Specific Emitter Identification via Active Learning

TL;DR

This paper introduces an active learning-based approach for specific emitter identification in wireless communications, reducing the need for large labeled datasets while improving recognition accuracy.

Contribution

It proposes a three-stage semi-supervised training scheme combining self-supervised contrastive learning, supervised training, and active sample selection for efficient SEI.

Findings

Outperforms traditional supervised methods with limited labels

Achieves higher recognition accuracy on ADS-B and WiFi datasets

Reduces labeling costs significantly

Abstract

With the rapid growth of wireless communications, specific emitter identification (SEI) is significant for communication security. However, its model training relies heavily on the large-scale labeled data, which are costly and time-consuming to obtain. To address this challenge, we propose an SEI approach enhanced by active learning (AL), which follows a three-stage semi-supervised training scheme. In the first stage, self-supervised contrastive learning is employed with a dynamic dictionary update mechanism to extract robust representations from large amounts of the unlabeled data. In the second stage, supervised training on a small labeled dataset is performed, where the contrastive and cross-entropy losses are jointly optimized to improve the feature separability and strengthen the classification boundaries. In the third stage, an AL module selects the most valuable samples from the unlabeled data for annotation based on the uncertainty and representativeness criteria, further enhancing generalization under limited labeling budgets. Experimental results on the ADS-B and WiFi datasets demonstrate that the proposed SEI approach significantly outperforms the conventional supervised and semi-supervised methods under limited annotation conditions, achieving higher recognition accuracy with lower labeling cost.