Germ-remaining rice quality evaluation method and system based on principal component analysis and entropy weight method

Abstract

The invention belongs to the technical field of germ-remaining rice quality evaluation, and discloses a germ-remaining rice quality evaluation method and system based on principal component analysis and an entropy weight method.The method comprises the steps that quality related indexes in the germ-remaining rice storage process are screened based on principal component analysis, and key evaluation indexes are determined; processing the key evaluation index by adopting an entropy weight method, and determining the evaluation index weight of the germ-remaining rice; and calculating and grading the quality score of the germ-remaining rice by adopting the germ-remaining rice quality evaluation model according to the germ-remaining rice evaluation index weight. The method can provide reference for evaluating the quality deterioration degree of the germ-remaining rice in the storage process.

Description

Technical Field

[0001] The present invention belongs to the technical field of evaluation of germinated brown rice quality, and particularly relates to a method and system for evaluating germinated brown rice quality based on principal component analysis and entropy weight method. Background Art

[0002] Germinated brown rice, also known as germinated rice or active rice, is rice with a germ retention rate of over 80% after the processing of paddy. Compared with polished rice, germinated brown rice retains more nutrients while maintaining good edible quality. However, during the processing of germinated brown rice, the protective layer of the caryopsis is damaged and the fat globules burst, resulting in the contact between fat metabolism-related enzymes and lipids, thereby triggering a series of chemical reactions, which accelerates the decline in the quality of germinated brown rice during storage. There are many related indicators affecting the quality of germinated brown rice, and the determination of each indicator during storage is rather cumbersome. Therefore, it is crucial to establish a quality evaluation model for germinated brown rice during storage.

[0003] The principal component analysis method is a comprehensive statistical analysis method that can summarize multiple original variables into several variables through dimensionality reduction, and can determine key evaluation indicators to simplify the problem. Since there are differences in the amount of information provided by different indicators when evaluating the quality of germinated brown rice, it is necessary to allocate appropriate weights to these indicators to ensure the scientificity and rationality of the evaluation results. However, the traditional analytic hierarchy process mainly relies on expert experience to construct a judgment matrix for calculation, and is often restricted by subjective factors, and its accuracy needs to be improved; the coefficient of variation method can overcome the shortcoming of subjectivity to a certain extent, but the prerequisite for using the coefficient of variation method is that the importance of each indicator is equivalent. Therefore, there are certain limitations in using these two methods to determine weights. The entropy weight method is an objective weight calculation method based on actual measured values, and its core lies in revealing the degree of data dispersion by calculating information entropy. The entropy weight method can dynamically determine weights according to the characteristics of the data itself, and has high accuracy. Therefore, the present invention establishes a quality evaluation model for germinated brown rice based on principal component analysis and entropy weight method, and further grades according to the comprehensive quality score of germinated brown rice during storage, providing a reference for the degree of quality deterioration of germinated brown rice during storage. Summary of the Invention

[0004] To solve the problems existing in the prior art, the present invention provides a method and system for evaluating germinated brown rice quality based on principal component analysis and entropy weight method, which can provide a reference for evaluating the degree of quality deterioration of germinated brown rice during storage.

[0005] To achieve the above object, the present invention provides the following solution:

[0006] A method for evaluating germinated brown rice quality based on principal component analysis and entropy weight method, the method comprising:

[0007] Screen the quality-related indicators during the storage of germinated brown rice based on principal component analysis to determine the key evaluation indicators;

[0008] Process the key evaluation indicators using the entropy weight method and determine the weight of the evaluation indicators for germinated brown rice;

[0009] Calculate and grade the quality score of germinated brown rice using the quality evaluation model for germinated brown rice according to the weight of the evaluation indicators for germinated brown rice.

[0010] Preferably, the quality-related indicators include: fatty acid value, lipase activity, malondialdehyde, texture characteristics, taste value, color difference;

[0011] The screening of the quality-related indicators during the storage of germinated brown rice based on principal component analysis includes:

[0012] Perform principal component analysis on the quality-related indicators using SPSS 27.0, and calculate the eigenvalue and the contribution rate of the principal component variance;

[0013] Construct a loading matrix according to the eigenvalue and the contribution rate of the principal component variance, and determine the key evaluation indicators using the load values.

[0014] Preferably, the process of using the entropy weight method to process the key evaluation indicators and determine the weight of the evaluation indicators for germinated brown rice includes:

[0015] Construct an evaluation matrix according to the key evaluation indicators;

[0016] Standardize the data in the evaluation matrix;

[0017] Calculate the proportion according to the standardized data;

[0018] Calculate the entropy value of the evaluation indicators for germinated brown rice according to the proportion;

[0019] Calculate the variation degree of the evaluation indicators for germinated brown rice according to the entropy value;

[0020] Calculate the weight of the evaluation indicators for germinated brown rice according to the variation degree.

[0021] Preferably, the standardization process of the data in the evaluation matrix includes:

[0022] Processing of positive indicators:

[0023]

[0024] Processing of negative indicators:

[0025]

[0026] Processing of moderate indicators:

[0027]

[0028] Among them, x ij is the data corresponding to the i-th row and the j-th column, min(x j ) is the minimum data in the j-th column, max(x j ) is the maximum data in the j-th column, y ij is the data obtained after the normalization process of x ij , and x 0 is a determined index.

[0029] Preferably, according to the data after the normalization process, calculating the proportion includes:

[0030] Calculating the proportion of the data in the i-th row and the j-th column to the sum of all data in the j-th column. Assuming there are m rows and n columns of data in total, the calculation formula is:

[0031]

[0032] Preferably, according to the proportion, calculating the entropy value of the evaluation index of germinated brown rice includes:

[0033] Calculating the entropy value of the j-th index, and the calculation formula is:

[0034]

[0035] Preferably, according to the entropy value, calculating the variation degree of the evaluation index of germinated brown rice includes:

[0036] The variation degree of the j-th index is:

[0037] g j = 1 - e j .

[0038] Preferably, according to the variation degree, calculating the weight of the evaluation index of germinated brown rice includes:

[0039] The weight of the j-th index is:

[0040]

[0041] Preferably, the evaluation model of germinated brown rice quality includes:

[0042] Y = 0.1577 × hardness + 0.2080 × aroma + 0.2051 × a* + 0.2251 × malondialdehyde + 0.2041 × fatty acid value

[0043] Among them, Y is the comprehensive score.

[0044] The present invention also provides a quality evaluation system for germinated brown rice based on principal component analysis and entropy weight method. The system is used to implement any of the above methods. The system includes: a screening module, a processing module, and an evaluation module;

[0045] The screening module is used to screen the quality-related indicators during the storage process of germinated brown rice based on principal component analysis to determine the key evaluation indicators;

[0046] The processing module is used to process the key evaluation indicators by using the entropy weight method and determine the weight of the germinated brown rice evaluation indicators;

[0047] The evaluation module is used to calculate and grade the quality score of germinated brown rice by using the germinated brown rice quality evaluation model according to the weight of the germinated brown rice evaluation indicators.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0049] The present invention discloses a method and system for evaluating the quality of germinated brown rice based on principal component analysis and entropy weight method. First, the quality-related indicators during the storage process of germinated brown rice are screened based on principal component analysis to determine the key evaluation indicators. Then, the selected indicators are processed by using the entropy weight method and the weights are determined. Finally, the quality score of germinated brown rice is calculated and graded by using the evaluation model. The present invention proposes a new method for evaluating the quality of germinated brown rice, which can provide a reference for evaluating the degree of quality deterioration during the storage process of germinated brown rice. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a schematic flow chart of a method for evaluating the quality of germinated brown rice based on principal component analysis and entropy weight method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments.

[0054] Example 1

[0055] As Figure 1 shown, the present invention provides a method for evaluating the quality of germinated brown rice based on principal component analysis and entropy weight method, and the method includes:

[0056] Screening the quality-related indicators during the storage process of germinated brown rice based on principal component analysis to determine the key evaluation indicators;

[0057] Processing the key evaluation indicators by the entropy weight method and determining the weight of the evaluation indicators of germinated brown rice;

[0058] Calculating and grading the quality score of germinated brown rice by using the quality evaluation model of germinated brown rice according to the weight of the evaluation indicators of germinated brown rice.

[0059] In this embodiment, the quality indicators of germinated brown rice obtained at different storage periods include:

[0060] The materials include: Rice with a germ retention rate of not less than 80% specified in GB / T 42227-2022 is used as germinated brown rice. In this embodiment, the germinated brown rice of Longjing 91 is selected as the research object. The storage temperature of the germinated brown rice in this embodiment is 4°C, the packaging material is Opp+Cpp, and the packaging method is vacuum packaging.

[0061] The determination methods of the quality indicators include:

[0062] Fatty acid value, lipase activity, malondialdehyde:

[0063] The fatty acid value is determined by the method in GB / T 20569—2006; the lipase activity is determined by referring to the method in GB / T5523—2008; the malondialdehyde is determined by using the kit produced by Suzhou Grees Biotechnology Co., Ltd.

[0064] Texture properties:

[0065] Take 50 g of rice, with a rice-to-water ratio of 1:2, cook for 30 min, and keep warm for 30 min. Take out the cooked rice and place it in a petri dish for determination on a texture analyzer. The parameter settings are: disc probe, the pre-test speed is 30 mm / min, the test speed and the post-test speed are 60 mm / min, the initial force is 0.1 N, and the deformation amount is 30%.

[0066] Taste value:

[0067] Weigh 30 g of rice samples. After cleaning, soak them for 30 min at a rice-to-water ratio of 1:1.35, cook for 30 min, and keep warm for 10 min. After the insulation ends, gently stir the rice in the pot until it is loose, cover it with filter paper, place it in a cooling box for 20 min. After cooling, replace the stainless-steel lid and then place it for another 100 min. Take 8.0 g of rice samples and put them into a stainless-steel ring. Use a tablet press to press each side of the stainless-steel ring for 10 s. Put the pressed rice cakes into a rice taste meter to measure the rice taste value.

[0068] Color difference:

[0069] Turn on the CS-580 spectrophotometric color difference meter and perform whiteboard and blackboard calibration; after the calibration ends, the color difference can be measured. In the color difference measurement, the L* value ranges from 0 to 100, changing from black to white. The a* value indicates redness or greenness, the b* value represents yellowness and blueness, and ΔE represents the total color difference.

[0070] In this embodiment, the screening of key evaluation indicators includes:

[0071] Calculate the eigenvalue and the contribution rate of the principal component variance:

[0072] Use SPSS 27.0 to perform principal component analysis on the original data and calculate the eigenvalue and the contribution rate of the principal component variance. As shown in Table 1, the eigenvalue of the first principal component is 14.209, accounting for 88.803% of the total variance. At this time, the cumulative contribution rate of the variance is greater than 85%, which is within the acceptable range and basically covers the main information of the original indicators.

[0073] Table 1

[0074]

[0075] Determine the evaluation indicators using the load value:

[0076] Use SPSS 27.0 to process the original data to obtain the load values of each factor. The load matrix of principal component 1 is shown in Table 2. The load value represents the correlation coefficient between each indicator and the principal component. The larger the absolute value, the greater the influence of the indicator on the principal component. The absolute values of the load values of fatty acid value, malondialdehyde, aroma, a*, and hardness in principal component 1 are relatively large, and their influence on principal component 1 is relatively high. Therefore, select these 5 indicators, namely fatty acid value, malondialdehyde, aroma, a*, and hardness, as the main evaluation indicators for germinated brown rice.

[0077] Table 2

[0078]

[0079] In this embodiment, the determination of the weights of the evaluation indicators for germinated brown rice includes:

[0080] Establish an evaluation matrix:

[0081] According to the evaluation indicators selected in Step 2, an evaluation matrix as shown in Table 3 was constructed.

[0082] Table 3

[0083]

[0084] Data standardization processing:

[0085] Since indicators of different natures will have a greater impact on the results, the influence of the dimension needs to be eliminated during the calculation process, and the data is standardized. The processing process is as follows:

[0086] Processing of positive indicators:

[0087]

[0088] Processing of negative indicators:

[0089]

[0090] Processing of moderate indicators:

[0091]

[0092] Among them, x ij is the data corresponding to the i-th row and the j-th column, min(x j ) is the smallest data in the j-th column, max(x j ) is the largest data in the j-th column, y ij is the data obtained after x ij is standardized, and x 0 is the determined indicator, generally the ideal value of this indicator.

[0093] To ensure the effectiveness of the indicators after standardization processing, 0.0001 is added to each result, and the final data is shown in Table 4.

[0094] Table 4

[0095]

[0096] Calculate the proportion:

[0097] Calculate the proportion of the data in the i-th row and the j-th column to the sum of all data in the j-th column. Assuming there are m rows and n columns of data in total, the calculation formula is as follows:

[0098]

[0099] Calculate the entropy value:

[0100] Calculate the entropy value of the j-th index (the j-th column), and the calculation formula is as follows:

[0101]

[0102] Calculate the degree of variation:

[0103] Calculate the degree of variation of the index. The degree of variation of the j-th index is as follows:

[0104] g j = 1 - e j

[0105] Calculate the weight:

[0106] Calculate the index weight. The weight of the j-th index is as follows:

[0107]

[0108] The finally obtained weight of the evaluation index of germinated brown rice is shown in Table 5.

[0109] Table 5

[0110]

[0111] In this embodiment, the establishment of the germinated brown rice quality evaluation model includes:

[0112] The germinated brown rice quality evaluation model is:

[0113] Y = 0.1577 × hardness + 0.2080 × aroma + 0.2051 × a* + 0.2251 × malondialdehyde + 0.2041 × fatty acid value

[0114] Among them, Y is the comprehensive score.

[0115] In this embodiment, the classification of the comprehensive quality of germinated brown rice includes:

[0116] Substitute the standardized data of the evaluation indexes of germinated brown rice with different storage times into the formula to obtain the comprehensive scores of 6 storage periods, as shown in Table 6.

[0117] Table 6

[0118]

[0119] Judge the quality of germinated brown rice according to the level of the Y value, and classify the germinated brown rice. The quality classification of germinated brown rice is shown in Table 7. Grade I: The quality of germinated brown rice is good, with bright color and excellent smell, suitable for storage; Grade II: The quality of germinated brown rice is better, with normal color and smell, relatively suitable for storage; Grade III: The quality of germinated brown rice is poor, with dull color and slightly poor smell, slightly not suitable for storage; Grade IV: The germinated brown rice is severely deteriorated, with yellowish surface and peculiar smell, severely not suitable for storage.

[0120] Table 7

[0121]

[0122] Example Two

[0123] The present invention also provides a quality evaluation system for germinated brown rice based on principal component analysis and entropy weight method. The system is used to implement any one of the above methods, and the system includes: a screening module, a processing module, and an evaluation module;

[0124] The screening module is used to screen the quality-related indicators during the storage process of germinated brown rice based on principal component analysis to determine the key evaluation indicators;

[0125] The processing module is used to process the key evaluation indicators by using the entropy weight method and determine the weight of the germinated brown rice evaluation indicators;

[0126] The evaluation module is used to calculate and grade the quality score of germinated brown rice by using the germinated brown rice quality evaluation model according to the weight of the germinated brown rice evaluation indicators.

[0127] The above-described embodiments are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for evaluating the quality of embryo-retained rice based on principal component analysis and entropy weight method, characterized in that: The method comprises: Based on principal component analysis, the quality-related indicators of germ-retained rice during storage were screened and key evaluation indicators were determined; The entropy weight method was used to process the key evaluation indicators and determine the weights of the evaluation indicators for embryo-retained rice. According to the weights of the evaluation indicators of germ-retained rice, the quality score of germ-retained rice is calculated and graded using the germ-retained rice quality evaluation model.

2. The method according to claim 1, characterized in that Quality-related indicators include: fatty acid value, lipase activity, malondialdehyde, texture characteristics, taste value, and color difference; The screening of quality-related indicators during the storage of germ-retained rice based on principal component analysis includes: SPSS27.0 was used to perform principal component analysis on quality-related indicators and calculate eigenvalues ​​and principal component variance contribution rates; According to the eigenvalues ​​and the variance contribution rate of the principal components, the loading matrix is ​​constructed, and the key evaluation indicators are determined using the loading values.

3. The method according to claim 1, characterized in that The entropy weight method was used to process the key evaluation indicators, and the weights of the evaluation indicators of embryo-retained rice were determined to include: Construct an evaluation matrix based on key evaluation indicators; Standardize the data in the evaluation matrix; Calculate the specific gravity based on the standardized data; According to the specific gravity, the entropy value of the evaluation index of embryo rice is calculated; According to the entropy value, the variation degree of evaluation indexes of embryo-retained rice is calculated; According to the degree of variation, the weights of evaluation indicators for embryo-retained rice were calculated.

4. The method according to claim 3, characterized in that Standardization of the data in the evaluation matrix includes: Processing of positive indicators: Treatment of negative indicators: Processing of appropriateness indicators: Among them, x ij is the data corresponding to the i-th row and j-th column, min(x j ) is the smallest data in the jth column, max(x j ) is the largest data in the jth column, y ij For x ij The data obtained after standardization, x0 is the determined indicator.

5. The method according to claim 4, characterized in that Based on the standardized data, the calculation weight includes: Calculate the proportion of the data in the i-th row and the j-th column to the sum of all the data in the j-th column. Assuming that there are m rows and n columns of data, the calculation formula is:

6. The method according to claim 5, characterized in that According to the specific gravity, the entropy values ​​of the evaluation indexes of embryo-retained rice are calculated as follows: Calculate the entropy value of the j-th indicator, the calculation formula is:

7. The method according to claim 6, characterized in that According to the entropy value, the variation degree of evaluation indexes of embryo-retained rice is calculated, including: The degree of variation of the jth indicator is: g j =1-e j 。 8. The method according to claim 7, characterized in that According to the degree of variation, the weights of evaluation indicators for embryo-retained rice are calculated, including: The weight of the jth indicator is:

9. The method according to claim 1, characterized in that: The quality evaluation model of germ-retained rice includes: Y=0.1577×hardness+0.2080×aroma+0.2051×a*+0.2251×malondialdehyde+0.2041×fatty acid value, where Y is the comprehensive score.

10. A system for evaluating the quality of embryo-retained rice based on principal component analysis and entropy weight method, the system being used to implement the method according to any one of claims 1 to 9, characterized in that: The system comprises: a screening module, a processing module and an evaluation module; The screening module is used to screen the quality-related indicators of germ-retained rice during storage based on principal component analysis to determine key evaluation indicators; The processing module is used to process the key evaluation indicators by using the entropy weight method and determine the weights of the evaluation indicators of embryo-retained rice; The evaluation module is used to calculate and grade the quality score of the germ-retained rice according to the weight of the germ-retained rice evaluation index using the germ-retained rice quality evaluation model.

Images