ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing

Hwa Hui Tew, Fan Ding, Gaoxuan Li, Junn Yong Loo, Chee-Ming Ting +2 more
1/2/2025
cs.LGcs.AIeess.SP

Official code: htew0001/ST-HCSS (1 star, last commit 2025-03-29).

Abstract

Higher-order sensor networks are more accurate in characterizing the nonlinear dynamics of sensory time-series data in modern industrial settings by allowing multi-node connections beyond simple pairwise graph edges. In light of this, we propose a deep spatio-temporal hypergraph convolutional neural network for soft sensing (ST-HCSS). In particular, our proposed framework is able to construct and leverage a higher-order graph (hypergraph) to model the complex multi-interactions between sensor nodes in the absence of prior structural knowledge. To capture rich spatio-temporal relationships underlying sensor data, our proposed ST-HCSS incorporates stacked gated temporal and hypergraph convolution layers to effectively aggregate and update hypergraph information across time and nodes. Our results validate the superiority of ST-HCSS compared to existing state-of-the-art soft sensors, and demonstrates that the learned hypergraph feature representations aligns well with the sensor data correlations. The code is available at https://github.com/htew0001/ST-HCSS.git

View on arXivView PDF

Code Implementations(1)

htew0001/ST-HCSSOfficial100%

ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing

10Dec 28, 20241 years ago

Similar Papers

Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction

81% match1 repo2024

KANS: Knowledge Discovery Graph Attention Network for Soft Sensing in Multivariate Industrial Processes

81% match2025

Hypergraph-based multi-scale spatio-temporal graph convolution network for Time-Series anomaly detection

80% match2024

A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide

80% match2024

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data

78% match1 repo1332023

Graph Neural Networks for Virtual Sensing in Complex Systems: Addressing Heterogeneous Temporal Dynamics

78% match1 repo142024

Cite this paper

@article{tew2025sthcss,
  title  = {ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing},
  author = {Hwa Hui Tew and Fan Ding and Gaoxuan Li and Junn Yong Loo and Chee-Ming Ting and Ze Yang Ding and Chee Pin Tan},
  year   = {2025},
  eprint = {2501.02016},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.02016v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.02016.svg)](https://codeofpaper.com/paper/2501.02016)

Discussion