Change-point detection in industrial data streams based on online dynamic mode decomposition with control

M Wadinger, M Kvasnica, Y Kawahara - arXiv preprint arXiv:2407.05976, 2024 - arxiv.org
We propose a novel change-point detection method based on online Dynamic Mode
Decomposition with control (ODMDwC). Leveraging ODMDwC's ability to find and track …

Identification of Rock Layer Interface Characteristics Using Drilling Parameters

S Long, Z Yue, WV Yue, H Hu, Y Feng, Y Yan… - Rock Mechanics and …, 2024 - Springer
Characteristics of interface between rock layers significantly affect the stability of the support
structure in underground excavation. However, there is a lack of in-situ test to probe …

[HTML][HTML] Non-intrusive load monitoring based on MoCo_v2, time series self-supervised learning

T Chen, J Gao, Y Yuan, S Guo, P Yang - Energy and Buildings, 2024 - Elsevier
Traditional non-intrusive load monitoring (NILM) methods rely on massive historical labeled
data. However, due to the privacy and high labeling cost of datasets, their generality and …

Normalizing self-supervised learning for provably reliable Change Point Detection

A Bazarova, E Romanenkova, A Zaytsev - arXiv preprint arXiv:2410.13637, 2024 - arxiv.org
Change point detection (CPD) methods aim to identify abrupt shifts in the distribution of input
data streams. Accurate estimators for this task are crucial across various real-world …