Article
Food Science & Technology
Qiulin Li, Xiaohong Wu, Jun Zheng, Bin Wu, Hao Jian, Changzhi Sun, Yibiao Tang
Summary: In this study, a combination of FT-NIR spectroscopy and fuzzy clustering algorithms was proposed for identifying the storage times of pork meat samples. The results demonstrated that this method achieved high recognition accuracy and had great potential for quality evaluation of other types of meat.
Article
Chemistry, Multidisciplinary
Soo Chung, Seung-Chul Yoon
Summary: By combining two hyperspectral imaging modalities, the Fusion model demonstrated higher accuracy in detecting foreign material on poultry products compared to single modalities, with a detected accuracy increase of 18% to 38% when compared to VNIR- and SWIR-based detection models.
APPLIED SCIENCES-BASEL
(2021)
Article
Food Science & Technology
Rui Hu, Min Zhang, Arun S. Mujumdar
Summary: The effect of thermal treatment using infrared and microwave fields on freezing of pork loin was investigated. The results show that both microwave and infrared pre-dehydration can reduce the thawing loss of pork loin and improve the texture and mouthfeel of the meat without damaging its color.
Article
Automation & Control Systems
Mas Ira Syafila Mohd Hilmi Tan, Mohd Faizal Jamlos, Ahmad Fairuz Omar, Kamarulzaman Kamarudin, Mohd Aminudin Jamlos
Summary: Ganoderma boninense (G. boninense) infection poses a significant threat to the palm oil industry by reducing oil palm productivity. Early detection of G. boninense is crucial as there is no effective treatment available. This study explores the use of near-infrared (NIR) spectroscopy to detect the biomarker ergosterol, and the results show promising potential for non-destructive and in-situ detection of G. boninense infection. The use of chemometric and machine learning techniques further validates the effectiveness of the NIR-based detection system. Evaluation: 8 points.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2023)
Article
Food Science & Technology
Qin Ouyang, Lihua Liu, Muhammad Zareef, Li Wang, Quansheng Chen
Summary: A portable visible and near-infrared (Vis-NIR) spectroscopy system was developed to assess pork cooking loss rate, comparing spectra from frozen and thawed pork. Partial least square (PLS) was used to predict cooking loss rate after selecting characteristic variables using four different algorithms. The results showed that the competitive adaptive reweighted sampling PLS (CARS-PLS) models had higher prediction results for both frozen and thawed pork spectra. The method has the potential to predict frozen pork quality without thawing.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2022)
Review
Food Science & Technology
Sara Rajic, Stefan Simunovic, Vesna Djordjevic, Mladen Raseta, Igor Tomasevic, Ilija Djekic
Summary: This review aims to develop a single score tool for meat quality evaluation based on visual and sensorial assessments of fresh meat. The study identifies meat color, sensory characteristics, and fat content as the most important intrinsic quality cues of fresh beef and pork, as well as the importance of price, certification logos, and brand for beef quality evaluation. A single-score tool named the Meat quality index has been developed, following approaches used in the food sector.
Article
Chemistry, Analytical
Mohamed Karim El Oufir, Karem Chokmani, Anas El Alem, Hachem Agili, Monique Bernier
Summary: This study proposes an innovative method for classifying seasonal snowpack based on spectral information, demonstrating the potential of NIR hyperspectral imagery to distinguish between different classes of snow with satisfactory success rates. The approach can be used for modelling physical parameters of snow using spectral data.
Article
Food Science & Technology
Xi Tang, Lin Rao, Lei Xie, Min Yan, Zuoquan Chen, Siyi Liu, Liqing Chen, Shijun Xiao, Nengshui Ding, Zhiyan Zhang, Lusheng Huang
Summary: Accurately and rapidly determining meat quality traits is essential in the food industry and pig breeding. This study assessed the predictive potential of 14 meat quality traits based on large-scale VIS/NIR hyperspectral images, demonstrating the great potential of hyperspectral imaging in predicting and visualizing various meat qualities.
Article
Food Science & Technology
Zhen Li, Ling Wu, Zongyun Yang, Yulong Zhang, Peng Wang, Xinglian Xu
Summary: This study aimed to verify the feasibility of using near-infrared spectroscopy (NIR) and compression speed for the classification of wooden breast (WB). The results showed that NIR and partial least squares discriminant analysis (PLSDA) can effectively distinguish between normal breast (NB) and WB. Additionally, the compression speed was used to achieve precise classification of WB. The compression speed can quantify and simulate the palpation method and is of significant importance in food classification.
FOOD RESEARCH INTERNATIONAL
(2022)
Article
Food Science & Technology
Yuhan Ding, Yuli Yan, Jun Li, Xu Chen, Hui Jiang
Summary: This paper proposes a method for classifying tea quality levels based on near-infrared spectroscopy. The method includes obtaining absorbance spectra of tea samples, converting the spectral data to transmittance, dimensionally reducing the data using PCA, establishing a SVM classification model, and optimizing the model using PSO and CLPSO algorithms. The experimental results show high classification accuracy of 99.17% for the proposed method.
Article
Agriculture, Multidisciplinary
Jingru Yang, Jin Wang, Guodong Lu, Shaomei Fei, Ting Yan, Cheng Zhang, Xiaohui Lu, Zhiyong Yu, Wencui Li, Xiaolin Tang
Summary: The paper proposed utilizing NIR spectroscopy for tea quality authentication, with the development of new CNN networks for tea classification, achieving high accuracy rates. Experimental results indicated that SNV is the best preprocessing method for tea NIR spectroscopy data, enhancing classification performance.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Agriculture, Dairy & Animal Science
Simone Savoia, Andrea Albera, Alberto Brugiapaglia, Liliana Di Stasio, Alessio Cecchinato, Giovanni Bittante
Summary: This study investigated the use of portable infrared spectrometers for predicting meat quality traits in beef cattle. Results showed that NIR predictions were effective for color traits, pH, and purge losses, indicating potential for indirect genetic selection.
JOURNAL OF ANIMAL SCIENCE AND BIOTECHNOLOGY
(2021)
Article
Chemistry, Analytical
Shuo Wang, Xiaofang Liu, Takehiro Tamura, Nobuyuki Kyouno, Han Zhang, Jie Yu Chen
Summary: This study developed a rapid method for predicting the sensory qualities of miso products using visible/near-infrared spectroscopy combined with a partial least-square regression algorithm, demonstrating its effectiveness and feasibility. The best performing model utilized the first derivative pretreatment of the spectra, effectively classifying miso products and potentially serving as a low-cost and nondestructive quality assessment tool.
ANALYTICAL LETTERS
(2021)
Article
Physics, Multidisciplinary
Liang Zou, Weinan Liu, Meng Lei, Xinhui Yu
Summary: The study developed a one-dimensional squeeze-and-excitation residual network (1D-SE-ResNet) for rapid assessment of pork freshness using NIRS technique, demonstrating the potential of NIRS analysis technique in pork freshness detection.
Article
Food Science & Technology
Michelle N. LeMaster, Robyn D. Warner, Surinder S. Chauhan, Darryl N. D'Souza, Frank R. Dunshea
Summary: This meta-regression analysis aimed to investigate the relationship between fibre type cross-sectional area (CSA) and frequency (%) and meat quality traits, specifically tenderness. The results showed that only pH, WBSF, and drip loss were significantly associated with fibre type frequency and CSA (p < 0.05). When limited to pork analysis, it was found that frequency of type I fibres was associated with decreased drip loss, increased cook loss, decreased lightness (L*), and increased sensory tenderness, while frequency of type IIb fibres was associated with increased drip loss (p < 0.05). Additionally, CSA of type I and IIb fibres was correlated with color traits of lightness and redness (p < 0.05). Further research should focus on different breeds and muscles to enhance understanding of the effects of fibre type frequency and CSA on meat quality.
Article
Agricultural Engineering
Yifan Bai, Junzhen Yu, Shuqin Yang, Jifeng Ning
Summary: A real-time recognition algorithm (Improved YOLO) is proposed in this paper for accurately identifying small, similar-colored, and overlapping strawberry seedling flowers and fruits. The experimental results show that the algorithm achieves high precision, recall, and average precision, and meets the real-time detection requirements, providing effective support for the automated management of strawberry seedling flower and fruit thinning.
BIOSYSTEMS ENGINEERING
(2024)
