Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Stacked Intelligent Metasurfaces for Task-Oriented Semantic Communications

Guojun Huang, Jiancheng An, Zhaohui Yang, Lu Gan, Mehdi Bennis, Mérouane Debbah

TL;DR

An innovative SIM-aided SemCom system for image recognition tasks, where a SIM is positioned in front of the transmitting antenna, using an efficient mini-batch gradient descent algorithm to train the transmission coefficients of SIM’s meta-atoms to learn the semantic representation of the image.

Abstract

Semantic communication (SemCom) leveraging advanced deep learning (DL) technologies enhances the efficiency and reliability of information transmission. Emerging stacked intelligent metasurface (SIM) with an electromagnetic neural network (EMNN) architecture enables complex computations at the speed of light. In this letter, we introduce an innovative SIM-aided SemCom system for image recognition tasks, where a SIM is positioned in front of the transmitting antenna. In contrast to conventional communication systems that transmit modulated signals carrying the image information or compressed semantic information, the carrier EM wave is directly transmitted from the source. The input layer of the SIM performs source encoding, while the remaining multi-layer architecture constitutes an EMNN for semantic encoding, transforming signals into a unique beam towards a receiving antenna corresponding to the image class. Remarkably, both the source and semantic encoding occur naturally as the EM waves propagate through the SIM. At the receiver, the image is recognized by probing the received signal magnitude across the receiving array. To this end, we utilize an efficient mini-batch gradient descent algorithm to train the transmission coefficients of SIM's meta-atoms to learn the semantic representation of the image. Extensive numerical results verify the effectiveness of utilizing the SIM-based EMNN for image recognition task-oriented SemComs, achieving more than 90\% recognition accuracy.

Stacked Intelligent Metasurfaces for Task-Oriented Semantic Communications

TL;DR

An innovative SIM-aided SemCom system for image recognition tasks, where a SIM is positioned in front of the transmitting antenna, using an efficient mini-batch gradient descent algorithm to train the transmission coefficients of SIM’s meta-atoms to learn the semantic representation of the image.

Abstract

Semantic communication (SemCom) leveraging advanced deep learning (DL) technologies enhances the efficiency and reliability of information transmission. Emerging stacked intelligent metasurface (SIM) with an electromagnetic neural network (EMNN) architecture enables complex computations at the speed of light. In this letter, we introduce an innovative SIM-aided SemCom system for image recognition tasks, where a SIM is positioned in front of the transmitting antenna. In contrast to conventional communication systems that transmit modulated signals carrying the image information or compressed semantic information, the carrier EM wave is directly transmitted from the source. The input layer of the SIM performs source encoding, while the remaining multi-layer architecture constitutes an EMNN for semantic encoding, transforming signals into a unique beam towards a receiving antenna corresponding to the image class. Remarkably, both the source and semantic encoding occur naturally as the EM waves propagate through the SIM. At the receiver, the image is recognized by probing the received signal magnitude across the receiving array. To this end, we utilize an efficient mini-batch gradient descent algorithm to train the transmission coefficients of SIM's meta-atoms to learn the semantic representation of the image. Extensive numerical results verify the effectiveness of utilizing the SIM-based EMNN for image recognition task-oriented SemComs, achieving more than 90\% recognition accuracy.
Paper Structure (16 sections, 8 equations, 4 figures, 1 algorithm)

This paper contains 16 sections, 8 equations, 4 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Transmitter
  4. Transmitting Antenna
  5. SIM
  6. Source Encoding Layer
  7. Semantic Encoding Layers
  8. Channel Model
  9. Receiver
  10. SIM-aided EMNN for Semantic Encoding
  11. Loss Function
  12. Training of EMNN
  13. Simulation Results
  14. Simulation Settings
  15. Performance Evaluation
  16. ...and 1 more sections

Figures (4)

  • Figure 1: A SIM-aided image recognition task-oriented SemCom system, where we consider $M$ image classes.
  • Figure 2: Recognition accuracy using the SIM-based EMNN.
  • Figure 3: Input image and the corresponding energy distribution at the receiving array.
  • Figure 4: The confusion matrix for recognizing ten digits.