Deep Learning-Based Drone Classification Using Radar Cross Section Signatures at mmWave Frequencies

IEEE Access

Rui Fu¹  Mohammed Abdulhakim Al-Absi²  Ahmed Abdulhakim Al-Absi³  Hoon-Jae Lee⁴  Young-Sil Lee⁵  Ki-Hwan Kim⁵ 

[1] Blockchain Laboratory of Agriculture and Vegetables, Weifang University of Science and Technology, Weifang, China;Department of Computer Engineering, Graduate School, Dongseo University, Sasang-gu, South Korea;Department of Smart Computing, Kyungdong University, Goseong, South Korea;Division of Information and Communication Engineering, Dongseo University, Sasang-gu, South Korea;International College, Dongseo University, Busan, South Korea;

关键词: Convolutional neural network;    drone detection;    micro doppler signature (MDS);    unmanned aerial vehicle;    UAV;    radar cross-section;   

DOI  :  10.1109/ACCESS.2021.3115805

来源: DOAJ

【 摘 要 】

This paper presents drone classification at millimeter-wave (mmWave) radars using the deep learning (DL) technique. The adoption mmWave technology in radar systems enables better resolution and aid in detecting smaller drones. Using radar cross-section (RCS) signature enables us to detect malicious drones and suitable action can be taken by respective authorities. Existing drone classification converts the RCS signature into images and then performs drone classification using a convolution neural network (CNN). Converting every signature into an image induces additional computation overhead; further CNN model is trained considering fixed learning rate. Thus, when using CNN-based drone classification under a highly dynamic environment exhibit poor classification accuracy. This paper present an improved long short-term memory (LSTM) by introducing a weight optimization model that can reduce computation overhead by not allowing the gradient to not flow through hidden states of the LSTM model. Further, present adaptive learning rate optimizing (ALRO) model for training the LSTM model. Experiment outcome shows LSTM-ALRO achieves much better drone detection accuracies of 99.88% when compared with the existing CNN-based drone classification model.

【 授权许可】

Unknown