Interrupted Sampling Repeater Jamming Suppression Using Complex-Valued FISTA-Net

Recent research has shown that the unrolling network is an effective and efficient method for suppressing interrupted sampling repeater jamming (ISRJ). However, in practice, variability in jamming location and duty cycle often prevents most unrolling networks from achieving satisfactory ISRJ suppression performance. To address this challenge, this article introduces complex-valued fast iterative shrinkage-thresholding algorithm network (CV-FISTA-Net), a complex-valued unrolling network inspired by the FISTA method. CV-FISTA-Net replaces the conventional soft-thresholding operator with a complex-valued convolutional neural network (CV-CNN) and a residual learning approach. This enhances training efficiency, signal denoising, and reconstruction fidelity. Furthermore, a random projection augmentation strategy is introduced to diversify the training set, bolstering the network's robustness against variations in ISRJ location and duty cycle. To improve generalization, a transfer learning technique is integrated, ensuring strong jamming suppression performance even with limited training data or under changing conditions, such as varying signal-to-noise ratios. Leveraging the computational efficiency of CV-FISTA-Net, we also propose an effective strategy for joint ISRJ suppression and inverse synthetic aperture radar (ISAR) imaging. Experiments on both simulated and real-measured data validate that CV-FISTA-Net achieves precise and robust ISRJ suppression amidst dynamic changes in jamming location and duty cycle.