⌘+K

Pulse Explore Communities Researchers Journals

Home Communities Explore

June 26, 2026Journal of KIISE

Topology-based Lightweight Anomaly Detection via Functional Patch Decomposition in Industrial Control Systems

Yooshin Kim Wonje Heo Chuck Chae Donghoon Shin

View at Publisher

Ask AI

Bookmark

Share

Key Points

To develop a lightweight anomaly detection method that combines precision and efficiency in industrial control systems.
Proposed a deep learning framework utilizing functional patch decomposition reflecting physical and logical topology.
Evaluated the model's performance using SWaT and WADI testbeds, ensuring real-time applicability.
Integrated anomaly scores at functional and system levels for improved detection.
Achieved high anomaly detection performance with robust distribution change handling.
Demonstrated excellent computational efficiency suitable for real-time systems.
Successfully combined contextual information into anomaly detection scores.

Implication

Shows enhanced anomaly detection performance in industrial control systems, indicating improved efficiency.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/6a40b9c461bb0a67205c5de6 https://doi.org/10.5626/jok.2026.53.6.455

View at Publisher

Ask AI

Bookmark

Share

Keep reading

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Novel adaptive approach for anomaly detection in nonlinear and time-varying industrial systems2024 · 1 citations
2WEDGE-Net: Wavelet-Driven Memory-Efficient Anomaly Detection for Industrial Edge ComputingOriginal Research · 2026
3A Multifaceted Approach for Enhancing Anomaly Detection in Industrial Systems with Adaptive Synthetic Sampling and Machine Learning Evaluation2024 · 3 citations
4AI-Driven Real-Time Anomaly Detection in Industrial Cyber-Physical Systems Using Hybrid Deep Learning with SWaT and WADI BenchmarksOriginal Research · 2026
5A hybrid generative and transformer-based framework for anomaly detection in industrial sensor time-series for predictive maintenanceOriginal Research · 2026 · 1 citations

More related papers

A Reality Gap Taxonomy for Physics-Informed Anomaly Detection in Industrial Control Systems: Cross-Regime Evaluation, Operating-Point and Temporal Distribution Shifts2026
AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detection2024
Industrial Anomaly Detection: A Comparison of Unsupervised Neural Network Architectures2020

More from Journal of KIISE

Dense Video-to-Video Retrieval with Spatio-Temporal Scene GraphsMon,
A Math Tutoring Dataset Based on Student Comprehension States for Socratic Question GenerationMon,