Is this project an undergraduate, graduate, or faculty project?
Undergraduate
Project Type
group
Campus
Daytona Beach
Authors' Class Standing
Lynette Ramirez: - Senior Undergraduate student Khushboo Patel - Graduate Student
Lead Presenter's Name
Lynette Ramirez
Lead Presenter's College
DB College of Engineering
Faculty Mentor Name
David Garcia Canales
Abstract
This research aims to detect Unmanned Aerial Vehicles (UAVs) through the implementation of innovative machine-learning techniques based on pattern recognition and quantum signal processing applied to acoustic data. The presence of UAV is detected in audio signals through spectral descriptors. Fourier transform-based frequency analysis is used to identify anomalies, and recognize patterns to train a Support Vector Machine algorithm enabling classification of the UAV from background noise. Quantum signal processing techniques are employed to improve the accuracy of UAV detection. The analysis demonstrates a 90 \% confidence in predicting drone presence. The proposed acoustic detection method is both cost-effective and innovative, utilizing sound, inherent in natural systems, to achieve reliable results.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
Yes, Spark Grant
Unmanned Aerial Vehicles Detection Using Acoustics and Quantum Signal Processing
This research aims to detect Unmanned Aerial Vehicles (UAVs) through the implementation of innovative machine-learning techniques based on pattern recognition and quantum signal processing applied to acoustic data. The presence of UAV is detected in audio signals through spectral descriptors. Fourier transform-based frequency analysis is used to identify anomalies, and recognize patterns to train a Support Vector Machine algorithm enabling classification of the UAV from background noise. Quantum signal processing techniques are employed to improve the accuracy of UAV detection. The analysis demonstrates a 90 \% confidence in predicting drone presence. The proposed acoustic detection method is both cost-effective and innovative, utilizing sound, inherent in natural systems, to achieve reliable results.