Deep leaning in food safety and authenticity detection: An integrative review and future prospects

Trends in Food Science & Technology, Journal Year: 2024, Volume and Issue: 146, P. 104396 - 104396

Published: Feb. 21, 2024

Language: Английский

---

Applications of hyperspectral imaging technology in the food industry

Nature Reviews Electrical Engineering, Journal Year: 2024, Volume and Issue: 1(4), P. 251 - 263

Published: March 26, 2024

Language: Английский

---

Rapid and non-destructive identification of Panax ginseng origins using hyperspectral imaging, visible light imaging, and X-ray imaging combined with multi-source data fusion strategies

Food Research International, Journal Year: 2024, Volume and Issue: 192, P. 114758 - 114758

Published: July 14, 2024

Language: Английский

---

Novel analysis of food processes by terahertz spectral imaging: A review of recent research findings

Trends in Food Science & Technology, Journal Year: 2024, Volume and Issue: 147, P. 104463 - 104463

Published: March 25, 2024

Process analysis is an important step for online food quality control during processing. Among the emerging non-destructive examination techniques that offer rapid detection, terahertz spectroscopy has attracted attention in analysing processes based on various parameters. Moreover, calibration and chemometric methods are frequently used spectral data analysis. The system normally consists of processing equipment time-domain imaging (THz-TDS), which often exhibits high prediction accuracy combined with appropriate chemometrics methods. Therefore, been considered highly suitable on-site in-situ process to enhance manufacturing thus improve product quality. In this review, applications THz-TDS dehydration, storage, freezing, fermentation, as well other areas, introduced discussed. these, technology intensive research related moisture changes, such dehydration storage under natural drying conditions. Emerging techniques, hot air (HAD) microwave vacuum (MVD), investigated. Applications including hygroscopic processes, were also reported. For freezing analysis, it mainly analyze (i) effect repeated thawing meat (ii) growth rate ice crystals. fermentation processing, although most confirmed feasibility THz-TDS, further investigation regarding still awaited. combination widely employed non-linear changes attributes emergence numerous recent years. It content polar substances hydrogen sulfide ammonia. Despite performance, drawbacks cost, interference from content, disturbance constituents protein significant obstacles universalization THz-TDS.

Language: Английский

---

Stacked Long and Short-Term Memory (SLSTM) - Assisted Terahertz Spectroscopy Combined with Permutation Importance for Rapid Red Wine Varietal Identification

Talanta, Journal Year: 2025, Volume and Issue: unknown, P. 127650 - 127650

Published: Jan. 1, 2025

Mislabeling of low-value red wines as high-value ones is common, which seriously undermines consumer rights and interests. However, traditional sensory chemical analysis methods have limitations, highlights the need for novel detection techniques. To address above issues, terahertz time-domain spectroscopy (THz-TDS) combined with deep learning (DL) was employed to distinguish different wine varieties quickly non-destructively, contributing correctly identifying labels. Compared other models, stacked long short-term memory (SLSTM) model based on first derivative (1-st der) spectra performed best (Precision: 85.72 %, Recall: 85.61 F1-score: 85.59 Accuracy: %). In addition, feature selection (FS) used explore feasibility improving accuracy reducing prediction time by eliminating redundant frequencies. full frequency, 1-st der-SLSTM permutation importance (PI) slightly lower 84.42 84.10 84.14 84.18 %), but reduced 2 s. Therefore, models can be selected needs weighing time. conclusion, current research demonstrates that SLSTM-assisted THz-TDS technology provides a approach fast, accurate non-destructive discrimination labels, facilitating maintenance market discipline.

Language: Английский

---

Rapid and accurate identification of Panax ginseng origins based on data fusion of near-infrared and laser-induced breakdown spectroscopy

Food Research International, Journal Year: 2025, Volume and Issue: 204, P. 115925 - 115925

Published: Feb. 7, 2025

Language: Английский

---

Terahertz spectra reconstructed using convolutional denoising autoencoder for identification of rice grains infested with Sitophilus oryzae at different growth stages

Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy, Journal Year: 2024, Volume and Issue: 311, P. 124015 - 124015

Published: Feb. 10, 2024

Rice grains are often infected by Sitophilus oryzae due to improper storage, resulting in quality and quantity losses. The efficacy of terahertz time-domain spectroscopy (THz-TDS) technology detecting at different stages infestation stored rice was employed the current research. Terahertz (THz) spectra for infested growth were acquired. Then, convolutional denoising autoencoder (CDAE) used reconstruct THz reduce noise-to-signal ratio. Finally, a random forest classification (RFC) model developed identify levels. Results showed that RFC based on reconstructed second-order derivative spectrum with an accuracy 84.78%, specificity 86.75%, sensitivity 86.36% F1-score 85.87% performed better than original first-order 89.13%, 91.38%, 88.18% 89.16%. In addition, layers inside CDAE visualized using feature maps explain improvement results, illustrating can eliminate noise spectral data. Overall, provided novel method effective detection grains.

Language: Английский

---

FT-NIR combined with machine learning was used to rapidly detect the adulteration of pericarpium citri reticulatae (chenpi) and predict the adulteration concentration

Food Chemistry X, Journal Year: 2024, Volume and Issue: 24, P. 101798 - 101798

Published: Sept. 2, 2024

Pericarpium citri reticulatae (PCR) has been used as a food and spice for many years is known its rich nutritional content unique aroma. However, price increases are often accompanied by adulteration. In this study, two kinds of adulterants (Orange peel-OP Mandarin Rind-MR) were identified chromaticity analysis, FT-NIR machine learning algorithm, the doping concentration was predicted quantitatively. The results show that colorimetric analysis cannot completely differentiate between PCR adulterants. Using spectral preprocessing combined with algorithms, successfully distinguished, classification accuracy reaching 99.30 % 98.64 respectively. After selecting characteristic wavelengths, R

Language: Английский

---

Rapid detection of Pu-erh tea vintage by data fusion strategy based on Terahertz and Raman Spectral technology

Infrared Physics & Technology, Journal Year: 2025, Volume and Issue: unknown, P. 105803 - 105803

Published: March 1, 2025

Language: Английский

---

Fast Real-Time Monitor of Rice Grains Infested with Sitophilus Oryzae Based on Terahertz Imaging Combined with Machine Learning

Food Control, Journal Year: 2025, Volume and Issue: unknown, P. 111290 - 111290

Published: March 1, 2025

Language: Английский

---