Deep Learning-Based Symbol-Frame Fusion Channel Estimation Network

Xiaojuan Bai; Yunqing Li

doi:10.62051/ijcsit.v5n3.05

Authors

Xiaojuan Bai
Yunqing Li

DOI:

https://doi.org/10.62051/ijcsit.v5n3.05

Keywords:

Deep learning, Vehicle communication, Channel estimation, FBF, SBS, Detail enhanced convolution

Abstract

In recent years, the application of deep learning technology in vehicle communication has gradually increased, especially in channel estimation. The existing channel estimation methods based on deep learning can be divided into two categories: frame by frame (FBF) estimation and symbol by symbol (SBS) estimation. FBF estimation method can obtain high estimation accuracy by processing the data of the entire OFDM frame, but there is a large delay; Although the SBS estimation method can quickly respond to channel changes, it is vulnerable to noise and multipath effects in high dynamic scenarios, resulting in reduced estimation accuracy. This paper proposes a new Symbol Frame Fusion Channel Estimation Network (SFusNet) based on deep learning. First, the detail enhanced differential convolution (DeConv) is used to replace the traditional convolution layer for FBF channel estimation to improve the feature extraction ability of the convolution layer. Then, the FBF channel estimation results are converted into one-dimensional data, and GRU is used for SBS channel estimation. The simulation results show that SFusNet performs better in restoring real channel 2D images, and has significant advantages in BER and NMSE performance compared with other existing schemes.

Downloads

Download data is not yet available.

References

[1] J. Wang, C. Li, H. Li and Y. Wang. Key Technologies and Development Status of Internet of Vehicles. 2017 9th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), 2017, pp. 29-32.

[2] IEEE Standard for Information Technology-Local and Metropolitan Area Networks Specific Requirements-Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications Amendment 6: Wireless Access in Vehicular Environments [M]. New York: 2010.

[3] Joseph A. Fernandez, Kevin Borries, Lin Cheng, B. V. K. Vijaya Kumar, Daniel D. Stancil, and Fan Bai. Performance of the 802.11p physical layer in vehicle-to-vehicle environments [J]. IEEE Transactions on Vehicular Technology, 2011, 61(1): 3-14.

[4] Zijun Zhao, Xiang Cheng, Miaowen Wen, Bingli Jiao and Cheng-Xiang Wang. Channel estimation schemes for IEEE 802.11p standard [J]. IEEE Intelligent Transportation Systems Magazine, 2013, 5(4): 38-49.

[5] Yoon-Kyeong Kim, Jang-Mi Oh, Yoo-Ho Shin and Cheol Mun. Time and frequency domain channel estimation scheme for IEEE 802.11p [C].17th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2014: 1085-1090.

[6] Abdul Karim Gizzini, Marwa Chafii, Ahmad Nimr, and Gerhard Fettweis. Deep learning based channel estimation schemes for IEEE 802.11p standard [J]. IEEE Access, 2020, 8: 113751-113765.

[7] Gizzini A. K, Chafii M, Nimr A, et al. Joint TRFI and deep learning for vehicular channel estimation [C]. 2020 IEEE Globecom Workshops GC Wkshps, 2020, 1-6.

[8] Pan J, Shan H, Li R, et al. Channel estimation based on deep learning in vehicle-to-everything environments [J]. IEEE Communications Letters, 2021, 25(6): 1891-1895.

[9] J. Hou, H. Liu, Y. Zhang, W. Wang and J. Wang. GRU-Based Deep Learning Channel Estimation Scheme for the IEEE 802.11p Standard [J]. IEEE Wireless Communications Letters, 2023, 12(5): 764-768.

[10] Soltani M, Pourahmadi V, Mirzaei A, et al. Deep learning-based channel estimation [J]. IEEE Communications Letters, 2019, 23(4): 652-655.

[11] Xuchen Zhu, Zhichao Sheng, Yong Fang, and Denghong Guo. A deep learning-aided temporal spectral ChannelNet for IEEE 802.11p-based channel estimation in vehicular communications [J]. EURASIP Journal on Wireless Communications and Networking, 2020, 94: 1-15.

[12] A. S. M. M. Jameel, A. Malhotra, A. E. Gamal and S. Hamidi-Rad. Deep OFDM Channel Estimation: Capturing Frequency Recurrence [J]. IEEE Communications Letters, 2024, 28(3):562-566.

[13] Dong C, Loy C C, He K, et al. Image super-resolution using deep convolutional networks [J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 38(2): 295-307.

[14] Zhang K, Zuo W, Chen Y, et al. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising [J]. IEEE transactions on image processing, 2017, 26(7): 3142- 3155.

[15] X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia. Ffa-net: Feature fusion attention network for single image dehazing [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020(34)7: 11908–11915.

[16] H. Wu, Y. Qu, S. Lin, J. Zhou, R. Qiao, Z. Zhang, Y. Xie, and L. Ma. Contrastive learning for compact single image dehazing [J]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021:10551–10560.

[17] H. Wu, J. Liu, Y. Xie, Y. Qu, and L. Ma. Knowledge Transfer Dehazing Network for NonHomogeneous Dehazing [J]. CVPR Workshop IEEE, 2020:1975–1983.

[18] H. Zhang and V. M. Patel. Densely connected pyramid dehazing network [J]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2018:3194–3203.

[19] C. Wang, H.-Z. Shen, F. Fan, M.-W. Shao, C.-S. Yang, J.-C. Luo, and L.-J. Deng. Eaa-net: A novel edge assisted attention network for single image dehazing [J]. Knowledge-Based Systems, 2021(228):107279.

[20] H. Bai, J. Pan, X. Xiang, and J. Tang. Self-guided image dehazing using progressive feature fusion [J]. IEEE Transactions on Image Processing, 2022(31): 1217–1229.

[21] K. Cho et al., “Learning phrase representations using RNN encoder– decoder for statistical machine translation,” in Proc. Conf. Empir. Methods Nat. Lang. Process. (EMNLP), Oct. 2014, pp. 1724–1734.

[22] G. Acosta-Marum and M. A. Ingram, "Six time- and frequency- selective empirical channel models for vehicular wireless LANs," IEEE Vehicular Technology Magazine, vol. 2, no. 4, pp. 4-11, Dec. 2007.