A Method for Detecting Anomalies in an Electromagnetic Environment Situation Using a Dual-Branch Prediction Network

Electromagnetic environment situation anomaly detection is a prerequisite for electromagnetic threat level assessment, and its research of great practical value. However, because the complexity environment, not efficient. Therefore, we propose dual-branch prediction network-based method to predict future achieve by fusing different development characteristics situations learned other branches. We extract state trend features using manual feature extraction module mine in-depth data distribution ConvLSTM, improve dynamic time regularization model according physical space, then provide method. experimentally demonstrate effectiveness proposed in accuracy.