Flight Conflict Detection Algorithm Based on Relevance Vector Machine

In response to the problems of slow running speed and high error rates traditional flight conflict detection algorithms, in this paper, we propose a algorithm based on use relevance vector machine. A set symmetrical historical data was used as training model, SMOTE resampling method optimize set. We obtained relatively trained it with machine, improving kernels through an intelligent algorithm. tested new data. The improved greatly able effectively reduce missed alarm rate in-flight symmetrically, thus ensuring safety.