[Measurement of chlorophyll content and distribution in tea plant's leaf using hyperspectral imaging technique].

Chlorophyll content and distribution in plant's leaves is an important index in estimation of plant nutrition information. In the present work, chlorophyll content and distribution in tea plant's leaves were measured by hyperspectral imaging technique. First, hyperspectral image data were captured from tea plant's leaves; then seven kinds of algorithms were used to extract the characteristic parameters from hyperspectral image; finally, seven fitted models were developed using the characteristics vectors and the reference measurements of chlorophyll contents respectively. Experimental results showed that the MSAVI2 model is superior to other models, and the results of the MSAVI2 model was achieved as follows: R = 0.843 3 and RMSE = 9.918 in the calibration set; R = 0.832 3 and RMSE = 8.601 in the prediction set. Finally, the chlorophyll content of each pixel in image was estimated by the fitted model, and the distribution of chlorophyll content in the tea plant's leaf was described by pseudo-color map. This study sufficiently demonstrated that the chlorophyll content and distribution in tea leaf can be measured by hyperspectral imaging technique.

[Determination of taste quality of green tea using FT-NIR spectroscopy and variable selection methods].

The present paper was attempted to study the feasibility to determine the taste quality of green tea using FT-NIR spectroscopy combined with variable selection methods. Chemistry evaluation, as the reference measurement, was used to measure the total taste scores of green tea infusion. First, synergy interval PLS (siPLS) was implemented to select efficient spectral regions from SNV preprocessed spectra; then, optimal variables were selected using genetic algorithm (GA) from these selected spectral regions by siPLS, and the optimal model was achieved with Rp = 0.8908, RMSEP = 4.66 in the prediction set when 38 variables and 6 PLS factors were included. Experimental results showed that the performance of siPLS-GA model was superior to those of others. This study demonstrated that NIR spectra could be used successfully to measure taste quality of green tea and siPLS-GA algorithm has superiority to other algorithm in developing NIR spectral regression model.

[Rapid diagnostics of early phosphorus deficiency in mini-cucumber plants under protected cultivation by near infrared spectroscopy].

The morphological symptom of phosphorus deficiency at early stage is similar to the appearance of leaf aging process in preliminary phase, so that visual diagnostics of phosphorus deficiency in mini-cucumber plants at early stage is practically impossible. Near infrared reflectance spectra contain information about differences in compositions of leaf tissues between phosphorus-deficient plants and healthy plants. In the present paper, near infrared reflectance spectroscopy was used to provide diagnostic information on phosphorus deficiency of mini-cucumber plants grown under non-soil conditions. Near infrared spectra was collected from 90 leaves of mini-cucumber plants. Raw cucumber spectra was preprocessed by SNV and divided into 27 intervals. The top 10 principal components (PCs) were extracted as the input of BP-ANN classifiers by principal component analysis (PCA) while the values of nutrient deficient were used as the output variables of BP-ANN and three layers BP-ANN discrimination model was built. The best experiment results were based on the top 3 principal components of No. 7 interval when the spectra was divided into 27 intervals and identification rates of the ANN model are 100% in both training set and the prediction set. The overall results show that NIR spectroscopy combined with BP-ANN can be efficiently utilized for rapid and early diagnostics of phosphorus deficiency in mini-cucumber plants.

[Identification of egg freshness using near infrared spectroscopy and one class support vector machine algorithm].

Near infrared (NIR) spectroscopy combined with pattern recognition was attempted to discriminate the freshness of eggs. The algorithm of one-class support vector machine (OC-SVM) was employed to solve the classification problem due to imbalanced number of training samples. In this work, 86 samples of eggs (71 samples of fresh eggs and 15 samples of unfresh eggs) were surveyed by Fourier transform NIR spectroscopy. Firstly, original spectra of eggs in the wave-number range of 10 000-4 000 cm(-1) were acquired. And then, principal component analysis (PCA) was employed to extract useful information from original spectral data, and the number of PCs was optimized. Finally, OC-SVM was performed to calibrate discrimination model, and the optimal PCs were used as the input eigenvectors of model. In order to obtain a good performance, the regularization parameter v and parameter sigma of the kernel function in OC-SVM model were optimized in building model. The optimal OC-SVM model was obtained with nu = 0.5 and sigma2 = 20.3. Experimental result shows that OC-SVM got better performance than conventional two-class SVM model under the same condition. The OC-SVM model was achieved with identification rates of 80 for both fresh eggs and unfresh eggs in the independent prediction set. The identification rates of fresh eggs were 100% in two-class SVM model. However, when the two-class SVM model was used to discriminate the unfresh eggs of, the identification rates were 0% in the independent prediction set. Compared with conventional two-class SVM model, the OC-SVM model showed its superior performance in discrimination of minority unfresh eggs samples. This work shows that it is feasible to identify egg freshness using NIR spectroscopy, and OC-SVM is an excellent choice in solving the problem of imbalanced number of samples in training set.

[A new method of characteristic wavelength sub-range selection of near infrared spectroscopy].

To improve and simplify the prediction model of carotenoid content of cucumber leaves, genetic algorithm (GA) combined with Metropolis acceptance criterion of simulated annealing algorithm (SAA) as well as interval partial least square (iPLS) were proposed and used to establish the calibration models of carotenoid content against cucumber leaves spectra. The cucumber leaves spectra data were divided into 40 intervals, among which 7 subsets, i. e. No. 3, 4, 14, 18, 21, 32 and 33, were selected by SAA-GA-iPLS. The comparison was made between SAA-GA-iPLS and traditional genetic algorithm interval partial least square (GA-iPLS), and the result of this study shows that SAA-GA-iPLS was better than traditional genetic algorithm interval partial least square (GA-iPLS).

[Study of simplification of prediction model for kiwifruit firmness using near infrared spectroscopy].

To simplify the prediction model of kiwifruit firmness, SNV was used to preprocess the near infrared (NIR) spectra (1 000-2 500 nm)of kiwifruit. PLS model simplification by optimizing spectral intervals and decreasing the number of factors through net analyte preprocessing (NAP)was carried out. Results showed that the performance of NAP/PLS model is the best. It was achieved with 5 factors in five wavenumber ranges(5 189-5 370, 4 549-4 620, 6 049-6 230, 6 999-7 730, and 6 249-6 614 cm(-1)). The optimal model was achieved with R2 = 0.819 41 and RMSECV = 0.701 77 in the calibration set and R2 = 0.780 67 and RMSEP = 0.882 71 in the prediction set. This indicates that the model not only may efficiently simplify PLS model, but also may improve precision and predictive ability.

Sensory quality evaluation for appearance of needle-shaped green tea based on computer vision and nonlinear tools.

Tea is one of the three greatest beverages in the world. In China, green tea has the largest consumption, and needle-shaped green tea, such as Maofeng tea and Sparrow Tongue tea, accounts for more than 40% of green tea (Zhu et al., 2017). The appearance of green tea is one of the important indexes during the evaluation of green tea quality. Especially in market transactions, the price of tea is usually determined by its appearance (Zhou et al., 2012). Human sensory evaluation is usually conducted by experts, and is also easily affected by various factors such as light, experience, psychological and visual factors. In the meantime, people may distinguish the slight differences between similar colors or textures, but the specific levels of the tea are hard to determine (Chen et al., 2008). As human description of color and texture is qualitative, it is hard to evaluate the sensory quality accurately, in a standard manner, and objectively. Color is an important visual property of a computer image (Xie et al., 2014; Khulal et al., 2016); texture is a visual performance of image grayscale and color changing with spatial positions, which can be used to describe the roughness and directivity of the surface of an object (Sanaeifar et al., 2016). There are already researchers who have used computer visual image technologies to identify the varieties, levels, and origins of tea (Chen et al., 2008; Xie et al., 2014; Zhu et al., 2017). Most of their research targets are crush, tear, and curl (CTC) red (green) broken tea, curly green tea (Bilochun tea), and flat-typed green tea (West Lake Dragon-well green tea) as the information sources. However, the target of the above research is to establish a qualitative evaluation method on tea quality (Fu et al., 2013). There is little literature on the sensory evaluation of the appearance quality of needle-shaped green tea, especially research on a quantitative evaluation model (Zhou et al., 2012; Zhu et al., 2017).

[The determination of beef tenderness using near-infrared spectroscopy].

The prediction of beef tenderness was studied using near-infrared spectroscopy. The absorption spectra of beef samples were collected between 4,000 and 10,000 cm(-1), the maximum shear force of these samples was obtained using the Warner-Bratzler attachment, and subjective judgment for the tenderness grade of beef was studied. Beef samples with the maximum shear force less than 6 kg were regarded as tender, and their tenderness grade was defined as the value of 1. Those with the maximum shear force greater than 9 kg were regarded as tough, and their tenderness grade was defined as the value of 3. And those with the maximum shear force between 6 and 9 kg were regarded as medium, and their tenderness grade was defined as the value of 2. The study shows that the absorption value of tougher beef is generally higher than that of tender beef. Multiple linear regression was used to build the model between the absorption value and tenderness grade. The results give the correlation coefficient r is 0.806. The accuracy of the model for predicting tenderness grade of beef was 84.21% for a validation set including 19 samples. This result indicates that NIR spectroscopy is capable of predicting tenderness grade of beef.

[Study on the identification of tea using near infrared reflectance spectroscopy].

A rapid tea identification method by near infrared spectroscopy coupled with pattern recognition based on principal components analysis and Mahalanobis' distance technique was proposed. Four famous brand teas in China were studied, including Longjing tea, Biluochun tea, Maofeng tea and Tieguanyin tea in the experiment. In the spectral region between 6 500 and 5 300 cm(-1), through preprocessing method of MSC (multiplicative scatter comection), the prediction model was built. The result showed that the model was the best with 8 principal component factors. The rates of identification in calibration set samples and prediction set samples were 98.75% and 95%, respectively. A new idea about quick and precise identification of tea was offered.

Determination of pork spoilage by colorimetric gas sensor array based on natural pigments.

A new colorimetric gas-sensor array based on four natural pigments, that were extracted from spinach (Spinacia oleracea), red radish (Raphanus sativus L.), winter jasmine (Jasminum nudiflorum), and black rice (Oryza sativa L. indica), was developed for pork freshness evaluation. A colour change profile for each sample was obtained by differentiating the images of the sensor array before and after exposure to the odour of sample. The total viable count (TVC) per gram of pork was obtained by classical microbiological plating methods, and the biogenic amines were measured by HPLC. Biogenic amine index (BAI) for the determination of meat freshness was developed from the sum of putrescine and cadaverine. The colour change profiles were analysed using principal component analysis and correlated with conventional methods (BAI, TVC). A partial least squares (PLS) prediction model was obtained with r=0.854 and 0.933 for BAI and TVC, respectively.

A new sensor for ammonia based on cyanidin-sensitized titanium dioxide film operating at room temperature.

Design and fabrication of an ammonia sensor operating at room temperature based on pigment-sensitized TiO2 films was described. TiO2 was prepared by sol-gel method and deposited on glass slides containing gold electrodes. Then, the film immersed in a 2.5×10(-4)M ethanol solution of cyanidin to absorb the pigment. The hybrid organic-inorganic formed film here can detect ammonia reversibly at room temperature. The relative change resistance of the films at a potential difference of 1.5V is determined when the films are exposed to atmospheres containing ammonia vapors with concentrations over the range 10-50 ppm. The relative change resistance, S, of the films increased almost linearly with increasing concentrations of ammonia (r=0.92). The response time to increasing concentrations of the ammonia is about 180-220 s, and the corresponding values for decreasing concentrations 240-270 s. At low humidity, ammonia could be ionized by the cyanidin on the TiO2 film and thereby decrease in the proton concentration at the surface. Consequently, more positively charged holes at the surface of the TiO2 have to be extracted to neutralize the adsorbed cyanidin and water film. The resistance response to ammonia of the sensors was nearly independent on temperature from 10 to 50°C. These results are not actually as good as those reported in the literature, but this preliminary work proposes simpler and cheaper processes to realize NH3 sensor for room temperature applications.

Determination of total flavonoids content in fresh Ginkgo biloba leaf with different colors using near infrared spectroscopy.

Total flavonoids content is often considered an important quality index of Ginkgo biloba leaf. The feasibility of using near infrared (NIR) spectra at the wavelength range of 10,000-4000cm(-1) for rapid and nondestructive determination of total flavonoids content in G. biloba leaf was investigated. 120 fresh G. biloba leaves in different colors (green, green-yellowish and yellow) were used to spectra acquisition and total flavonoids determination. Partial least squares (PLS), interval partial least squares (iPLS) and synergy interval partial least squares (SiPLS) were used to develop calibration models for total flavonoids content in two colors leaves (green-yellowish and yellow) and three colors leaves (green, green-yellowish and yellow), respectively. The level of total flavonoids content for green, green-yellowish and yellow leaves was in an increasing order. Two characteristic wavelength regions (5840-6090cm(-1) and 6620-6880cm(-1)), which corresponded to the absorptions of two aromatic rings in basic flavonoid structure, were selected by SiPLS. The optimal SiPLS model for total flavonoids content in the two colors leaves (r(2)=0.82, RMSEP=2.62mg g(-1)) had better performance than PLS and iPLS models. It could be concluded that NIR spectroscopy has significant potential in the nondestructive determination of total flavonoids content in fresh G. biloba leaf.

Study on classification of soy sauce by electronic tongue technique combined with artificial neural network.

Electronic tongue as an analytical tool coupled with pattern recognition was attempted to classify 4 different brands and 2 categories (produced by different processes) of Chinese soy sauce. An electronic tongue system was used for data acquisition of the samples. Some effective variables were extracted from electronic tongue data by principal component analysis (PCA). Backpropagation artificial neural network (BP-ANN) was applied to build identification models. PCA score plots show an obvious cluster trend of different brands and different categories of soy sauce in the 2-dimensional space. The optimal BP-ANN model for different brands was achieved when principal components (PCs) were 2, and the identification rate of the discrimination model was 100% in both the calibration set and the prediction set, and the optimal BP-ANN model for different categories had the same result. This work demonstrates that electronic tongue technology combined with a suitable pattern recognition method can be successfully used in the classification of different brands and categories of soy sauce.