Modulation types clustering (MC) is crucial for adaptive high-frequency communication between devices in the Industrial Internet of Things. The strength of MC resides in its self-supervised framework, enabling it to extract modulation features efficiently without any manual labeling. However, the misalignment of proxy tasks and erroneous pseudolabeling constrain the performance of prevalent MC feature extraction techniques that utilize time series signals. In this article, we compare the saliency maps on time_frequency image (TFI) with that on time series signal, highlighting the consistency of TFI reconstruction with modulation feature extraction. Subsequently, in order to address the sensitivity of K-means to outliers, Sinkhorn_Knopp labeling (SKLb) is proposed to balance the scale of clusters and neighboring distances. Moreover, in consideration of the potential instability of the SKLb iteration result in backpropagation, the Sinkhorn_Knopp loss is proposed to ensure stable training of the model. Finally, two models, SK-IDC and SK-STDC, were tested on four datasets. Experimental results on these datasets present that our approach outperforms original signal representation and prevalent deep clustering methods, achieving State-of-the-Art performance.

中文翻译：

---

无监督信号调制聚类的 Sinkhorn__nopp 损失生成模型


调制类型集群 (MC) 对于工业物联网中设备之间的自适应高频通信至关重要。 MC 的优势在于其自我监督框架，使其能够有效地提取调制特征，而无需任何手动标记。然而，代理任务的错位和错误的伪标记限制了利用时间序列信号的流行 MC 特征提取技术的性能。在本文中，我们将时频图像（TFI）上的显着图与时间序列信号上的显着图进行了比较，强调了 TFI 重建与调制特征提取的一致性。随后，为了解决 K 均值对异常值的敏感性，提出了 Sinkhorn_Knopp 标记（SKLb）来平衡簇的规模和邻近距离。此外，考虑到SKLb迭代结果在反向传播中潜在的不稳定性，提出了Sinkhorn_Knopp损失以保证模型的稳定训练。最后，在四个数据集上测试了两个模型 SK-IDC 和 SK-STDC。这些数据集的实验结果表明，我们的方法优于原始信号表示和流行的深度聚类方法，实现了最先进的性能。