Abstract:

Low Probability of Intercept (LPI) radar waveform recognition is one of the crucial functions in the electronic intelligence systems. Advances in artificial intelligence promote the performance of the LPI waveform recognition with various signal features defined with analytical expressions. However, noisy LPI waveform recognition is still a challenge for traditional approaches even with noise elimination techniques, especially for the heavily contaminated noisy LPI signals. Recently, the adaptive analysis techniques such as Variational Mode Decomposition (VMD) and Empirical Mode Decomposition (EMD) provide potential methods that explore the inherent features of signals and formulate adaptive features for signal recognitions. In this paper, we propose an adaptive feature construction framework that utilizes both the adaptive features (via VMD and EMD) and pre-defined analytical features (via Wigner-Ville Distribution (WVD), Choi-William Distribution (CWD), and wavelet analysis) to construct the fusion feature, which is further applied on the Convolutional Neural Networks (CNN) based LPI waveform recognition system. The experimental results show that the proposed Feature Adaptive LPI Network-based Exploitation (FALPINE) approach achieves higher probability of correct classification (PCC) than state-of-the-art works, which demonstrates the superior performance of the proposed approach.