Enhanced MIMO-SCMA Detector by Deep Learning

Main Article Content

Triratana Metkarunchit


        In this paper, we propose a deep learning approach for multiple input multiple output - sparse code multiple access (MIMO-SCMA) signal detection by using a deep neural network via spreading the procedure of the message passing algorithm (MPA). The MPA can be transformed into a sparsely connected neural network. The neural network can be trained off-line and then implemented for online detection. Besides when the neural network has been trained, the network weights corresponding to the edges of a factor graph. From the simulation result of the MIMO-SCMA system over the quasi-static Rayleigh fading channel, found that the neural network detection better performance than the traditional MPA.


Download data is not yet available.

Article Details

Research Article


[1] Cisco, “Cisco Visual Networking Index: Forecast and Trends,2017–2022 White Paper,” [Online] Available:https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white-paper-c11-741490.html. (accessed: July 21, 2019)

[2] Fabio Giust, Luca Cominardi, and Carlos J Bernardos, “Distributed mobility management for future 5G networks:overview and analysis of existing approaches,” IEEE Communications Magazine, Vol. 53, No. 1, pp. 142–149, 2015.

[3] Mamta Agiwal, Abhishek Roy, and Navrati Saxena, “Next generation 5G wireless networks: A comprehensive survey, IEEE Communications Surveys & Tutorials, Vol. 18, No. 3, pp. 1617–1655, 2016.

[4] F. Wei and W. Chen, “A low complexity SCMA decoder based on list sphere decoding,” in Proc. IEEE GLOBECOM, Washington, DC, USA, Dec. 2016, pp. 1–6.

[5] M. Alam and Q. Zhang, “Performance study of SCMA codebook design,” in Proc. IEEE WCNC, San Francisco, CA, Mar. 2017, pp. 1–5.

[6] F. R. Kschischang, B. J. Frey, and H. A. Loeliger, “Factor graphs and the sum-product algorithm,” IEEE Trans. Inf.Theory, Vol. 47, No. 2, pp.498–519, Feb. 2001.

[7] Chaoyun Zhang, Pan Zhou, Chenghua Li, and Lijun Liu, “A convolutional neural network for leaves recognition using data augmentation,” In Proc. 2015 IEEE Int.Conference on Computer and Information ; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, Liverpool, UK, Dec. 2015, pp. 2143–2150, DOI: 10.1109/CIT/IUCC/DASC/PICOM.2015.318

[8] Richard Socher, Yoshua Bengio, and Christopher D Manning,“Deep learning for NLP (without magic),” In Proc. 50th AnnualMeeting of the Association for Computational Linguistics:Tutorial Abstracts, Jeju Island, Korea, Jul. 2012, p. 5.

[9] Chaoyun Zhang, Paul Patras and Hamed Haddadi, “Deep Learning in Mobile and Wireless Networking: A Survey,” IEEECommunications Surveys & Tutorials, Vol. 21, No. 3, pp.2224 - 2287, Mar. 2019, DOI: 10.1109/COMST.2019.2904897

[10] Akhil Gupta and Rakesh Kumar Jha, “A survey of 5G network: Architecture and emerging technologies,” IEEEAccess, vol. 3, pp. 1206–1232, 2015.

[11] Chunxiao Jiang, Haijun Zhang, Yong Ren, Zhu Han, Kwang-Cheng Chen, and Lajos Hanzo, “Machine learning paradigmsfor next generation wireless networks,” IEEE WirelessCommunications, Vol. 24, No. 2, pp. 98–105, 2017.

[12] Duong D Nguyen, Hung X Nguyen, and Langford B White,“Reinforcement learning with network-assisted feedback for heterogeneous rat selection,” IEEE Transactions onWireless Communications, Vol. 16, No. 9, pp. 6062 – 6076, Sept. 2017, DOI: 10.1109/TWC.2017.2718526

[13] Fairuz Amalina Narudin, Ali Feizollah, Nor Badrul Anuar, and Abdullah Gani, “Evaluation of machine learningclassifiers for mobile malware detection,” Soft Computing,Vol. 20, No. 1, pp. 343–357, 2016.

[14] Wencong Xiao, Jilong Xue, Youshan Miao, Zhen Li, Cheng Chen, Ming Wu, Wei Li, and Lidong Zhou, “Tux2: Distributedgraph computation for machine learning,” in Proc. 14thUSENIX Symposium on Networked Systems Design andImplementation (NSDI ’17), Boston, MA, USA, Mar. 2017, pp.669–682.

[15] Timothy J O’Shea, Tugba Erpek, and T Charles Clancy,“Deep learning based MIMO communications,” Accessed: Jul. 2017. [Online]. Available: https://arxiv.org/abs/1707.07980

[16] Minhoe Kim, Nam-I Kim, Woongsup Lee and Dong-Ho Cho,“Deep Learning-Aided SCMA,” IEEE Communications Letters,Vol. 22, No. 4, pp. 720 – 723, 2018

[17] Chao Lu, Wei Xu, Hong Shen, Hua Zhang, and Xiaohu You, “An Enhanced SCMA Detector Enabled by Deep Neural Network,” Accessed: Aug, 2018. [Online]. Available: https://arxiv.org/abs/1808.08015

[18] M. Abadi et al., “Tensorflow: Large-scale machine learning on heterogeneous systems,” Accessed: Aug, 2018. [Online].Available: https://arxiv.org/abs/1603.04467

[19] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd International Conference for Learning Representations, San Diego, 2015, [Online]. Available: https://arxiv.org/abs/1412.6980

[20] Triratana Metkarunchit, “SCMA codebook design base on circular-QAM,” in Proc. Integrated Communication Navigation and Surveillance Conference (ICNS), Virginia,USA, May. 2017, DOI: 10.1109/ICNSURV.2017.8011917

[21] Triratana Metkarunchit, “Achieving Higher Full-diversity Gain of Downlink STBC-MIMO SCMA System,” Journal ofCommunications, Vol. 13, No. 9, pp. 535-539, Sep. 2018.