Ship and Corner Reflector Identification Based on Extreme Learning Machine
Haodong Yuan, Xiongjun Fu, Congxia Zhao, Min Xie, Xuanyi Gao · 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · 2019
Corner reflector is a typical passive electronic jamming. In this paper, in order to reject corner reflector jamming effectively, the extreme learning machine algorithm is proposed to be used to discriminate ship and corner reflector base on the radar high resolution range profile (HRRP) differences, and the ship, the array corner reflectors and the combined corner reflectors electromagnetic models are built to verify the feasibility of this method. The simulation results show that there are average correct recognition rates all over 91% in SNR of ranging 0dB~15dB using the algorithm proposed with the average training time of 0.25 seconds. Compared to the support vector machine and deep belief network algorithm, the recognition rate and the training speed of the method proposed both have a better performance in the identification of ship and corner reflector.