Radar recognition system based on XG-Boost

Abstract

With the development of science and technology, radar recognition has gradually entered our lives. With the introduction of deep learning technology in the field of radar recognition, with its strong automatic feature learning ability and end-to-end processing advantages, its recognition accuracy has been further improved. Based on this, a radar recognition system based on XG-Boost is proposed in this paper. The system was used to identify five different materials: air, books, hands, knives and plastic boxes. After a series of experiments, it is found that the recognition accuracy of XG-Boost algorithm is as high as 97.8%, which is higher than the 96.4% of SVC algorithm and 92.8% of GaussianNB algorithm. And the XG-Boost algorithm has achieved 100% recognition rate for air, books, hands and plastic boxes. There was only an error in the identification of the knife.