CN108169165A - Maltose mixture quantitative analysis method based on tera-hertz spectra and image information fusion - Google Patents
Maltose mixture quantitative analysis method based on tera-hertz spectra and image information fusion Download PDFInfo
- Publication number
- CN108169165A CN108169165A CN201711377485.6A CN201711377485A CN108169165A CN 108169165 A CN108169165 A CN 108169165A CN 201711377485 A CN201711377485 A CN 201711377485A CN 108169165 A CN108169165 A CN 108169165A
- Authority
- CN
- China
- Prior art keywords
- spectrum
- maltose
- image
- data
- maltose mixture
- 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.)
- Granted
Links
- OWEGMIWEEQEYGQ-UHFFFAOYSA-N 100676-05-9 Natural products OC1C(O)C(O)C(CO)OC1OCC1C(O)C(O)C(O)C(OC2C(OC(O)C(O)C2O)CO)O1 OWEGMIWEEQEYGQ-UHFFFAOYSA-N 0.000 title claims abstract description 95
- GUBGYTABKSRVRQ-PICCSMPSSA-N Maltose Natural products O[C@@H]1[C@@H](O)[C@H](O)[C@@H](CO)O[C@@H]1O[C@@H]1[C@@H](CO)OC(O)[C@H](O)[C@H]1O GUBGYTABKSRVRQ-PICCSMPSSA-N 0.000 title claims abstract description 95
- 239000000203 mixture Substances 0.000 title claims abstract description 94
- 238000001228 spectrum Methods 0.000 title claims abstract description 60
- 230000004927 fusion Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004445 quantitative analysis Methods 0.000 title claims abstract description 15
- 239000013598 vector Substances 0.000 claims abstract description 27
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 230000003595 spectral effect Effects 0.000 claims description 25
- 238000000862 absorption spectrum Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 8
- 238000000411 transmission spectrum Methods 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004611 spectroscopical analysis Methods 0.000 abstract 1
- 241000209140 Triticum Species 0.000 description 9
- 235000021307 Triticum Nutrition 0.000 description 9
- 239000004698 Polyethylene Substances 0.000 description 8
- 235000013339 cereals Nutrition 0.000 description 8
- 238000001514 detection method Methods 0.000 description 8
- 235000013312 flour Nutrition 0.000 description 8
- 229920000573 polyethylene Polymers 0.000 description 8
- -1 polyethylene Polymers 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000035784 germination Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 229920002472 Starch Polymers 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012843 least square support vector machine Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 235000019698 starch Nutrition 0.000 description 1
- 239000008107 starch Substances 0.000 description 1
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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
- G01N21/3586—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation by Terahertz time domain spectroscopy [THz-TDS]
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of maltose mixture quantitative analysis method based on tera-hertz spectra and image information fusion, step includes：1) feature extraction, and the data fusion that will be extracted are carried out to the spectrum of maltose mixture and image sample data；2) it is modeled using the fused data of spectrum and image, to maltose mixture quantitative analysis.Beneficial effects of the present invention are：1st, precision of prediction of the invention is significantly better than the precision of prediction using single spectrum or single image；2nd, the present invention carries out independent feature extraction using PCA algorithms to spectroscopic data and image data, can effectively remove noise, can preferably extract for the relevant feature vector of modeling, and then effectively improve the precision of prediction of Multi-source Information Fusion model；3rd, a kind of Boosting iteration ends judge index is proposed according to structural risk minimization theory, realizes the Automatic Optimal to least square method supporting vector machine basic model parameter.
Description
Technical Field
The invention relates to a quantitative analysis method for a maltose mixture based on terahertz spectrum and image information fusion.
Background
If the grains are stored improperly, imagination such as mildew, bud deformation, hardening, worm damage, aging and the like easily occurs, so that the smell, color, component content and the like of the grains are changed, and in recent years, a plurality of grain quality detection methods such as an electronic nose, machine vision, near infrared rays, X rays and the like emerge, but the requirements of accurate and rapid early detection of the bud deformation of the grains cannot be met. In the grain germination process, the most main chemical component change is that starch is converted into sugar for growth, and maltose molecules have an obvious characteristic absorption peak in a THz wave band, so that the degree of germination of a sample can be judged through quantitative analysis of the maltose molecules in grain particles, and further early detection of the grain is realized.
THz waves are a new reliable nondestructive detection technology with huge potential, the spectrum of which contains abundant physical and chemical information, and information which cannot be obtained by other spectral analysis and imaging technologies can be obtained. Due to its unique characteristics, THz-wave and imaging techniques have been widely used in the fields of medical imaging, security inspection, quality detection and quality control. The existing quantitative analysis methods for maltose mixtures all adopt a single method, and the prediction accuracy is low due to insufficient information of the single method.
Disclosure of Invention
The invention aims to provide a quantitative analysis method for a maltose mixture based on fusion of terahertz spectrum and image information, and solves the technical problems of insufficient information amount and low prediction accuracy of a single method.
Aiming at the mentioned problems, the invention provides a quantitative analysis method of a maltose mixture based on terahertz spectrum and image information fusion, which comprises the following steps:
1) performing characteristic extraction on spectrum and image sample data of the maltose mixture, and fusing the extracted data;
2) the maltose mixture was quantitatively analyzed by using fused data modeling of spectra and images.
The preferred scheme is as follows: step 1 is preceded by obtaining sample data of spectra and images of the maltose mixture.
The preferred scheme is as follows: acquiring spectral sample data of a maltose mixture, the steps comprising:
1) measuring the maltose mixture with each concentration by adopting a THz-TDS system to obtain a spectrum;
2) obtaining a frequency domain spectrum of the sample by adopting Fourier transform;
3) the absorption spectrum and refractive index of the maltose mixture at different concentrations were calculated.
The preferred scheme is as follows: sheets of maltose mixtures of different concentrations were placed on a moving platform in the THz-TDS system and reflection imaging measurements were taken to obtain partial THz images of maltose mixtures of different concentrations.
The preferred scheme is as follows: and performing individual feature extraction on the spectral data and the image data by adopting a PCA algorithm.
The preferred scheme is as follows: the specific method for predicting the spectrum and image characteristic data of the maltose mixture by using the Boosting-LS-SVM multi-source information fusion model comprises the following steps:
1) determining Boosting iteration termination judgment conditions according to a risk minimization theory;
2) iterating the Boosting-LS-SVM multi-source information fusion model according to iteration termination judgment conditions;
3) and evaluating the prediction error of the Boosting-LS-SVM multi-source information fusion model by adopting the correlation coefficient and the root mean square error.
The preferred scheme is as follows: supposing that n samples are used for establishing a fusion model, for the kth maltose mixture, performing feature extraction by adopting a PCA algorithm sample spectrum and image data, wherein if THz transmission spectrum sample data and reflection image sample data of one maltose mixture sample are respectively:
xk1＝{xk1，1，xk1，2，…，xk1，n1and xk2＝{xk2，1，xk2，2，…，xk2，n2} (1)
Wherein x isk1And xk2The THz transmission spectrum data reflection image data of the kth maltose mixture respectively represent that a feature vector set after feature extraction is respectively as follows:
zk1＝{zk1，1，zk1，2，…zk1，n1and zk2＝{zk2，1，zk2，2，…zk2，n2} (2)
Wherein z isk1And zk2Respectively fusing the spectral and image feature data to form a kth input vector of the information fusion model, wherein the kth input vector is expressed as:
wherein z iskAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
The preferred scheme is as follows: the iteration termination judgment condition formula is as follows:
wherein C ismIs the termination index value obtained after the mth iteration, and Cm＞Cm-1(m > 1), and z represents a comprehensive characteristic vector of a maltose mixture spectral image; y represents a concentration value of the mixture;Fm(z) represents the basic regression model obtained after the mth Boosting iteration, Fm(z) represents the spectral image fusion model prediction result obtained after m Boosting iterations,. betamRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismAnd representing parameters of the LS-SVM basic model in the mth iteration process.
The preferred scheme is as follows: z is a radical ofkThe predicted value of (c) can be expressed as:
wherein K (z, z)k) is a kernel function, t is the number of iterations, βmRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismRepresents the parameters of the LS-SVM base model in the mth iteration process, zkAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
The invention has the following beneficial effects:
1. the prediction precision of the method is obviously superior to that of the method adopting a single spectrum or a single image;
2. according to the method, the spectral data and the image data are subjected to independent feature extraction by adopting a PCA algorithm, so that noise can be effectively removed, feature vectors related to modeling can be well extracted, and the prediction precision of a multi-source information fusion model is effectively improved;
3. a Boosting iteration termination judgment index is provided according to a structural risk minimization theory, and automatic optimization of the parameters of a basic model of a least square support vector machine is realized.
Drawings
FIG. 1 is a maltose THz absorption spectrum;
FIG. 2 is a THz absorption spectrum of a maltose wheat flour mixture;
FIG. 3(a) is a THz image of a maltose mixture of different concentrations for maltose and polyethylene mixture;
FIG. 3(b) is a THz image of a maltose mixture of different concentrations of maltose and wheat flour mixture;
FIG. 4 is a scatter plot of the correlation between predicted and actual results for a mixture of maltose and polyethylene, and a mixture of maltose and wheat flour.
Detailed Description
The present invention is further described in detail below to enable those skilled in the art to practice the invention with reference to the description of the polyethylene blend.
It will be understood that terms such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
The invention provides a quantitative analysis method for a maltose mixture based on terahertz spectrum and image information fusion, which comprises the following steps:
1) performing characteristic extraction on spectrum and image sample data of the maltose mixture, and fusing the extracted data;
2) the maltose mixture was quantitatively analyzed by using fused data modeling of spectra and images.
The preferred scheme is as follows: step 1 is preceded by obtaining sample data of spectra and images of the maltose mixture.
The preferred scheme is as follows: acquiring spectral sample data of a maltose mixture, the steps comprising:
1) measuring the maltose mixture with each concentration by adopting a THz-TDS system to obtain a spectrum;
2) obtaining a frequency domain spectrum of the sample by adopting Fourier transform;
3) the absorption spectrum and refractive index of the maltose mixture at different concentrations were calculated.
The preferred scheme is as follows: sheets of maltose mixtures of different concentrations were placed on a moving platform in the THz-TDS system and reflection imaging measurements were taken to obtain partial THz images of maltose mixtures of different concentrations.
The preferred scheme is as follows: and performing individual feature extraction on the spectral data and the image data by adopting a PCA algorithm.
The preferred scheme is as follows: the specific method for predicting the spectrum and image characteristic data of the maltose mixture by using the Boosting-LS-SVM multi-source information fusion model comprises the following steps:
1) determining Boosting iteration termination judgment conditions according to a risk minimization theory;
2) iterating the Boosting-LS-SVM multi-source information fusion model according to iteration termination judgment conditions;
3) and evaluating the prediction error of the Boosting-LS-SVM multi-source information fusion model by adopting the correlation coefficient and the root mean square error.
The preferred scheme is as follows: supposing that n samples are used for establishing a fusion model, for the kth maltose mixture, performing feature extraction by adopting a PCA algorithm sample spectrum and image data, wherein if THz transmission spectrum sample data and reflection image sample data of one maltose mixture sample are respectively:
xk1＝{xk1，1，xk1，2，…，xk1，n1and xk2＝{xk2，1，xk2，2，…，xk2，n2} (1)
Wherein x isk1And xk2The THz transmission spectrum data reflection image data of the kth maltose mixture respectively represent that a feature vector set after feature extraction is respectively as follows:
zk1＝{zk1，1，zk1，2，…zk1，n1and zk2＝{zk2，1，zk2，2，…zk2，n2} (2)
Wherein z isk1And zk2Respectively fusing the spectral and image feature data to form a kth input vector of the information fusion model, wherein the kth input vector is expressed as:
wherein z iskAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
The preferred scheme is as follows: the iteration termination judgment condition formula is as follows:
wherein C ismIs the termination index value obtained after the mth iteration, and Cm＞Cm-1(m > 1), and z represents a comprehensive characteristic vector of a maltose mixture spectral image; y represents a concentration value of the mixture; fm(z) represents the basic regression model obtained after the mth Boosting iteration, Fm(z) represents the spectral image fusion model prediction result obtained after m Boosting iterations,. betamRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismAnd representing parameters of the LS-SVM basic model in the mth iteration process.
The preferred scheme is as follows: z is a radical ofkThe predicted value of (c) can be expressed as:
wherein K (z, z)k) Is a corefunction, t is the number of iterations, βmRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismRepresents the parameters of the LS-SVM base model in the mth iteration process, zkAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
1. THz spectral characteristics of maltose mixture
The measurement was carried out on each maltose mixture concentration using the THz-TDS system, three measurements were carried out on each mixture sample, the average spectrum was calculated, and between each two concentration sample mixtures a reference was first measured, then the frequency domain spectrum of the sample was obtained using fourier transform, and finally the absorption spectrum and refractive index of the different concentration maltose mixtures were calculated, the absorption spectrum of a portion of the maltose and polyethylene mixture being given in fig. 1, and the absorption spectrum of a portion of the maltose and wheat flour mixture being given in fig. 2.
2. THz image characteristics of maltose mixture
Different concentrations of maltose mixture flakes were placed on the moving platform in the THz-TDS system and reflectance imaging measurements were performed. Partial THz images (at 1.0 THz) obtained for different concentrations of maltose and polyethylene mixtures are shown in fig. 3(a), and partial THz images (at 1.0 THz) obtained for different concentrations of maltose and wheat flour mixtures are shown in fig. 3(b), where 0% represents pure polyethylene or wheat flour. As can be seen, the obvious change occurs between the THz images along with the increase of the maltose content, which shows that the THz imaging technology is feasible to realize the quantitative detection of the maltose component.
3. Wheat maltose quantitative analysis modeling based on terahertz spectrum and image information fusion technology
(1) And performing feature extraction on the spectrum and image sample data of the maltose mixture.
Supposing that n samples are used for establishing a fusion model, for the kth maltose mixture, performing feature extraction by adopting a PCA algorithm sample spectrum and image data, wherein if THz transmission spectrum sample data and reflection image sample data of one maltose mixture sample are respectively:
xk1＝{xk1，1，xk1，2，…，xk1，n1and xk2＝{xk2，1，xk2，2，…，xk2，n2} (1)
Wherein x isk1And xk2The THz transmission spectrum data reflection image data of the kth maltose mixture respectively represent that a feature vector set after feature extraction is respectively as follows:
zk1＝{zk1，1，zk1，2，…zk1，n1and zk2＝{zk2，1，zk2，2，…zk2，n2} (2)
Wherein z isk1And zk2Respectively fusing the spectral and image feature data to form a kth input vector of the information fusion model, wherein the kth input vector is expressed as:
wherein z iskAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
(2) And predicting the spectrum and image characteristic data of maltose mixture by using a Boosting-LS-SVM multi-source information fusion model.
According to an iteration termination judgment condition formula:
wherein C ismIs the termination index value obtained after the mth iteration, and Cm＞Cm-1(m＞1) And z represents a comprehensive feature vector of a maltose mixture spectral image; y represents a concentration value of the mixture; fm(z) represents the basic regression model obtained after the mth Boosting iteration, Fm(z) represents the spectral image fusion model prediction result obtained after m Boosting iterations,. betamRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismthe optimal iteration times of the Boosting-LS-SVM fusion model obtained by calculation are t times, and the weight values of the LS-SVM basic model in the previous t iterations are respectively beta1，β2，…βnThe parameters of the basic model are respectively: a is1，a2，…atAnd a1，b2，…btThen the obtained combined model pair zkThe predicted value of (c) can be expressed as:
wherein K (z, z)k) Is a kernel function.
In order to prevent the influence of unbalanced information amount of spectrum and image data on the prediction accuracy of an information fusion model, firstly, a PCA algorithm is adopted to respectively perform feature extraction on THz spectrum data samples and image data samples, the number of feature signals of each data sample is controlled, the first 4 principal components in the THz spectrum data and the first 5 principal components in the image data are selected as the input of an LS-SVM model, and then the Boosting-LS-SVM algorithm is used for performing information fusion modeling on the feature data. Meanwhile, the LS-SVM algorithm adopts a Radial Basis Function (RBF) and a grid search algorithm to evaluate the generalization performance of the spectral image combination model. In the Boosting-LS-SVM algorithm, two parameters C and gamma of a basic model LS-SVM are firstly set according to an empirical value, then Boosting iteration is carried out on the LS-SVM basic model according to the above-mentioned iteration termination judgment condition, and finally a prediction error of the model is evaluated by adopting a correlation coefficient R and a root mean square error RMSE, wherein the calculation formula is as follows:
wherein,a standard measurement representing the maltose content,and expressing the prediction value of the Boosting-LS-SVM fusion model. The smaller the RMSE value, the higher the prediction accuracy of the fusion model.
Judging the index value C after the iteration termination of m Boosting iterations in the Boosting-LS-SVM algorithmmCan be expressed as:
wherein Fm(z) represents the spectral image fusion model prediction result obtained after m Boosting iterations,. betamRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismAnd representing parameters of the LS-SVM basic model in the mth iteration process.
(3) Establishing a wheat maltose quantitative analysis fusion model based on Boosting integration method
Under the corresponding optimal characteristic data combination, single THz spectral characteristic data, single THz image characteristic data, THz spectral characteristic data and image characteristic data are combined to perform Boosting-LS-SVM modeling, and the optimal prediction results and corresponding parameters of three Boosting-LS-SVM fusion models of a maltose-polyethylene mixture and a maltose-wheat flour mixture are listed in Table 1.
From table 1, it can be seen that the prediction accuracy of the Boosting-LS-SVM model constructed by using THz spectral feature data and image feature data is significantly better than the optimal prediction result of the Boosting-LS-SVM model constructed by using single spectral data and single image data feature extraction. The result proves that the PCA + Boosting-LS-SVM information fusion model provided by the method can effectively remove noise, can better extract the feature vector related to modeling, and further effectively improves the prediction precision of the multi-source information fusion model.
TABLE 1 Boosting-LS-SVM model prediction results and corresponding parameters for maltose mixtures
As shown in fig. 4, a prediction result and actual result correlation scatter diagram of the Boosting-LS-SVM information fusion model constructed by using the feature data after spectral data and image data are individually feature-extracted by using the PCA method is used for a mixture of maltose and polyethylene and a mixture of maltose and wheat flour. As can be seen from the figure, the prediction value of the maltose mixture by the PCA + Boosting-LS-SVM multi-source information fusion model adopted by the method can better approach the actual measurement value, the linear correlation degree of the two is higher, the prediction accuracy of the maltose content in the maltose mixture can be obviously improved by the method provided by the method, the method is an effective maltose quantitative detection method, an important theoretical and technical basis is laid for early detection of grain bud mutation, and the method has great application and popularization values.
While embodiments of the invention have been disclosed above, it is not limited to the applications listed in the description and the embodiments, which are fully applicable in all kinds of fields of application of the invention, and further modifications may readily be effected by those skilled in the art, so that the invention is not limited to the specific details without departing from the general concept defined by the claims and the scope of equivalents.
Claims (9)
1. The method for quantitatively analyzing the maltose mixture based on the fusion of the terahertz spectrum and the image information is characterized by comprising the following steps of:
1) performing characteristic extraction on spectrum and image sample data of the maltose mixture, and fusing the extracted data;
2) the maltose mixture was quantitatively analyzed by using fused data modeling of spectra and images.
2. The method for quantitatively analyzing the maltose mixture based on the fusion of the terahertz spectrum and the image information according to claim 1, wherein step 1 is preceded by obtaining sample data of the spectrum and the image of the maltose mixture.
3. The method for quantitatively analyzing the maltose mixture based on the fusion of the terahertz spectrum and the image information according to claim 2, wherein the steps of acquiring the spectrum sample data of the maltose mixture comprise:
1) measuring the maltose mixture with each concentration by adopting a THz-TDS system to obtain a spectrum;
2) obtaining a frequency domain spectrum of the sample by adopting Fourier transform;
3) the absorption spectrum and refractive index of the maltose mixture at different concentrations were calculated.
4. The quantitative analysis method for the maltose mixture based on the terahertz spectrum and image information fusion as claimed in claim 2, characterized in that, different concentrations of maltose mixture slices are placed on a moving platform in the THz-TDS system, and reflection imaging measurement is carried out to obtain partial THz images of the maltose mixtures with different concentrations.
5. The quantitative analysis method for the maltose mixture based on the fusion of the terahertz spectrum and the image information as claimed in claim 1, characterized in that the PCA algorithm is adopted to perform the individual feature extraction on the spectrum data and the image data.
6. The quantitative analysis method for the maltose mixture based on the terahertz spectrum and image information fusion as claimed in claim 1, wherein the spectrum and image feature data of the maltose mixture are quantitatively analyzed by using a Boosting-LS-SVM multi-source information fusion model, and the specific steps comprise:
1) determining Boosting iteration termination judgment conditions according to a risk minimization theory;
2) iterating the Boosting-LS-SVM multi-source information fusion model according to iteration termination judgment conditions;
3) and evaluating the prediction error of the Boosting-LS-SVM multi-source information fusion model by adopting the correlation coefficient and the root mean square error.
7. The method for quantitatively analyzing the maltose mixture based on the fusion of the terahertz spectrum and the image information as claimed in claim 6, wherein assuming that n samples are used for establishing the fusion model, for the kth maltose mixture, the PCA algorithm is used to extract the features of the sample spectrum and the image data, if the THz transmission spectrum sample data and the reflection image sample data of one maltose mixture sample are respectively:
xk1＝{xk1，1，xk1，2，…，xk1，n1and xk2＝{xk2，1，xk2，2，…，xk2，n2} (1)
Wherein x isk1And xk2The THz transmission spectrum data reflection image data of the kth maltose mixture respectively represent that a feature vector set after feature extraction is respectively as follows:
zk1＝{zk1，1，zk1，2，…zk1，n1and zk2＝{zk2，1，zk2，2，…zk2，n2} (2)
Wherein z isk1And zk2Respectively fusing the spectral and image feature data to form a kth input vector of the information fusion model, wherein the kth input vector is expressed as:
wherein z iskAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
8. The method for quantitatively analyzing the maltose mixture based on the fusion of the terahertz spectrum and the image information as claimed in claim 7, wherein the iteration termination judgment condition is formulated as:
wherein C ismIs the termination index value obtained after the mth iteration, and Cm＞Cm-1(m > 1), and z represents a comprehensive characteristic vector of a maltose mixture spectral image; y represents a concentration value of the mixture; fm(z) represents the basic regression model obtained after the mth Boosting iteration, Fm(z) represents the spectral image fusion model prediction result obtained after m Boosting iterations,. betamRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismAnd representing parameters of the LS-SVM basic model in the mth iteration process.
9. The method for quantitatively analyzing maltose mixture based on terahertz spectrum and image information fusion as claimed in claim 8, wherein z iskThe predicted value of (c) can be expressed as:
wherein K (z, z)k) is a kernel function, t is the number of iterations, βmRepresenting the weight of the LS-SVM basic model in the mth iteration process; a ismRepresents the parameters of the LS-SVM base model in the mth iteration process, zkAnd fusing a feature vector set of the kth sample spectrum and the image feature data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711377485.6A CN108169165B (en) | 2017-12-19 | 2017-12-19 | Maltose mixture quantitative analysis method based on terahertz spectrum and image information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711377485.6A CN108169165B (en) | 2017-12-19 | 2017-12-19 | Maltose mixture quantitative analysis method based on terahertz spectrum and image information fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108169165A true CN108169165A (en) | 2018-06-15 |
| CN108169165B CN108169165B (en) | 2020-10-23 |
Family
ID=62522527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711377485.6A Active CN108169165B (en) | 2017-12-19 | 2017-12-19 | Maltose mixture quantitative analysis method based on terahertz spectrum and image information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108169165B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109507187A (en) * | 2018-11-23 | 2019-03-22 | 哈尔滨工业大学（威海） | A kind of laser gain material manufacturing defect diagnostic method and its device |
| CN110108649A (en) * | 2019-05-06 | 2019-08-09 | 北京工商大学 | The fast non-destructive detection method of oil crops quality based on terahertz light spectral technology |
| CN110728325A (en) * | 2019-10-12 | 2020-01-24 | 太原科技大学 | Variable voltage DR image fusion method based on support degree transformation |
| CN113252598A (en) * | 2021-05-19 | 2021-08-13 | 中国电子科技集团公司第四十一研究所 | Full-electronics terahertz near-field spectrum comprehensive test device and method |
| CN113607678A (en) * | 2021-07-29 | 2021-11-05 | 河南工业大学 | Terahertz technology-based quantitative analysis method for glucose and wheat mixture |
| CN114088656A (en) * | 2020-07-31 | 2022-02-25 | 中国科学院上海高等研究院 | Terahertz spectrum substance identification method and system, storage medium and terminal |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102590211A (en) * | 2011-01-11 | 2012-07-18 | 郑州大学 | Method for utilizing spectral and image characteristics to grade tobacco leaves |
| CN106124435A (en) * | 2016-07-04 | 2016-11-16 | 江苏大学 | Based on visible ray, near-infrared, the rice new-old quality inspection device of Terahertz fusion spectral technique and detection method |
-
2017
- 2017-12-19 CN CN201711377485.6A patent/CN108169165B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102590211A (en) * | 2011-01-11 | 2012-07-18 | 郑州大学 | Method for utilizing spectral and image characteristics to grade tobacco leaves |
| CN106124435A (en) * | 2016-07-04 | 2016-11-16 | 江苏大学 | Based on visible ray, near-infrared, the rice new-old quality inspection device of Terahertz fusion spectral technique and detection method |
Non-Patent Citations (1)
| Title |
|---|
| YUYING JIANG 等: "Early detection of germinated wheat grains using terahertz image and chemometrics", 《SCIENTIFIC REPORTS》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109507187A (en) * | 2018-11-23 | 2019-03-22 | 哈尔滨工业大学（威海） | A kind of laser gain material manufacturing defect diagnostic method and its device |
| CN110108649A (en) * | 2019-05-06 | 2019-08-09 | 北京工商大学 | The fast non-destructive detection method of oil crops quality based on terahertz light spectral technology |
| CN110728325A (en) * | 2019-10-12 | 2020-01-24 | 太原科技大学 | Variable voltage DR image fusion method based on support degree transformation |
| CN114088656A (en) * | 2020-07-31 | 2022-02-25 | 中国科学院上海高等研究院 | Terahertz spectrum substance identification method and system, storage medium and terminal |
| CN113252598A (en) * | 2021-05-19 | 2021-08-13 | 中国电子科技集团公司第四十一研究所 | Full-electronics terahertz near-field spectrum comprehensive test device and method |
| CN113607678A (en) * | 2021-07-29 | 2021-11-05 | 河南工业大学 | Terahertz technology-based quantitative analysis method for glucose and wheat mixture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108169165B (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108169165B (en) | Maltose mixture quantitative analysis method based on terahertz spectrum and image information fusion | |
| Huang et al. | Rapid and nondestructive prediction of amylose and amylopectin contents in sorghum based on hyperspectral imaging | |
| CN108680515B (en) | Single-grain rice amylose quantitative analysis model construction and detection method thereof | |
| Sun et al. | Detection of internal qualities of hami melons using hyperspectral imaging technology based on variable selection algorithms | |
| CN109253985B (en) | Method for identifying wood grade for koto panel by near infrared spectrum based on neural network | |
| CN102937575B (en) | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination | |
| Zhang et al. | Moisture detection of single corn seed based on hyperspectral imaging and deep learning | |
| CN105548070A (en) | Apple soluble solid near-infrared detection part compensation method and system | |
| CN104255118B (en) | Rapid lossless testing method based on near infrared spectroscopy technology for paddy rice seed germination percentage | |
| CN116385784A (en) | Method and system for measuring and calculating chlorophyll content of rice under cadmium stress | |
| CN111445469A (en) | Hyperspectrum-based apple damage parameter lossless prediction method after impact | |
| CN110609011A (en) | Near-infrared hyperspectral detection method and system for starch content of single-kernel corn seeds | |
| Noypitak et al. | Detection of cracked shell in intact aromatic young coconut using near infrared spectroscopy and acoustic response methods | |
| CN113030007B (en) | Method for rapidly testing quality stability of tobacco essence based on similarity learning algorithm | |
| CN105866043A (en) | Method for detecting apple sour through hyperspectral technology | |
| Qiao et al. | Research on simultaneous detection of SSC and FI of blueberry based on hyperspectral imaging combined MS-SPA | |
| Luka et al. | Hyperspectral imaging systems for rapid assessment of moisture and chromaticity of foods undergoing drying: Principles, applications, challenges, and future trends | |
| Wang et al. | Monitoring model for predicting maize grain moisture at the filling stage using NIRS and a small sample size | |
| CN113049526B (en) | Corn seed moisture content determination method based on terahertz attenuated total reflection | |
| CN117191739A (en) | Near infrared spectrum quantitative detection method and system for correcting moisture interference | |
| CN110596038A (en) | Method for rapidly determining starch content of sweet potatoes | |
| Zhang et al. | Hyperspectral detection of walnut protein contents based on improved whale optimized algorithm | |
| Yuan et al. | Application of hyperspectral imaging to discriminate waxy corn seed vigour after aging. | |
| CN115327023A (en) | Plant leaf nitrogen content detection method and system | |
| CN114878549A (en) | Corn aflatoxin detection method based on Raman spectrum |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |