Intelligent task-oriented semantic communications: theory, technology and challenges

被引：0
作者：
Liu, Chuanhong [1 ]
Guo, Caili [1 ,2 ]
Yang, Yang [2 ]
Chen, Jiujiu [1 ]
Zhu, Meiyi [1 ]
Sun, Lu'nan [1 ]
机构：
[1] Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing
[2] Beijing Key Laboratory of Network System Construction and Integration, Beijing University of Posts and Telecommunications, Beijing
来源：
Tongxin Xuebao/Journal on Communications | 2022年 / 43卷 / 06期
关键词：
6G; intelligent task; semantic coding; semantic communication; semantic entropy;
D O I：
10.11959/j.issn.1000-436x.2022117
中图分类号：
学科分类号：
摘要：
In the future, intelligent interconnection of all things, such as machine-to-machine and human-to-machine, poses challenges to traditional communication methods. The semantic communication method that extracts semantic information from source information and transmits them provides a novel solution for the 6G communication system. First, the development process and research status of semantic communications were reviewed, the two bottleneck problems faced by semantic communications were analyzed, and an intelligent task-oriented semantic communication architecture was proposed. The measurement methods of task-oriented semantic entropy and semantic channel capacity were given. For different intelligent tasks, semantic coding and semantic source-channel joint coding schemes were proposed respectively. Besides, a semantic communication platform was built to verify the proposed method. Finally, the future challenges and open issues of semantic communications were summarized. Compared with traditional communication methods, semantic communication can significantly reduce the amount of transmitted data and the transmission delay, and it will play an important role in the future communication of the Internet of everything. © 2022 Editorial Board of Journal on Communications. All rights reserved.
引用
收藏
页码：41 / 57
页数：16
相关论文
共 55 条
  • [41] HUYNH-THU Q, GHANBARI M., Scope of validity of PSNR in image/video quality assessment, Electronics Letters, 44, 13, (2008)
  • [42] WANG Z, BOVIK A C., A universal image quality index, IEEE Signal Processing Letters, 9, 3, pp. 81-84, (2002)
  • [43] WANG Z, BOVIK A C, SHEIKH H R, Et al., Image quality assessment: from error visibility to structural similarity, IEEE Transactions on Image Processing, 13, 4, pp. 600-612, (2004)
  • [44] KIM J, LEE S., Deep learning of human visual sensitivity in image quality assessment framework, Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1969-1977, (2017)
  • [45] ZHANG R, ISOLA P, EFROS A A, Et al., The unreasonable effectiveness of deep features as a perceptual metric, Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 586-595, (2018)
  • [46] HU Y Q, ZHOU W, ZHAO S X, Et al., SDM: semantic distortion measurement for video encryption, Proceedings of 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition, pp. 764-768, (2018)
  • [47] HUSSAIN A J, AL-FAYADH A, RADI N., Image compression techniques: a survey in lossless and lossy algorithms, Neurocomputing, 300, pp. 44-69, (2018)
  • [48] YANG Z H, WANG Y H, XU C, Et al., Discernible image compression, Proceedings of the 28th ACM International Conference on Multimedia, pp. 1561-1569, (2020)
  • [49] WEI L S., Mathematical statistics(2nd edition), (2015)
  • [50] SHWARTZ-ZIV R, TISHBY N., Opening the black box of deep neural networks via information, (2017)
123456