GP ‐KAT: Enhanced Kolmogorov–Arnold Transformer With Periodic Gaussian Process for Anomaly Detection in Thin‐Film Transistor Array Manufacturing
IET Signal Processing · 2026-01 · 2026 (1)
DOI: 10.1049/sil2/1914287 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Signal Processing, online erschienen am 02.08.2026. Verfasst von Weiwei Chen und 1 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In thin‐film transistor (TFT) array manufacturing, material inconsistencies and process imperfections frequently induce defects that severely compromise production yield. Traditional manual inspection remains labor‐intensive and susceptible to subjective bias, thereby limiting manufacturing capacity. While convolutional neural networks (CNNs) have shown promise in automating anomaly detection, the application of vision transformers (ViTs) in this domain remains relatively unexplored. This study introduces Gaussian Process Kolmogorov–Arnold Transformer ( GP ‐KAT), a structure‐aware architecture that combines the nonlinear representation capacity of the KAT with GP‐inspired locally periodic kernel modeling and variance‐aware anomaly prediction. To address the inherent periodicity of TFT array imagery, we propose a GPKAN layer that incorporates a locally periodic Gaussian kernel to enhance structural feature extraction. Furthermore, a feature variance augmented head is designed to explicitly quantify predictive uncertainty, facilitating more reliable anomaly scoring under ambiguous conditions. Extensive experiments on a newly curated industrial dataset show that GP ‐KAT outperforms representative ViT‐based baselines under a unified training protocol. By improving detection accuracy and providing informative uncertainty estimates under the tested conditions, the proposed approach offers a promising direction for TFT array inspection.
Zitieren
APA
Chen, W., & Leong, W. Y. (2026). GP ‐KAT: Enhanced Kolmogorov–Arnold Transformer With Periodic Gaussian Process for Anomaly Detection in Thin‐Film Transistor Array Manufacturing. IET Signal Processing, 2026(1). https://doi.org/10.1049/sil2/1914287
Vancouver
Chen W, Leong WY. GP ‐KAT: Enhanced Kolmogorov–Arnold Transformer With Periodic Gaussian Process for Anomaly Detection in Thin‐Film Transistor Array Manufacturing. IET Signal Processing. 2026;2026(1). doi:10.1049/sil2/1914287
BibTeX
@article{Chen2026,
author = {Chen, Weiwei and Leong, Wai Yie},
title = {GP ‐KAT: Enhanced Kolmogorov–Arnold Transformer With Periodic Gaussian Process for Anomaly Detection in Thin‐Film Transistor Array Manufacturing},
journal = {IET Signal Processing},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1049/sil2/1914287}
}
EUVIMED