CN111929285A - Spectral identification method for alcohol doped in laser-induced fluorescent red wine - Google Patents

Spectral identification method for alcohol doped in laser-induced fluorescent red wine Download PDF

Info

Publication number
CN111929285A
CN111929285A CN202010804651.1A CN202010804651A CN111929285A CN 111929285 A CN111929285 A CN 111929285A CN 202010804651 A CN202010804651 A CN 202010804651A CN 111929285 A CN111929285 A CN 111929285A
Authority
CN
China
Prior art keywords
red wine
laser
particle
pso
induced
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.)
Withdrawn
Application number
CN202010804651.1A
Other languages
Chinese (zh)
Inventor
汤超
卞凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui University of Science and Technology
Original Assignee
Anhui University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui University of Science and Technology filed Critical Anhui University of Science and Technology
Priority to CN202010804651.1A priority Critical patent/CN111929285A/en
Publication of CN111929285A publication Critical patent/CN111929285A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/6402—Atomic fluorescence; Laser induced fluorescence
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N2021/6417—Spectrofluorimetric devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Molecular Biology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Mathematics (AREA)
  • Pathology (AREA)
  • Evolutionary Computation (AREA)
  • Immunology (AREA)
  • Computing Systems (AREA)
  • Mathematical Analysis (AREA)
  • Biochemistry (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Databases & Information Systems (AREA)
  • Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
  • Algebra (AREA)
  • Optics & Photonics (AREA)
  • Operations Research (AREA)

Abstract

The invention relates to a spectrum identification method for alcohol-doped laser-induced fluorescent red wine, which comprises the following steps: (1) obtaining an original fluorescence spectrogram of a red wine sample by using a laser-induced fluorescence spectrometer; (2) carrying out attribute reduction on original fluorescence spectrum data of the red wine sample by using a BP-REF algorithm; (3) dividing the spectrum data of the red wine sample into a training set and a testing set by adopting a bootstrap method (bootstrapping); (4) optimizing an initial weight W of a learning vector quantization neural network (LVQ) model by utilizing a Particle Swarm Optimization (PSO); (5) and (4) taking red wine spectrum data on the test set as the input of the model, thereby carrying out detection and identification on different types of red wines. The method adopts the PSO and the LVQ to be combined for the classification and identification of the laser-induced fluorescence red wine doped alcohol, has the characteristics of strong generalization capability, high classification accuracy and high practical application value, and has great significance for the real-time accurate detection of the red wine adulteration.

Description

Spectral identification method for alcohol doped in laser-induced fluorescent red wine
Technical Field
The invention relates to the field of food safety detection, in particular to a spectrum identification method for alcohol doped laser-induced fluorescence red wine
Background
The red wine is fruit wine brewed by natural fermentation of grapes, and the main components of the red wine are grape juice and alcohol converted by sugar fermentation. Wherein the grape juice accounts for more than 80%. Besides grape juice and alcohol, red wine also contains tartaric acid, pectin, minerals, tannic acid and other substances, and the variety of the substances exceeds 1000, and the variety of the substances beneficial to human body exceeds 300. The red wine has great effect on the health of human body, can increase appetite, has nourishing effect on human body, can also maintain beauty, resist aging and help digestion, has the functions of losing weight, promoting urination and sterilizing, and can reduce the risk of cancer when people drink the red wine for a long time in a proper amount. However, some illegal vendors adulterate red wine for high profit, which not only harms the health of people, but also greatly harms the development of the regular red wine industry and destroys the market order.
At present, methods for detecting whether red wine is adulterated are commonly used, mainly including nuclear magnetic resonance spectroscopy, ion chromatography, high performance liquid chromatography and the like, but experimental instruments used in the detection methods are complex to operate, strict in experimental environment requirements and long in experimental time, and the red wine cannot be detected quickly and conveniently.
The Laser Induced Fluorescence (LIF) technology has the characteristics of high rapidity, high sensitivity and the like. When laser irradiates on red wine, the red wine can emit a specific fluorescence, and the related information of a red wine sample to be detected can be known through a collected fluorescence data spectrogram. The LIF technology is combined with a Particle Swarm Optimization (PSO) and a learning vector quantization neural network (LVQ) to be used for detecting the red wine adulteration, and the method has great significance for accurately identifying the red wine adulteration.
Disclosure of Invention
The invention aims to provide a spectrum identification method for alcohol doped red wine through laser induction fluorescence, which can overcome the defects of red wine identification and can realize quick and previous identification of red wine adulteration.
The invention adopts the following technical scheme for realizing the purpose:
a spectrum identification method for alcohol doped with laser-induced fluorescent red wine comprises the following steps:
(1) extracting an original fluorescence spectrogram of a red wine sample: measuring the spectrum data of the red wine sample doped with alcohol in different proportions by using a laser-induced fluorescence spectrometer, and acquiring the original fluorescence spectrum data of the red wine sample;
(2) preprocessing an original fluorescence spectrum of a red wine sample: reducing the attribute of original fluorescence spectrum data by using BP-REF, removing the characteristic with low importance degree, and keeping the characteristic with high importance degree;
(3) dividing red wine data samples: dividing red wine fluorescence spectrum data into a training set and a testing set by using a bootstrapping dividing method;
(4) PSO optimizes the initial weight: establishing an LVQ model, and optimizing the initial weight W of the model by using a PSO algorithm in the training process so as to achieve the best result;
(5) and (3) testing a model result: the red wine spectral data on the test set are input from the input end of the PSO-LVQ model, and the identification of different types of red wine can be carried out.
In the step (1), a USB2000+ type laser-induced fluorescence spectrometer (Ocean optics, USA) is selected in the experiment, a laser source is a 405nm blue-violet semiconductor laser, the power of incident laser is 120mW, the range of a detected fluorescence spectrum is 340-1021 nm, and the resolution is set to be 0.5 nm.
In the step (2), the number of hidden layers of the BP is selected to be 5.
In the step (3), the ratio of the number of samples in the training set to the number of samples in the test set is 2: 1.
In the step (4), the model initial weight W is optimized by using a PSO algorithm in the training process, and the specific steps are as follows:
(41) carrying out normalization processing on the fluorescence data processed by BP-REF;
(42) defining the change rate of the average aggregation distance and the maximum distance between the particle swarm random individuals and the input samples as a fitness function of a PSO-LVQ algorithm; the fitness function of the PSO-LVQ algorithm is formulated as follows:
Figure BDA0002627931470000021
in the formula DmmaxIs the maximum aggregate distance, D, of the input sample and the random individualmmeanIs the average aggregate distance;
(43) the position and velocity of the particles in the particle group, the position of the particles being represented by vector X, the velocity of the particles being represented by vector V, the optimum position for the passage of the particles being represented by vector pbest, and the optimum position for the passage of the entire particles being represented by vector gbest;
(44) initializing a particle swarm, continuously updating the position and the speed of each particle through iteration, evaluating the performance of each particle through a fitness function after each iteration of each particle, and acquiring an individual extreme value (pbest) of each particle and a global extreme value (gbest) of each particle;
(45) initializing the position X and the speed V of the particles, and assuming that the number of the particles in the D-dimensional space is N, namely the position interval of each dimension is [ X ]min，d,Xmax，d]Each dimension of the velocity interval is [ -v [ ]max，d,vmax，d]；
(46) In the iterative process, the position X and the velocity V of the particle are continuously updated, and the updated formula is as follows:
d-dimension velocity update formula of particle i:
Figure BDA0002627931470000022
Figure BDA0002627931470000023
d-dimension position update formula of particle i:
Figure BDA0002627931470000024
in the formula
Figure BDA0002627931470000025
Represents the d-dimensional component of the velocity vector of the particle i at the k-th iteration,
Figure BDA0002627931470000026
d-dimensional component, c, representing the i-position vector of the k-th iteration particle1，c2Is an acceleration constant, r1，r2Is a random parameter, and the value interval is [0, 1]]W is the inertia weight;
(47) the inertia weight w affects the particle velocity and the search precision, and for achieving balance between the two, a dynamic inertia weight w formula is defined as follows:
Figure BDA0002627931470000027
in the formula, wmaxIs the maximum inertia weight, wminIs the minimum inertial weight, run is the current iteration number, runmaxIs the maximum total number of iterations;
(48) if the set maximum iteration number is reached or the requirement is met, the PSO finishes the optimization process, and the obtained optimal initial weight W is given to the LVQ algorithm, otherwise, the step (46) is continued.
In the step (5), the identification performance and generalization capability of the established model are analyzed according to the classification chart and classification accuracy of the laser-induced fluorescence spectrum data of the red wine.
Has the advantages that:
compared with the prior art, the method has the advantages that the method utilizes the characteristics of the laser-induced fluorescence technology and has the characteristics of high detection speed, simple operation and the like on the detection of the adulteration of the red wine by utilizing the characteristics of the laser-induced fluorescence technology compared with the red wine detection methods on the market, such as nuclear magnetic resonance spectroscopy technology, ion chromatography and high performance liquid chromatography. Although the unoptimized Ant Colony Optimization (ACO) has good robustness, the ACO has low convergence rate and is easy to fall into local optimization; the efficiency of a Genetic Algorithm (GA) is lower than that of other optimization algorithms, premature convergence is easy to occur, and no effective quantitative analysis method exists in the aspects of accuracy, feasibility and the like of the algorithm; the PSO algorithm can effectively improve the optimizing precision, has good convergence speed, is combined with the LVQ algorithm to detect the adulteration of the laser-induced fluorescent red wine, has the characteristics of high precision, high speed and the like, and has important significance for detecting the adulteration of the red wine.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of the algorithm for optimizing LVQ initial weights by the PSO algorithm of the present invention.
Detailed Description
The invention is further illustrated by the following specific examples.
The invention has developed a laser-induced fluorescence red wine and mixed the spectrum recognition method of the alcohol, combine PSO-LVQ and laser-induced fluorescence technology organically, utilize the portable fluorescence spectrometer apparatus to gather the fluorescence spectrum data of the red wine, can obtain the fluorescence spectrogram of different kinds of red wine samples; firstly, reducing the attribute of original fluorescence spectrum data by using BP-REF, removing the characteristic with low importance degree, and keeping the characteristic with high importance degree; then, dividing the red wine fluorescence spectrum data into a training set and a testing set by using a bootstrapping dividing method; optimizing the test weight of the LVQ model by using BP-REF and carrying out model training on a training set; and finally, using the test set for model classification result testing and performance verification.
The invention discloses a spectrum identification method for alcohol doped with laser-induced fluorescence red wine under the condition of combining PSO-LVQ and laser-induced fluorescence technology, which comprises the following specific steps:
(1) extracting an original fluorescence spectrogram of a red wine sample: the method is characterized in that a USB2000 < + > type laser induced fluorescence spectrometer (Ocean optics company, USA) is selected in the experiment, a laser source is a 405nm blue-violet light semiconductor laser, the set value of the laser incidence wavelength is 405nm, the power of the incident laser is 120mW, the range of a detected fluorescence spectrum is 340-1021 nm, and the resolution is set to be 0.5 nm; spectra suite is used as acquisition and recording software of spectral data, five samples of great wall red wine, Zhang Yu red wine, yellow tail kangaroo red wine, Benfu red wine and alcohol (mixed according to a ratio of 1: 1) are acquired, and original fluorescence spectral data of the red wine sample are acquired.
(2) Pretreatment of original fluorescence spectrum of a honey sample: the obtained red wine original fluorescence spectrum data has a large number of features, wherein the features comprise features with low importance, the features can influence the accuracy of experimental classification and have great influence on experimental errors, so that the BP-REF algorithm is used for carrying out feature reduction on the red wine original spectrum data, unimportant features are removed, the redundancy of the data is reduced, and the noise interference resistance of the red wine is increased.
(3) Dividing a honey sample data sample set: dividing the spectrum data of the red wine into a training set and a testing set according to a ratio of 2:1 by using a bootstrapping dividing method;
(4) PSO optimizes the initial weight: establishing an LVQ model, and optimizing the initial weight W of the model by using a PSO algorithm in the training process, wherein the method comprises the following specific steps:
(41) carrying out normalization processing on the fluorescence data processed by BP-REF, wherein the interval is (0, 1);
(42) defining the change rate of the average aggregation distance and the maximum distance between the particle swarm random individuals and the input samples as a fitness function of a PSO-LVQ algorithm; the fitness function of the PSO-LVQ algorithm is formulated as follows:
Figure BDA0002627931470000031
in the formula DmmaxIs the maximum aggregate distance, D, of the input sample and the random individualmmeanIs the average aggregate distance;
(43) the position and velocity of the particles in the particle group, the position of the particles being represented by vector X, the velocity of the particles being represented by vector V, the optimum position for the passage of the particles being represented by vector pbest, and the optimum position for the passage of the entire particles being represented by vector gbest;
(44) initializing a particle swarm, continuously updating the position and the speed of each particle through iteration, evaluating the performance of each particle through a fitness function after each iteration of each particle, and acquiring an individual extreme value (pbest) of each particle and a global extreme value (gbest) of each particle;
(45) initializing the position X and the speed V of the particles, and assuming that in a D-dimensional space, the number of the particles is N, the position interval of each dimension is [10,1000], and the speed interval of each dimension is [ -1,1 ];
(46) in the iterative process, the position X and the velocity V of the particle are continuously updated, and the updated formula is as follows:
d-dimension velocity update formula of particle i:
Figure BDA0002627931470000032
d-dimension position update formula of particle i:
Figure BDA0002627931470000033
in the formula
Figure BDA0002627931470000034
Represents the d-dimensional component of the velocity vector of the particle i at the k-th iteration,
Figure BDA0002627931470000035
d-dimensional component, c, representing the i-position vector of the k-th iteration particle1＝c2＝0.8，r1，r2Is a random parameter, and the value interval is [0, 1]]W is the inertia weight;
(47) the inertia weight w affects the particle velocity and the search precision, and for achieving balance between the two, a dynamic inertia weight w formula is defined as follows:
Figure BDA0002627931470000036
in the formula, wmaxIs the maximum inertia weight, wmax＝0,9；wminIs the minimum inertia weight, wmin0.4; run is the current iteration number, runmaxIs the maximum total number of iterations, runmax＝1000；
(48) If the set maximum iteration number is 1000 or the requirement is met, the PSO finishes the optimization process, and gives the obtained optimal initial weight W to the LVQ algorithm, otherwise, the step (46) is continued.
(5) And (3) testing a model result: and analyzing the identification performance and generalization capability of the established model according to the classification chart and classification accuracy of the laser-induced fluorescence spectrum data of the predicted red wine.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.

Claims (5)

1. A laser-induced fluorescence red wine-doped alcohol spectrum identification method is characterized by comprising the following steps: the method comprises the following steps:
(1) extracting an original fluorescence spectrogram of a red wine sample: measuring the spectrum data of the red wine sample doped with alcohol in different proportions by using a laser-induced fluorescence spectrometer, and acquiring the original fluorescence spectrum data of the red wine sample;
(2) preprocessing an original fluorescence spectrum of a red wine sample: reducing the attribute of original fluorescence spectrum data by using BP-REF, removing the characteristic with low importance degree, and keeping the characteristic with high importance degree;
(3) dividing red wine data samples: dividing red wine fluorescence spectrum data into a training set and a testing set by using a bootstrapping dividing method;
(4) PSO optimizes the initial weight: establishing an LVQ model, and optimizing the initial weight of the model by using a BP-REF algorithm in the training process;
(5) and (3) testing a model result: the red wine spectral data on the test set are input from the input end of the PSO-LVQ model, and the identification of different types of red wine can be carried out.
2. The method for spectral recognition of alcohol doped with laser-induced fluorescent red wine according to claim 1, wherein the method comprises the following steps: in the step (1), a USB2000+ type laser-induced fluorescence spectrometer (Ocean optics, USA) is selected in the experiment, a laser source is a 405nm blue-violet semiconductor laser, the power of incident laser is 120mW, the range of a detected fluorescence spectrum is 340-1021 nm, and the resolution is set to be 0.5 nm.
3. The method for spectral recognition of alcohol doped with laser-induced fluorescent red wine according to claim 1, wherein the method comprises the following steps: in the step (2), the number of hidden layers of the BP is selected to be 5.
4. The method for spectral recognition of alcohol doped with laser-induced fluorescent red wine according to claim 1, wherein the method comprises the following steps: in the step (4), the model initial weight W is optimized by using a PSO algorithm in the training process, and the specific steps are as follows:
(41) carrying out normalization processing on the fluorescence data after BP-REF processing;
(42) defining the change rate of the average aggregation distance and the maximum distance between the particle swarm random individuals and the input samples as a fitness function of a PSO-LVQ algorithm; the fitness function of the PSO-LVQ algorithm is formulated as follows:
Figure FDA0002627931460000011
in the formula DmmaxIs the maximum aggregate distance, D, of the input sample and the random individualmmeanIs the average aggregate distance;
(43) the position and velocity of the particles in the particle group, the position of the particles being represented by vector X, the velocity of the particles being represented by vector V, the optimum position for the passage of the particles being represented by vector pbest, and the optimum position for the passage of the entire particles being represented by vector gbest;
(44) initializing a particle swarm, continuously updating the position and the speed of each particle through iteration, evaluating the performance of each particle through a fitness function after each iteration of each particle, and acquiring an individual extreme value (pbest) of each particle and a global extreme value (gbest) of each particle;
(45) initializing the position X and the speed V of the particles, and assuming that the number of the particles in the D-dimensional space is N, namely the position interval of each dimension is [ X ]min，d，Xmax，d]Each dimension of the velocity interval is [ -v [ ]max，d，vmax，d]；
(46) In the iterative process, the position X and the velocity V of the particle are continuously updated, and the updated formula is as follows:
d-dimension velocity update formula of particle i:
Figure FDA0002627931460000012
d-dimension position update formula of particle i:
Figure FDA0002627931460000013
in the formula
Figure FDA0002627931460000014
Represents the d-dimensional component of the velocity vector of the particle i at the k-th iteration,
Figure FDA0002627931460000015
d-dimension components representing the position vector of the particle i of the k iteration, wherein c1 and c2 are acceleration constants, r1 and r2 are random parameters, and the value interval of the random parameters is [0, 1]]W is the inertia weight;
(47) the inertia weight w affects the particle velocity and the search precision, and for achieving balance between the two, a dynamic inertia weight w formula is defined as follows:
Figure FDA0002627931460000016
in the formula, wmaxIs the maximum inertia weight, wminIs the minimum inertial weight, run is the current iteration number, runmaxIs the maximum total number of iterations;
(48) if the set maximum iteration number is reached or the requirement is met, the PSO finishes the optimization process, and the obtained optimal initial weight W is given to the LVQ algorithm, otherwise, the step (46) is continued.
5. The method for spectral recognition of alcohol doped with laser-induced fluorescent red wine according to claim 1, wherein the method comprises the following steps: and (5) analyzing the identification performance and generalization capability of the established model according to the classification chart and classification accuracy of the laser-induced fluorescence spectrum data of the predicted red wine.
CN202010804651.1A 2020-08-11 2020-08-11 Spectral identification method for alcohol doped in laser-induced fluorescent red wine Withdrawn CN111929285A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010804651.1A CN111929285A (en) 2020-08-11 2020-08-11 Spectral identification method for alcohol doped in laser-induced fluorescent red wine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010804651.1A CN111929285A (en) 2020-08-11 2020-08-11 Spectral identification method for alcohol doped in laser-induced fluorescent red wine

Publications (1)

Publication Number Publication Date
CN111929285A true CN111929285A (en) 2020-11-13

Family

ID=73311190

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010804651.1A Withdrawn CN111929285A (en) 2020-08-11 2020-08-11 Spectral identification method for alcohol doped in laser-induced fluorescent red wine

Country Status (1)

Country Link
CN (1) CN111929285A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113916860A (en) * 2021-11-02 2022-01-11 淮阴工学院 Pesticide residue type identification method based on fluorescence spectrum
CN114935565A (en) * 2022-05-30 2022-08-23 淮阴工学院 Method for detecting content of rhodamine B in grape juice based on laser-induced fluorescence technology

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050196047A1 (en) * 2004-02-03 2005-09-08 Yuri Owechko Object recognition system incorporating swarming domain classifiers
CN104897992A (en) * 2015-06-08 2015-09-09 湖南城市学院 Distributed power supply disturbance classification device and on-line detection method thereof
CN106869990A (en) * 2017-03-02 2017-06-20 新疆大学 Coal gas Permeability Prediction method based on LVQ CPSO BP algorithms
CN107121407A (en) * 2017-06-02 2017-09-01 中国计量大学 The method that near-infrared spectrum analysis based on PSO RICAELM differentiates Cuiguan pear maturity
CN111398233A (en) * 2020-04-07 2020-07-10 安徽理工大学 Laser spectrum detection method for red wine quality

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050196047A1 (en) * 2004-02-03 2005-09-08 Yuri Owechko Object recognition system incorporating swarming domain classifiers
CN104897992A (en) * 2015-06-08 2015-09-09 湖南城市学院 Distributed power supply disturbance classification device and on-line detection method thereof
CN106869990A (en) * 2017-03-02 2017-06-20 新疆大学 Coal gas Permeability Prediction method based on LVQ CPSO BP algorithms
CN107121407A (en) * 2017-06-02 2017-09-01 中国计量大学 The method that near-infrared spectrum analysis based on PSO RICAELM differentiates Cuiguan pear maturity
CN111398233A (en) * 2020-04-07 2020-07-10 安徽理工大学 Laser spectrum detection method for red wine quality

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张超等: "基于粒子群算法优化LVQ神经网络的应用研究", 《贵州大学学报(自然科学版)》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113916860A (en) * 2021-11-02 2022-01-11 淮阴工学院 Pesticide residue type identification method based on fluorescence spectrum
CN113916860B (en) * 2021-11-02 2023-04-25 淮阴工学院 Pesticide residue type identification method based on fluorescence spectrum
CN114935565A (en) * 2022-05-30 2022-08-23 淮阴工学院 Method for detecting content of rhodamine B in grape juice based on laser-induced fluorescence technology
CN114935565B (en) * 2022-05-30 2024-03-29 淮阴工学院 Method for detecting rhodamine B content in grape juice based on laser-induced fluorescence technology

Similar Documents

Publication Publication Date Title
Weng et al. Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy
CN101915744A (en) Near infrared spectrum nondestructive testing method and device for material component content
CN109187392B (en) Zinc liquid trace metal ion concentration prediction method based on partition modeling
CN109858477A (en) The Raman spectrum analysis method of object is identified in complex environment with depth forest
CN108844917A (en) A kind of Near Infrared Spectroscopy Data Analysis based on significance tests and Partial Least Squares
CN111929285A (en) Spectral identification method for alcohol doped in laser-induced fluorescent red wine
CN107679569A (en) Raman spectrum substance automatic identifying method based on adaptive hypergraph algorithm
US20220390374A1 (en) Method for extracting raman characteristic peaks employing improved principal component analysis
CN111398233A (en) Laser spectrum detection method for red wine quality
CN109472287A (en) Three-dimensional fluorescence spectrum feature extracting method based on Two-Dimensional Gabor Wavelets
CN112505010A (en) Transformer fault diagnosis device and method based on fluorescence spectrum
CN113008805A (en) Radix angelicae decoction piece quality prediction method based on hyperspectral imaging depth analysis
CN111259929A (en) Random forest based food-borne pathogenic bacteria classification model training method
CN104914225A (en) Method for forecasting content of clarifying agent in fruit juice based on smell sense fingerprint information
CN116858822A (en) Quantitative analysis method for sulfadiazine in water based on machine learning and Raman spectrum
CN112926625A (en) Method for analyzing deviation influence factors of satellite radiation data
CN109598245B (en) Edible oil transverse relaxation attenuation curve signal feature extraction method based on 1D-CNN
CN113640244B (en) Fruit tree variety identification method based on visible near infrared spectrum
CN115420726A (en) Method for rapidly identifying target object by using reconstructed SERS spectrum
CN115630329A (en) Edible essence classification method based on convolutional neural network
CN111122532A (en) Spectrum detection method for honey-doped syrup
Poona et al. Reducing hyperspectral data dimensionality using random forest based wrappers
CN110108661B (en) Tea near infrared spectrum classification method based on fuzzy maximum entropy clustering
CN111693484A (en) Sesame oil variety identification method based on terahertz time-domain spectroscopy
CN113916860B (en) Pesticide residue type identification method based on fluorescence spectrum

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20201113

WW01 Invention patent application withdrawn after publication