Modern spectroscopic techniques combined with chemometrics for process quality control of traditional Chinese medicine: A review

Microchemical Journal, Journal Year: 2025, Volume and Issue: unknown, P. 113605 - 113605

Published: April 1, 2025

Language: Английский

---

Prediction of freezing point and moisture distribution of beef with dual freeze-thaw cycles using hyperspectral imaging

Food Chemistry, Journal Year: 2024, Volume and Issue: 456, P. 139868 - 139868

Published: May 27, 2024

Language: Английский

---

Rapid and Non-Destructive Geographical Origin Identification of Chuanxiong Slices Using Near-Infrared Spectroscopy and Convolutional Neural Networks

Agriculture, Journal Year: 2024, Volume and Issue: 14(8), P. 1281 - 1281

Published: Aug. 3, 2024

Ligusticum Chuanxiong, a perennial herb of considerable medicinal value commonly known as holds pivotal importance in sliced form for ensuring quality and regulating markets through geographical origin identification. This study introduces an integrated approach utilizing Near-Infrared Spectroscopy (NIRS) Convolutional Neural Networks (CNNs) to establish efficient method rapidly determining the Chuanxiong slices. A dataset comprising 300 samples from 6 distinct origins was analyzed using 1D-CNN model. In this study, we initially established traditional classification By Spectrum Outlier feature TQ-Analyst 9 software exclude outliers, have enhanced performance After evaluating various spectral preprocessing techniques, selected Savitzky–Golay filtering combined with Multiplicative Scatter Correction (S-G + MSC) process raw data. significantly improved predictive accuracy 2000 iterations training, CNN model achieved prediction 92.22%, marking 12.09% improvement over methods. The application Class Activation Mapping algorithm not only visualized extraction but also model’s by additional 7.41% when features extracted research provides powerful tool control slices presents novel perspective on inspection other agricultural products.

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

---

Near-infrared spectroscopy analysis of compound fertilizer based on GAF and quaternion convolution neural network

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2023, Volume and Issue: 240, P. 104900 - 104900

Published: June 15, 2023

Language: Английский

---

Overall control of the quality consistency of Citri Retriculatae Pericapium by combining HPLC fingerprint, terahertz time-domain spectroscopy and chemometrics

New Journal of Chemistry, Journal Year: 2024, Volume and Issue: 48(5), P. 2048 - 2062

Published: Jan. 1, 2024

Combining HPLC-FP and THz-TDs to evaluate the quality of Citri Retriculatae Pericapium.

Language: Английский

---

ChenpiAge Identification Based on Terahertz Spectral Imaging and ResNet

Artificial Intelligence and Robotics Research, Journal Year: 2024, Volume and Issue: 13(01), P. 9 - 18

Published: Jan. 1, 2024

Language: Английский

---

Non-destructively qualitative and quantitative inspection methods based on THz spectroscopy and imaging

Optical Engineering, Journal Year: 2024, Volume and Issue: 63(02)

Published: Feb. 9, 2024

Sunflower seeds, recognized for their nutritional value and taste, are a well-loved snack. However, throughout growth storage, sunflower seeds can develop various defects that not only compromise quality but also present potential health hazards. To address these issues ensure adherence to safety standards, we investigate the use of THz spectroscopy imaging techniques non-destructive identification classification common in seeds. The study begins by analyzing features identify defective particularly those affected mildew. It establishes three qualitative discrimination models (support vector machine, random forest, backpropagation neural networks), which achieve overall accuracies 88.3%, 91.7%, 95%, respectively. Furthermore, transmission is employed as quantitative method visualize internal structure kernels provide precise plumpness estimates. A noteworthy innovation analysis time delays reflected pulses at each pixel, enabling extraction valuable kernel thickness information. These data then utilized convert traditional two-dimensional scanning into intricate three-dimensional (3D) images, facilitating direct measurements both 3D weight. findings have significant implications improving may extend assessment other agricultural products, contributing enhanced control food industry.

Language: Английский

---

CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel

Journal of Food Quality, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 13

Published: May 14, 2024

Xinhui tangerine peel has valuable medicinal value. The longer it is stored in an appropriate environment, the higher its flavonoid content, resulting increased In order to correctly identify age of peel, previous studies have mostly used manual identification or physical and chemical analysis, which a tedious costly process. This work investigates automatic recognition based on deep learning attention mechanisms. We proposed effective ConvNeXt fusion module (CNFA), consists three parts, block for extracting low-level features’ information aggregating hierarchical features, channel squeeze-and-excitation (cSE) spatial (sSE) generating sufficient high-level feature from both dimensions. To analyze features different ages evaluate performance CNFA module, we conducted comparative experiments using CNFA-integrated network dataset. algorithm compared with related models structure other experimental results showed that had accuracy 97.17%, precision 96.18%, recall 96.09%, F1 score 96.13% providing visual solution intelligent development industry.

Language: Английский

---

Identification of millet origin using terahertz spectroscopy combined with ensemble learning

Infrared Physics & Technology, Journal Year: 2024, Volume and Issue: 142, P. 105547 - 105547

Published: Sept. 1, 2024

Language: Английский

---