Abstract
In this paper, for the long code decoding problem, we analyze the performance of belief propagation (BP) decoder in neural network. The decoding of long codes has always been a concern of LDPC decoding. In recent years, the application of neural networks in the communication field has gradually become widespread. As a result, we are considering and combining the two. The decoding method proposed in this paper uses model-driven deep learning. The network we propose is a neural standardized BP LDPC decoding network. Model-driven deep learning absorbs the advantages of both model-driven and data-driven, which combines them adaptively. The network structure proposed in this paper takes advantage of model-driven to expand the iterative process of decoding between check nodes and variable nodes into the neural network. We can increase the number of iterations by increasing the CN layer and VN layer of the hidden layer. Furthermore, by changing the SNR to detect its relationship with system robustness, and, finally, determine the appropriate SNR range.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gallager, R.: Low-density parity-check codes. IRE Trans. Inf. Theory 8(1), 21–28 (1962)
Mackay, D.J.C., Neal, R.M.: Near Shannon limit performance of low density parity check codes. Electron. Lett. 32(18), 1645–1646 (1996)
Nachmani, E., Be’ery, Y., Burshtein, D.: Learning to decode linear codes using deep learning. In: 2016 54thAnnual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 341–346. IEEE, Monticello, IL, USA (2016)
Wang, Q., Wang, S., Fang, H.: A model-driven deep learning method for normalized min-sum LDPC decoding. In: 2020 IEEE International Conference on Communications Workshops (ICC Workshops), pp.1–6. IEEE, Dublin, Ireland, Ireland (2020)
Tanner, R.M.: A recursive approach to low complexity codes. IEEE Trans. Inf. Theory 27(5), 533–547 (1981)
He, H., Jin, S., Wen, C.-K., Gao, F., Li, G.Y., Xu, Z.: Model-driven deep learning for physical layer communications. IEEE Wirel. Commun. 26(5), 77–83 (2019)
Zhang, J., He, H.: Yang X: Model-driven deep learning based Turbo-MIMO receiver. In: 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pp. 1–5. IEEE, Atlanta, GA, USA (2020)
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Cito, C., Corrado, G.S., Davis, A.: Tensorflow: Large-scale machine learning on heterogeneous systems. arXiv preprint arXiv:1603.04467 (2016)
Channel Codes. www.uni-kl.de/channel-codes. Last accessed 2020/11/27
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tang, Y., Zhou, L., Zhang, S., Chen, Y. (2022). Modern-Driven Deep Learning for Belief Propagation LDPC Decoding. In: Jain, L.C., Kountchev, R., Hu, B., Kountcheva, R. (eds) Smart Communications, Intelligent Algorithms and Interactive Methods. Smart Innovation, Systems and Technologies, vol 257. Springer, Singapore. https://doi.org/10.1007/978-981-16-5164-9_30
Download citation
DOI: https://doi.org/10.1007/978-981-16-5164-9_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5163-2
Online ISBN: 978-981-16-5164-9
eBook Packages: EngineeringEngineering (R0)