RIE-SenseNet: Riemannian Manifold Embedding of Multi-Source Industrial Sensor Signals for Robust Pattern Recognition
This addresses robust pattern recognition for industrial sensor networks, but it appears incremental as it combines existing concepts like hyperbolic geometry and data augmentation in a specific domain.
The paper tackled the problem of robust pattern recognition for complex industrial sensor signals with nonlinear structure and shifting distributions by proposing RIE-SenseNet, a geometry-aware Transformer model that embeds data in a Riemannian manifold, achieving over 90% F1-score and surpassing CNN and Transformer baselines.
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.