A hierarchical ensemble pipeline using shapelet and statistical features, per-channel stacking, and cross-channel aggregation with time-series cross-validation and masking achieves strong generalization on the ESA-ADB anomaly detection benchmark.
In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetry
A hierarchical ensemble pipeline using shapelet and statistical features, per-channel stacking, and cross-channel aggregation with time-series cross-validation and masking achieves strong generalization on the ESA-ADB anomaly detection benchmark.