Data Driven Environmental Awareness Using Wireless Signals

2024-10-17

AI Summary

To address power violations and spectrum interference caused by inaccurate indoor/outdoor localization of wireless devices in the 6 GHz shared spectrum, this paper proposes a fine-grained environmental classification method that fuses multi-source wireless signals (cellular/Wi-Fi RSSI across all available bands) with GPS accuracy metrics. The method robustly discriminates among three critical scenarios: deep indoor, near-window, and outdoor. We design a lightweight deep neural network—first to systematically integrate heterogeneous RF and GNSS features—and specifically optimize it to suppress the safety-critical error of misclassifying outdoor locations as deep indoor. Experiments on real-world deployments demonstrate state-of-the-art accuracy and significantly lower critical misclassification rates compared to baseline models (e.g., decision trees, random forests), thereby validating the feasibility of non-intrusive, RF-fingerprint-based regulatory compliance monitoring.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Robust classification of the operational environment of wireless devices is becoming increasingly important for wireless network optimization, particularly in a shared spectrum environment. Distinguishing between indoor and outdoor devices can enhance reliability and improve coexistence with existing, outdoor, incumbents. For instance, the unlicensed but shared 6 GHz band (5.925 - 7.125 GHz) enables sharing by imposing lower transmit power for indoor unlicensed devices and a spectrum coordination requirement for outdoor devices. Further, indoor devices are prohibited from using battery power, external antennas, and weatherization to prevent outdoor operations. As these rules may be circumvented, we propose a robust indoor/outdoor classification method by leveraging the fact that the radio-frequency environment faced by a device are quite different indoors and outdoors. We first collect signal strength data from all cellular and Wi-Fi bands that can be received by a smartphone in various environments (indoor interior, indoor near windows, and outdoors), along with GPS accuracy, and then evaluate three machine learning (ML) methods: deep neural network (DNN), decision tree, and random forest to perform classification into these three categories. Our results indicate that the DNN model performs the best, particularly in minimizing the most important classification error, that of classifying outdoor devices as indoor interior devices.

Problem

• Indoor-Outdoor Classification
• Wireless Network Optimization
• 6GHz Band Spectrum Sharing

Innovation

• Wireless Signal Feature
• Deep Neural Network
• Indoor-Outdoor Classification