Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
research-article

Enhancing RF Sensing with Deep Learning: A Layered Approach

Published: 01 February 2021 Publication History

Abstract

In recent years, radio frequency (RF) sensing has gained increasing popularity due to its pervasiveness, low cost, non-intrusiveness, and privacy preservation. However, realizing the promises of RF sensing is highly nontrivial, given typical challenges such as multipath and interference. One potential solution leverages deep learning to build direct mappings from the RF domain to target domains, hence avoiding complex RF physical modeling. While earlier solutions exploit only simple feature extraction and classification modules, an emerging trend adds functional layers on top of elementary modules for more powerful generalizability and flexible applicability. To better understand this potential, this article takes a layered approach to summarize RF sensing enabled by deep learning. Essentially, we present a four-layer framework: physical, backbone, generalization, and application. While this layered framework provides readers a systematic methodology for designing deep interpreted RF sensing, it also facilitates making improvement proposals and hints at future research opportunities.

References

[1]
B. Guo et al., “Behavior Recognition Based on Wi-Fi CSI: Part 1,” IEEE Commun. Mag., vol. 55, no. 10, Oct. 2017, pp. 90–90.
[2]
Y. Ma et al., “WiFi Sensing with Channel State Information: A Survey.” ACM Comp. Surv., vol. 52. no. 3, 2019, pp. 1–36.
[3]
A. Belmonte-Hernández et al., “Recurrent Model for Wireless Indoor Tracking and Positioning Recovering Using Generative Networks,” IEEE Sensors J., vol. 20, no. 6, 2019, pp. 3356–65.
[4]
W. Jiang et al., “Towards Environment Independent Device Free Human Activity Recognition,” Proc. 24th ACM Mobi-Com, 2018, pp. 289–304.
[5]
Y. Zheng et al., “Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi,” Proc. 17th ACM MobiSys, 2019, pp. 313–25.
[6]
J. Guan et al., “Through Fog High-Resolution Imaging Using Millimeter Wave Radar,” Proc. 33rd IEEE CVPR, 2020, pp. 11, 464–71.
[7]
M. Zhao et al., “Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture,” Proc. 34th ACM ICML, 2017, pp. 4100–09.
[8]
L. O. Fhager et al., “Pulsed Millimeter Wave Radar for Hand Gesture Sensing and Classification,” IEEE Sensors Lett., vol. 3, no. 12, 2019, pp. 1–4.
[9]
Q. Li et al., “AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems,” IEEE Trans. Emerging Topics Computational Intelligence (Early Access), 2019.
[10]
S. Ding et al., “RF-Net: A Unified Learning Framework for RF-Enabled One-Shot Human Activity Recognition,” Proc. 18th ACM SenSys, 2020, pp. 1–14.
[11]
M. Tamzeed Islam et al., “Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition,” Proc. 16th IEEE DCOSS, 2020, pp. 35–42.
[12]
J. Yang et al., “MobileDA: Towards Edge Domain Adaptation,” IEEE Internet of Things J., vol. 7, no. 8, 2020, pp. 6909–18.
[13]
F. Wang et al., “Person-in-WiFi: Fine-Grained Person Perception Using WiFi,” Proc. 33rd IEEE ICCV, 2019, pp. 5452–61.
[14]
Y. Yang et al., “Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO Systems,” IEEE Trans. Commun. (Early Access), 2020.
[15]
M. Alrabeiah et al., “ViWi: A Deep Learning Dataset Framework for Vision-Aided Wireless Communications,” Proc. IEEE VTC-Spring, 2020, pp. 1–5.

Cited By

View all
  • (2025)Real-Time Video Forgery Detection via Vision-WiFi Silhouette CorrespondenceIEEE Transactions on Mobile Computing10.1109/TMC.2024.348355024:3(1585-1601)Online publication date: 1-Mar-2025
  • (2024)π-jackProceedings of the 33rd USENIX Conference on Security Symposium10.5555/3698900.3699309(7321-7338)Online publication date: 14-Aug-2024
  • (2024)RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data AugmentationProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36596208:2(1-26)Online publication date: 15-May-2024
  • Show More Cited By

Index Terms

  1. Enhancing RF Sensing with Deep Learning: A Layered Approach
      Index terms have been assigned to the content through auto-classification.

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image IEEE Communications Magazine
      IEEE Communications Magazine  Volume 59, Issue 2
      February 2021
      95 pages

      Publisher

      IEEE Press

      Publication History

      Published: 01 February 2021

      Qualifiers

      • Research-article

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)0
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 20 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2025)Real-Time Video Forgery Detection via Vision-WiFi Silhouette CorrespondenceIEEE Transactions on Mobile Computing10.1109/TMC.2024.348355024:3(1585-1601)Online publication date: 1-Mar-2025
      • (2024)π-jackProceedings of the 33rd USENIX Conference on Security Symposium10.5555/3698900.3699309(7321-7338)Online publication date: 14-Aug-2024
      • (2024)RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data AugmentationProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36596208:2(1-26)Online publication date: 15-May-2024
      • (2024)UWB-Fi: Pushing Wi-Fi towards Ultra-wideband for Fine-Granularity SensingProceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services10.1145/3643832.3661889(42-55)Online publication date: 3-Jun-2024
      • (2024)TFSemantic: A Time–Frequency Semantic GAN Framework for Imbalanced Classification Using Radio SignalsACM Transactions on Sensor Networks10.1145/361409620:4(1-22)Online publication date: 11-May-2024
      • (2024)AutoDLAR: A Semi-supervised Cross-modal Contact-free Human Activity Recognition SystemACM Transactions on Sensor Networks10.1145/360725420:4(1-20)Online publication date: 11-May-2024
      • (2024)Pa-Count: Passenger Counting in Vehicles Using Wi-Fi SignalsIEEE Transactions on Mobile Computing10.1109/TMC.2023.326322923:4(2684-2697)Online publication date: 1-Apr-2024
      • (2023)Algorithmic Sensing: A Joint Sensing and Learning PerspectiveProceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services10.1145/3581791.3597509(624-626)Online publication date: 18-Jun-2023
      • (2023)Integrated Human Activity Sensing and CommunicationsIEEE Communications Magazine10.1109/MCOM.002.220039161:5(90-96)Online publication date: 1-May-2023
      • (2022)Integrating monostatic sensing with communication for IoTProceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems10.1145/3556562.3558571(43-48)Online publication date: 21-Oct-2022
      • Show More Cited By

      View Options

      View options

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media