A recurrent neural decoder for convolutional codes

Hamalainen, A.; Henriksson, J.

doi:10.1109/icc.1999.765550

Cited by 31 publications

(19 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed hard decision decoding ANN scheme offers similar or better performance compared with the previously reported ANN decoders as given in ; however, the soft decision decoding scheme outperforms them all. Although like‐to‐like comparison is difficult to make in terms of the complexity because of the differences in the neural architecture, a comparison in overall decoding complexity and the delay can be made.…”

Section: Comparative Study Of the Artificial Neural Network And The Vmentioning

confidence: 59%

“…The Viterbi algorithm (VA) is an efficient method for decoding the convolutional code using the maximum likelihood sequence estimator technique. However, complexity, delay and memory requirement associated with the VA are relatively high and hence a sub‐optimal decoding of the convolutional code using the artificial neural network (ANN) has been intensively studied . ANN, as an alternative to the VA, has been suggested because of the low complexity, parallel processing, adaptability and fault tolerance capabilities.…”

Section: Introductionmentioning

confidence: 99%

“…A number of structures and approaches have been proposed to improve the performance of ANN as a convolutional decoder. They can broadly be classified into three classes: (i) a feedforward network trained using minimum Hamming distance codewords , (ii) a recurrent neural network (RNN) with iterative decoding , and (iii) a fixed‐weight training‐free neural network .…”

Section: Introductionmentioning

confidence: 99%

“…In the second approach, the decoding problem is formulated as a noise energy function minimization problem where the gradient descent algorithm can be employed to solve it . An RNN with the iterative decoding is applied to decode 1 ∕ N convolutional code using the gradient descent algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Adaptive ‘soft’ sliding block decoding of convolutional code using the artificial neural network

Rajbhandari

Ghassemlooy

Angelova

2012

Trans. Emerging Tel. Tech.

View full text Add to dashboard Cite

A Viterbi algorithm (VA) is the optimal decoding strategy for the convolutional code. The Viterbi algorithm is complex and requires a large memory and delay. In this paper, an alternative sub‐optimal decoder based on the artificial neural network (ANN) is proposed and studied using a sliding block decoding algorithm. The ANN is trained in a supervised manner and the system parameters are optimised using computer simulations for the optimum performance. Comparative study with the Viterbi decoder is carried out. The performance of the ANN decoder is found to be comparable to the Viterbi ‘soft’ decoding with much reduced decoding length. The key advantages of the proposed ANN decoder compared with other ANN decoders are the reduced decoding and training length, adaptive decoding, no iteration required and possibility of parallel decoding. Copyright © 2012 John Wiley & Sons, Ltd.

show abstract

Section: Comparative Study Of the Artificial Neural Network And The Vmentioning

confidence: 59%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive ‘soft’ sliding block decoding of convolutional code using the artificial neural network

Rajbhandari

Ghassemlooy

Angelova

2012

Trans. Emerging Tel. Tech.

View full text Add to dashboard Cite

show abstract

“…[1], [2]). With the recent success of deep learning in wide areas of applications (including natural language processing, image processing, autonomous driving, financial investment, computer games, and many others), neural networks have regained increasing interests in the domain of communicational signal processing (e.g.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Learning for MU-SIMO Joint Transmitter and Noncoherent Receiver Design

Xue

Yi³

et al. 2019

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

Abstract-This work aims to handle the joint transmitter and noncoherent receiver optimization for multiuser single-input multiple-output (MU-SIMO) communications through unsupervised deep learning. It is shown that MU-SIMO can be modeled as a deep neural network with three essential layers, which include a partially-connected linear layer for joint multiuser waveform design at the transmitter side, and two nonlinear layers for the noncoherent signal detection. The proposed approach demonstrates remarkable MU-SIMO noncoherent communication performance in Rayleigh fading channels.Index Terms-Unsupervised deep learning, joint transmitter and receiver design, noncoherent detection, multiuser single-input and multiple-output (MU-SIMO).

show abstract

Performance Analysis of L2 and L5 CNAV Broadcast Ephemeris for Orbit Calculation

et al. 2015

View full text Add to dashboard Cite

Ephemeris error is a limiting factor in GPS position accuracy. The newly introduced GPS Civil Navigation (CNAV) broadcast message, an upgraded version of the legacy NAV message, is designed to provide users with more precise satellite orbit and timing parameters. A CNAV broadcast test was conducted in 2013 on the L2C and L5 bands. Since April 2014, pre‐operational CNAV started to broadcast to civilian users. Baseband civil GPS signals on L1, L2, and L5 were recorded during the broadcast test and the pre‐operational broadcast using wideband software radio front ends. The signals were acquired and tracked, with navigation messages decoded by the conventional Viterbi method and a computationally efficient matrix‐based method. GPS ephemerides were extracted from the messages to compute satellite orbit solutions. This paper evaluates the orbit solution of both CNAV and Legacy NAV during the same time period to demonstrate the improvements in the CNAV ephemeris accuracy. Copyright © 2015 Institute of Navigation.

show abstract

A recurrent neural decoder for convolutional codes

Cited by 31 publications

References 5 publications

Adaptive ‘soft’ sliding block decoding of convolutional code using the artificial neural network

Adaptive ‘soft’ sliding block decoding of convolutional code using the artificial neural network

Unsupervised Deep Learning for MU-SIMO Joint Transmitter and Noncoherent Receiver Design

Performance Analysis of L2 and L5 CNAV Broadcast Ephemeris for Orbit Calculation

Contact Info

Product

Resources

About