Risk-Aware Density–Boundary Graph Reweighting for Rare Event Detection in Intelligent Risk Monitoring Systems
Applied Sciences · 16.08.2026 · 16 (16) · 8160
DOI: 10.3390/app16168160 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.08.2026. Verfasst von Ruihan Geng und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Chongqing, China, Chongqing Key Project for Technological Innovation and Application Development.
Abstract (Originalsprache)
Rare-event detection is a critical task in intelligent risk monitoring systems, where missed minority events may lead to financial loss, security threats, or operational failures. Existing imbalance-handling methods frequently apply one class-level correction and therefore ignore the heterogeneous geometric roles of minority observations. This study presents density–boundary graph reweighting (DBGR), a unified sample-level weighting framework that combines continuous minority sparsity and majority-boundary exposure and regularizes the resulting scores through a minority-only K-nearest-neighbor graph. Its methodological contribution lies in this joint pre-training formulation and in producing classifier-compatible weights, rather than in claiming novelty for density estimation, graph propagation, or weighting individually. Two variants are considered: DBGR-Safe for sparse and relatively safe minority prototypes and DBGR-Danger for sparse boundary observations. Experiments on financial fraud detection, industrial fault diagnosis, and network intrusion detection show recall-oriented gains with XGBoost and reduced variability for the tested LightGBM setting, while the benefit is limited for Random Forest. On Creditcard, DBGR-Danger improves Recall from 0.8223 to 0.8949 and F2 from 0.8410 to 0.8931. On NSL-KDD U2R, focal loss remains better in Recall, F2, and PR-AUC, whereas DBGR-Safe achieves the best F1. DBGR is therefore positioned as a complementary, classifier-compatible strategy rather than a universally superior imbalance-handling method.
Förderung
- Natural Science Foundation of Chongqing, China
- Chongqing Key Project for Technological Innovation and Application Development
Zitieren
APA
Geng, R., Xu, T., Zhou, X., & Dai, W. (2026). Risk-Aware Density–Boundary Graph Reweighting for Rare Event Detection in Intelligent Risk Monitoring Systems. Applied Sciences, 16(16), 8160. https://doi.org/10.3390/app16168160
Vancouver
Geng R, Xu T, Zhou X, Dai W. Risk-Aware Density–Boundary Graph Reweighting for Rare Event Detection in Intelligent Risk Monitoring Systems. Applied Sciences. 2026;16(16):8160. doi:10.3390/app16168160
BibTeX
@article{Geng2026,
author = {Geng, Ruihan and Xu, Tingting and Zhou, Xingqi and Dai, Wenhao},
title = {Risk-Aware Density–Boundary Graph Reweighting for Rare Event Detection in Intelligent Risk Monitoring Systems},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {16},
pages = {8160},
doi = {10.3390/app16168160}
}
EUVIMED