Nitrogen‑phosphorus responses and Vis/NIR prediction in fresh tea leaves

Food Chemistry, Journal Year: 2025, Volume and Issue: 476, P. 143369 - 143369

Published: Feb. 10, 2025

Language: Английский

---

Rapid and Low-Cost Quantification of Adulteration Content in Camellia Oil Utilizing UV-Vis-NIR Spectroscopy Combined with Feature Selection Methods

Molecules, Journal Year: 2023, Volume and Issue: 28(16), P. 5943 - 5943

Published: Aug. 8, 2023

This study aims to explore the potential use of low-cost ultraviolet-visible-near infrared (UV-Vis-NIR) spectroscopy quantify adulteration content soybean, rapeseed, corn and peanut oils in Camellia oil. To attain this aim, test oil samples were firstly prepared with different adulterant ratios ranging from 1% 90% at varying intervals, their spectra collected by an in-house built experimental platform. Next, preprocessed using Savitzky–Golay (SG)–Continuous Wavelet Transform (CWT) feature wavelengths extracted four algorithms. Finally, Support Vector Regression (SVR) Random Forest (RF) models developed rapidly predict content. The results indicated that SG–CWT decomposition scale 25 Iterative Variable Subset Optimization (IVSO) algorithm can effectively improve accuracy models. Furthermore, SVR model performed best for predicting camellia soybean oil, while RF optimal adulterated corn, or Additionally, we verified models’ robustness examining correlation between absorbance certain screened IVSO. demonstrates feasibility UV-Vis-NIR authentication

Language: Английский

---

Deep learning-powered whole slide image analysis in cancer pathology

Laboratory Investigation, Journal Year: 2025, Volume and Issue: unknown, P. 104186 - 104186

Published: April 1, 2025

Language: Английский

---

HiViT: Hierarchical attention-based Transformer for multi-scale whole slide histopathological image classification

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127164 - 127164

Published: March 1, 2025

Language: Английский

---