用黎曼流形嵌入工业传感器信号，提升模式识别鲁棒性
RIE-SenseNet: Riemannian Manifold Embedding of Multi-Source Industrial Sensor Signals for Robust Pattern Recognition
- 基于双曲几何的Transformer模型，捕捉传感器数据非线性结构
- 在多种工业数据集上F1分数超90%，显著优于传统CNN和Transformer
- 适合需要高鲁棒性的工业异常检测与故障诊断场景
工业传感器网络产生具有非线性结构和分布漂移的复杂信号。我们提出RIE-SenseNet，一种新型几何感知Transformer模型，将传感器数据嵌入黎曼流形以应对这些挑战。通过利用双曲几何进行序列建模，并引入基于流形的数据增强技术，RIE-SenseNet保持了传感器信号的结构特征，并生成真实的合成样本。实验表明，RIE-SenseNet在多个工业数据集上的F1分数均超过90%，远超CNN和Transformer基线模型。结果表明，将非欧几里得特征表示与几何一致的数据增强相结合，可显著提升工业传感中模式识别的鲁棒性。
原文摘要 · Abstract (English)
Industrial sensor networks produce complex signals with nonlinear structure and shifting distributions. We propose RIE-SenseNet, a novel geometry-aware Transformer model that embeds sensor data in a Riemannian manifold to tackle these challenges. By leveraging hyperbolic geometry for sequence modeling and introducing a manifold-based augmentation technique, RIE-SenseNet preserves sensor signal structure and generates realistic synthetic samples. Experiments show RIE-SenseNet achieves >90% F1-score, far surpassing CNN and Transformer baselines. These results illustrate the benefit of combining non-Euclidean feature representations with geometry-consistent data augmentation for robust pattern recognition in industrial sensing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。