Building Semantic Communication System via Molecules: An End-to-End Training Approach

被引:0
|
作者
Cheng Yukun [1 ,2 ]
Chen Wei [1 ,3 ]
Ai Bo [1 ,4 ,5 ]
机构
[1] School of Electronic and Information Engineering,Beijing Jiaotong University
[2] Frontiers Science Center for Smart High-speed Railway System,Beijing Jiaotong University
[3] Key Laboratory of Railway Industry of Broadband Mobile Information Communications,Beijing Jiaotong University
[4] Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications,Beijing Jiaotong University
[5] School of Information Engineering,Zhengzhou
关键词
D O I
暂无
中图分类号
学科分类号
摘要
The concept of semantic communication provides a novel approach for applications in scenarios with limited communication resources. In this paper, we propose an end-to-end(E2E) semantic molecular communication system, aiming to enhance the efficiency of molecular communication systems by reducing the transmitted information. Specifically, following the joint source channel coding paradigm, the network is designed to encode the task-relevant information into the concentration of the information molecules, which is robust to the degradation of the molecular communication channel. Furthermore, we propose a channel network to enable the E2E learning over the non-differentiable molecular channel. Experimental results demonstrate the superior performance of the semantic molecular communication system over the conventional methods in classification tasks.
引用
下载
收藏
页码:113 / 124
页数:12
相关论文
共 50 条
  • [41] End-to-end multilingual speech recognition system with language supervision training
    Liu, Danyang
    Xu, Ji
    Zhang, Pengyuan
    IEICE Transactions on Information and Systems, 2020, E103D (06) : 1427 - 1430
  • [42] End-to-End Multilingual Speech Recognition System with Language Supervision Training
    Liu, Danyang
    Xu, Ji
    Zhang, Pengyuan
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2020, E103D (06): : 1427 - 1430
  • [43] ENZYMATIC END-TO-END JOINING OF DNA MOLECULES
    LOBBAN, PE
    KAISER, AD
    JOURNAL OF MOLECULAR BIOLOGY, 1973, 78 (03) : 453 - +
  • [44] A Novel End-To-End Approach For Offline Signature Verification System
    Thakare, Bhushan S.
    Deshmukh, Hemant R.
    2018 3RD INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2018,
  • [45] A CENTRALIZED MODEL FOR ESTABLISHING END-TO-END COMMUNICATION SERVICES VIA MANAGEMENT AGENTS
    Rakas, Slavica Bostjancic
    Stojanovic, Mirjana
    PROMET-TRAFFIC & TRANSPORTATION, 2019, 31 (03): : 245 - 255
  • [46] SEMI-SUPERVISED TRAINING FOR END-TO-END MODELS VIA WEAK DISTILLATION
    Li, Bo
    Sainath, Tara N.
    Pang, Ruoming
    Wu, Zelin
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 2837 - 2841
  • [47] Solving Chemistry Problems via an End-to-End Approach: A Proof of Concept
    Liu, Xiaotong
    Zhang, Tianfu
    Yang, Tao
    Liu, Xiulei
    Song, Xin
    Yang, Yong
    Li, Ning
    Rignanese, Gian-Marco
    Li, Yongwang
    Wen, Xiaodong
    JOURNAL OF PHYSICAL CHEMISTRY A, 2020, 124 (42): : 8866 - 8873
  • [48] End-to-end Speech Translation via Cross-modal Progressive Training
    Ye, Rong
    Wang, Mingxuan
    Li, Lei
    INTERSPEECH 2021, 2021, : 2267 - 2271
  • [49] End-to-End Learning of Autonomous Vehicle Lateral Control via MPC Training
    Mentasti, Simone
    Bersani, Mattia
    Arrigoni, Stefano
    Matteucci, Matteo
    Cheli, Federico
    INTELLIGENT AUTONOMOUS SYSTEMS 16, IAS-16, 2022, 412 : 195 - 211
  • [50] Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination*
    Hawkins, Cole
    Liu, Xing
    Zhang, Zheng
    SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE, 2022, 4 (01): : 46 - 71