Szczegóły publikacji
Opis bibliograficzny
PRISM: powerful time series to image (TS2I) representations for multivariate anomaly detection / Mateusz SMENDOWSKI, Kamil FABER, Piotr NAWROCKI, Nathalie Japkowicz, Roberto Corizzo // W: Machine Learning and Knowledge Discovery in Databases : research track : European Conference, ECML PKDD 2026 : Naples, Italy, September 7–11, 2026 : proceedings , Pt. 1 / eds. Michelangelo Ceci, [et al.]. — Cham : Springer Nature, cop. 2027. — ( Lecture Notes in Computer Science ; ISSN 0302-9743. Lecture Notes in Artificial Intelligence ; 16941 ). — ISBN: 978-3-032-37653-4; e-ISBN: 978-3-032-37654-1. — S. 39–55. — Bibliogr., Abstr. — Publikacja dostępna online od: 2026-08-25
Autorzy (5)
- AGHSmendowski Mateusz
- AGHFaber Kamil
- AGHNawrocki Piotr
- Japkowicz Nathalie
- Corizzo Roberto
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 170052 |
|---|---|
| Data dodania do BaDAP | 2026-09-23 |
| DOI | 10.1007/978-3-032-37654-1_3 |
| Rok publikacji | 2027 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database 2026 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Time-series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices, especially in multivariate settings. While transforming time series into images has shown success in forecasting and classification, it remains unclear how multivariate, high-dimensional series should be mapped to multi-channel images and whether vision backbones can match time-domain baselines in TSAD. We introduce PRISM, a plug-and-play meta-workflow enabling systematic construction and evaluation of image-based representations for multivariate TSAD. Our evaluation spanning over 7,000 experiments shows that well-designed PRISM configurations are competitive with 24 time-domain baselines, achieving the best VUS-PR on 10 of 14 datasets, with an average improvement of 41% over the best competing method on those datasets. Further, we identify channelization – how the channel dimension of multi-channel images is constructed – as a critical and previously understudied design dimension, and introduce MSM, a novel statistics-based scheme achieving 11–27% gains over PCA-based alternatives. Finally, ImageNet-pretrained encoders transfer effectively to TSAD, with frozen encoders retaining 92% of fine-tuned performance while training 1.8 times faster. Our code is available at: https://github.com/Smendowski/PRISM.
