Method for rapidly identifying different processing modes and host plant cynomorium songaricum based on electronic nose technology

Abstract

The invention relates to the technical field of cynomorium songaricum identification, in particular to a method for rapidly identifying cynomorium songaricum of different processing modes and host plants based on an electronic nose technology. The method comprises the following steps: filling 1.0 g of a sample into a 10mL silica gel cap penicillin bottle, balancing in a water bath at 60 DEG C for 25 minutes, and detecting by using an electronic nose; and statistical analysis. According to the method, the electronic nose technology is adopted, the cynomorium songaricum which is processed in different modes and comes from different host plants is detected and analyzed, the influence of the different host plants and the processing modes on the flavor of the cynomorium songaricum is known, and then a powerful theoretical basis is provided for rapid quality identification and characteristic flavor evaluation of the cynomorium songaricum. In the aspect of data analysis, a Gaussian Naive Bayes (GNB) classification model statistical method is adopted, qualitative judgment is performed on the characteristic smell of the cynomorium songaricum through a retention value of an electronic nose, a judgment model is constructed, and a solid theoretical foundation is laid for future qualitative prediction.

Description

Technical Field

[0001] The invention relates to the technical field of Cynomorium songaricum identification, and in particular to a method for rapidly identifying Cynomorium songaricum with different processing methods and host plants based on electronic nose technology. Background Art

[0002] As people's pursuit of healthy life is getting hotter and hotter, many health products with medicinal and edible properties are gradually integrated into daily life. Among them, Cynomorium songaricum, as a rare plant with both medicinal and edible properties, is particularly favored by the market. However, this also allows some lawless elements to discover the opportunity for huge profits, so they began to manufacture and sell counterfeit and shoddy products in the market. These products often falsely label their efficacy and are inferior in quality, so consumers cannot get the actual health effects after using them. Therefore, how to quickly and accurately identify the quality of Cynomorium songaricum has become an important issue in current research.

[0003] As a new type of detection technology, electronic nose is fast, accurate and non-destructive. At present, electronic nose has been widely used in the detection of food flavor quality, but it has not been applied to Cynomorium songaricum, and there is no application for related invention patents.

[0004] In summary, the existing technology has the following problems: lack of rapid and effective methods and technical means for the quality identification of Cynomorium songaricum. The introduction of electronic nose technology is expected to solve this problem and provide strong technical support for the healthy development of the Cynomorium songaricum industry. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for quickly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology. The method can quickly and accurately identify different processing methods and host plants of Cynomorium songaricum, which is of great significance for protecting the rights and interests of consumers and promoting the healthy development of the Cynomorium songaricum industry.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for quickly identifying Cynomorium songaricum with different processing methods and host plants based on electronic nose technology, characterized in that it comprises the following steps:

[0008] Step 1, sample processing; the different host plants of the samples are Cynomorium songaricum and Cynomorium serratum; the different processing methods of the samples include the following: (1) 3 slice thicknesses: 0.5 cm, 1 cm, and 2 cm thick fleshy stem slices; (2) 6 drying methods: oven 105°C for 30 min, drying at 65°C to constant weight; oven 105°C for 30 min, drying at 85°C to constant weight; oven 65°C for constant weight; oven 85°C for constant weight; vacuum freeze drying: 0.096hP, -100°C for constant weight; natural sun drying: placed outdoors for natural sun drying to constant weight; the 3 slice thicknesses and 6 drying methods are combined into 18 processing methods; the sample is crushed with a high-speed crusher and passed through an 80-mesh sieve for subsequent analysis;

[0009] Step 2: 1.0 g of sample was placed in a 10 mL silica gel cap vial, and then equilibrated in a 60°C water bath for 25 min before detection using an electronic nose; the detection conditions and parameters were as follows: air intake rate 1 L·min-1; sensor cleaning time 180 s; sensor cleaning flow rate 6 L·min-1; sample detection time 90 s;

[0010] Step 3. Statistical analysis: The electronic nose sensor response value data was used as the independent variable, and the processing method and host plant were used as the dependent variables. The data were shuffled, 80% of them were randomly selected as the training set, and the remaining 20% ​​were used as the test set. A Gaussian naive Bayes (GNB) model was established, and the machine learning algorithm was used to further accurately identify different categories of Cynomorium samples; each measurement indicator had 3 replicates, and the obtained data were analyzed and processed using SPSSPRO software and Origin 2022 software.

[0011] In view of the unique smell characteristics of Cynomorium songaricum, the present invention adopts electronic nose technology to detect and analyze Cynomorium songaricum after different processing methods and from different host plants, understand the influence of different host plants and processing methods on the flavor of Cynomorium songaricum, and then provide a strong theoretical basis for the rapid quality identification and characteristic flavor evaluation of Cynomorium songaricum. In data analysis, the Gaussian Naive Bayes (GNB) classification model statistical method is adopted to qualitatively discriminate the characteristic smell of Cynomorium songaricum through the retention value of the electronic nose, and a discrimination model is constructed to lay a solid theoretical foundation for future qualitative prediction.

[0012] The present invention has the following beneficial effects:

[0013] 1. Rapidity: Electronic nose technology has the characteristics of rapid response and can complete odor detection and identification in a short time, which greatly shortens the time for quality identification of Cynomorium songaricum and improves detection efficiency.

[0014] 2. Accuracy: Electronic nose technology can sense very slight differences in odor by simulating the olfactory function of the human nose, and accurately analyze and judge the characteristic odor of Cynomorium songaricum, thereby achieving accurate identification of the quality of Cynomorium songaricum.

[0015] 3. Non-destructive: Compared with traditional chemical analysis methods, electronic nose technology does not require processing or destruction of samples, can maintain the integrity of samples, and avoids errors that may be introduced during sample processing.

[0016] 4. Intelligence: Through intelligent sensory technology, the electronic nose can automatically detect and analyze Cynomorium songaricum with different host plants and processing methods, reducing the interference of human factors and improving the objectivity and reliability of detection.

[0017] 5. Wide applicability: Electronic nose technology is not only suitable for the quality identification of Cynomorium songaricum, but can also be applied to the quality inspection of other Chinese medicinal materials or foods with unique odor characteristics. It has wide applicability and application prospects.

[0018] In summary, the present invention uses electronic nose technology to identify the quality of Cynomorium songaricum, which has the advantages of rapidity, accuracy, non-destructiveness, intelligence and wide applicability, and provides strong technical support for quality control and market supervision of the Cynomorium songaricum industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The electronic nose radar fingerprints of the odor characteristics of Cynomorium songaricum in 18 processing methods in the present invention;

[0020] Figure 2 The confusion matrix heat map of the training set (A) and test set (B) results of the GNB model for 18 processing methods in the present invention;

[0021] Figure 3 The confusion matrix heat map of the training set (A) and test set (B) results of the GNB model for three slice thicknesses in the present invention;

[0022] Figure 4 The confusion matrix heat map of the training set (A) and test set (B) results of the GNB model for the six drying methods in the present invention;

[0023] Figure 5 The confusion matrix heat map of the training set (A) and test set (B) results of the GNB model for the three types of drying methods in the present invention;

[0024] Figure 6 The electronic nose radar fingerprints of the odor characteristics of different host plants Cynomorium songaricum in the present invention;

[0025] Figure 7This is a heat map of the confusion matrix of the training set (A) and test set (B) results of the GNB model for different host plants in the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Embodiment 1

[0028] 1. Sample processing

[0029] Different host plants: Take fresh Cynomorium songaricum and Cynomorium songaricum.

[0030] Different processing methods: (1) 3 slice thicknesses: 0.5cm, 1cm, and 2cm thick fleshy stem slices. (2) 6 drying methods: oven 105℃ for 30min, drying at 65℃ to constant weight; oven 105℃ for 30min, drying at 85℃ to constant weight; oven 65℃ to constant weight; oven 85℃ to constant weight; vacuum freeze drying: 0.096hP, -100℃ to constant weight; natural sun drying: placed outdoors to dry naturally to constant weight. Each treatment is numbered, where letters A to C represent slice thickness, numbers 1 to 6 represent drying methods, and the combination of numbers and letters represents processing methods. The specific numbers are shown in Table 1. The above samples were crushed with a high-speed grinder and passed through an 80-mesh sieve for subsequent analysis.

[0031] Table 1 Slice thickness, drying method and processing method number

[0032]

[0033] 2. Instruments

[0034] Table 2 Test instruments

[0035]

[0036] 3. Experimental methods

[0037] 1.0g of the sample to be tested was placed in a 10mL silica gel cap vial and tested after equilibration in a 60℃ water bath for 25min. Test conditions and parameters: air intake rate 1L·min-1; sensor cleaning time 180s; sensor cleaning flow rate 6L·min-1; sample detection time 90s. The substance classification corresponding to each sensor of the electronic nose is shown in Table 3.

[0038] Table 3 Classification of substances corresponding to electronic nose sensors

[0039]

[0040]

[0041] 4. Statistical analysis

[0042] The electronic nose sensor response value data was used as the independent variable, and the processing method and host plant as the dependent variables. The data were shuffled, and 80% of them were randomly selected as the training set and the remaining 20% ​​as the test set. A Gaussian naive Bayes (GNB) model was established, and the machine learning algorithm was used to further accurately identify different categories of Cynomorium songaricum samples.

[0043] Each measurement indicator was repeated three times, and the obtained data were analyzed and processed using SPSSPRO and Origin 2022 software.

[0044] 4.1 Identification of Cynomorium songaricum with different processing methods based on electronic nose technology

[0045] 4.1.1 Analysis of electronic nose response values

[0046] from Figure 1 It can be seen that the 18 electronic nose sensors all responded to the volatile components of Cynomorium songaricum processed by different methods, but there were differences in the response characteristics of different sensors, and their contribution to the test data was also different. Under different slice thicknesses, the electronic nose response values ​​of the same drying method were basically the same; while under the same slice thickness, the electronic nose response values ​​of different drying methods had a large difference, which is consistent with the conclusion that the drying method has a greater impact on nutrients and antioxidant activity. Overall, the response value of the dried sample was the highest, followed by sun drying, and the lowest was freeze drying. There were four sensors that had the greatest impact on the response value of the Cynomorium songaricum odor, namely S1, S2, S10 and S15 sensors. Among them, the S1 sensor was mainly sensitive to short-chain alkanes, the S2 sensor was mainly sensitive to carbon-containing substances, the S10 sensor was mainly sensitive to hydrogen-containing gases, and the S15 sensor was mainly sensitive to carbon-containing substances and alcohols and aldehydes. This shows that the differences in the odor of Cynomorium songaricum processed by different methods are mainly concentrated on compounds such as short-chain alkanes, carbon-containing substances, hydrogen-containing gases, alcohols and aldehydes. In summary, there are differences in the odor of the finished products of Cynomorium songaricum after being processed by different methods.

[0047] 4.1.2 Establishment of Gaussian Naive Bayes (GNB) classification model based on electronic nose

[0048] (1) Establishment of GNB classification model for 18 processing methods based on electronic nose

[0049] By observing the confusion matrix heat map of the 18 processing method training sets ( Figure 2A), which is the intersection of model predictions and actual situations, and it is found that all prediction set samples are predicted correctly. View the confusion matrix diagram of the test data ( Figure 2 B), it was found that there were 5 samples predicted correctly, namely A2, A3, A5, C5 and C6; there were 6 samples predicted incorrectly, namely 1 B3, B4, B5, C1 and 2 A1. As shown in Table 4-1, the accuracy, precision and recall of this model on the training set were all 100.0%, and the F1-Score was 1.000, which performed very well. However, the accuracy and recall obtained on the test set were both 45.5%, the precision was 40.9%, and the F1-Score was 0.424, and the evaluation effect was average. This shows that the 18 processing methods GNB discrimination model established based on the electronic nose data cannot accurately predict the Cynomorium samples with different processing methods.

[0050] Table 4-11 Evaluation results of GNB model for 18 processing methods

[0051]

[0052] (2) Establishment of GNB classification model for three slice thicknesses

[0053] Depend on Figure 3 A shows that there are 28 samples correctly predicted in the GNB model training set with three slice thicknesses, including 11 0.5 cm slice samples, 13 1 cm slice samples, and 4 2 cm slice samples; there are 15 samples wrongly predicted, including 3 0.5 cm slice samples, 3 1 cm slice samples, and 9 2 cm slice samples. Figure 3 B shows that there are 7 samples predicted correctly in the test set, including 4 0.5 cm slice samples, 2 1 cm slice samples, and 1 2 cm slice sample; there are only 2 samples predicted incorrectly, both of which are 2 cm slice samples. As shown in Table 4-2, the accuracy and recall rate of this model on the training set are both 65.1%, the precision rate is 68.3%, and the F1-Score is 0.627, which performs well. The accuracy and recall rate obtained on the test set are 63.6%, the precision rate is 81.8%, and the F1-Score is 0.579, and the evaluation effect is also good. It shows that the three slice thickness GNB discrimination models established based on the electronic nose data can accurately predict Cynomorium samples with different slice thicknesses.

[0054] Table 4-2 Evaluation results of GNB model for three slice thicknesses

[0055]

[0056] (3) Establishment of GNB classification model for six drying methods based on electronic nose

[0057] Depend on Figure 4 A shows that there are 36 samples correctly predicted in the GNB model training set of 6 drying methods, including 5 samples of 105℃ fixation for 30min and 65℃ drying, 6 samples of 105℃ fixation for 30min and 85℃ drying, 7 samples of 65℃ drying, 5 samples of 85℃ drying, 6 samples of sun drying and 7 samples of freeze drying; there are 7 samples wrongly predicted, including 1 sample of 105℃ fixation for 30min and 65℃ drying, 3 samples of 105℃ fixation for 30min and 85℃ drying and 3 samples of 85℃ drying. Figure 4 B shows that there are 8 samples predicted correctly in the test set, including 2 samples with 105℃ fixation for 30min and 65℃ drying, 1 sample with 65℃ drying, 3 samples with sun drying and 2 samples with freeze drying; there are only 3 samples predicted incorrectly, including 1 sample with 105℃ fixation for 30min and 65℃ drying, 1 sample with 65℃ drying and 1 sample with 85℃ drying. As shown in Table 4-3, the accuracy and recall rate of this model on the training set are both 83.7%, the precision rate is 86.9%, and the F1-Score is 0.836, which is a good performance. The accuracy and recall rate obtained on the test set are 72.7%, the precision rate is 81.8%, and the F1-Score is 0.764, and the evaluation effect is also good. It shows that the 6 drying methods GNB discrimination model established based on the electronic nose data can accurately predict Cynomorium samples with different slice thicknesses.

[0058] Table 4-3 Evaluation results of GNB model for 6 drying methods

[0059]

[0060] (4) Establishment of GNB classification model for three types of drying methods based on electronic nose

[0061] Depend on Figure 5 A shows that all 43 samples in the GNB model training set of the three drying methods were predicted correctly, and Figure 5 B shows that all 11 samples in the test set model are also correctly predicted. As shown in Table 4-4, the accuracy, precision and recall of this model on the training set and test set are all 100.0%, and the F1-score is 1.000, which is very good. This shows that the three-category drying method GNB discrimination model established based on the electronic nose data can effectively and accurately predict samples of different drying methods.

[0062] Table 4-4 GNB model evaluation results for three types of drying methods

[0063]

[0064] 4.2 Identification of Cynomorium songaricum from different host plants based on electronic nose technology

[0065] 4.2.1 Analysis of electronic nose response values

[0066] from Figure 6 It can be seen that the 18 sensors have different response values ​​to the volatile components of different host plants Cynomorium. Overall, the electronic nose response value of Cynomorium salsa is greater than that of Cynomorium sargentii. Among the 18 sensors, 6 sensors, S4, S6, S9, S14, S15 and S16, have a greater impact on the response value of Cynomorium odor. Among them, S4 and S16 are mainly sensitive to sulfides, S6 is mainly sensitive to aldehydes and ketones, S9 is mainly sensitive to alkanes, alcohols, ketones and other substances, S14 is mainly sensitive to short-chain alkanes, and S15 is mainly sensitive to carbon-containing substances as well as alcohols and aldehydes. This shows that the differences in the odor of different host plants Cynomorium are mainly concentrated on compounds such as sulfides, aldehydes and ketones, alkanes, short-chain alkanes, alcohols, ketones and aldehydes. In summary, Cynomorium salsa from different host plants has differences in odor characteristics.

[0067] 4.2.2 Establishment of Gaussian Naive Bayes (GNB) classification model based on electronic nose

[0068] Depend on Figure 7 As can be seen from A, all samples in the GNB model training set of different host plants are predicted correctly, and Figure 7 B shows that all samples in the test set model are also correctly predicted. As shown in Table 4-5, the accuracy, precision and recall of this model on the training set and test set are all 100.0%, and the F1-Score is 1.000, which means that the evaluation effect of the training set and the test set is very good, indicating that the two host plant GNB discrimination models established based on the electronic nose sensor data can accurately predict the samples of Cynomorium songaricum (BW) and Cynomorium nitrarum (BC).

[0069] Table 4-5 Evaluation results of GNB model for different host plants

[0070]

[0071] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for quickly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology, characterized in that: The steps include: Step 1: Sample processing; Step 2: 1.0 g of sample was placed in a 10 mL silica gel cap vial, equilibrated in a 60°C water bath for 25 min, and then tested with an electronic nose; Step 3: Statistical analysis.

2. A method for rapidly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology according to claim 1, characterized in that: In step one, the different host plants of the samples are Cynomorium songaricum and Cynomorium songaricum.

3. A method for rapidly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology according to claim 1, characterized in that: In step 1, the different processing methods of the sample include the following: (1) 3 slice thicknesses: 0.5 cm, 1 cm, and 2 cm thick fleshy stem slices; (2) 6 drying methods: oven sterilization at 105°C for 30 min, drying at 65°C to constant weight; oven sterilization at 105°C for 30 min, drying at 85°C to constant weight; oven drying at 65°C to constant weight; oven drying at 85°C to constant weight; vacuum freeze drying: 0.096hP, -100°C to constant weight; natural sun drying: placed outdoors to dry naturally to constant weight; the 3 slice thicknesses and 6 drying methods are combined into 18 processing methods.

4. A method for rapidly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology according to claim 1, characterized in that: In step 1, the sample was crushed with a high-speed crusher and passed through an 80-mesh sieve for subsequent analysis.

5. A method for rapidly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology according to claim 1, characterized in that: In step 2, the test conditions and parameters are: air intake rate 1L·min -1 ;Sensor cleaning time is 180s;Sensor cleaning flow rate is 6L·min -1 ; Sample detection time 90s.

6. A method for rapidly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology according to claim 1, characterized in that: In step three, the electronic nose sensor response value data were used as independent variables, and the processing method and host plant were used as dependent variables. The data were shuffled, and 80% of them were randomly selected as the training set and the remaining 20% ​​as the test set. A Gaussian naive Bayes (GNB) model was established to further accurately identify different categories of Cynomorium songaricum samples through machine learning algorithms.

7. A method for rapidly identifying different processing methods and host plants of Cynomorium songaricum based on electronic nose technology according to claim 1, characterized in that: In step three, each measurement indicator was repeated three times, and the obtained data were analyzed and processed using SPSSPRO software and Origin 2022 software.

Images