Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Indoor/Outdoor Spectrum Sharing Enabled by GNSS-based Classifiers

Hossein Nasiri, Muhammad Iqbal Rochman, Monisha Ghosh

TL;DR

This work tackles the problem of reliably distinguishing indoor vs outdoor environments to enable spectrum sharing in the mid-band. It adds GNSS signals to the I/O classification pipeline and evaluates threshold-based and ML methods on a geographically diverse GNSS dataset collected with an extended SigCap app, showing GNSS features improve generalization and accuracy, especially when fused with Wi-Fi data and using temporal aggregation. The contributions include GNSS-enabled data collection across multiple cities, a thorough comparison of Th-based and ML methods, and the demonstration that containment concepts can inform transmit-power control beyond traditional indoor/outdoor labels. The findings have practical implications for automatic power management and regulation-friendly spectrum sharing in bands like $6$ GHz.

Abstract

The desirability of the mid-band frequency range (1 - 10 GHz) for federal and commercial applications, combined with the growing applications for commercial indoor use-cases, such as factory automation, opens up a new approach to spectrum sharing: the same frequency bands used outdoors by federal incumbents can be reused by commercial indoor users. A recent example of such sharing, between commercial systems, is the 6 GHz band (5.925 - 7.125 GHz) where unlicensed, low-power-indoor (LPI) users share the band with outdoor incumbents, primarily fixed microwave links. However, to date, there exist no reliable, automatic means of determining whether a device is indoors or outdoors, necessitating the use of other mechanisms such as mandating indoor access points (APs) to have integrated antennas and not be battery powered, and reducing transmit power of client devices which may be outdoors. An accurate indoor/outdoor (I/O) classification addresses these challenges, enabling automatic transmit power adjustments without interfering with incumbents. To this end, we leverage the Global Navigation Satellite System (GNSS) signals for I/O classification. GNSS signals, designed inherently for outdoor reception and highly susceptible to indoor attenuation and blocking, provide a robust and distinguishing feature for environmental sensing. We develop various methodologies, including threshold-based techniques and machine learning approaches and evaluate them using an expanded dataset gathered from diverse geographical locations. Our results demonstrate that GNSS-based methods alone can achieve greater accuracy than approaches relying solely on wireless (Wi-Fi) data, particularly in unfamiliar locations. Furthermore, the integration of GNSS data with Wi-Fi information leads to improved classification accuracy, showcasing the significant benefits of multi-modal data fusion.

Indoor/Outdoor Spectrum Sharing Enabled by GNSS-based Classifiers

TL;DR

This work tackles the problem of reliably distinguishing indoor vs outdoor environments to enable spectrum sharing in the mid-band. It adds GNSS signals to the I/O classification pipeline and evaluates threshold-based and ML methods on a geographically diverse GNSS dataset collected with an extended SigCap app, showing GNSS features improve generalization and accuracy, especially when fused with Wi-Fi data and using temporal aggregation. The contributions include GNSS-enabled data collection across multiple cities, a thorough comparison of Th-based and ML methods, and the demonstration that containment concepts can inform transmit-power control beyond traditional indoor/outdoor labels. The findings have practical implications for automatic power management and regulation-friendly spectrum sharing in bands like GHz.

Abstract

The desirability of the mid-band frequency range (1 - 10 GHz) for federal and commercial applications, combined with the growing applications for commercial indoor use-cases, such as factory automation, opens up a new approach to spectrum sharing: the same frequency bands used outdoors by federal incumbents can be reused by commercial indoor users. A recent example of such sharing, between commercial systems, is the 6 GHz band (5.925 - 7.125 GHz) where unlicensed, low-power-indoor (LPI) users share the band with outdoor incumbents, primarily fixed microwave links. However, to date, there exist no reliable, automatic means of determining whether a device is indoors or outdoors, necessitating the use of other mechanisms such as mandating indoor access points (APs) to have integrated antennas and not be battery powered, and reducing transmit power of client devices which may be outdoors. An accurate indoor/outdoor (I/O) classification addresses these challenges, enabling automatic transmit power adjustments without interfering with incumbents. To this end, we leverage the Global Navigation Satellite System (GNSS) signals for I/O classification. GNSS signals, designed inherently for outdoor reception and highly susceptible to indoor attenuation and blocking, provide a robust and distinguishing feature for environmental sensing. We develop various methodologies, including threshold-based techniques and machine learning approaches and evaluate them using an expanded dataset gathered from diverse geographical locations. Our results demonstrate that GNSS-based methods alone can achieve greater accuracy than approaches relying solely on wireless (Wi-Fi) data, particularly in unfamiliar locations. Furthermore, the integration of GNSS data with Wi-Fi information leads to improved classification accuracy, showcasing the significant benefits of multi-modal data fusion.

Paper Structure

This paper contains 20 sections, 1 equation, 6 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset Overview
  4. GNSS Data Collection
  5. Dataset Summary and Geographic Diversity
  6. Data Processing and Preparation
  7. Feature Analysis and Classifiers
  8. Feature Analysis
  9. Receiver Operating Characteristic (ROC) Curves
  10. CNR vs. Elevation Angle Scatter Plots
  11. Classification Methods
  12. Results
  13. Classification Performance
  14. Further Improvement by Temporal Aggregation (Extended Window Technique)
  15. Comparison of GNSS and Wireless Data Classification
  16. ...and 5 more sections

Figures (6)

  • Figure 1: Symbolic illustration of the dataset structure. Rows with the same timestamp are grouped with a shared background color.
  • Figure 2: Geographic locations used in data collection (see Table \ref{['tab:indoor_outdoor_samples']} for abbreviations).
  • Figure 3: ROC curves for (a) an individual satellite's CNR, (b) mean CNR (c) number of observed satellites.
  • Figure 4: Scatter plots of CNR vs. Elevation Angle.
  • Figure 5: SigCap application showing live I/O classification.
  • ...and 1 more figures