RF-Based UAV Detection and Identification Using Hierarchical Learning Approach.

Area of Science:

• Electrical Engineering
• Computer Science
• Artificial Intelligence

Background:

• Unmanned Aerial Vehicles (UAVs) have diverse applications, but their illicit use presents a significant security challenge.
• Effective identification and detection of UAVs are crucial for addressing security concerns and enabling responsible usage.

Purpose of the Study:

• To propose a novel machine learning-based approach for efficient identification and detection of UAVs.
• To develop a hierarchical ensemble learning system for accurate UAV classification and mode determination.

Main Methods:

• Utilized Radio Frequency (RF) data for UAV detection and identification.
• Implemented a hierarchical ensemble learning model with four classifiers for sequential analysis.
• Incorporated pre-processing, feature extraction, and filtering stages to enhance RF signal analysis.

Main Results:

• The proposed approach achieved high accuracy, around 99%, in identifying UAV presence, type, and flight mode.
• Demonstrated superior efficiency compared to existing UAV detection systems in the literature.
• Successfully classified specific UAV models like Bebop and AR, and their operational modes.

Conclusions:

• The developed machine learning model offers a robust solution for real-time UAV detection and identification.
• The hierarchical ensemble approach provides a scalable and accurate method for monitoring airspace and mitigating potential threats from unauthorized UAVs.