Cost-Aware Conformal Learning for Reliable Accident Detection Under Exchangeability Violations
Sensors · 11.11.2026 · 26 (22) · 7125
DOI: 10.3390/s26227125 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.11.2026. Verfasst von Ghulam Mustafa und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Conformal prediction can give an accident detector coverage guarantees on its confidence, but only when the calibration and test data are exchangeable. Accident image benchmarks break it: a hash audit of three benchmarks finds 9% to 59% of test images have an exact copy in training, confirmed by learned embeddings and structural similarity. The damage falls on confidence, not accuracy: after grouping, accuracy stays near 98%, yet a detector calibrated on leaky data appears to hold a 90% guarantee while covering only 67% of novel images, a gap of 22.1 points with the calibration sets matched. We build a duplicate grouped split and report on a locked test set, where empirical coverage is near 90%. A cost-aware allocation of the coverage budget, our main contribution, is model-agnostic: it raises accident coverage from 91% to 98% and lowers accidents declared normal for every base method in every run, at the price of normal coverage falling to 80%, false alerts rising from seven to 33, and 9% human review, so the 90% budget is a frequency-weighted average, not a per-class level. On a rare severe class, 0.4% of records, it cuts missed cases from 34 to three.
Zitieren
APA
Mustafa, G., Rehman, Z. U., Khan, M. A., & Kim, B. (2026). Cost-Aware Conformal Learning for Reliable Accident Detection Under Exchangeability Violations. Sensors, 26(22), 7125. https://doi.org/10.3390/s26227125
Vancouver
Mustafa G, Rehman ZU, Khan MA, Kim B. Cost-Aware Conformal Learning for Reliable Accident Detection Under Exchangeability Violations. Sensors. 2026;26(22):7125. doi:10.3390/s26227125
BibTeX
@article{Mustafa2026,
author = {Mustafa, Ghulam and Rehman, Zia Ul and Khan, Muhammad Adnan and Kim, Byung-Seo},
title = {Cost-Aware Conformal Learning for Reliable Accident Detection Under Exchangeability Violations},
journal = {Sensors},
year = {2026},
volume = {26},
number = {22},
pages = {7125},
doi = {10.3390/s26227125}
}
EUVIMED