A time-frequency feature prediction network for time-varying radio frequency interference

The time-varying radio frequency interference has strong nonlinear dynamic characteristics, which is difficult to be predicted by linear method effectively, making the anti-interference decision without sufficient information support. To solve this problem, a recurrent neural network for spectrum prediction based on time-frequency correlation features proposed. A sliding window used characterize two-dimensional of series, and problem transformed into similar spatiotemporal sequence prediction. gradient bridge structure across time frames added reduce attenuation in long multi-level propagation. training efficiency performance are improved loss function with better matching. Simulation experimental results verify validity results.