Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NNCTC: Physical Layer Cross-Technology Communication via Neural Networks

Haoyu Wang, Jiazhao Wang, Demin Gao, Wenchao Jiang

TL;DR

NNCTC introduces a general, model-driven neural-network framework to implement cross-technology communication at the physical layer, replacing hand-engineered waveform emulation with end-to-end trainable nets. It demonstrates conversion of WiFi PHY blocks (DFT/IDFT, QAM mapping/demapping, quantization) into differentiable neural components and an autoencoder-style QAM emulation. The approach achieves higher PRR and lower SER than traditional WEBeE/WIDE in a WiFi-to-ZigBee link and supports CCK-based CTC as well, with notable reductions in training data and computation compared to large-model baselines. This work advances practical, lightweight NN-based PHY emulation for flexible, scalable CTC across heterogeneous wireless technologies.

Abstract

Cross-technology communication(CTC) enables seamless interactions between diverse wireless technologies. Most existing work is based on reversing the transmission path to identify the appropriate payload to generate the waveform that the target devices can recognize. However, this method suffers from many limitations, including dependency on specific technologies and the necessity for intricate algorithms to mitigate distortion. In this work, we present NNCTC, a Neural-Network-based Cross-Technology Communication framework inspired by the adaptability of trainable neural models in wireless communications. By converting signal processing components within the CTC pipeline into neural models, the NNCTC is designed for end-to-end training without requiring labeled data. This enables the NNCTC system to autonomously derive the optimal CTC payload, which significantly eases the development complexity and showcases the scalability potential for various CTC links. Particularly, we construct a CTC system from Wi-Fi to ZigBee. The NNCTC system outperforms the well-recognized WEBee and WIDE design in error performance, achieving an average packet reception rate(PRR) of 92.3% and an average symbol error rate(SER) as low as 1.3%.

NNCTC: Physical Layer Cross-Technology Communication via Neural Networks

TL;DR

NNCTC introduces a general, model-driven neural-network framework to implement cross-technology communication at the physical layer, replacing hand-engineered waveform emulation with end-to-end trainable nets. It demonstrates conversion of WiFi PHY blocks (DFT/IDFT, QAM mapping/demapping, quantization) into differentiable neural components and an autoencoder-style QAM emulation. The approach achieves higher PRR and lower SER than traditional WEBeE/WIDE in a WiFi-to-ZigBee link and supports CCK-based CTC as well, with notable reductions in training data and computation compared to large-model baselines. This work advances practical, lightweight NN-based PHY emulation for flexible, scalable CTC across heterogeneous wireless technologies.

Abstract

Cross-technology communication(CTC) enables seamless interactions between diverse wireless technologies. Most existing work is based on reversing the transmission path to identify the appropriate payload to generate the waveform that the target devices can recognize. However, this method suffers from many limitations, including dependency on specific technologies and the necessity for intricate algorithms to mitigate distortion. In this work, we present NNCTC, a Neural-Network-based Cross-Technology Communication framework inspired by the adaptability of trainable neural models in wireless communications. By converting signal processing components within the CTC pipeline into neural models, the NNCTC is designed for end-to-end training without requiring labeled data. This enables the NNCTC system to autonomously derive the optimal CTC payload, which significantly eases the development complexity and showcases the scalability potential for various CTC links. Particularly, we construct a CTC system from Wi-Fi to ZigBee. The NNCTC system outperforms the well-recognized WEBee and WIDE design in error performance, achieving an average packet reception rate(PRR) of 92.3% and an average symbol error rate(SER) as low as 1.3%.
Paper Structure (38 sections, 10 equations, 20 figures, 1 table)

This paper contains 38 sections, 10 equations, 20 figures, 1 table.

Table of Contents

  1. Introduction
  2. Motivation
  3. Restatement of Existing Issues
  4. Opportunities
  5. Challenges
  6. Overview
  7. Realization of Physical Layer CTC via Neural Network
  8. Mathematical Foundations of Transitioning from the Physical Layer to Neural Networks
  9. Mathematical Basis of NNCTC
  10. Neural Network Driven by Mathematical Model
  11. The Transformation of the WiFi Physical Layer into Neural Networks
  12. Convert DFT and IDFT processes to neural networks
  13. Convert QAM Demapper/Mapper to neural network
  14. Convert quantization process to neural network
  15. QAM Emulation via Neural Network
  16. ...and 23 more sections

Figures (20)

  • Figure 1: Workflow of NNCTC and conventional CTC
  • Figure 2: Configuration examples from mathematical foundations to neural networks
  • Figure 3: Conventional CTC QAM Emulation Process
  • Figure 4: Autoencoder for QAM emulation
  • Figure 5: Constellation Diagram Comparison of Analog/Digital Emulation
  • ...and 15 more figures