Physics-Constrained Deep Learning for Security Ink Colorimetry with Attention-Based Spectral Sensing DOI Creative Commons
Po-Tong Wang,

Chiu Wang Tseng,

Li-Der Fang

и другие.

Sensors, Год журнала: 2024, Номер 25(1), С. 128 - 128

Опубликована: Дек. 28, 2024

The proliferation of sophisticated counterfeiting poses critical challenges to global security and commerce, with annual losses exceeding $2.2 trillion. This paper presents a novel physics-constrained deep learning framework for high-precision ink colorimetry, integrating three key innovations: physics-informed neural architecture achieving unprecedented color prediction accuracy (CIEDE2000 (ΔE00): 0.70 ± 0.08, p < 0.001), advanced attention mechanisms improving feature extraction efficiency by 58.3%, Bayesian optimization ensuring robust parameter tuning. Validated across 1500 industrial samples under varying conditions (±2 °C, 30–80% RH), this system demonstrates substantial improvements in production 50% reduction rejections, 35% decrease calibration time, 96.7% gamut coverage. These achievements establish new benchmarks printing applications provide scalable solutions next-generation anti-counterfeiting technologies, offering promising outlook the future.

Язык: Английский

Considerations about the gap between research in near-infrared spectroscopy and official methods and recommendations of analysis in foods DOI Creative Commons
Giacomo Squeo, Jordi Cruz, Davide De Angelis

и другие.

Current Opinion in Food Science, Год журнала: 2024, Номер 59, С. 101203 - 101203

Опубликована: Авг. 2, 2024

Near-infrared spectroscopy (NIR spectroscopy) is a powerful analytical technology for measuring food characteristics. More and more applications of NIR have been studied, an increasing number commercial solutions are available on the market. However, only 25 documents about issued by international bodies, while scientific papers published in recent years has always higher than 60/year. Studies prove that could boost sustainability system, quality, optimisation production real-time monitoring. Considering technical, analytical, environmental advantages spectroscopy, efforts should be made to extend applicability promote development official methods based spectroscopy.

Язык: Английский

Процитировано

9
The Application of Handheld Near-Infrared Spectroscopy and Raman Spectroscopic Imaging for the Identification and Quality Control of Food Products DOI Creative Commons
Hui Yan, Marina De Géa Neves,

Barry M. Wise

и другие.

Molecules, Год журнала: 2023, Номер 28(23), С. 7891 - 7891

Опубликована: Дек. 1, 2023

The following investigations describe the potential of handheld NIR spectroscopy and Raman imaging measurements for identification authentication food products. On one hand, during last decade, has made greatest progress among vibrational spectroscopic methods in terms miniaturization price/performance ratio, on other method can achieve best lateral resolution when examining heterogeneous composition samples. utilization both is further enhanced via combination with chemometric evaluation respect to detection, identification, discrimination illegal counterfeiting To demonstrate solution practical problems these two techniques, results our recent obtained various industrial processes customer-relevant product examples have been discussed this article. Specifically, monitoring extraction (e.g., ethanol clove water wolfberry) quality differentiation cocoa nibs beans) spectroscopy, detection quantification adulterations powdered dairy products were outlined some detail. Although present work only demonstrates exemplary process examples, applications provide a balanced overview materials different physical properties manufacturing order be able derive modified or production processes.

Язык: Английский

Процитировано

14
Rapid on-site analysis of soil microplastics using miniaturized NIR spectrometers: Key aspect of instrumental variation DOI Creative Commons
Krzysztof B. Beć, Justyna Grabska,

Frank Pfeifer

и другие.

Journal of Hazardous Materials, Год журнала: 2024, Номер 480, С. 135967 - 135967

Опубликована: Сен. 26, 2024

Язык: Английский

Процитировано

5
Near Infrared Spectroscopy: A “Restless” Analytical Technique for a Multiplicity of Applications DOI
Heinz W. Siesler

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Interpretability in near-infrared (NIR) spectroscopy: Current pathways to the long-standing challenge DOI Creative Commons
Krzysztof B. Beć, Justyna Grabska, Christian W. Huck

и другие.

TrAC Trends in Analytical Chemistry, Год журнала: 2025, Номер 189, С. 118254 - 118254

Опубликована: Апрель 14, 2025

Язык: Английский

Процитировано

0
Miniaturized Near-Infrared spectrophotometers in forensic analytical science − a critical review DOI

Letícia. P. Foli,

Maria do Carmo Hespanhol da Silva,

Kaíque A.M.L. Cruz

и другие.

Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy, Год журнала: 2024, Номер 315, С. 124297 - 124297

Опубликована: Апрель 15, 2024

Язык: Английский

Процитировано

2
Evolution of vibrational biospectroscopy: multimodal techniques and miniaturisation supported by machine learning DOI Creative Commons

A. J. McLean,

Thulya Chakkumpulakkal Puthan Veettil, Magdalena Giergiel

и другие.

Vibrational Spectroscopy, Год журнала: 2024, Номер 133, С. 103708 - 103708

Опубликована: Июнь 5, 2024

The field of vibrational biospectroscopy has undergone continuous evolution, advancing from its earliest pioneers to the current innovators. Emerging frontier technologies have enabled reach new heights, expanding applications in biomedical and clinical settings. Key advancements include incorporation multimodal spectroscopy, improvements spatial resolution miniaturization spectrometers coupled with machine learning. Multimodal spectroscopy is a growing subfield within biospectroscopy, offering different perspectives same sample better understand origins modes. Meanwhile, opened door for studies personalized diagnostics, made possible by integration combination miniaturized learning paved way novel disease detection approaches. This review will discuss historical progression potential future applications, particular focus on use learning, biomedicine. primary goal this provide insight into prospects identify gaps literature assess impact domain.

Язык: Английский

Процитировано

2
Handheld Near-Infrared Spectroscopy for Undried Forage Quality Estimation DOI Creative Commons
William Yamada,

Jerry H. Cherney,

D. J. R. Cherney

и другие.

Sensors, Год журнала: 2024, Номер 24(16), С. 5136 - 5136

Опубликована: Авг. 8, 2024

This study investigates the efficacy of handheld Near-Infrared Spectroscopy (NIRS) devices for in-field estimation forage quality using undried samples. The objective is to assess precision and accuracy multiple NIRS instruments—NeoSpectra, TrinamiX, AgroCares—when evaluating key metrics such as Crude Protein (CP), Neutral Detergent Fiber (aNDF), Acid (ADF), Lignin (ADL), in vitro Total Digestibility (IVTD)and (NDFD). Samples were collected from silage bunkers across 111 farms New York State scanned different methods (static, moving, turntable). results demonstrate that dynamic scanning patterns (moving turntable) enhance predictive models compared static scans. constituents (ADF, aNDF) (CP) show higher robustness minimal impact water interference, maintaining similar R2 values dried Conversely, IVTD, NDFD, ADL are adversely affected by content, resulting lower values. underscores importance understanding effects on forage, water‘s high absorption bands at 1400 1900 nm introduce significant spectral interference. Further investigation into PLSR loading factors necessary mitigate these effects. findings suggest that, while hold promise rapid, on-site assessment, careful consideration methodology crucial accurate prediction models. research contributes valuable insights optimizing use portable technology analysis, enhancing feed utilization efficiency, supporting sustainable dairy farming practices.

Язык: Английский

Процитировано

2
Fast detection of the tenderness of mulberry leaves by a portable near-infrared spectrometer with variable selection DOI

Ziniu Zhao,

Yihan Liu, Yang Shuo

и другие.

Infrared Physics & Technology, Год журнала: 2023, Номер 133, С. 104818 - 104818

Опубликована: Июль 5, 2023

Язык: Английский

Процитировано

6
A Multivariate Analysis-Driven Workflow to Tackle Uncertainties in Miniaturized NIR Data DOI Creative Commons
Giulia Gorla,

Paolo Taborelli,

Barbara Giussani

и другие.

Molecules, Год журнала: 2023, Номер 28(24), С. 7999 - 7999

Опубликована: Дек. 7, 2023

This study focuses on exploring and understanding measurement errors in analytical procedures involving miniaturized near-infrared instruments. Despite recent spreading different application fields, there remains a lack of emphasis the accuracy reliability these devices, which is critical concern for accurate scientific outcomes. The investigates multivariate errors, revealing their complex nature influence that preprocessing techniques can have. research introduces possible workflow practical error analysis experiments diverse samples Notably, it how sample characteristics impact case solid pills tablets, typical pharmaceutical samples. ASCA was used instrumental factors potential limitations method current were discussed. joint interpretation matrices resume through image histograms K index are discussed order to evaluate common methods assess signals.

Язык: Английский

Процитировано

5