Zhiming Guo

Comparisons of different regressions tools in measurement of antioxidant activity in green tea using near infrared spectroscopy

To rapidly and efficiently measure antioxidant activity (AA) in green tea, near infrared (NIR) spectroscopy was employed with the help of a regression tool in this work. Three different linear and nonlinear regressions tools (i.e. partial least squares (PLS), back propagation artificial neural network (BP-ANN), and support vector machine regression (SVMR)), were systemically studied and compared in developing the model. The model was optimized by a leave-one-out cross-validation, and its performance was tested according to root mean square error of prediction (RMSEP) and correlation coefficient (R(p)) in the prediction set. Experimental results showed that the performance of SVMR model was superior to the others, and the optimum results of the SVMR model were achieved as follow: RMSEP=0.02161 and R(p)=0.9691 in the prediction set. The overall results sufficiently demonstrate that the spectroscopy coupled with the SVMR regression tool has the potential to measure AA in green tea.

Identification of green tea’s (Camellia sinensis (L.)) quality level according to measurement of main catechins and caffeine contents by HPLC and support vector classification pattern recognition

High performance liquid chromatography (HPLC) was identified green teas quality level by measurement of catechins and caffeine content. Four grades of roast green teas were attempted in this work. Five main catechins ((-)-epigallocatechin gallate (EGCG), (-)-epigallocatechin (EGC), (-)-epicatechin gallate (ECG), (-)-epicatechin (EC), and (+)-catechin (C)) and caffeine contents were measured simultaneously by HPLC. As a new chemical pattern recognition, support vector classification (SVC) was applied to develop identification model. Some parameters including regularization parameter (R) and kernel parameter (K) were optimized by the cross-validation. The optimal SVC model was achieved with R=20 and K=2. Identification rates were 95% in the training set and 90% in the prediction set, respectively. Finally, compared with other pattern recognition approaches, SVC algorithm shows its excellent performance in identification results. Overall results show that it is feasible to identify green teas quality level according to measurement of main catechins and caffeine contents by HPLC and SVC pattern recognition.

Rapid Pseudomonas Species Identification from Chicken by Integrating Colorimetric Sensors with Near-Infrared Spectroscopy

Pseudomonas spp. are the dominant spoilage bacteria which can cause chicken spoilage. Some traditional detection methods are often unsuitable for their rapid real-time detection. Thus, in this paper, a fusion strategy based on colorimetric sensors and near-infrared spectroscopy was applied to rapidly identify Pseudomonas spp. in chicken. First, four different species of Pseudomonas—Pseudomonas gessardii, Pseudomonas psychrophila, Pseudomonas fragi, and Pseudomonas fluorescens—were isolated from putrid chicken, and then, the odor and spectral information of the Pseudomonas species and their mixture were obtained by colorimetric sensors and near-infrared spectroscopy, respectively. Thirty-six odor characteristic variables and 33 spectral characteristic variables were extracted from each technique and used for data fusion based on principal component analysis (PCA). Back-propagation artificial neural network (BP-ANN) was used to build identification model for the discrimination of the different Pseudomonas species. The results showed that the discrimination capability of the model based on data fusion was superior to that based on the two techniques independently, and eventually BP-ANN achieved 100% classification rate by cross-validation and 98.75% classification rate in predication set. This work indicates that the combination of colorimetric sensors and near-infrared spectroscopy is promising for the rapid identification of Pseudomonas species in chicken extract, and hence may be applied towards quality monitoring.

Intelligent evaluation of color sensory quality of black tea by visible-near infrared spectroscopy technology: A comparison of spectra and color data information

Instrumental test of black tea samples instead of human panel test is attracting massive attention recently. This study focused on an investigation of the feasibility for estimation of the color sensory quality of black tea samples using the VIS-NIR spectroscopy technique, comparing the performances of models based on the spectra and color information. In model calibration, the variables were first selected by genetic algorithm (GA); then the nonlinear back propagation-artificial neural network (BPANN) models were established based on the optimal variables. In comparison with the other models, GA-BPANN models from spectra data information showed the best performance, with the correlation coefficient of 0.8935, and the root mean square error of 0.392 in the prediction set. In addition, models based on the spectra information provided better performance than that based on the color parameters. Therefore, the VIS-NIR spectroscopy technique is a promising tool for rapid and accurate evaluation of the sensory quality of black tea samples.

Noise-free microbial colony counting method based on hyperspectral features of agar plates

A noise-free bacterial colony counting method identifying noise (i.e., sausage, bacon, and millet fragments) with similar colors or shapes to those of colonies was developed for food quality assessment. First, spectral features corresponding to colony cluster regions and background regions (agar medium and food fragments) were extracted after collection of hyperspectral images. A cluster-segmenting calibration model that could identify colony clusters and background regions was developed. Second, spectral features of colony centers and borders were extracted, and a colony-separating calibration model that could separate single colonies from clusters (multiple colonies contacting each other) was developed. Third, each pixel of an agar plate hyperspectral image was identified using established calibration models, enabling the colonies on the agar plate to be counted successfully (R2 = 0.9998). The results demonstrated that the proposed method could identify the noises caused by food fragments with similar colors or shapes to those of colonies.

Development of on-line detection system for simultaneous assessment of edible quality and internal defect in apple by NIR transmittance spectroscopy

L is a potential renewable raw material for synthesis of various value-added chemicals that can substitute fossil-derived consumer products. A huge amount of lignin is produced as a by-product of paper industry while cellulosic components of plant biomass are utilized for the production of paper pulp. In spite of vast potential, lignin remains the least exploited component of plant biomass due to its extremely complex cross-linked three dimensional structures. Nature has provided a few enzymes known to degrade lignin biomass; however, till date there are no efficient processes available for enzymatic degradation of these extremely complex molecules. Development of effective lignin degrading enzymes may be possible by amending activity of some currently available enzymes, using protein engineering techniques. Directed evolution is one such protein engineering tool that could be used for this purpose but application of this technique for improving efficiency of potential lignin degrading enzymes is limited due to lack of an effective high throughput screening method. With an objective of detecting the Lignin Degradation Products (LDPs), we identified E. coli promoters that are up-regulated by vanillin and a few other potential lignin degradation products. 7 potential promoters were identified by RNA-Seq analysis of E. coli BL21 cells pre-exposed to a sub-lethal dose of vanillin for different exposure times. A ‘Very Green Fluorescence Protein’ (vGFP) gene was recombinantly placed under control of these promoters within a customized plasmid and transformed in E. coli BL21 cells to generate the whole cell biosensors. Fluorescence of two biosensors enhanced significantly while grown in the presence of the lignin degradation products (e.g. vanillin, acetovanillone and guaiacol), which was detected by Fluorescence-Activated Cell Sorting (FACS) analysis. The sensors did not show any increase of fluorescence by the presence of lignin, lignin model compounds or non-specific chemicals. The fluorescence change by the presence of LDPs was dose-dependent; one sensor can detect vanillin at the concentration as low as 0.5mm.