprint

Nonlinear distortion
Satellites
Neural networks
Traveling wave tubes
Convolutional codes
Quadrature phase shift keying
Decoding
Modulation
Hardware
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Software

Cite this

You, C., & Hong, D. (1995). Neural convolutional decoders in the satellite channel. 443-448. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .
You, Cheolwoo ; Hong, Daesik. / Neural convolutional decoders in the satellite channel. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .6 p.
@conference{097963a0bd6b46b88b0d546d1835754f,
title = "Neural convolutional decoders in the satellite channel",
abstract = "The Neural Convolutional Decoders (NCD) have been used as an alternative for decoding convolutional codes. The motivation of the NCD is to reduce the hardware complexity of the conventional convolutional decoders and maintain the performance. To show the role of the nonlinearity of the neural networks, simulations are performed under the satellite channel that has the nonlinear distortion. We restrict our attention to the case of coherent QPSK modulation. In this case, the neural networks can learn the nonlinear distortion of the satellite channel including the filtering effects and the nonlinear effects of the traveling-wave tube (TWT) amplifiers. In result, the performance of the NCD with a simple structure is almost equal to that of the soft decision Viterbi decoder for the systematic code with 32-bit paths which need 128-bit memory storage. And, the performance difference between the NCD for the systematic code and the soft decision Viterbi decoder for the nonsystematic code is about 1.0 dB and nearly identical to that caused by the dissimilarity of the error-correcting ability in two codes. Therefore, if we could efficiently train the NCD for the nonsystematic codes, the NCD would perform as well as the soft decision Viterbi decoder for the nonsystematic code.",
author = "Cheolwoo You and Daesik Hong",
year = "1995",
month = "12",
day = "1",
language = "English",
pages = "443--448",
note = "Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) ; Conference date: 27-11-1995 Through 01-12-1995",

}

You, C & Hong, D 1995, 'Neural convolutional decoders in the satellite channel' Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95/11/27 - 95/12/1, pp. 443-448.

Neural convolutional decoders in the satellite channel. / You, Cheolwoo; Hong, Daesik.

1995. 443-448 Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Neural convolutional decoders in the satellite channel

AU - You, Cheolwoo

AU - Hong, Daesik

PY - 1995/12/1

Y1 - 1995/12/1

N2 - The Neural Convolutional Decoders (NCD) have been used as an alternative for decoding convolutional codes. The motivation of the NCD is to reduce the hardware complexity of the conventional convolutional decoders and maintain the performance. To show the role of the nonlinearity of the neural networks, simulations are performed under the satellite channel that has the nonlinear distortion. We restrict our attention to the case of coherent QPSK modulation. In this case, the neural networks can learn the nonlinear distortion of the satellite channel including the filtering effects and the nonlinear effects of the traveling-wave tube (TWT) amplifiers. In result, the performance of the NCD with a simple structure is almost equal to that of the soft decision Viterbi decoder for the systematic code with 32-bit paths which need 128-bit memory storage. And, the performance difference between the NCD for the systematic code and the soft decision Viterbi decoder for the nonsystematic code is about 1.0 dB and nearly identical to that caused by the dissimilarity of the error-correcting ability in two codes. Therefore, if we could efficiently train the NCD for the nonsystematic codes, the NCD would perform as well as the soft decision Viterbi decoder for the nonsystematic code.

AB - The Neural Convolutional Decoders (NCD) have been used as an alternative for decoding convolutional codes. The motivation of the NCD is to reduce the hardware complexity of the conventional convolutional decoders and maintain the performance. To show the role of the nonlinearity of the neural networks, simulations are performed under the satellite channel that has the nonlinear distortion. We restrict our attention to the case of coherent QPSK modulation. In this case, the neural networks can learn the nonlinear distortion of the satellite channel including the filtering effects and the nonlinear effects of the traveling-wave tube (TWT) amplifiers. In result, the performance of the NCD with a simple structure is almost equal to that of the soft decision Viterbi decoder for the systematic code with 32-bit paths which need 128-bit memory storage. And, the performance difference between the NCD for the systematic code and the soft decision Viterbi decoder for the nonsystematic code is about 1.0 dB and nearly identical to that caused by the dissimilarity of the error-correcting ability in two codes. Therefore, if we could efficiently train the NCD for the nonsystematic codes, the NCD would perform as well as the soft decision Viterbi decoder for the nonsystematic code.

UR - http://www.scopus.com/inward/record.url?scp=0029547760&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029547760&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029547760

SP - 443

EP - 448

ER -

You C, Hong D. Neural convolutional decoders in the satellite channel. 1995. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .