WCSE

A UAV Spectrum Classification Framework Based on ResNet50 Algorithm

Abstract—Unmanned Aerial Vehicle (UAV) category recognition is a significant problem for airport airspace operation. An accurate and efficient identification of UAV is expected to fast predict of UAV behavior and implement the defense. This study presents an UAV spectrum classification framework using radio frequency (RF) signals. In the framework, the spectrum is combined with the ResNet50 neural network model. An open source dataset namely DroneRF is used to test the efficiency of the proposed method. The experimental results show that the highest accuracy rate of the proposed framework reached to 100%. Compared with the state-ofthe-art method, this study has a higher improvement of accuracy rates.

Index Terms—UAV, spectrum detection, artificial intelligence, classification

Qihang Liu
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, CHINA
Shuo Su
College of Electronic and Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics,CHINA
Yao Yao, Bing Gui, Zhiyuan Shen
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, CHINA

[Download]

Cite: Qihang Liu, Shuo Su, Yao Yao, Bing Gui, Zhiyuan Shen, "A UAV Spectrum Classification Framework Based on ResNet50 Algorithm" Proceedings of 2023 the 13th International Workshop on Computer Science and Engineering (WCSE 2023), pp. 231-237, June 16-18, 2023.