Article
Spectroscopy
Hao Jin, Gui -Mei Dong, Hai-Yun Wu, Yan-Rong Yang, Ming-Yue Huang, Meng -Yuan Wang, Ren-Jie Yang
Summary: A qualitative analysis method for melamine-adulterated milk based on two-trace two-dimensional auto-correlation spectra was proposed. Infrared spectroscopy was used to measure the spectral data of pure milk and melamine-adulterated milk. The intensity of auto-correlation peaks at specific wave numbers was selected as independent variables for modeling. The method achieved 100% accuracy for individual brands and 99.05% accuracy for all four brands combined.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2023)
Article
Spectroscopy
Xijun Wu, Baoran Xu, Renqi Ma, Yudong Niu, Shibo Gao, Hailong Liu, Yungang Zhang
Summary: This study utilized Raman spectroscopy in combination with convolutional neural network (CNN) and chemometrics to identify and quantify adulterated honey samples. The shallow CNNs accurately classified honey samples adulterated with single-variety syrup into four categories with over 97% accuracy, while the general CNN model achieved an accuracy of 94.79% for detecting honey adulterated with any type of syrup. Additionally, partial least square regression (PLS) successfully predicted the purity of honey mixed with single syrup. The proposed methods based on Raman spectra have significant practical importance for ensuring food safety and quality control of honey products.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2022)
Article
Spectroscopy
Ming-Yue Huang, Ren-Jie Yang, Ze-yuan Zheng, Hai-yun Wu, Yan-rong Yang
Summary: A discrimination method for adulterated milk based on temperature-perturbed 2D infrared correlation spectroscopy and NPLS-DA is proposed. The method can accurately classify pure and adulterated milk by calculating 2D correlation spectra and building discrimination models. Compared to the conventional 3D stacked map, this method achieves higher discrimination accuracy.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2022)
Article
Spectroscopy
Ming-yue Huang, Jia Long, Hai-yun Wu, Ren-jie Yang, Hao Jin, Yan-rong Yang
Summary: To improve the accuracy of adulterated milk discrimination, a detection method based on temperature-perturbed generalized two-dimensional (2D) correlation characteristic slice spectra was proposed. A total of 240 samples were prepared and the infrared attenuated total reflection spectra were collected at different temperatures. Discrimination models based on 2D correlation characteristics slice spectra were established using N-way partial least squares discriminant analysis (NPLS-DA). The results showed that the proposed method effectively extracted characteristic information and improved the accuracy of discrimination.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2023)
Article
Agronomy
Xin Zhao, Yunpeng Wang, Xin Liu, Hongzhe Jiang, Zhilei Zhao, Xiaoying Niu, Chunhua Li, Bin Pang, Yanlei Li
Summary: In this study, the adulteration of goat milk powder by urea, melamine, and starch was quantified using near infrared (NIR) spectroscopy and chemometrics. For single adulterants, models were built with good predictive ability. For multiple adulterants, different methods were used to build the models, with PLS2 showing better results. MCR-ALS models were able to detect adulteration with new and unknown substitutes.
Article
Multidisciplinary Sciences
Freeh N. Alenezi
Summary: The study introduces a method for variable selection in high dimensional data modeling, using majority scoring with backward elimination in PLS to improve prediction accuracy. The method performs well in predicting corn and diesel contents, while also examining the impact of data properties on prediction behavior.
SCIENTIFIC REPORTS
(2021)
Article
Spectroscopy
Chao Tan, Hui Chen, Zan Lin
Summary: This study investigates the feasibility of using ATR-MIR spectroscopy and various interval-based PLS algorithms to detect illegally adulterated Chinese patent medicine. The results show that the modified cmwPLS algorithm produced the best prediction model, automatically optimizing window width and position.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2021)
Article
Spectroscopy
Haiyun Wu, Renjie Yang, Yong Wei, Guimei Dong, Hao Jin, Yanan Zeng, Chenglong Ai
Summary: This study proposes an improved method for identifying milk adulteration using near infrared spectroscopy and discriminant analysis. The results show that the proposed method can effectively reduce the influence of milk brands on the identification models.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2022)
Article
Biochemical Research Methods
Ruoyu Tang, Xinyu He, Ruiqi Wang
Summary: The study presents a general computational method for constructing maps between different cell fates and parametric conditions by systematic perturbations. The method does not require accurate parameter measurements or bifurcations. The maps obtained can help in understanding how systematic perturbations drive cell fate decisions and transitions, providing valuable information for predicting and controlling cell states.
Article
Automation & Control Systems
Tahir Mehmood, Arzoo Kanwal, Muhammad Moeen Butt
Summary: This article introduces a classification strategy based on the combination of PLS and Naive Bayes for high-dimensional data sets. Through comparison with reference methods, the classifier is validated to have high accuracy in classifying embryonal cancer and prostate cancer.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Agriculture, Dairy & Animal Science
G. Rovere, G. de los Campos, A. L. Lock, L. Worden, A. Vazquez, K. Lee, R. J. Tempelman
Summary: Through analyzing a large number of milk samples, the study found that Bayesian regression methods outperformed partial least squares in predicting milk fatty acids, and identified spectral regions associated with fatty acids as well as the impact of carbon number and unsaturation level on the strength of associations.
JOURNAL OF DAIRY SCIENCE
(2021)
Article
Chemistry, Multidisciplinary
Boyan Gao, Jingyao Zhang, Weiying Lu
Summary: The ANOVA-projected difference resolution method (ANOVA-PDR) was developed to detect possible food adulteration in extra virgin olive oils (EVOOs) by UV-Vis spectra and compared with multivariate classification. This method quantitatively analyzed the separation of classes based on origin, adulteration level, and adulteration type. The results showed that ANOVA-PDR was more effective in distinguishing the internal classes according to the three main factors, compared to conventional methods. The partial least-squares-discriminant analysis (PLS-DA) and PLS regression (PLSR) modeling further confirmed the importance of these factors in spectral variations.
APPLIED SCIENCES-BASEL
(2023)
Article
Spectroscopy
Maogang Li, Yaozhou Feng, Yan Yu, Tianlong Zhang, Chunhua Yan, Hongsheng Tang, Qinglin Sheng, Hua Li
Summary: Infrared spectroscopy combined with partial least squares (PLS) can be used for quantitative analysis of PAHs in soil, but variable selection methods are needed to extract effective information and improve predictive performance. The siPLS-GA calibration model was used in this study to extract feature variables, showing a low RMSE and high R-2, with excellent predictive performance demonstrated in external validation.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2021)
Article
Food Science & Technology
Chengyun Zhu, Hui Jiang, Quansheng Chen
Summary: This study proposes a label-free rapid detection method for aflatoxin B-1 (AFB(1)) in pressing peanut oil based on Raman spectroscopy technology combined with appropriate chemometric methods. The results demonstrate that this method can be used to quickly detect the safety of edible oil with high precision.
Article
Chemistry, Analytical
Alessandra Biancolillo, Jean-Michel Roger, Federico Marini
Summary: In this paper, a feature selection strategy for N-way data based on the Covariance Selection (CovSel) approach, referred to as N-CovSel, is discussed. The method allows the selection of meaningful features of different dimensionality and proposes different strategies for further analysis of the selected features.
ANALYTICA CHIMICA ACTA
(2022)
