A driver discrimination method based on channel state detection

The invention relates to a method for distinguishing different drivers based on wireless channel detection, which utilizes common computer equipment to build a wireless channel information data acquisition platform. The detection is divided into two stages: offline training stage and online test stage; The off-line phase collects the channel state information data of different drivers, pretreats the data, extracts statistical features, and stores them into fingerprint databases of different actions after normalization processing to establish actions. Mapping relation of data fingerprint; In the on-line phase, the data are processed in the same way, and the test data are classified and detected by machine learning algorithm. At the same time, in order to test the accuracy of classification,the amplitude and phase information of channel state information data are synthetically used to observe the classification results in three cases. The invention can effectively realize the identification and differentiation