Near infrared spectroscopy coupled with radial basis function neural network for at-line monitoring of Lactococcus lactis subsp. fermentation

Study on effects of airborne Pb pollution on quality indicators and accumulation in tea plants using Vis-NIR spectroscopy coupled with radial basis function neural network

Tea plants that have a large leaf area mainly suffer from heavy metal accumulation in the above-ground parts through foliar uptake. With the world rapid industrialization, this pollution in tea is considered a crucial challenge due to its potential health risks. The present study proposes an innovative approach based on visible and near-infrared (Vis-NIR) spectroscopy coupled with chemometrics for the characterization of tea chemical indicators under airborne lead stress, which can be performed fast and in situ. The effects of lead stress on chemical indicators and accumulation in leaves of the two tea varieties at different time intervals and levels of treatment were investigated. In addition, changes in cell structure and leaf stomata were monitored during foliar uptake of aerosol particles by transmission electron microscopy (TEM) and scanning electron microscopy (SEM). The spectral variation was able to classify the tea samples into the Pb treatment groups through the linear discriminant analysis (LDA) model. Two machine learning techniques, namely, partial least squares (PLS) and radial basis function neural network (RBFNN), were evaluated and compared for building the quantitative determination models. The RBFNN models combined with correlation-based feature selection (CFS) and PLS data compression methods were used to optimize the prediction performance. The results demonstrated that the PLS-RBFNN as a non-linear model outperformed the PLS model and provided the R-value of 0.944, 0.952, 0.881, 0.937, and 0.930 for prediction of MDA, starch, sucrose, fructose, glucose, respectively. It can be concluded that the proposed approach has strong application potential in monitoring the quality and safety of plants under airborne heavy metal stress.

Real-Time Monitoring of Yogurt Fermentation Process by Aquaphotomics Near-Infrared Spectroscopy

Automated quality control could have a substantial economic impact on the dairy industry. At present, monitoring of yogurt production is performed by sampling for microbiological and physicochemical measurements. In this study, Near-Infrared Spectroscopy (NIRS) is proposed for non-invasive automated control of yogurt production and better understanding of lactic acid bacteria (LAB) fermentation. UHT (ultra-high temperature) sterilized milk was inoculated with Bulgarian yogurt and placed into a quartz cuvette (1 mm pathlength) and test-tubes. Yogurt absorbance spectra (830-2500 nm) were acquired every 15 min, and pH, in the respective test-tubes, was measured every 30 min, during 8 h of fermentation. Spectral data showed substantial baseline and slope changes with acidification. These variations corresponded to respective features of the microbiological growth curve showing water structural changes, protein denaturation, and coagulation of milk. Moving Window Principal Component Analysis (MWPCA) was applied in the spectral range of 954-1880 nm to detect absorbance bands where most variations in the loading curves were caused by LAB fermentation. Characteristic wavelength regions related to the observed physical and multiple chemical changes were identified. The results proved that NIRS is a valuable tool for real-time monitoring and better understanding of the yogurt fermentation process.

PLS-LS-SVM based modeling of ATR-IR as a robust method in detection and qualification of alprazolam

According to the United States pharmacopeia (USP), Gold standard technique for Alprazolam determination in dosage forms is HPLC, an expensive and time-consuming method that is not easy to approach. In this study chemometrics assisted ATR-IR was introduced as an alternative method that produce similar results in fewer time and energy consumed manner. Fifty-eight samples containing different concentrations of commercial alprazolam were evaluated by HPLC and ATR-IR method. A preprocessing approach was applied to convert raw data obtained from ATR-IR spectra to normal matrix. Finally, a relationship between alprazolam concentrations achieved by HPLC and ATR-IR data was established using PLS-LS-SVM (partial least squares least squares support vector machines). Consequently, validity of the method was verified to yield a model with low error values (root mean square error of cross validation equal to 0.98). The model was able to predict about 99% of the samples according to R² of prediction set. Response permutation test was also applied to affirm that the model was not assessed by chance correlations. At conclusion, ATR-IR can be a reliable method in manufacturing process in detection and qualification of alprazolam content.