Specific emitter identification (SEI) plays a crucial role in the security of the Industrial Internet of Things (IIoT). In recent years, research on applying deep learning (DL) methods for signal identification has mushroomed. However, DL-based SEI methods rely on a huge amount of training data and powerful computing devices, limiting their application scenarios. In addition, DL models are considered black box models with poor interpretability. To solve the above problems, this paper proposes a novel few-shot SEI solution using knowledge graph-driven incremental broad learning (KG-IBL). Specifically, this paper uses a deep belief network (DBN) to dig deep into features and expand the broad structure with additional enhancement nodes. Furthermore, the proposed KG-IBL does not need to retrain all data to achieve dynamic incremental update learning. To our knowledge, this is the first endeavor to integrate KG with broad learning for addressing the few-shot SEI problem. The experimental results demonstrate that the proposed KG-IBL surpasses existing incremental methods in both identification performance and computational overhead. Last but not least, the accuracy of the proposed KG-IBL is 97.5%, which is only 1.67% lower than the theoretical upper limit, and the training time is nearly 267 times lower than that of deep learning models. The code and dataset are available for download at https://github.com/Lollipophua/KG-IBL .

中文翻译：

---

KG-IBL： 知识图谱驱动的增量广泛学习，用于小样本特定发射器识别


特定发射机识别 （SEI） 在工业物联网 （IIoT） 的安全性中起着至关重要的作用。近年来，关于应用深度学习 （DL） 方法进行信号识别的研究如雨后春笋般涌现。然而，基于 DL 的 SEI 方法依赖于大量的训练数据和强大的计算设备，这限制了它们的应用场景。此外，DL 模型被认为是可解释性较差的黑盒模型。针对上述问题，本文提出了一种使用知识图谱驱动的增量广泛学习 （KG-IBL） 的新型小样本 SEI 解决方案。具体来说，本文使用深度信念网络 （DBN） 来深入挖掘特征，并通过额外的增强节点扩展广泛的结构。此外，所提出的 KG-IBL 不需要重新训练所有数据来实现动态增量更新学习。据我们所知，这是将 KG 与广泛学习相结合以解决少数 SEI 问题的第一次尝试。实验结果表明，所提出的 KG-IBL 在识别性能和计算开销方面都超过了现有的增量方法。最后但同样重要的是，所提出的 KG-IBL 的准确率为 97.5%，仅比理论上限低 1.67%，训练时间比深度学习模型低近 267 倍。代码和数据集可在 https://github.com/Lollipophua/KG-IBL 下载。