Intelligent quantification of Mn(VII) using a YOLO v3 artificial intelligence-driven smartphone monitoring platform based on nitrogen-doped blue fluorescence carbon dots

🔗 원문 전체 보기 → Royal Society of Chemistry

요약

Analyst, 2026, Advance ArticleDOI: 10.1039/D6AN00481D, PaperXiaofeng Li, Liru Yan, Jiaqi He, Pengfei Guo, Xin Qiao, Liqin Cui, Shaomin Shuang, Lihong ShiYOLO v3 artificial intelligence-driven smartphone monitoring platform for intelligent quantification of Mn…

본문

Intelligent quantification of Mn(vii) using a YOLO v3 artificial intelligence-driven smartphone monitoring platform based on nitrogen-doped blue fluorescence carbon dots

* Corresponding authors

a Department of Physics and Electronic Engineering, Taiyuan University, Taiyuan, Shanxi 030012, PR China

b College of Chemistry and Chemical Engineering, Shanxi University, Taiyuan 030006, PR China
E-mail: [email protected], [email protected]

c Science Experiment Center, Xinzhou Normal University, Xinzhou, Shanxi 034000, PR China

Abstract

Real-time, accurate, and field-portable measurement of Mn(VII) is pivotal for food safety, medical management, and environmental governance. However, existing approaches are still time-consuming and typically require costly laboratory-based techniques and trained professionals. To address this issue, a YOLO v3 artificial intelligence (AI) algorithm-driven smartphone-assisted monitoring platform incorporating a smartphone with a self-programming program and blue fluorescence (FL) carbon dots (B-CDs) proves effective for rapid quantification of Mn(VII) through a successive FL transition. B-CDs were prepared through a one-step hydrothermal procedure utilizing L-malic acid, indomethacin, and EDTA disodium as precursors, manifesting intriguing blue FL under 320 nm excitation. The FL intensity of as-prepared B-CDs is significantly quenched upon addition of Mn(VII), leading to the FL color variation of B-CDs from blue to cyan. Based on the sensing phenomena, the constructed intelligent sensing platform accomplishes rapid and in-field detection of Mn(VII) with low detection limits of 0.21 nM. More importantly, intelligent quantification of Mn(VII) in irrigation water is achieved through the proposed method. The application of a YOLO v3 AI strategy on an intelligent sensing platform will provide novel insight for the development of automated sensors.