Low-Cost COTS GNSS Interference Monitoring, Detection, and Classification System.

Area of Science:

• Electrical Engineering
• Computer Science
• Aerospace Engineering

Background:

• Interference signals degrade Global Navigation Satellite System (GNSS) receiver performance, causing position errors and outages.
• Existing interference monitoring solutions are costly, limiting deployment density and the ability to detect sparse interference signals.

Purpose of the Study:

• To introduce a low-cost Commercial-Off-The-Shelf (COTS) GNSS interference monitoring, detection, and classification receiver.
• To develop a generalized, high-performance architecture using machine learning (ML) that eliminates the need for human-in-the-loop (HIL) calibration.
• To enable significantly increased receiver deployment for a higher probability of intercept (POI).

Main Methods:

• Utilized tailored signal pre-processing of raw signal samples and GNSS measurements.
• Employed machine learning (ML) algorithms for interference detection and classification.
• Detailed the architecture of the monitoring system, including energy consumption analysis and optimization.

Main Results:

• Controlled interference scenarios demonstrated superior detection and classification capabilities compared to conventional methods.
• Machine learning results confirmed accurate and reliable interference detection and classification are achievable with COTS hardware.
• The proposed architecture offers high performance with optimized energy consumption.

Conclusions:

• The developed low-cost COTS GNSS interference receiver provides a viable solution for enhancing GNSS signal security.
• Widespread deployment of these receivers significantly increases the probability of detecting and mitigating interference.
• ML-driven, HIL-free calibration offers a scalable and effective approach to GNSS interference management.