An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

Abstract

Aiming at the current problem that it is difficult to deal with an unknown radar emitter in the radar emitter identification process, we propose an unknown radar emitter identification method based on semi-supervised and transfer learning. Firstly, we construct the support vector machine (SVM) model based on transfer learning, using the information of labeled samples in the source domain to train in the target domain, which can solve the problem that the training data and the testing data do not satisfy the same-distribution hypothesis. Then, we design a semi-supervised co-training algorithm using the information of unlabeled samples to enhance the training effect, which can solve the problem that insufficient labeled data results in inadequate training of the classifier. Finally, we combine the transfer learning method with the semi-supervised learning method for the unknown radar emitter identification task. Simulation experiments show that the proposed method can effectively identify an unknown radar emitter and still maintain high identification accuracy within a certain measurement error range.

Transfer Reinforcement Learning for Combinatorial Optimization Problems

“…For transfer learning, the knowledge base is first generated in a source domain and then applied to the target domain [17,18]. This approach is extremely beneficial in various situations, particularly when training for the target problem is complex [70]. By conducting experiments on a source problem, knowledge can be transferred to the target problem.…”

Physical Layer Authentication in Wireless Networks-Based Machine Learning Approaches

“…Machine learning (ML) is a subset of artificial intelligence (AI) that emerged from pattern recognition [ 10 ]. Lately, research in wireless communication has noted the distinction and effectiveness of machine learning by identifying the probability of learning based on signal classification [ 11 ] and specific emitter identification [ 12 , 13 ]. However, ML algorithms may face difficulty handling high-dimensional data because of the sizeable signals of raw data.…”

“…However, expert-defined signal features require a lot of the raw signal data to be preprocessed, for example, synchronization, carrier tracking, demodulation, signal-to-noise ratio (SNR) estimation, and the computational cost of measuring or estimating the expert features [ 67 ]. Moreover, their different domains extract features in signal processing, including the time domain, frequency domain, and time-frequency domain [ 13 ]. As well, these domains are based on five signal parameters pulse repetition interval (PRI), the direction of arrival (DOA), pulse frequency (PF), pulse width (PW), pulse amplitude (PA); all these parameters are combined in a pulse descriptive word (PWD) [ 16 , 69 ].…”

Intrapulse Recognition of Radar Signals Via Bicubic Interpolation WVD

“…Domain transformations, signal properties, and hardware equipment can all lead to variations in the dimensions of intra-pulse samples that need to be recognized. These issueshave hindered the development of IPR technology, especially under complex conditions [24][25] [26][27][28] [29]. Therefore, addressing the issue of varying dimensions is crucial for IPR.…”