This study compares the performance of a Hybrid Quantum Neural Network (HQNN) with a Convolutional Neural Network (CNN) for drone detection and classification using radar data. The HQNN shows superior performance at low signal-to-noise ratios, emphasizing its potential for real-world applications. The research delves into the complexities of radar returns from drones, utilizing models like Martin-Mulgrew to simulate signals. By analyzing X-band radar data from various drones, the study evaluates the effectiveness of both HQNN and CNN models across different SNR levels. Results indicate that HQNN excels in scenarios with low SNR, making it a promising approach for drone detection tasks. The paper also discusses the architecture and training methods for both types of neural networks, providing insights into their design choices and model evaluations.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Aiswariya Sw... at arxiv.org 03-05-2024
https://arxiv.org/pdf/2403.02080.pdfDeeper Inquiries