Near infrared spectrum rapid evaluation method for brown rice protein content

Abstract

The invention provides a near infrared spectrum rapid evaluation method for the protein content of brown rice. The method comprises the following steps: acquiring optical signals of different varieties of brown rice under a near-infrared band and physicochemical indexes measured according to a traditional method, preprocessing the acquired optical signals by utilizing a smoothing (Savitzky-Golay) method, and constructing a brown rice protein content evaluation model based on machine learning and a characteristic band selection algorithm; effective prediction of the protein content of the brown rice is realized only through optical characteristic parameters. According to the method, the protein content of the brown rice can be predicted only by collecting the near infrared spectrum of the brown rice, and in food processing enterprises, the technology can remarkably improve the efficiency and stability of product quality monitoring, support real-time online detection and provide an efficient and rapid quality control scheme for the enterprises, so that the product consistency is improved, the waste of raw materials is reduced, and the production cost is reduced. The production benefit is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of spectral analysis and relates to the detection of brown rice quality by applying near-infrared spectroscopy technology. Background Art

[0002] Rice is the main staple food for people in most parts of China and has a dominant position. With the improvement of residents' living standards, consumers have higher requirements for food quality. The high-quality standard of edible rice is a comprehensive trait, which is generally divided into milling quality, appearance quality, cooking and taste quality, and nutritional quality. Among them, the cooking and taste quality are directly related to consumers and determine the acceptability of brown rice. Traditional methods are very accurate in evaluating the quality of brown rice. However, these methods usually require complicated pretreatment, professional operation, and use a large amount of chemicals, making it difficult to achieve rapid detection of large-scale samples. In contrast, spectroscopy technology allows the spectral information of samples to be obtained with little or no damage to the samples. Therefore, spectroscopy technology is increasingly being used in food testing, and the use of vibrational spectroscopy technology to achieve real-time, rapid and accurate detection of rice quality has important scientific research value and application prospects.

[0003] Vibrational spectroscopy is an important means for rapid quality identification of agricultural products and processed foods. At present, common vibrational spectroscopy techniques related to rice include near-infrared (NIR) spectroscopy, Fourier transform infrared (FTIR) spectroscopy, hyperspectral imaging (HIS), Raman spectroscopy, fluorescence spectroscopy (FS), terahertz spectroscopy and laser-induced breakdown spectroscopy (LIBS). These spectral techniques have achieved the prediction of quality indicators such as moisture, starch, and freshness. However, the near-infrared spectroscopy technology has not yet effectively achieved the accurate detection of brown rice protein content. The fundamental reason is that molecular spectra are mostly band spectra, and the spectral lines are easy to overlap, resulting in serious spectral interference, which needs to be improved by combining chemometrics. Different chemometric methods in some current studies have given unsatisfactory prediction results, which may be related to the small number of samples and the small differences between samples. The characteristic band screening method can effectively improve the accuracy of the model and help improve the generalization ability of the model. This will contribute to the development of the rice industry. Summary of the invention

[0004] The invention aims to provide a novel method for quickly detecting protein content in brown rice. By using near-infrared spectroscopy, the optical signal of brown rice is obtained and the protein content of brown rice is measured, and pre-processing is performed by smoothing (Savitzky-Golay), and the optical correlation system of brown rice protein content is constructed by combining the continuous projection algorithm (SPA), the competitive adaptive reweighted sampling algorithm (CARS), the non-information variable elimination (UVE), the iterative information retention algorithm (IRIV), the interval combination optimization (ICO) characteristic band screening algorithm with the partial least squares (PLS), and the support vector machine (SVM) algorithm analysis, so as to realize the detection of brown rice protein content by the optical characteristics of brown rice.

[0005] The benefits of the present invention are as follows: (1) the variation patterns of the chemical quality and optical properties of brown rice are explored, and a high-throughput optical database of brown rice is constructed; (2) a prediction model for the physical and chemical quality of brown rice using near-infrared spectroscopy is developed, and a characteristic band screening method is used to digitally evaluate the physical and chemical quality of brown rice; (3) a method for rapidly predicting the quality characteristics of brown rice is developed, which simplifies the detection steps of the brown rice quality indexes. Compared with the traditional determination of the quality indexes of brown rice, the present invention saves time, reduces labor, and significantly reduces the determination cost; (4) the quality characteristics of brown rice are rapidly predicted only by rapid optical property characterization of brown rice, providing technical support for food companies to achieve rapid, efficient, and stable product quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 : Abstract with attached pictures

[0007] Figure 2 :Schematic diagram of brown rice varieties

[0008] Figure 3 :Protein content frequency distribution diagram

[0009] Figure 4 :Results of different feature screening algorithms in the near-infrared band (a) SPA feature wavelength extraction process; (b) feature bands selected by SPA algorithm; (c) CARS feature wavelength extraction process; (d) feature bands extracted by CARS algorithm;

[0010] Figure 5 : Results of different feature screening algorithms in the near-infrared band (a) UVE stability diagram; (b) Feature bands extracted by the UVE algorithm; (c) IRIV algorithm variable retention iteration curve; (d) Feature bands extracted by the IRIV algorithm DETAILED DESCRIPTION

[0011] A near infrared spectroscopy rapid evaluation method for brown rice protein content, the specific implementation method is as follows:

[0012] 1. Experimental Materials and Methods

[0013] Brown rice sample preparation: 155 varieties of rice were sown in mid-to-late May. Mature seeds were harvested in batches from mid-September to early October, 40 days after heading. Varieties with similar maturity were selected, and the collected seeds were naturally air-dried and left to mature indoors for one month. Brown rice was then obtained by husking, and the rice grains were ground into fine powder using a vibrating ball mill GT300 and passed through a 100-mesh sieve for later use.

[0014] Protein content determination: Use rapid N Exceed nitrogen analyzer (elementar, Germany), use 1 / 10,000 electronic balance to weigh 250.0 mg of brown rice flour and aspartic acid (Asp) standard, wrap it with tin foil and compact it. After turning on the nitrogen analyzer and waiting for the self-test to heat up, open the CO2 and O2 valves and start loading. First place three blank samples (Blank), set the Method to BlankwithO2; then place 5 standard samples, set the Method to 250 mg Standard, and set the protein factor to 6.25. Place each variety of brown rice samples in turn. After loading, the instrument automatically analyzes. After the run is completed, read and use GraphPadPrism to analyze the data.

[0015] Vibrational spectrum and spectral data acquisition: This study collected point spectra. The spectral detection system in the near-infrared band (900-2500nm) includes a tungsten-halogen light source (ASBN-100-L), a near-infrared spectrometer (NIR2500), a Y-type optical fiber (FIB-Y-600-L(2)-NIR) and a standard white plate (STD-WS). The condition parameters for collecting the near-infrared spectrum of brown rice are set as follows: integration time 6ms, window smoothing 7, and average times 10 times to improve the signal-to-noise ratio. The optical fiber probe should be close to the standard white plate or sample for spectral signal collection. The calibration is to collect the reflectance spectrum of the standard white plate by turning off and on the light source, and the collected spectra are used as dark spectra and light source spectra for reference before collecting sample spectra. Subsequently, the dark spectrum reflectance (D) and the light source spectrum reflectance (W) are used to convert the spectral reflectance (S) of each sample into the reflectance (R) relative to the standard white plate.

[0016]

[0017] Spectral data set: 465 spectra in total (155 varieties × 3 repeated measurements).

[0018] 2. Spectral preprocessing and model construction

[0019] use R2023a (The MathWorks, USA) was used to construct support vector machine (SVM) and partial least squares (PLS) models. Before building the model, 465 spectral data were smoothed (Savitzky-Golay) preprocessed. The calibration set and validation set were divided into a ratio of 3:1 using the random principle. For the calibration set of the model: 155 varieties of rice, including 349 near-infrared spectra. For the validation set of the model; 155 varieties of rice, including 116 near-infrared spectra. In addition, PLS and SVM regression models were constructed based on the results of feature band screening using the continuous projection algorithm (SPA), competitive adaptive reweighted sampling algorithm (CARS), non-information variable elimination (UVE), iterative information retention algorithm (IRIV), and interval combination optimization (ICO). The root mean square error (RMSEV) of the validation set and the prediction accuracy (R c 2 ) and the prediction accuracy of the validation set (R v 2 ) was used to evaluate the prediction performance of the model.

[0020] 3. Analysis of changes in physical and chemical quality characteristics of brown rice

[0021] like Figure 2 As shown in Figure 2, all varieties of brown rice showed no significant differences in appearance, indicating that appearance characteristics cannot directly reflect the differences in protein content between varieties. However, there are obvious changes in protein content among different varieties of brown rice (see Figure 3 ). According to the data in Table 1, the total protein content of brown rice ranges from 6.55% to 11.99%, indicating that the differences in protein content among these varieties are quite significant. Further analysis found that the distribution of these protein contents generally showed a normal distribution trend (see Figure 3 ), indicating that the protein content of most varieties is concentrated near the middle value, and extremely low or high protein content is relatively rare.

[0022] Table 1 Variation of protein content in different varieties of brown rice

[0023]

[0024] 4. Comparative analysis of the results of predicting brown rice quality characteristics based on machine learning combined with characteristic band selection algorithm

[0025] The results of selecting near-infrared spectral data based on different characteristic band selection algorithms are as follows: Figure 4As shown in the figure, Figure a shows that as the number of variables increases, the root mean square error of the SPA algorithm gradually decreases until the number of variables reaches 17 and the model error no longer decreases significantly. Figure b shows the locations of the 17 characteristic wavelengths selected by the SPA algorithm. Figure c shows the feature selection process of the CARS algorithm. The cross-validation root mean square error first decreases and then increases with the increase in the number of sampling times, reaching the lowest value around 400 times. It can be seen that CARS continuously reduces the characteristic variables to find the wavelengths that contribute the most to the model to optimize the model's prediction ability and prevent overfitting. Finally, 41 characteristic bands are selected as shown in Figure d. The results based on UVE and IRIV are as follows Figure 5 As shown in Figure a, the red part is random noise. By comparing the t values ​​of the actual variables and random variables, we can determine which variables have important contributions to the model. The variables with higher t values ​​in the blue curve will be retained, while the actual variables that perform similarly to the red curve (random variables) will be eliminated. Finally, 111 characteristic bands are selected, mainly concentrated in 1200-1300nm and 1800-2250nm. The results of IRIV are shown in Figures c and d. By the sixth iteration, the number of variables was reduced to a stable value and was close to the number of variables finally retained. Finally, 19 characteristic variables were selected.

[0026] The results of predicting the protein content of brown rice based on PLS and SVM algorithms combined with the characteristic band selection algorithm are shown in Table 2. c 2 It indicates the prediction accuracy of the model for the calibration set, R v 2 R represents the prediction accuracy of the model for the validation set, RMSEV represents the average prediction deviation of the model for the validation set, and RMSEC represents the average prediction deviation of the model for the calibration set. c 2 With R v 2 The larger the value and the smaller the RMSE, the better the prediction effect of the model. In Table 2, the prediction effect of the protein content of brown rice based on the SVM model is significantly better than that based on PLS. Among the models based on the PLS algorithm, the model using the CARS feature band selection algorithm has the best effect (R v 2 =0.6638, RMSEV = 0.7325). Among all the models for predicting protein content, the model based on ICO-SVM algorithm can best predict the protein content of brown rice (R v 2 =0.8651, RMSEV=1.1067) and using only 59 characteristic bands can significantly reduce the computational cost, improve the detection efficiency, and has commercial value.

[0027] Table 2 Prediction of brown rice protein content based on PLS and SVM algorithms combined with characteristic band selection algorithm

[0028]

[0029] In summary, the prediction results of brown rice protein content based on machine learning technology combined with characteristic band selection algorithm show that by selecting a small number of key bands for modeling, not only the complexity of the model is greatly simplified, but also the prediction accuracy is significantly improved. This result shows that the optimized characteristic band screening strategy can accurately and quickly predict the protein content of brown rice. This study provides important support for the application of near-infrared spectroscopy technology in rapid and non-destructive detection of brown rice quality, demonstrates its great potential and broad application prospects in actual detection, and helps to improve the detection efficiency in food production and quality control.

[0030] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the above embodiments do not limit the present invention in any form, and any technical solution obtained by equivalent replacement or equivalent transformation falls within the protection scope of the present invention.

Claims

1. A near infrared spectroscopy rapid evaluation method for brown rice protein content comprises the following steps: S1. 155 varieties of brown rice were sown in mid-to-late May. The mature seeds were harvested in batches from mid-September to early October, 40 days after heading. The varieties with similar maturity were selected, and the collected seeds were naturally air-dried and placed indoors for one month of post-ripening. Then, the rice was husked and ground to obtain brown rice. The rice grains were ground into fine powder using a vibrating ball mill and passed through a 100-mesh sieve for later use. S2. The condition parameters for collecting near-infrared spectra of brown rice are set as follows: integration time 6ms, window smoothing 7, and average times 10 times to improve the signal-to-noise ratio. The fiber optic probe should be close to the standard white plate or sample for spectral signal collection. The calibration collects the reflectance spectrum of the standard white plate by turning off and on the light source, and the collected spectra are used as dark spectra and light source spectra for reference before collecting sample spectra. Subsequently, the spectral reflectance (S) of each sample is converted to the reflectance (R) relative to the standard white plate using the dark spectrum reflectance (D) and the light source spectrum reflectance (W). S3. Using a rapid N Exceed nitrogen analyzer (elementar, Germany), 250.0 mg of brown rice flour and aspartic acid (Asp) standard were weighed using a 1 / 10,000 electronic balance, and the samples were wrapped in tin foil and compacted. Turn on the nitrogen analyzer and wait for the self-test to finish heating. Then open the CO2 and O2 valves and start loading samples. First place three blank samples (Blank), set the Method to BlankwithO2; then place 5 standard samples, set the Method to 250mg Standard, and set the protein factor to 6.

25. Place the brown rice samples of each variety in turn. After loading, the instrument automatically analyzes. After the run is completed, read and use GraphPadPrism to analyze the data. S4. Construct support vector machine (SVM) and partial least squares (PLS) models. Before building the model, the 465 spectral data were smoothed (Savitzky-Golay) preprocessed. The calibration set and validation set were divided into a 3:1 ratio using the random principle. For the calibration set of the model: 155 varieties of rice, including 349 near-infrared spectra. For the validation set of the model: 155 varieties of rice, including 116 near-infrared spectra. The root mean square error (RMSEV) of the validation set and the prediction accuracy (R c 2 ) and the prediction accuracy of the validation set (R v 2 ) was used to evaluate the prediction performance of the model. S5, PLS and SVM regression models are also constructed based on the results of continuous projection algorithm (SPA), competitive adaptive reweighted sampling algorithm (CARS), non-information variable elimination (UVE), iterative information retention algorithm (IRIV), and interval combination optimization (ICO) feature band screening. The root mean square error (RMSEV) of the validation set and the prediction accuracy (R c 2 ) and the prediction accuracy of the validation set (R v 2 ) was used to evaluate the prediction performance of the model.

Images