Method for rapidly detecting gelatinization characteristics of rice based on near infrared spectrum

Abstract

The invention relates to a rice gelatinization characteristic rapid detection method based on a near infrared spectrum, which comprises the following steps: acquiring optical signals of different varieties of rice in a near infrared band and gelatinization characteristic values measured according to a traditional method, preprocessing the acquired optical signals by utilizing a smoothing (Savitzky-Golay) method; an evaluation model of rice gelatinization temperature, peak time, peak viscosity, minimum viscosity, cold glue viscosity, disintegration value, retrogradation value and subduction value is constructed based on machine learning and a characteristic wave band selection algorithm, and effective prediction of rice gelatinization characteristics is achieved only through optical characteristic parameters. According to the method, the gelatinization characteristics of the rice can be evaluated only by collecting the near infrared spectrum of the rice, and technical support is provided for rapid, efficient and stable product quality monitoring of food processing enterprises. Therefore, a rapid, efficient and stable quality monitoring technical support is provided for food processing enterprises, so that the quality control in the production process is more convenient and accurate. Through the technology, an enterprise can adjust production parameters in time so as to ensure the consistency and excellent quality of products.

Description

Technical Field

[0001] The present invention belongs to the technical field of spectral analysis, and relates to the detection of the gelatinization characteristic values of rice by using near-infrared spectroscopy technology. Background Art

[0002] Rice, as the main food for people in most parts of China, holds a dominant position. With the improvement of the living standards of residents, consumers have higher requirements for the quality of grains. The high-quality standards of edible rice are a comprehensive trait, generally divided into milling quality, appearance quality, cooking and eating quality, and nutritional quality, etc. Among them, the cooking and eating quality is directly related to consumers and determines the acceptability of rice. Traditional methods are very accurate in evaluating the characteristic values of rice. However, these methods usually require complicated pretreatment, need to be operated by professionals, and use a large amount of chemicals, making it difficult to achieve rapid detection of large-scale samples. On the contrary, spectroscopy technology allows obtaining the spectral information of a sample with little or no damage to the sample. Therefore, spectral technology is being increasingly used in food detection. It has important scientific research value and application prospects to use vibrational spectroscopy technology to achieve real-time, rapid, and accurate detection of rice quality.

[0003] Rice, as the staple food for 60% of the Chinese population, holds a dominant position in ensuring food security. With the improvement of the living standards of residents, consumers' requirements for the quality of rice are constantly increasing. The quality of rice is a comprehensive trait, generally divided into milling quality, appearance quality, cooking and eating quality, and nutritional quality, etc. Starch is the first type of storage substance in rice, accounting for 95% of the dry weight of rice, and is the most crucial factor affecting the cooking and eating quality of rice. Rice starch is mainly divided into two categories: amylose and amylopectin. In production, the eating quality of rice is mainly evaluated by measuring the physical and chemical indexes such as the gel consistency, gelatinization characteristics, and hot paste viscosity characteristics of polished rice flour. Using traditional methods to measure the physical and chemical indexes such as the gel consistency, gelatinization characteristics, and hot paste viscosity characteristics of polished rice flour is time-consuming and laborious, making it difficult to achieve rapid detection of large-scale samples. At the same time, the destructive grinding of rice also makes the seeds unable to be further planted. On the contrary, spectroscopy technology allows obtaining the spectral information of a sample quickly with little or no damage to the sample. The commonly used near-infrared grain analyzer on the market can achieve non-destructive and rapid analysis of quality traits such as protein content, moisture, and amylose content, and has been purchased and used by many units. However, there are few reports on the spectral analysis of starch gelatinization and hot paste viscosity characteristics.

[0004] Near-infrared spectroscopy is an important means for the rapid identification of the quality 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 spectroscopy techniques have realized the prediction of quality indicators such as moisture, starch, and freshness. However, the accurate detection of the gelatinization characteristics of rice has not been effectively achieved based on vibrational spectroscopy techniques. The fundamental reason is that molecular spectra are mostly band spectra, and spectral lines are prone to overlap, resulting in relatively serious spectral interference, which needs to be improved by combining chemometrics. In some current studies, different chemometric methods have given unsatisfactory prediction results, which may be related to the too small number of samples and the small differences between samples. Different spectroscopy techniques have different principles, so they have different prediction potentials for the quality attributes of rice. The method based on characteristic band screening can greatly improve the accuracy of the model and help to enhance the generalization ability of the model. This will contribute to the development of the rice industry. Summary of the Invention

[0005] The object of the present invention is to provide a new method for rapidly detecting the gelatinization characteristic values of rice. By using near-infrared spectroscopy, the optical signals of rice are obtained and the gelatinization characteristic parameters of rice (gelatinization temperature, peak time, peak viscosity, minimum viscosity, cold paste viscosity, breakdown value, setback value, breakdown reduction value) are collected. After preprocessing by smoothing (Savitzky-Golay), the characteristic band screening algorithms such as successive projections algorithm (SPA), competitive adaptive reweighted sampling algorithm (CARS), uninformative variable elimination (UVE), and iterative retaining information algorithm (IRIV) are combined with partial least squares (PLS) and support vector machine (SVM) algorithms to analyze and construct the optical correlation system of the gelatinization characteristic values of rice, so as to realize the detection of the gelatinization characteristics of rice from the optical characteristics of rice.

[0006] The advantages of the present invention are as follows: (1) The change rules of the chemical quality and optical characteristics of rice are explored, and a high-throughput optical database of rice is constructed; (2) A prediction model for the gelatinization characteristic values of rice by near-infrared spectroscopy is developed, and the physical and chemical quality of rice is digitally evaluated by using the characteristic band screening method; (3) A method for rapidly predicting the gelatinization characteristics of rice is developed, which simplifies the detection steps of the gelatinization characteristic values of rice. Compared with the traditional determination of the gelatinization characteristic values of rice, the present invention can realize rapid and non-destructive detection and significantly reduce the determination cost; (4) Only by rapidly characterizing the optical characteristics of rice, the rapid prediction of the gelatinization characteristic values of rice is realized, which provides rapid, efficient, and stable product quality control for food enterprises. Brief Description of the Drawings

[0007] Figure 1 : Abstract Drawing

[0008] Figure 2 : Schematic diagram of rice varieties

[0009] Figure 3 : (a) Box plot of gelatinization characteristic values; (b) Frequency distribution diagram of gelatinization temperature; (c) Frequency distribution diagram of peak time

[0010] Figure 4 : Results of different feature selection algorithms in the near-infrared band (a) Process of extracting characteristic wavelengths by SPA; (b) Characteristic bands selected by SPA algorithm; (c) Process of extracting characteristic wavelengths by CARS; (d) Characteristic bands extracted by CARS algorithm

[0011] Figure 5 : (a) Stability diagram of UVE; (b) Characteristic bands extracted by UVE algorithm; (c) Iterative curve of variable retention by IRIV algorithm; (d) Characteristic bands extracted by IRIV algorithm Specific implementation manner

[0012] A rapid detection method for rice gelatinization characteristics based on near-infrared spectroscopy, and the specific implementation manner is as follows:

[0013] 1. Experimental materials and methods

[0014] Preparation of rice samples: 155 rice varieties were sown in the middle and late May. Taking 40 days after heading as the standard, the mature seeds were harvested in batches from mid-September to early October. Selecting varieties with similar maturity periods, after the collected seeds were naturally air-dried, they were placed indoors for after-ripening for one month, and then brown rice and polished rice were obtained through hulling and grinding. The rice grains were ground into fine powder through a 100-mesh sieve using a vibrating ball mill GT300 for standby.

[0015] RVA spectrum determination: According to the methods in the national standard of the People's Republic of China GB / T 24852-2010 and the AACC (American Association of Cereal Chemists) procedure (1995-61-02), using the RVA-TecMaster rapid viscosity analyzer developed and produced by Perten Company of Sweden and the supporting analysis software TCW3, measure the curve of viscosity changing with time and obtain the characteristic values of the RVA spectrum. Turn on the rapid viscosity analyzer and preheat it for 30 minutes. Open the TCW3 control software and load the set rice rapid analysis program. Measure (25 ± 0.1) mL of water meeting the requirements of GB / T 6682, and accurately weigh (3.00 ± 0.01) g of polished rice flour using an analytical balance accurate to one ten-thousandth. Transfer all the experimental materials to the supporting aluminum sample cylinder and quickly stir them evenly until the sample is completely dispersed. Place the stirrer into the aluminum sample cylinder, transfer it to the copper half base, and insert the connector into the card slot to ensure that the cylinder is stably connected to the rapid viscosity analyzer. After ensuring that the conditions permit, press the motor cap of the instrument and run the test program. After the test is completed, export the obtained RVA spectrum and 8 characteristic values therein, namely peak viscosity, minimum viscosity, cold paste viscosity, peak time, gelatinization temperature, breakdown value, setback value, and consistency value. Among them, the units of peak viscosity, minimum viscosity, cold paste viscosity, breakdown value, setback value, and consistency value are expressed in centipoise (cP), and the measurement results are rounded to the nearest integer; the unit of peak time is minute (min), and the measurement result is accurate to 0.01; the unit of gelatinization temperature is degree Celsius (°C), and the measurement result is accurate to 0.01.

[0016] Near-infrared spectrum and spectral data acquisition: In this study, spot spectra were collected. The spectral detection system in the near-infrared band (900 - 2500 nm) includes a tungsten halogen light source (ASBN-100-L), a near-infrared spectrometer (NIR2500), a Y-shaped optical fiber (FIB-Y-600-L(2)-NIR), and a standard white board (STD-WS). The condition parameters for collecting the near-infrared spectrum of rice are set as follows: integration time 6 ms, window smoothing 7, and average number 10 times to improve the signal-to-noise ratio. The optical fiber probe should be closely attached to the standard white board or the sample for spectral signal acquisition. Calibration is carried out by closing and opening the light source to collect the reflection spectra of the standard white board, and the collected spectra are used as the dark spectrum and light source spectrum for reference before sample spectrum collection respectively. Subsequently, using the dark spectrum reflectance (D) and the light source spectrum reflectance (W), the spectral reflectance (S) of each sample is converted into the reflectance (R) relative to the standard white board.

[0017]

[0018] Spectral data set: A total of 465 spectra (155 varieties × 3 repeated measurements).

[0019] 2. Spectral Pretreatment and Model Construction

[0020] Use R2023a (The MathWorks, USA) to construct support vector machine (SVM) and partial least squares (PLS) models. Before building the models, 465 spectral data are preprocessed by smoothing (Savitzky - Golay). According to the random principle, the calibration set and the validation set are divided in a ratio of 3:1. 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 are constructed based on the results of feature band screening by successive projections algorithm (SPA), competitive adaptive reweighted sampling algorithm (CARS), uninformative variable elimination (UVE), iterative retaining information algorithm (IRIV), and interval combination optimization (ICO). The prediction performance of the model is evaluated by the root mean square error of the validation set (RMSEV), the prediction accuracy of the calibration set (R c 2 ) and the coefficient of determination of the prediction accuracy of the validation set (R v 2 ).

[0021] 3. Analysis of Changes in Physicochemical Gelatinization Characteristics of Rice

[0022] As Figure 2 shown, among all varieties, there is no obvious difference in the appearance of rice. However, the changes in its gelatinization characteristics are obvious ( Figure 3 ). As shown in Table 1, for the 8 characteristic values of the RVA profile, the peak viscosity is up to 5298 cP at most, which reflects the stronger swelling power of the starch molecules of this variety; the lowest viscosity appears after most of the starch granules are broken, reflecting the ability of starch to resist shear at high temperatures. The distribution of the lowest viscosity ranges from 1181 cP to 3964 cP, indicating that there are significant differences in the shear resistance of starches from different varieties of rice; the cool paste viscosity reflects the ability of the starch paste to form a gel after cooling. The cool paste viscosities of different varieties of rice increase from 1798 cP to 7548 cP. The higher the cool paste viscosity, the stronger the ability of the starch to form a gel; the breakdown value (BDV) is the difference between the highest viscosity and the lowest viscosity. The standard deviation of the breakdown values of 155 samples of rice in this sample reaches 542.45, and there are significant differences among varieties. The setback value is the difference between the cool paste viscosity and the peak viscosity. During the determination of rice starch, it reflects the hardness of the cooked rice texture. It can be seen that the setback values of some varieties are negative, indicating that the low apparent amylose content leads to a harder texture of the cooked rice. As Figure 3As shown, the gelatinization temperature of most varieties is concentrated above 75°C. The gelatinization temperature is directly proportional to the cooking time and the amount of water absorbed, which is affected by the amylopectin structure and the crystal properties of starch molecules. The peak time distribution ranges from 4.06 to 6.33 min, roughly showing a normal distribution.

[0023] Table 1 Changes in the physical and chemical indexes of different varieties of rice

[0024]

[0025] 4. Comparative analysis of the results of predicting rice gelatinization characteristic values based on machine learning combined with the characteristic band selection algorithm

[0026] The results of selecting near-infrared spectral data based on different characteristic band selection algorithms are as Figure 4 shown. Figure a shows that with the increase in the number of variables in the SPA algorithm, the root mean square error of the model gradually decreases until the model error no longer decreases significantly when the number of variables reaches 17. Figure b shows the positions of the 17 characteristic wavelengths selected by the SPA algorithm. Figure c shows the process of feature selection by the CARS algorithm. The root mean square error of cross-validation first decreases and then increases with the increase in the number of sampling times and reaches the lowest value at about 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 prediction ability of the model and prevent overfitting. Finally, as shown in Figure d, 41 characteristic bands are selected.

[0027] The results of UVE are as Figure 5 shown in a and b. It can be seen from Figure a that the red part is random noise. By comparing the t-values of the actual variables and the random variables, it is determined which variables are important for the model. The variables with higher t-values in the blue curve will be retained, while the actual variables similar to the red curve (random variables) will be eliminated. Finally, 111 characteristic bands are selected, mainly concentrated at 1200 - 1300 nm and 1800 - 2250 nm. The results of IRIV are shown in Figure c and d. By the 6th iteration, the number of variables decreases to a stable value and is close to the number of variables finally retained. Finally, 19 characteristic variables are selected.

[0028] The results of predicting rice gelatinization characteristic values based on the PLS and SVM algorithms combined with the characteristic band selection algorithm are shown in Table 2. The effect of predicting rice gelatinization characteristic values based on the CARS-SVM model is significantly better than that based on CARS-PLS. In addition, among all the models for predicting gelatinization characteristic values, the CARS-SVM model can best predict the peak time (R v 2 = 0.9829, RMSEV = 0.5285), peak viscosity (R v 2= 0.8268, RMSEV = 729.1909), the disintegration value (R v 2 = 0.8736, RMSEV = 517.7335) The results are satisfactory and have commercial value.

[0029] Table 2 Prediction of rice gelatinization characteristic values based on the PLS and SVM algorithms combined with the characteristic band selection algorithm

[0030]

[0031]

[0032] In summary, based on machine learning technology combined with the characteristic band selection algorithm, the prediction results of rice gelatinization characteristic values 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 indicates that by adopting an optimized characteristic band screening strategy, the rice gelatinization characteristic values can be accurately and quickly predicted. This study provides important support for the application of near-infrared spectroscopy technology in the rapid non-destructive detection of rice quality, demonstrates its great potential and broad application prospects in actual detection, and helps to improve the detection efficiency in grain production and quality control.

[0033] 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. Any technical solutions obtained by using equivalent replacements or equivalent transformations fall within the protection scope of the present invention.

Claims

1. A rapid detection method for rice gelatinization characteristics based on near infrared spectroscopy, comprising the following steps: S1. 155 rice varieties 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. They were then husked and ground to obtain brown rice and polished 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 the near-infrared spectrum of 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 the dark spectrum and light source spectrum for reference before collecting the sample spectrum. 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, RVA spectrum determination: According to the method in the National Standard of the People's Republic of China GB / T 24852-2010 and the AACC (American Association of Cereal Chemists) regulations (1995-61-02), the viscosity change curve over time is measured to obtain the characteristic values ​​of the RVA spectrum. Preheat the rapid viscosity analyzer for 30 minutes, load the rice rapid program, weigh water and rice flour into the sample tube, stir evenly and place it into the instrument, and start the test program. After the test is completed, the RVA spectrum and the 8 characteristic values ​​therein are exported, namely peak viscosity, minimum viscosity, cold gel viscosity, peak time, gelatinization temperature, disintegration value, reduction value and recovery value. 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. In addition, PLS and SVM regression models were constructed based on the results of the continuous projection algorithm (SPA), competitive adaptive reweighted sampling algorithm (CARS), uninformative variable elimination (UVE), and iterative information retention algorithm (IRIV) 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