LAUSR

RF transmitter identification is facing a big challenge since the increasing use of wireless devices in recent years. Traditional methods for identification are implemented by choosing specific rapid fingerprints manually, which fails to distinguish threats from unknown or rogue transmitters in a few shots under the complex electromagnetic environment. In order to solve this problem, a combined Siamese networks learning method for RF transmitter identification (CSNTI) is proposed in this work by considering both the data augmentation and the classical fingerprints of RF signals. The proposed method is composed of a series of classifiers trained by Siamese networks. Each classifier is utilized to distinguish one transmitter from others. Based on the special structure of Siamese networks, the number of training samples for each classifier increases greatly, which is efficient for data augmentation and takes full use of the limited RF transmitter signals. Then, the softmax procedure is followed to normalize the output of all classifiers. A criterion for unknown transmitters’ identification is proposed. Numerical experiments for basic classification and new devices identification with eight known transmitters and three unknown transmitters are validated. Results of compared methods suggest that the highest accuracy across a broad range of conditions is achieved by the proposed method.