基于轻量化视觉Transformer的间歇采样干扰类型识别OA

As the electromagnetic spectrum environment becomes increasingly complex,enhancing the recognition capa-bility of Interrupted Sampling Repeater Jamming(ISRJ)—a representative type of jamming characterized by strong con-cealment and dynamic behavior-has become crucial for ensuring radar detection performance.ISRJ is an intra-pulse co-herent jamming method realized via partial sampling,storage,and coherent retransmission of radar signals.Existing rec-ognition methods predominantly treat ISRJ as a single category,with limited modeling capacity and insufficient param-eter generalization,thereby restricting their effectiveness in complex electromagnetic environments.To address this limi-tation,this study proposes an integrated recognition framework that synergistically combines time-frequency feature di-mensionality reduction with a lightweight Vision Transformer architecture.The framework first employs a Kronecker separable dictionary learning algorithm based on closed-form Alternating Least Squares(ALS)for structure-preserving reduction of time-frequency representations.This approach effectively retains key discriminative features of ISRJ,in-cluding"intermittency"and"striped structures",while substantially reducing computational cost and memory over-head.Subsequently,a lightweight Vision Transformer that integrates local convolutional priors and global self-attention mechanisms is developed to balance fine-grained feature representation with long-range dependency modeling,thereby improving robustness to parameter variations.The inference speed surpasses that of both standard Transformers and typi-cal lightweight CNNs,with particularly pronounced advantages in multi-class ISRJ recognition under low Jamming-to-Noise Ratio(JNR)conditions,demonstrating improved efficiency and practical deployment potential.