Learning using privileged information for HRRP-based radar target recognition

• Published in: IET signal processing Vol. 12; no. 2; pp. 188 - 197
• Main Authors: Guo, Yu, Xiao, Huaitie, Kan, Yingzhi, Fu, Qiang
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.04.2018
• Subjects: close nonlinear boundary advantage; complex high‐resolution range profile; ESVDD‐neg; extended support vector data description‐with‐negative examples; fast Fourier transforms; fast Fourier transform‐magnitude feature classification; HRRP‐based radar target recognition; learning (artificial intelligence); learning paradigm; low signal‐to‐noise ratio; machine learning method; radar automatic target recognition problem; radar computing; radar signal processing; radar target recognition; Research Article; signal classification; translation sensitivity; UCI datasets; fast Fourier transforms; fast Fourier transform-magnitude feature classification; ESVDD-neg; UCI datasets; extended support vector data description-with-negative examples; HRRP-based radar target recognition; machine learning method; low signal-to-noise ratio; radar signal processing; signal classification; translation sensitivity; radar computing; radar target recognition; learning paradigm; close nonlinear boundary advantage; complex high-resolution range profile; learning (artificial intelligence); radar automatic target recognition problem
• ISSN: 1751-9675; 1751-9683; 1751-9683
• DOI: 10.1049/iet-spr.2016.0625

A novel machine learning method named extended support vector data description with negative examples (ESVDD-neg) is developed to classify the fast Fourier transform-magnitude feature of complex high-resolution range profile (HRRP), motivated by the problem of radar automatic target recognition. The proposed method not only inherits the close non-linear boundary advantage of support vector data description with negative examples model but also incorporates a new learning paradigm named learning using privileged information into the model. It leads to the appealing application with no assumptions regarding the distribution of data and needs less training samples and prior information. Besides, the second order central moment is selected as privileged information for better recognition performance, weakening the effect of translation sensitivity, and the normalisation contributes to eliminating the amplitude sensitivity. Hence, there will be a remarkable improvement of recognition accuracy not only with small training dataset but also under the condition of low signal-to-noise ratio. Numerical experiments based on two publicly UCI datasets and HRRPs of four aircrafts demonstrate the feasibility and superiority of the proposed method. The noise robust ESVDD-neg is ideal for HRRP-based radar target recognition.