Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sums: Sniffing Unknown Multiband Signals under Low Sampling Rates

Jinbo Peng, Zhe Chen, Zheng Lin, Haoxuan Yuan, Zihan Fang, Lingzhong Bao, Zihang Song, Ying Li, Jing Ren, Yue Gao

TL;DR

The paper addresses blind monitoring of unknown multiband wireless signals under sub-Nyquist sampling. It introduces Sums, a hardware-algorithm co-design that couples an eight-channel multi-coset front end sampling GHz-wide bandwidth at 50 MSPS with a Transformer-based multi-task network that jointly performs spectrum sensing, modulation classification, physical layer protocol recognition, and demodulation. Empirical results show that Sums achieves higher accuracy than state-of-the-art baselines across spectrum sensing, modulation classification, and demodulation while handling heterogeneous, mixed-signals scenarios. This work reduces cost and energy for wideband sniffers and enables practical spectrum monitoring and sharing in increasingly crowded spectra.

Abstract

Due to sophisticated deployments of all kinds of wireless networks (e.g., 5G, Wi-Fi, Bluetooth, LEO satellite, etc.), multiband signals distribute in a large bandwidth (e.g., from 70 MHz to 8 GHz). Consequently, for network monitoring and spectrum sharing applications, a sniffer for extracting physical layer information, such as structure of packet, with low sampling rate (especially, sub-Nyquist sampling) can significantly improve their cost- and energy-efficiency. However, to achieve a multiband signals sniffer is really a challenge. To this end, we propose Sums, a system that can sniff and analyze multiband signals in a blind manner. Our Sums takes advantage of hardware and algorithm co-design, multi-coset sub-Nyquist sampling hardware, and a multi-task deep learning framework. The hardware component breaks the Nyquist rule to sample GHz bandwidth, but only pays for a 50 MSPS sampling rate. Our multi-task learning framework directly tackles the sampling data to perform spectrum sensing, physical layer protocol recognition, and demodulation for deep inspection from multiband signals. Extensive experiments demonstrate that Sums achieves higher accuracy than the state-of-theart baselines in spectrum sensing, modulation classification, and demodulation. As a result, our Sums can help researchers and end-users to diagnose or troubleshoot their problems of wireless infrastructures deployments in practice.

Sums: Sniffing Unknown Multiband Signals under Low Sampling Rates

TL;DR

The paper addresses blind monitoring of unknown multiband wireless signals under sub-Nyquist sampling. It introduces Sums, a hardware-algorithm co-design that couples an eight-channel multi-coset front end sampling GHz-wide bandwidth at 50 MSPS with a Transformer-based multi-task network that jointly performs spectrum sensing, modulation classification, physical layer protocol recognition, and demodulation. Empirical results show that Sums achieves higher accuracy than state-of-the-art baselines across spectrum sensing, modulation classification, and demodulation while handling heterogeneous, mixed-signals scenarios. This work reduces cost and energy for wideband sniffers and enables practical spectrum monitoring and sharing in increasingly crowded spectra.

Abstract

Due to sophisticated deployments of all kinds of wireless networks (e.g., 5G, Wi-Fi, Bluetooth, LEO satellite, etc.), multiband signals distribute in a large bandwidth (e.g., from 70 MHz to 8 GHz). Consequently, for network monitoring and spectrum sharing applications, a sniffer for extracting physical layer information, such as structure of packet, with low sampling rate (especially, sub-Nyquist sampling) can significantly improve their cost- and energy-efficiency. However, to achieve a multiband signals sniffer is really a challenge. To this end, we propose Sums, a system that can sniff and analyze multiband signals in a blind manner. Our Sums takes advantage of hardware and algorithm co-design, multi-coset sub-Nyquist sampling hardware, and a multi-task deep learning framework. The hardware component breaks the Nyquist rule to sample GHz bandwidth, but only pays for a 50 MSPS sampling rate. Our multi-task learning framework directly tackles the sampling data to perform spectrum sensing, physical layer protocol recognition, and demodulation for deep inspection from multiband signals. Extensive experiments demonstrate that Sums achieves higher accuracy than the state-of-theart baselines in spectrum sensing, modulation classification, and demodulation. As a result, our Sums can help researchers and end-users to diagnose or troubleshoot their problems of wireless infrastructures deployments in practice.
Paper Structure (24 sections, 8 equations, 9 figures, 1 table)

This paper contains 24 sections, 8 equations, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Motivation and Background
  3. Multiband Signals Sampling
  4. Frequency Sweeping Limitation
  5. Heterogeneous Signals
  6. System Design
  7. Multi-coset Sub-sampling Hardware
  8. Signal Analysis Network
  9. Samples Embedding Module
  10. Spectrum Sensing Module
  11. Modulation Classification Module
  12. Demodulation Module
  13. Loss Functions
  14. Implementation
  15. Signal sampling
  16. ...and 9 more sections

Figures (9)

  • Figure 1: An example scenario for unknown multiband signals monitoring in a wideband spectrum.
  • Figure 2: Mutual effects between spectrum sensing and blind demodulation.
  • Figure 3: The architecture of Sums comprises two main components: the multi-coset sub-sampling to capture wide-spectrum signal efficiently and the signal analysis network for spectrum sensing, modulation classification and blind demodulation.
  • Figure 4: Multi-coset sub-sampling hardware configuration.
  • Figure 5: Multi-coset sub-sampling hardware
  • ...and 4 more figures