Robust Reliability for UAV Detection in Edge AI: A Data-Centric Framework via Structural–Semantic Curation, Maximin Selection, and Raspberry Pi Validation
ReCIBE, Revista electrónica de Computación, Informática, Biomédica y Electrónica · 19.10.2026 · 15 (3)
DOI: 10.32870/naj2v525 ↗Kurz gefasst
Fachartikel in der Zeitschrift ReCIBE, Revista electrónica de Computación, Informática, Biomédica y Electrónica, online erschienen am 19.10.2026. Verfasst von LUIS ANGEL OLVERA OLVERA und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
UAV-based detection systems operating under real-world conditions exhibit failures under severe domain shifts and scale degradation, where average metrics may conceal critical vulnerabilities. This work hypothesizes that data-centric optimization, through structural deduplication (pHash/DCT) and teacher–student semantic auditing, improves worst-case robustness and cross-domain generalization in lightweight detectors without increasing model complexity under Edge AI constraints. A Data-Centric AI (DCAI) framework tailored for Edge AI is proposed, integrating: (i) perceptual deduplication via pHash to reduce structural redundancy; (ii) a teacher–student auditing scheme using YOLO11x to control semantic noise and geometric consistency; and (iii) a search space formulated as a hierarchical Design of Experiments (DoE) ablation framework (R0–R4), with minimum-recall gating and multicriteria decision-making (MCDM) selection under the Wald maximin criterion. Experimental results show limited improvements in average metrics (~1%), but consistent gains under failure scenarios, reaching up to +5.95% in precision and +1.36% in recall in the worst-case setting. GLM/ANOVA analysis demonstrates that dataset and scenario dominate performance variance (η²â‚š ≈ 0.96–0.99), while seed effects are not statistically significant (p > 0.05), confirming stability and reproducibility. Validation on Raspberry Pi 5 using NCNN demonstrates edge deployment feasibility, maintaining precision > 0.94 and recall > 0.90 at distances between 5–25 m under controlled degradation. The contribution lies in the systemic integration of a DCAI model within a hierarchical DoE framework evaluated under a maximin criterion (MCDM), enabling causal attribution of performance improvements to data design rather than to architecture under real-world Edge AI constraints for UAV applications.
Zitieren
APA
OLVERA, L. A. O., Díaz, L. A., & Pérez, J. L. (2026). Robust Reliability for UAV Detection in Edge AI: A Data-Centric Framework via Structural–Semantic Curation, Maximin Selection, and Raspberry Pi Validation. ReCIBE, Revista electrónica de Computación, Informática, Biomédica y Electrónica, 15(3). https://doi.org/10.32870/naj2v525
Vancouver
OLVERA LAO, Díaz LA, Pérez JL. Robust Reliability for UAV Detection in Edge AI: A Data-Centric Framework via Structural–Semantic Curation, Maximin Selection, and Raspberry Pi Validation. ReCIBE, Revista electrónica de Computación, Informática, Biomédica y Electrónica. 2026;15(3). doi:10.32870/naj2v525
BibTeX
@article{OLVERA2026,
author = {OLVERA, LUIS ANGEL OLVERA and Díaz, Luis Antonio and Pérez, Jorge Luis},
title = {Robust Reliability for UAV Detection in Edge AI: A Data-Centric Framework via Structural–Semantic Curation, Maximin Selection, and Raspberry Pi Validation},
journal = {ReCIBE, Revista electrónica de Computación, Informática, Biomédica y Electrónica},
year = {2026},
volume = {15},
number = {3},
doi = {10.32870/naj2v525}
}
EUVIMED