Pavel Klavík, A. Cristiano I. Malossi, et al.
Philos. Trans. R. Soc. A
This paper addresses the task of anomaly diagnosis when the underlying data generation process has a complex spatio-temporal (ST) dependency. The key technical challenge is to extract actionable insights from the dependency tensor characterizing high-order interactions among temporal and spatial indices. We formalize the problem as supervised dependency discovery, where the ST dependency is learned as a side product of multivariate time-series classification. We show that temporal positional encoding used in existing ST transformer works has a serious limitation in capturing higher frequencies (short time scales). We propose a new positional encoding with a theoretical guarantee, based on discrete Fourier transform. We also propose a new ST dependency discovery framework, which can provide readily consumable diagnostic information in both spatial and temporal directions. Finally, we demonstrate the utility of the proposed model, DFStrans (Diagnostic Fourier-based Spatio-temporal Transformer), in a real industrial application of building elevator control.
Pavel Klavík, A. Cristiano I. Malossi, et al.
Philos. Trans. R. Soc. A
Tsuyoshi Idé
ICDM 2005
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
Ankit Vishnubhotla, Charlotte Loh, et al.
NeurIPS 2023