CN116646019B - Propolis liquid quality detection data processing method and system - Google Patents
Propolis liquid quality detection data processing method and system Download PDFInfo
- Publication number
- CN116646019B CN116646019B CN202310920001.7A CN202310920001A CN116646019B CN 116646019 B CN116646019 B CN 116646019B CN 202310920001 A CN202310920001 A CN 202310920001A CN 116646019 B CN116646019 B CN 116646019B
- Authority
- CN
- China
- Prior art keywords
- cluster
- clustering
- indicate
- data
- propolis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000241413 Propolis Species 0.000 title claims abstract description 117
- 229940069949 propolis Drugs 0.000 title claims abstract description 117
- 239000007788 liquid Substances 0.000 title claims abstract description 59
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 230000003595 spectral effect Effects 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 46
- 230000008569 process Effects 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000001228 spectrum Methods 0.000 claims description 47
- 238000010521 absorption reaction Methods 0.000 claims description 43
- 238000004364 calculation method Methods 0.000 claims description 37
- 229930003935 flavonoid Natural products 0.000 claims description 10
- 150000002215 flavonoids Chemical class 0.000 claims description 10
- 235000017173 flavonoids Nutrition 0.000 claims description 10
- ISWSIDIOOBJBQZ-UHFFFAOYSA-N phenol group Chemical group C1(=CC=CC=C1)O ISWSIDIOOBJBQZ-UHFFFAOYSA-N 0.000 claims description 9
- 235000013824 polyphenols Nutrition 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000002310 reflectometry Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 15
- 238000004458 analytical method Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000002371 ultraviolet--visible spectrum Methods 0.000 description 5
- 239000012535 impurity Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000004480 active ingredient Substances 0.000 description 2
- 150000001413 amino acids Chemical class 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 238000004566 IR spectroscopy Methods 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 125000003118 aryl group Chemical group 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000007766 cera flava Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000028327 secretion Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Crystallography & Structural Chemistry (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application relates to the technical field of data processing, and provides a propolis quality detection data processing method and system, wherein the method comprises the following steps: acquiring spectral data of propolis liquid to be detected, preprocessing the spectral data, clustering the acquired spectral data by adopting a fuzzy C-means algorithm, and calculating the clustering error bias of each iterative cluster in the clustering process according to different characteristics of different components of the propolis liquid in response to the spectral data to obtain a new value of ambiguity in the clustered cluster after each iteration, thereby completing the clustering of the spectral data of the propolis liquid; obtaining a spectrogram of the cluster according to the clustering result, further calculating a quality reference index of the propolis liquid to be detected, and judging the quality of the propolis liquid to be detected according to a comparison result of the quality reference index and a preset threshold value. Therefore, the clustering effect on the spectral data of the propolis can be improved, the accuracy of analyzing the relative content of the components of the propolis can be improved, and the accuracy of detecting the quality of the propolis is higher.
Description
Technical Field
The application relates to the technical field of digital data processing, in particular to a propolis quality detection data processing method and system.
Background
Propolis liquid is a substance with aromatic smell obtained by collecting gum from plant spore and trunk of bee, and mixing with bee upper jaw secretion and Cera flava. The propolis liquid contains more beneficial components, has good effects of resisting bacteria, resisting inflammation, enhancing immunity, clearing heat and detoxicating, and the like, has higher edible and application values, and has been widely applied to the fields of food, health care products, medicines, and the like.
The efficacy of the propolis is directly related to the active ingredients contained in the propolis, and the quality of the propolis is different due to different content of the ingredients, so that the production quality of the propolis is controlled, and the efficacy and the value of the propolis can be exerted. The quality of the propolis can be detected by adopting an infrared spectrometry method, spectral data of the propolis is collected, the collected data is subjected to clustering analysis, and the production quality of the propolis is analyzed. However, the calculation accuracy of the objective function in the traditional fuzzy C-means algorithm is low, so that the clustering result is poor, the analysis of the propolis component content data is directly influenced, the accuracy of propolis quality detection is reduced, and a propolis product with poor quality flows into the market.
Disclosure of Invention
In view of the above problems, the application provides a method and a system for processing propolis quality detection data, which can adaptively adjust the ambiguity of an ambiguity C mean algorithm after each iteration according to the absorption intensity of different components of propolis under different wavelengths, so as to improve the clustering effect on propolis spectral data, further improve the accuracy of analyzing the relative content of the propolis components, and realize higher accuracy of propolis quality detection.
In a first aspect, an embodiment of the present application provides a method for processing propolis quality detection data, including:
acquiring first spectrum data of propolis liquid to be detected;
preprocessing the first spectrum data by adopting a baseline correction algorithm to obtain second spectrum data;
calculating the clustering error bias of the first clustering cluster obtained by each iteration in the clustering process of the second spectral data by adopting a fuzzy C-means clustering algorithm, and carrying out self-adaptive adjustment on the fuzzy degree of the fuzzy C-means clustering algorithm according to the clustering error bias in the next iteration until the clustering process of the second spectral data of the propolis liquid to be detected is completed, so as to obtain a second clustering cluster;
determining a spectrogram of each second cluster according to the second spectral data in each second cluster;
calculating a quality reference index of the propolis liquid to be detected according to the spectrogram of each second cluster;
and comparing the quality reference index with a preset threshold value, and judging the quality of the propolis liquid to be detected according to the comparison result.
In one possible implementation, the method includes: the first spectrum data are the absorptivity and reflectivity of the propolis liquid to be detected under different wavelengths.
In one possible implementation manner, in a clustering process of the second spectrum data by adopting a fuzzy C-means clustering algorithm, calculating a clustering error bias of the first cluster obtained by each iteration, and in the next iteration, adaptively adjusting the ambiguity of the fuzzy C-means clustering algorithm according to the clustering error bias, including:
performing center attribution calculation on each second spectrum data in each first cluster obtained by each iteration in the clustering process to obtain the center attribution of each second spectrum data in each first cluster;
carrying out component characteristics and illuminance calculation on each first cluster to obtain component characteristics and illuminance of different components in each first cluster;
calculating the absorption peak offset of each first cluster according to the information entropy of the center attribution set of all the second spectrum data in each first cluster and the corresponding component characteristic illumination of different components in each first cluster;
calculating the cluster center offset of the same first cluster center before and after the adjacent two iterative clusters to obtain the cluster center offset;
obtaining the cluster error bias in each iterative cluster based on the absorption peak bias and the cluster center bias of each first cluster;
and adaptively adjusting the ambiguity of the fuzzy C-means clustering algorithm in the next iteration according to the cluster error bias.
In one possible implementation manner, performing a center attribution calculation on each second spectrum data in each first cluster obtained by each iterative cluster includes: the calculation formula of the center attribution degree is as follows:
wherein ,indicate->Within the cluster->Center degree of ownership of the second spectral data, < >>Indicate->Second spectral data to +.>Euclidean distance of second spectrum data of cluster centers of the cluster clusters; />Indicate->Second spectral data to +.>Euclidean distance of second spectral data of cluster center of each cluster, < ->Indicating removal of->The number of other clusters of the clusters in which the second spectral data is located.
In one possible implementation manner, the computing the component characteristics of each first cluster to obtain the component characteristics of different components in each first cluster includes: the calculation formula of the component characteristics p illuminance of different components is as follows:
wherein ,indicate->The>Wavelengths corresponding to the second spectral data, < >>Indicate->The amount of second spectral data in the cluster, < >>Indicate->Phenolic contrast in the clusters, +.>Indicate->Flavonoid pairings in individual clusters; />Indicate->A set of wavelengths corresponding to the second spectral data within the cluster of clusters,>represents the median of the second spectral data in the collection,/->Indicate->Other components in the clusters pair illumination.
In one possible implementation manner, calculating the absorption peak offset of each first cluster according to the information entropy of the attribution of all the second spectrum data centers in each first cluster and the corresponding component characteristics of different components in each first cluster, including: the calculation formula of the absorption peak offset of each first cluster is as follows:
wherein ,indicate->Absorption peak shift of individual clusters, +.>Indicate->Center attribution degree set of second spectrum data in each cluster, and +.>Indicate->Information entropy of center attribution degree set of second spectrum data in each cluster,/for each cluster>Indicate->Phenolic contrast in the clusters, +.>Indicate->Flavonoid pairings in individual clusters;indicate->Other components in the cluster pairs illuminance; />Representing the minimum value in the fetch data.
In one possible implementation manner, calculating the cluster center offset of the same first cluster center before and after the adjacent two iterative clusters to obtain the cluster center offset includes: the calculation formula of the cluster center offset is as follows:
wherein ,indicate->Cluster center offset of individual clusters, +.>Euclidean distance for representing clustering center data of the same cluster before and after two adjacent clusters,/->Indicate->Iterative->Cluster center data of individual clusters, +.>Indicate->Iterative->Cluster center data of individual clusters, < ->The iteration is->And performing the next iteration calculation after the iteration.
In one possible implementation manner, based on the absorption peak offset and the cluster center offset of each first cluster, obtaining cluster intra-cluster error bias after each iterative cluster; according to the clustering error bias, the ambiguity of the fuzzy C-means clustering algorithm in the next iteration is self-adaptively adjusted, and the method comprises the following steps: the calculation formula of the cluster error skewness is as follows:
wherein ,indicate->Absorption peak shift of individual clusters, +.>Indicate->Cluster center offset for individual clustersDegree (f)>Indicate->Cluster error bias of each cluster;
and mapping each clustering error bias into a [1,2.5] range by adopting a linear scaling algorithm, and taking an average value to obtain the ambiguity of the fuzzy C-means clustering algorithm in the next iteration.
In one possible implementation manner, calculating a quality reference index of the propolis solution to be detected according to the spectrogram of each second cluster includes: the calculation formula of the quality reference index of the propolis liquid to be detected is as follows:
wherein ,indicating the quality reference index of the propolis liquid to be treated, < + >>Indicate->Height difference of absorption peak contrast in each cluster spectrogram, +.>Is->Area difference of absorption peak contrast in each cluster spectrogram, +.>Representing the number of clusters.
In a second aspect, an embodiment of the present application provides a propolis quality detection data processing system, including a memory and a processor, where the memory stores executable codes, and the processor executes the executable codes to implement embodiments as possible in the first aspect.
In a third aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the embodiments as possible in the first aspect.
The application has the beneficial effects that: the method comprises the steps of carrying out clustering analysis on collected spectral data of propolis by adopting a fuzzy C-means clustering algorithm according to different characteristic of different components of the propolis in spectral data, calculating the central attribution and the absorption peak offset of each datum according to the distribution characteristic of the data in each iterative clustering cluster and the characteristic of the data of different components in the clustering process, constructing a clustering error offset, calculating the value of the ambiguity in each clustering cluster based on the clustering error offset until an objective function reaches an optimal solution or reaches the maximum iterative times, stopping iteration, completing the clustering analysis on the spectral data of the propolis, and the clustering processing process can better reflect the difference of the clustering effect of each iteration, adaptively obtain the value of the ambiguity in each clustering cluster, improve the clustering effect on the spectral data of the propolis, further improve the accuracy of analyzing the relative content of the propolis components and realize higher accuracy of quality detection on the propolis.
Drawings
Fig. 1 is a flow chart of steps of a method for processing propolis quality detection data according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a propolis quality detection data processing system according to an embodiment of the present application;
fig. 3 is a block diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present application can be understood in detail, a more particular description of the application, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings, and some, but not all of which are illustrated in the appended drawings. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the application, fall within the scope of protection of the application.
The terminology used in the description of the embodiments of the application herein is for the purpose of describing particular embodiments of the application only and is not intended to be limiting of the application.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those skilled in the art will appreciate that "one or more" is intended to be construed as "one or more" unless the context clearly indicates otherwise.
Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.
Referring to fig. 1, the embodiment of the application discloses a propolis liquid quality detection data processing method, which comprises the following steps:
step S11, obtaining first spectrum data of propolis liquid to be detected;
step S12, preprocessing the first spectrum data by adopting a baseline correction algorithm to obtain second spectrum data;
step S13, calculating the clustering error bias of the first clustering cluster obtained by each iteration in the clustering process of the second spectral data by adopting a fuzzy C-means clustering algorithm, and carrying out self-adaptive adjustment on the fuzzy degree of the fuzzy C-means clustering algorithm according to the clustering error bias in the next iteration until the clustering process of the second spectral data of the propolis liquid to be detected is completed, so as to obtain a second clustering cluster;
step S14, determining a spectrogram of each second cluster according to the second spectrum data in each second cluster;
step S15, calculating a quality reference index of the propolis liquid to be detected according to the spectrogram of each second cluster;
and S16, comparing the quality reference index with a preset threshold value, and judging the quality of the propolis liquid to be detected according to the comparison result.
The method comprises the steps of collecting spectral data of propolis liquid to be detected by an ultraviolet-visible spectrum instrument, specifically placing a propolis liquid sample to be detected into the ultraviolet-visible spectrum instrument for detection to obtain the spectral data of the propolis liquid to be detected, and selecting specific types of operators of the ultraviolet-visible spectrum instrument according to actual conditions. Meanwhile, in order to avoid the influence of impurities and background signals on collected spectrum data, the impurities and the background signals need to be removed from the collected spectrum data, a baseline correction algorithm is adopted in the embodiment to remove the impurities and the background signals from the collected spectrum data, the collected spectrum data is preprocessed, and the clustering error skewness of each iteration data is analyzed according to the processed data characteristics. The baseline correction algorithm may be a piecewise linear fitting method, a local extremum median method, a polynomial fitting method, or the like, which is not specifically limited herein.
It should be further noted that, the Fuzzy C-means algorism (FCM) is most widely and successfully applied in many Fuzzy clustering algorithms, and the steps of the FCM algorithm are as follows:
(1) Selecting the number of categories, setting the maximum iteration number, selecting proper fuzziness (also called a fuzzy factor, a fuzzy coefficient, a fuzzy weighting index and the like), and initializing a matrix determined by a membership function; (2) calculating a central value of the cluster; (3) calculating a new membership matrix; (4) Comparing membership matrixes before and after adjacent iterations, stopping the algorithm if the change of the membership matrixes is smaller than a certain threshold value or the maximum iteration number is reached, and turning to (2) otherwise; the fuzzy C-means clustering algorithm belongs to the conventional technology and is not particularly limited herein. The ambiguity m in the fuzzy C-means clustering algorithm is essentially a parameter for describing the degree of blurring, when m=1, fuzzy clustering is degraded into HCM, and generally, the optimal selection range of m is [1,2.5].
In the steps of the embodiment, the spectral data of the propolis liquid to be detected is obtained, a baseline correction algorithm is adopted for preprocessing the spectral data, then a fuzzy C-means clustering algorithm is adopted for carrying out clustering processing, the clustering error bias of a first clustering cluster obtained by each iteration is calculated, the fuzzy degree of the fuzzy C-means clustering algorithm is adaptively adjusted according to the clustering error bias in the next iteration until the clustering processing of the second spectral data of the propolis liquid to be detected is completed, until an objective function reaches an optimal solution or the iteration stop of the maximum preset iteration times, the clustering analysis of the spectral data of the propolis liquid is completed, a spectrogram of the clustering cluster is obtained according to the clustering analysis result, then the quality reference index of the propolis liquid to be detected is calculated, and the quality of the propolis liquid to be detected is judged according to the comparison result of the quality reference index and a preset threshold value. The clustering error bias is calculated according to the absorption intensity of different components under different wavelengths, so that the difference of each iteration clustering effect of the clustering can be better reflected, the value of the intra-cluster ambiguity after each iteration can be adaptively obtained, the clustering effect on the spectral data of the propolis can be improved, the accuracy of analyzing the relative content of the propolis components is further improved, and the accuracy of detecting the quality of the propolis is higher.
In an alternative embodiment of the present application, further comprising: the first spectrum data are the absorptivity and reflectivity of the propolis liquid to be detected under different wavelengths.
Specifically, in the embodiment of the application, the absorptivity and the reflectivity of the propolis liquid at different wavelengths are recorded according to the difference of the absorption characteristics of different components in the propolis liquid, namely the spectral data of the propolis liquid is acquired.
In an optional embodiment of the present application, in a clustering process of the second spectrum data using a fuzzy C-means clustering algorithm, calculating a cluster error bias of the first cluster obtained by each iteration, and in a next iteration, adaptively adjusting the ambiguity of the fuzzy C-means clustering algorithm according to the cluster error bias, including:
performing center attribution calculation on each second spectrum data in each first cluster obtained by each iteration in the clustering process to obtain the center attribution of each second spectrum data in each first cluster;
carrying out component characteristics and illuminance calculation on each first cluster to obtain component characteristics and illuminance of different components in each first cluster;
calculating the absorption peak offset of each first cluster according to the information entropy of the center attribution set of all the second spectrum data in each first cluster and the corresponding component characteristic illumination of different components in each first cluster;
calculating the cluster center offset of the same first cluster center before and after the adjacent two iterative clusters to obtain the cluster center offset;
obtaining the cluster error bias in each iterative cluster based on the absorption peak bias and the cluster center bias of each first cluster;
and adaptively adjusting the ambiguity of the fuzzy C-means clustering algorithm in the next iteration according to the cluster error bias.
The components affecting the quality of the propolis mainly comprise phenol components, flavonoid components, amino acid components and the like, the content of the components determines the quality and the value of the propolis, and the content of each component plays different roles in the efficacy of the propolis and directly affects the efficacy of the propolis. Therefore, the detection of the content of each component of the propolis can obtain the corresponding production quality of the propolis, and the quality of the propolis is detected.
Under the ultraviolet-visible spectrum, the phenolic component and the flavonoid component have obvious absorption peaks, wherein the maximum absorption peaks of different components are different in appearance positions, the phenolic component has a larger absorption peak near 280nm, and the flavonoid component has a larger absorption peak near 350 nm. The amino acid component has weak absorption peak in ultraviolet visible spectrum, mainly at 220There is a certain absorption intensity in the 280nm wavelength region. Therefore, the different components have different performance characteristics in the spectrum data, and the spectrum data of the propolis liquid can be clustered better according to the characteristics.
In the embodiment of the application, the spectral data of the propolis liquid is clustered by adopting a fuzzy C-means clustering algorithm, and the spectral data is input into a data set of spectral data of one sampleThe clustering number is->Iteration number->The threshold value of the change amount of the objective function is +.>. Clustering the data according to the input data and related parameters, and calculating the clustering error skewness of each iteration cluster in the clustering process according to different characteristics of the reaction of different components of the propolis in the spectral data to obtain a new ambiguity value in the cluster after each iteration, thereby completing the clustering of the propolis spectral data.
In an optional embodiment of the present application, performing a center attribute calculation on each second spectrum data in each first cluster obtained by each iterative cluster includes: the calculation formula of the center attribution degree is as follows:
in the aboveIndicate->Data to->The Euclidean distance of the cluster center of each cluster; />Indicate->Data to->Euclidean distance of cluster centers of individual clusters, wherein +.>The data belong to->Clustering, remove->The number of clusters in which data is located is +.>；/>Indicate->Within the cluster->The degree of central attribution of the individual data. Wherein:
in the aboveRepresenting the calculation of the euclidean distance between two data,/->Representing the>Data of->Indicate->Cluster center data of the individual clusters.
In the embodiment of the application, when the firstWithin the cluster->The closer the individual data is to the cluster center of the cluster to which it belongs, the +.>The smaller the value of (2); first->Within the cluster->The greater the distance of data from the cluster center of the other clusters, i.e.The greater the value of (2), the greater the ∈>The larger the value of (2), the calculated +.>The larger the value of (2) the less ambiguous the data is near the cluster center of the belonging cluster and the data is divided relative to the other clusters, i.e. the data belongs to +.>The greater the central degree of attribution of the individual clusters.
According to the embodiment of the application, the central attribution degree of the data in each cluster is calculated, and the attribution condition of each data in the cluster relative to the cluster center can be judged.
In an optional embodiment of the present application, component characteristic illuminance calculation is performed on each first cluster to obtain component characteristic illuminance of different components in each first cluster, including: the calculation formula of the component characteristics p illuminance of different components is as follows:
wherein ,indicate->The>Wavelengths corresponding to the second spectral data, < >>Indicate->The amount of second spectral data in the cluster, < >>Indicate->Phenolic contrast in the clusters, +.>Indicate->Flavonoid pairings in individual clusters; />Indicate->A set of wavelengths corresponding to the second spectral data within the cluster of clusters,>represents the median of the second spectral data in the collection,/->Indicate->Other components in the clusters pair illumination.
In an optional embodiment of the present application, calculating the absorption peak offset of each first cluster according to the information entropy of the attribution of all the second spectrum data centers in each first cluster and the corresponding component characteristic p illuminance of different components in each first cluster includes: the calculation formula of the absorption peak offset of each first cluster is as follows:
wherein ,indicate->Absorption peak shift of individual clusters, +.>Indicate->Center attribution degree set of second spectrum data in each cluster, and +.>Indicate->Information entropy of center attribution degree set of second spectrum data in each cluster,/for each cluster>Indicate->Phenolic contrast in the clusters, +.>Indicate->Flavonoid pairings in individual clusters;indicate->Other components in the cluster pairs illuminance; />Representing the minimum value in the fetch data.
It should be noted that, because the features of the data in the different components are different, the shift of the absorption peak of each cluster is calculated according to the features of the different components, and in the embodiment of the application, the shift of the absorption peak of the spectral data cluster can be calculated according to the entropy of the attribution of the data center in the cluster and the component feature pair illuminationWhen the clustering effect is more accurate, the information entropy of the center attribution degree in the cluster is smaller, namely +.>The smaller; and the better the clustering of different components, the smaller the contrast of the corresponding features, namelyThe smaller the value of (2), the absorption peak offset of the cluster is calculated>Smaller, therein->Indicate->Absorption peak shift of individual clusters. Due to the effect of propolis liquid mainly due to phenolsAnd the flavonoid component content, a control analysis was performed in consideration of the characteristics of the two components in calculating the clustering effect. The better the clustering effect on the two components in the clustering process, the more accurate the judgment on the quality of the propolis liquid.
It should be further noted that, the information entropy may be used to describe uncertainty of information, in the information theory, the information entropy is generally used to measure the degree of uncertainty in a group of data, and the more uncertain data sets have larger information entropy, and the specific calculation formula belongs to the prior art, which is not limited in detail herein.
And the judgment of the clustering effect can further consider the change of the clustering centers before and after iteration. If the cluster center changes little or no in the cluster before and after the iteration in the process of clustering iteration, the clustering operation may already achieve a better effect, and the numerical value change and the distance change can be considered for the cluster center before and after the iteration.
Therefore, in an optional embodiment of the present application, calculating the cluster center offset of the same first cluster center before and after two adjacent iterative clusters to obtain the cluster center offset includes: the calculation formula of the cluster center offset is as follows:
wherein ,indicate->Cluster center offset of individual clusters, +.>Euclidean distance for representing clustering center data of the same cluster before and after two adjacent clusters,/->Indicate->Iterative->Cluster center data of individual clusters, +.>Indicate->Iterative->Cluster center data of individual clusters, < ->The iteration is->And performing the next iteration calculation after the iteration.
Further, based on the absorption peak offset and the cluster center offset of each first cluster, obtaining cluster aggregation error offset after each iterative clustering; according to the clustering error bias, the ambiguity of the fuzzy C-means clustering algorithm in the next iteration is self-adaptively adjusted, and the method comprises the following steps: the calculation formula of the cluster error skewness is as follows:
wherein ,indicate->Absorption peak shift of individual clusters, +.>Indicate->Cluster center offset of individual clusters, +.>Indicate->Cluster error bias of each cluster;
and mapping each clustering error bias into a [1,2.5] range by adopting a linear scaling algorithm, and taking an average value to obtain the ambiguity of the fuzzy C-means clustering algorithm in the next iteration.
It should be noted that, when the clustering effect is good, the probability that the data in each cluster belongs to the same component is high, that is, the numerical value of the data is about the numerical value of the strongest absorption peak,the smaller the value of (2); and the smaller the change of the cluster center before and after iteration, i.e. +.>The smaller the value of (2), the calculated +.>The smaller the value of (c) is, the better the clustering effect after this iteration is. And according to the calculated cluster error bias, calculating the value of the intra-cluster ambiguity after each iteration in the FCM algorithm. The calculated cluster error skewness is calculated by adopting a linear proportional scaling algorithm>The value of (2) maps to [1,2.5]]And in the range, calculating the average value of the values after the linear mapping of all the cluster error skewness, and self-adaptively adjusting the ambiguity m according to the average value of the values after the linear mapping of all the cluster error skewness in all the cluster clusters after each iteration.
In the embodiment of the application, the ambiguity in the cluster can be adaptively adjusted according to the characteristics of the cluster after each iteration through the cluster analysisAccording to the specific calculation process of the FCM algorithm, outputting a clustering result of the propolis spectrum data.
In an optional embodiment of the present application, calculating a quality reference index of the propolis solution to be detected according to the spectrogram of each second cluster includes: the calculation formula of the quality reference index of the propolis liquid to be detected is as follows:
wherein ,indicating the quality reference index of the propolis liquid to be treated, < + >>Indicate->Height difference of absorption peak contrast in each cluster spectrogram, +.>Is->Area difference of absorption peak contrast in each cluster spectrogram, +.>Representing the number of clusters, +.>The normalization process is represented, where a maximum minimum normalization method is employed.
The spectral data of the propolis liquid can be subjected to clustering analysis according to the clustering result. According to the obtained data in the clusters, a spectrogram of each cluster can be obtained, the heights and the areas of the absorption peak of the propolis liquid with standard concentration under the same wavelength and the absorption peak in the spectrogram of the cluster of the propolis liquid to be detected are respectively compared, and the propolis liquid is calculatedWhether the content of the components reaches the standard. In the calculation formula of the quality reference index, when the content of the active ingredients in the cluster is lower, calculating to obtain and />The value of (2) is larger, and the obtained propolis liquid to be detected is +.>The larger value of (2) indicates that the quality of the propolis liquid to be detected is poorer. The threshold value is set to +.>If the calculated quality reference index exceeds the threshold value, the content of the components in the propolis liquid does not reach the standard, and the quality of the propolis liquid is poor.
Referring to fig. 2, an embodiment of the present application discloses a propolis quality inspection data processing system 20, which includes a processor 21 and a memory 22; wherein the memory 22 is used for storing a computer program; the processor 21 is configured to implement the propolis liquid quality detection data processing method provided in the foregoing method embodiment by executing a computer program.
The specific process of the above-mentioned propolis quality detection data processing method may refer to the corresponding content disclosed in the foregoing embodiment, and will not be described herein again.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the storage may be a temporary storage or a permanent storage.
In addition, the propolis quality detection data processing system 20 further comprises a power supply 23, a communication interface 24, an input/output interface 25 and a communication bus 26; wherein, the power supply 23 is used for providing working voltage for each hardware device on the propolis quality detection data processing system 20; the communication interface 24 can create a data transmission channel between the propolis quality detection data processing system 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
Further, the embodiment of the application also discloses a computer readable storage medium, as shown in fig. 3, for storing a computer program 31, wherein the computer program, when executed by a processor, implements the propolis quality detection data processing method provided in the foregoing method embodiment.
The specific process of the above-mentioned propolis quality detection data processing method may refer to the corresponding content disclosed in the foregoing embodiment, and will not be described herein again.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above describes in detail a method and a system for processing propolis quality detection data provided by the present application, and specific examples are applied to illustrate the principle and implementation of the present application, and the above description of the examples is only used to help understand the method and core idea of the present application; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the idea of the present application, the present disclosure should not be construed as limiting the present application in summary.
Claims (7)
1. A propolis liquid quality detection data processing method is characterized by comprising the following steps:
acquiring first spectrum data of propolis liquid to be detected;
preprocessing the first spectrum data by adopting a baseline correction algorithm to obtain second spectrum data;
calculating the clustering error bias of the first clustering cluster obtained by each iteration in the clustering process of the second spectral data by adopting a fuzzy C-means clustering algorithm, and carrying out self-adaptive adjustment on the fuzzy degree of the fuzzy C-means clustering algorithm according to the clustering error bias in the next iteration until the clustering process of the second spectral data of the propolis liquid to be detected is completed, so as to obtain a second clustering cluster;
determining a spectrogram of each second cluster according to the second spectrum data in each second cluster;
calculating a quality reference index of the propolis liquid to be detected according to the spectrogram of each second cluster;
comparing the quality reference index with a preset threshold value, and judging the quality of the propolis liquid to be detected according to a comparison result;
calculating the clustering error bias of the first clustering cluster obtained by each iteration in the clustering process of the second spectrum data by adopting a fuzzy C-means clustering algorithm, and carrying out self-adaptive adjustment on the fuzzy degree of the fuzzy C-means clustering algorithm according to the clustering error bias in the next iteration, wherein the method comprises the following steps:
performing center attribution calculation on each second spectrum data in each first cluster obtained by each iteration in the clustering process to obtain center attribution of each second spectrum data in each first cluster;
performing component characteristics and illuminance calculation on each first cluster to obtain component characteristics and illuminance of different components in each first cluster;
calculating the absorption peak offset of each first cluster according to the information entropy of the center attribution degree set of all the second spectrum data in each first cluster and the corresponding component characteristic illumination of different components in each first cluster;
calculating the cluster center offset of the same first cluster center before and after the two adjacent iterative clusters to obtain the cluster center offset;
obtaining the cluster error bias in the cluster after each iterative clustering based on the absorption peak bias and the cluster center bias of each first cluster;
adaptively adjusting the ambiguity of the fuzzy C-means clustering algorithm in the next iteration according to the cluster error skewness;
obtaining cluster aggregation error bias after each iterative clustering based on the absorption peak bias of each first cluster and the cluster center bias; according to the clustering error bias, the ambiguity of the fuzzy C-means clustering algorithm in the next iteration is self-adaptively adjusted, and the method comprises the following steps: the calculation formula of the cluster error skewness is as follows:
wherein ,indicate->Absorption peak shift of individual clusters, +.>Indicate->The degree of cluster center offset of the individual clusters,indicate->Cluster error bias of each cluster;
mapping each clustering error skewness into a range of [1,2.5] by adopting a linear scaling algorithm, and taking an average value to obtain the ambiguity of the fuzzy C-means clustering algorithm in the next iteration;
according to the spectrogram of each second cluster, calculating the quality reference index of the propolis liquid to be detected, including: the calculation formula of the quality reference index of the propolis liquid to be detected is as follows:
wherein ,indicating the quality reference index of the propolis liquid to be treated, < + >>Indicate->Height difference of absorption peak contrast in each cluster spectrogram, +.>Is->Area difference of absorption peak contrast in each cluster spectrogram, +.>Representing the number of clusters.
2. The method for processing propolis quality inspection data according to claim 1, comprising: the first spectrum data are the absorptivity and the reflectivity of the propolis liquid to be detected under different wavelengths.
3. The method for processing propolis liquid quality inspection data according to claim 1, wherein performing center ascription calculation on each second spectrum data in each first cluster obtained by iterative clustering comprises: the calculation formula of the center attribution degree is as follows:
wherein ,indicate->Within the cluster->Center degree of ownership of the second spectral data, < >>Indicate->Second spectral data to +.>Euclidean distance of second spectrum data of cluster centers of the cluster clusters; />Indicate->Second spectral data to +.>Euclidean distance of second spectral data of cluster center of each cluster, < ->Indicating removal of->The number of other clusters of the clusters in which the second spectral data is located.
4. The method for processing propolis quality detection data according to claim 1, wherein performing component characteristic illuminance calculation on each of the first cluster clusters to obtain component characteristic illuminance of different components in each of the first cluster clusters, includes: the calculation formula of the component characteristics of the different components is as follows:
wherein ,indicate->The>Wavelengths corresponding to the second spectral data, < >>Indicate->The amount of second spectral data in the cluster, < >>Indicate->Phenolic contrast in the clusters, +.>Indicate->Flavonoid pairings in individual clusters; />Indicate->A set of wavelengths corresponding to the second spectral data within the cluster of clusters,>represents the median of the second spectral data in the collection,/->Indicate->Other components in the clusters pair illumination.
5. The method according to claim 1, wherein calculating the peak offset of each first cluster according to the information entropy of the attribution degree of all second spectrum data centers in each first cluster and the illuminance of the component characteristics of different components in each corresponding first cluster comprises: the calculation formula of the absorption peak offset of each first cluster is as follows:
wherein ,indicate->Absorption peak shift of individual clusters, +.>Indicate->Center attribution degree set of second spectrum data in each cluster, and +.>Indicate->Information entropy of the center attribution degree set of the second spectrum data in the cluster,indicate->Phenolic contrast in the clusters, +.>Indicate->Flavonoid pairings in individual clusters; />Indicate->Other components in the cluster pairs illuminance; />Representing the minimum value in the fetch data.
6. The method for processing propolis liquid quality inspection data according to claim 1, wherein calculating the cluster center offset of the same first cluster center before and after two adjacent iterative clusters to obtain the cluster center offset comprises: the calculation formula of the cluster center offset is as follows:
wherein ,indicate->Cluster center offset of individual clusters, +.>Euclidean distance for representing clustering center data of the same cluster before and after two adjacent clusters,/->Indicate->Iterative->Cluster center data of individual clusters, +.>Indicate->Iterative->Cluster center data of individual clusters, < ->The iteration is->And performing the next iteration calculation after the iteration.
7. A propolis quality inspection data processing system, comprising:
a processor;
a memory for storing a computer program for execution by the processor;
wherein the processor, when executing the computer program, implements the propolis quality detection data processing method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310920001.7A CN116646019B (en) | 2023-07-26 | 2023-07-26 | Propolis liquid quality detection data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310920001.7A CN116646019B (en) | 2023-07-26 | 2023-07-26 | Propolis liquid quality detection data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116646019A CN116646019A (en) | 2023-08-25 |
| CN116646019B true CN116646019B (en) | 2023-09-29 |
Family
ID=87625081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310920001.7A Active CN116646019B (en) | 2023-07-26 | 2023-07-26 | Propolis liquid quality detection data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116646019B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504245A (en) * | 2016-10-28 | 2017-03-15 | 东北大学 | A kind of damaging pathological tissues image partition method of multi-modal brain image |
| CN109030407A (en) * | 2018-04-16 | 2018-12-18 | 江苏大学 | A kind of apple variety classification method of mixed fuzzy C mean cluster |
| CN114492935A (en) * | 2021-12-27 | 2022-05-13 | 山东浪潮工业互联网产业股份有限公司 | Pollution discharge data prediction method, device, equipment and medium |
| CN115454779A (en) * | 2022-09-28 | 2022-12-09 | 建信金融科技有限责任公司 | Cloud monitoring stream data detection method and device based on cluster analysis and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8422826B2 (en) * | 2009-06-05 | 2013-04-16 | Varian Medical Systems, Inc. | Method and apparatus to facilitate using fused images to identify materials |
-
2023
- 2023-07-26 CN CN202310920001.7A patent/CN116646019B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504245A (en) * | 2016-10-28 | 2017-03-15 | 东北大学 | A kind of damaging pathological tissues image partition method of multi-modal brain image |
| CN109030407A (en) * | 2018-04-16 | 2018-12-18 | 江苏大学 | A kind of apple variety classification method of mixed fuzzy C mean cluster |
| CN114492935A (en) * | 2021-12-27 | 2022-05-13 | 山东浪潮工业互联网产业股份有限公司 | Pollution discharge data prediction method, device, equipment and medium |
| CN115454779A (en) * | 2022-09-28 | 2022-12-09 | 建信金融科技有限责任公司 | Cloud monitoring stream data detection method and device based on cluster analysis and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 一种隶属关系不确定的可能性模糊聚类方法;陈健美;陆虎;宋余庆;宋顺林;徐景;谢从华;倪巍伟;;计算机研究与发展(09);全文 * |
| 基于中点密度函数的模糊聚类算法;周跃跃;胡婕;苏涛;;计算机应用(01);全文 * |
| 模糊Ｋ-Ｈaｒｍｏｎiｃ－Ｋｏｈｏｎｅｎ网络的ＦＴＩＲ光谱数据聚类分析;陈勇;《光谱学与光谱分析》;第第43卷卷(第第1期期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116646019A (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qiongyan et al. | Detecting spikes of wheat plants using neural networks with Laws texture energy | |
| EP3904859B1 (en) | System and method for determining a platelet volume for a blood sample, computer program and computer readable medium | |
| CN117132778B (en) | Spectrum measurement correction calculation method and system | |
| CN108830249B (en) | Winter wheat powdery mildew remote sensing monitoring method based on ASD hyperspectral data | |
| CN110363125A (en) | Using the method for Model Transfer identification different cultivars Citrus Huanglongbing pathogen | |
| CN110751172A (en) | Weakly supervised learning pathology full-image category inference method and system | |
| CN116646019B (en) | Propolis liquid quality detection data processing method and system | |
| CN116309599A (en) | Water quality visual monitoring method based on sewage pretreatment | |
| CN116404186A (en) | Power lithium-manganese battery production system | |
| CN115952067A (en) | Database operation abnormal behavior detection method and readable storage medium | |
| CN110517226B (en) | Tobacco stem region extraction method based on bilateral filtering and multi-feature texture image fusion | |
| CN115034693B (en) | Biological information data security management method, system and storage medium based on Internet of things | |
| CN110335249A (en) | Citrus Huanglongbing pathogen detection method based on high light spectrum image-forming technology | |
| CN115392311A (en) | Efficient sugarcane stalk node identification method based on variational modal decomposition | |
| CN112634226B (en) | Head CT image detection device, method, electronic device and storage medium | |
| CN111929656B (en) | Entropy value statistics-based noise estimation method for vehicle-mounted millimeter wave radar system | |
| Di et al. | The research on the feature extraction of sunflower leaf rust characteristics based on color and texture feature | |
| CN117290559B (en) | Water treatment agent content monitoring method and system | |
| CN117953491B (en) | Leaf vegetable disease diagnosis method and system | |
| CN116504314B (en) | Gene regulation network construction method based on cell dynamic differentiation | |
| CN113792748B (en) | Method and device for creating diabetic retinopathy classifier based on feature extraction and double support vector machines | |
| CN117953491A (en) | Leaf vegetable disease diagnosis method and system | |
| CN117520997B (en) | Data processing method and system for beauty robot | |
| CN117893537B (en) | Decoloring detection method and system for tray surface material | |
| CN115147837B (en) | Athetis lepigone feeding method and system based on optical image recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |