A Parameter-Optimized SLS-TSVM Method for Working Modes Recognition of Airborne Fire Control Radar

Due to the non-cooperative characteristic of electronic warfare, the reconnaissance intelligence is limited. To realize radar working modes recognition under this circumstance, a parameter-optimized SLS-TSVM method is proposed. First, extract features of intercepted signals and establish the intelligence database. Next, pseudo-mark the unlabeled signal samples by regional sample labeling method, during which grid search and $K$-fold cross validation are applied to optimize parameters, adjust model and improve generalization ability. Simulation results show that recognition accuracy of Velocity Search (VS) / Single Target Track (STT) / Range While Search (RWS) / Track While Scan (TWS) modes reaches 99.1%, proving good recognition performance and practical value of proposed method.