A Human-AI Collaborative Framework for Airport X-Ray Weapon Detection Using Deep Transfer Learning
Résumé
This study investigates the combined impact of human factors and deep learning on weapon detection performance in airport X-ray screening. A controlled experiment with 78 participants evaluated the effects of operator motivation and screen background color on detection accuracy and response time. The results showed that motivation significantly improves accuracy and reduces response time, particularly for prohibited items, whereas background color has no measurable effect. To address human performance variability, a transfer learning–based detection framework using SE-ResNet-50 was developed, achieving 98.87% accuracy and surpassing existing benchmarks. These findings highlight that integrating human-centered design principles with Artificial Intelligence (AI)-assisted systems can enhance detection consistency and reliability, offering actionable insights for operational airport security and the design of future AI-human collaborative systems.
Citer ce document
Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)
Accès au document
Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter
Voir l'article sur le site de la revueLicence et provenance
Licence : CC BY
Notice moissonnée depuis OpenAlex le 12/10/2026. Le document reste hébergé par sa source.
Voir le document à la source →