A Few-Shot Modulation Recognition Method Based on Pseudo-Label Semi-Supervised Learning

Abstract

In order to solve the problem of insufficient labeled samples in modulation recognition, this paper proposes a few-shot modulation recognition algorithm based on pseudo-label semi-supervised learning (pseudo-label algorithm). First of all, high quality artificial feature, excellent classifier and data-labeling method are used to build efficient pseudo label system, and then the pseudo label system is combined with signal classification method based on the deep learning to realize the modulation classification under the condition of a small number of labeled samples and a large number of unlabeled samples. The simulation results show that the pseudo-label algorithm can improve the model recognition performance by 5%-10% when the six kinds of digital signals are classified and identified and its SNR is greater than 5 dB. At the same time, the algorithm has a simple network design and is of great application value.

Combining BERT Model with Semi-Supervised Incremental Learning for Heterogeneous Knowledge Fusion of High-Speed Railway On-Board System

“…To decrease the construction burden of labeled data sets, maximize the advantages of unlabeled and limited-labeled samples, and rapidly expand the size of the training set, we propose a pseudo-label-based semi-supervised incremental (SSI) learning strategy, which enables the model to collaboratively utilize pseudo-labeled samples to further optimize the heterogeneous knowledge fusion effect. Although unlabeled test data does not have the label information, they are the same as labeled data, which are obtained from the same data source and meet the assumption of independent and identically distributed [ 25 ]. Therefore, the information they contain is very beneficial to the optimization model.…”