Comparison of spectrogram, persistence spectrum and percentile spectrum based image representation performances in drone detection and classification using novel HMFFNet: Hybrid Model with Feature Fusion Network
作者：
Highlights：
• HMFFNet, a new drone detection and classification framework, is proposed.
• RF signals are represented by spectrogram, persistence and percentile spectrums.
• VGG19 net is utilized for feature extraction from the obtained images.
• Features are fused in various combinations and then processed using SVM classifier.
• Obtained experimental results are compared with that of state-of-the-art studies.
摘要
•HMFFNet, a new drone detection and classification framework, is proposed.•RF signals are represented by spectrogram, persistence and percentile spectrums.•VGG19 net is utilized for feature extraction from the obtained images.•Features are fused in various combinations and then processed using SVM classifier.•Obtained experimental results are compared with that of state-of-the-art studies.
论文关键词：Artificial intelligence,RF signal,Drone classification,VGG19,SVM,Hybrid model,Feature fusion,HMFFNet
论文评审过程：Received 28 December 2021, Revised 31 March 2022, Accepted 27 May 2022, Available online 16 June 2022, Version of Record 25 June 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117654
