Enhancing the application of near-infrared spectroscopy in grain mycotoxin detection: An exploration of a transfer learning approach across contaminants and grains

Food Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 143854 - 143854

Published: March 1, 2025

Language: Английский

---

Bio-nanoparticles sensor couple with smartphone digital image colorimetry and dispersive liquid–liquid microextraction for aflatoxin B1 detection

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 19, 2025

A novel nanobiosensor-based colorimetric method was developed by integrating ZnO nanoparticles functionalized with curcumin, dispersive liquid–liquid microextraction (DLLME), and smartphone digital image colorimetry for the sensitive detection of aflatoxin B1 (AFB1) in baby food samples. The unique combination biologically-derived curcumin created a sensing platform, while DLLME provided efficient pre-concentration target analyte. custom-designed portable box enabled standardized capture analysis using camera software. Under optimized conditions chloroform as extraction solvent acetonitrile disperser solvent, achieved remarkable limit 0.09 μg/kg within linear concentration range 0–1 μg/L. calibration curves demonstrated excellent linearity (R2 > 0.9906) high precision (RSD < 5.52%). successfully validated samples, achieving recoveries (89.8–94.2%). This innovative integration nanobiosensing, microextraction, technology offers rapid, highly sensitive, cost-effective platform on-site AFB1 safety applications, particularly beneficial resource-limited settings.

Language: Английский

---

Deep Learning-Based Detection of Aflatoxin B1 Contamination in Almonds Using Hyperspectral Imaging: A Focus on Optimized 3D Inception–ResNet Model

Toxins, Journal Year: 2025, Volume and Issue: 17(4), P. 156 - 156

Published: March 22, 2025

Aflatoxin B1, a toxic carcinogen frequently contaminating almonds, nuts, and food products, poses significant health risks. Therefore, rapid non-destructive detection method is crucial to detect aflatoxin B1-contaminated almonds ensure safety. This study introduces novel deep learning approach utilizing 3D Inception–ResNet architecture with fine-tuning classify using hyperspectral images. The proposed model achieved higher classification accuracy than traditional methods, such as support vector machine (SVM), random forest (RF), quadratic discriminant analysis (QDA), decision tree (DT), for classifying B1 contaminated almonds. A feature selection algorithm was employed enhance processing efficiency reduce spectral dimensionality while maintaining high accuracy. Experimental results demonstrate that the (Lightweight) achieves superior performance 90.81% validation accuracy, an F1-score of 0.899, area under curve value 0.964, outperforming approaches. Lightweight model, 381 layers, offers computationally efficient alternative suitable real-time industrial applications. These research findings highlight potential imaging combined in supports development automated screening systems safety, reducing contamination-related risks

Language: Английский

---

Aflatoxin detection in naturally contaminated peanuts based on vision transformer and multi-scale convolutional fusion

Food Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 144300 - 144300

Published: April 1, 2025

Language: Английский

---

Detection of Mycotoxins in Cereal Grains and Nuts Using Machine Learning Integrated Hyperspectral Imaging: A Review

Toxins, Journal Year: 2025, Volume and Issue: 17(5), P. 219 - 219

Published: April 27, 2025

Cereal grains and nuts are the world’s most produced food economic backbone of many countries. Food safety in these commodities is crucial, as they highly susceptible to mold growth mycotoxin contamination warm, humid environments. This review explores hyperspectral imaging (HSI) integrated with machine learning (ML) algorithms a promising approach for detecting quantifying mycotoxins cereal nuts. study aims (1) critically evaluate current non-destructive techniques processing foods applications ML identifying through HSI, (2) highlight challenges potential future research directions enhance reliability efficiency detection systems. The showed effectiveness classifying nuts, HSI systems increasingly adopted industrial settings. Mycotoxins exhibit heightened sensitivity specific spectral bands within facilitating accurate detection. Additionally, selecting only relevant features reduces model complexity enhances process. contributes deeper understanding integration By directions, it provides valuable insights advancing methods industry using HSI.

Language: Английский

---

Towards Intelligent Food Safety: Machine Learning Approaches for Aflatoxin Detection and Risk Prediction

Trends in Food Science & Technology, Journal Year: 2025, Volume and Issue: unknown, P. 105055 - 105055

Published: April 1, 2025

Language: Английский

---

Guide DNA dephosphorylation-modulated Pyrococcus furiosus Argonaute fluorescence biosensor for the detection of alkaline phosphatase and aflatoxins B1

Biosensors and Bioelectronics, Journal Year: 2024, Volume and Issue: 265, P. 116692 - 116692

Published: Aug. 23, 2024

Language: Английский

---

Pixel-Level Spectral Aflatoxin B1 Content Intelligent Prediction via Fine-Tuning Large Language Model (LLM)

Food Control, Journal Year: 2024, Volume and Issue: unknown, P. 111071 - 111071

Published: Dec. 1, 2024

Language: Английский

---

A fluorescence and colorimetric dual-mode sensor based on the aptamer-adsorbed hollow cerium oxide for sensitive and visual detection of Aflatoxin B1 in food

Microchemical Journal, Journal Year: 2024, Volume and Issue: unknown, P. 112387 - 112387

Published: Dec. 1, 2024

Language: Английский

---

“Three-in-One” Mil@Pda-Uiol@Aiegens Driven Lateral Flow Immunosensor for Multimodal Detection of Aflatoxin B1

Published: Jan. 1, 2024

Language: Английский

---