UAV signal recognition of heterogeneous integrated KNN based on genetic algorithm

To address the detection difficulty problem of unmanned aerial vehicles (UAVs) in complex electromagnetic environments, this paper proposes a genetic algorithm-based heterogeneous integrated k-nearest neighbor (KNN) model for UAV signal recognition. First, the original data is pre-processed by discrete Fourier transform (DFT). Next, the genetic algorithm is deployed to find feature points for each base classifier to be integrated into the high-density power spectrum. Following this, each base classifier to be integrated is set into a strong classifier, and finally, the data to be detected is transferred to the trained integrated classifier to get the UAV signal detection results. The experimental results show that the genetic algorithm bagging KNN (GA-Bagging-KNN) algorithm achieves 98% accuracy in detecting binary classification and 79% accuracy in quadruple classification.