CN112834451B - Sample identification method and device based on infrared spectrum and storage medium - Google Patents
Sample identification method and device based on infrared spectrum and storage medium Download PDFInfo
- Publication number
- CN112834451B CN112834451B CN202110036604.1A CN202110036604A CN112834451B CN 112834451 B CN112834451 B CN 112834451B CN 202110036604 A CN202110036604 A CN 202110036604A CN 112834451 B CN112834451 B CN 112834451B
- Authority
- CN
- China
- Prior art keywords
- spectrum
- standard
- test
- data
- sample
- 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
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001228 spectrum Methods 0.000 claims abstract description 158
- 238000012360 testing method Methods 0.000 claims abstract description 80
- 239000000126 substance Substances 0.000 claims abstract description 59
- 230000003595 spectral effect Effects 0.000 claims abstract description 49
- 238000004566 IR spectroscopy Methods 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 229940079593 drug Drugs 0.000 claims description 3
- 239000003814 drug Substances 0.000 claims description 3
- 239000002360 explosive Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 239000003153 chemical reaction reagent Substances 0.000 abstract description 2
- 238000001819 mass spectrum Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000000862 absorption spectrum Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- ZPUCINDJVBIVPJ-LJISPDSOSA-N cocaine Chemical compound O([C@H]1C[C@@H]2CC[C@@H](N2C)[C@H]1C(=O)OC)C(=O)C1=CC=CC=C1 ZPUCINDJVBIVPJ-LJISPDSOSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- BQJCRHHNABKAKU-KBQPJGBKSA-N morphine Chemical compound O([C@H]1[C@H](C=C[C@H]23)O)C4=C5[C@@]12CCN(C)[C@@H]3CC5=CC=C4O BQJCRHHNABKAKU-KBQPJGBKSA-N 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- GVGLGOZIDCSQPN-PVHGPHFFSA-N Heroin Chemical compound O([C@H]1[C@H](C=C[C@H]23)OC(C)=O)C4=C5[C@@]12CCN(C)[C@@H]3CC5=CC=C4OC(C)=O GVGLGOZIDCSQPN-PVHGPHFFSA-N 0.000 description 1
- SNIOPGDIGTZGOP-UHFFFAOYSA-N Nitroglycerin Chemical compound [O-][N+](=O)OCC(O[N+]([O-])=O)CO[N+]([O-])=O SNIOPGDIGTZGOP-UHFFFAOYSA-N 0.000 description 1
- 239000000006 Nitroglycerin Substances 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000002835 absorbance Methods 0.000 description 1
- 229960003920 cocaine Drugs 0.000 description 1
- 229960002069 diamorphine Drugs 0.000 description 1
- 238000000295 emission spectrum Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 229960003711 glyceryl trinitrate Drugs 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 240000004308 marijuana Species 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229960001252 methamphetamine Drugs 0.000 description 1
- MYWUZJCMWCOHBA-VIFPVBQESA-N methamphetamine Chemical compound CN[C@@H](C)CC1=CC=CC=C1 MYWUZJCMWCOHBA-VIFPVBQESA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229960005181 morphine Drugs 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000001845 vibrational spectrum Methods 0.000 description 1
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
- G01N21/17—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a sample identification method, equipment and a storage medium based on infrared spectroscopy, wherein the sample identification method comprises the steps of establishing a standard spectrum library of substances on the basis of infrared spectroscopy of a series of standard substances, wherein each piece of spectrum data in the standard spectrum library is called as a standard spectrum; constructing a series of test samples, carrying out infrared spectrum scanning on the test samples, and extracting each piece of spectrum data of the test samples as a test spectrum; calculating a weighted correlation coefficient of the test spectrum and the standard spectrum, setting a similar interval according to the weighted correlation coefficient, and establishing an infrared spectrum identification model; performing infrared spectrum scanning on a sample to be detected to obtain spectral data of the sample to be detected; and inputting the spectral data into an infrared spectrum recognition model to recognize the sample to be detected. The sample identification method provided by the invention adopts an infrared spectrum technology, and compared with instruments such as a mass spectrum and the like, the method does not use a chemical reagent, is green and environment-friendly, applies a weighted correlation coefficient in an identification model, and has high identification accuracy and high detection efficiency.
Description
Technical Field
The invention relates to the technical field of infrared spectrum identification, in particular to a sample identification method, sample identification equipment and a storage medium based on infrared spectrum.
Background
The infrared spectrum is mainly divided into absorption spectrum, emission spectrum and scattering spectrum, and is referred to herein as infrared absorption spectrum. The infrared absorption spectrum is derived from a vibrational spectrum caused by vibrational rotation and energy level transition of molecules. The infrared spectrum is generally divided into 3 regions: far infrared region (about 400-10 cm) -1 ) Middle infrared region (about 4000-400 cm) -1 ) Near infrared region (14000-4000 cm) -1 )。
Although the prior art can carry out matching identification on substances according to the characteristic peak positions of infrared spectra of different substances, the method needs to search peaks by a machine and involves extraction of peak shape characteristics and the like, the process is complex, the subjectivity is strong, and the method is not suitable for online detection, so that the development of a sample identification method suitable for the infrared spectra is urgently needed.
Accordingly, there is a need for improvements and developments in the art.
Disclosure of Invention
The invention mainly aims to solve the technical problems of complex identification process and low efficiency of the existing method for identifying substances by utilizing infrared spectrum.
The invention provides a sample identification method based on infrared spectrum, which comprises the following steps:
establishing a standard spectrum library of substances based on infrared spectra of a series of standard substances, wherein each piece of spectral data in the standard spectrum library is called as a standard spectrum;
constructing a series of test samples, carrying out infrared spectrum scanning on the test samples, and extracting each piece of spectrum data of the test samples to be used as a test spectrum;
calculating the weighted correlation coefficient of the test spectrum and the standard spectrum, setting a similar interval according to the weighted correlation coefficient, and establishing an infrared spectrum identification model;
performing infrared spectrum scanning on a sample to be detected to obtain spectral data of the sample to be detected;
and inputting the spectrum data into the infrared spectrum recognition model to recognize the sample to be detected.
Optionally, in the first embodiment of the first aspect of the present invention, in the standard spectrum library, an average value of m data points corresponding to p pieces of spectral data of the same substance measured in different batches is used as the standard spectrum s of the substance original ，
Optionally, in a second implementation manner of the first aspect of the present invention, before the calculating the weighted correlation coefficient between the test spectrum and the standard spectrum, the calculating includes:
filtering the test spectrum and the standard spectrum, and calculating to obtain mathematical expectation and variance of the standard spectrum data after filtering and mathematical expectation and variance of the test spectrum data after filtering;
and standardizing the standard spectrum data after the filtering processing and the test spectrum data after the filtering processing.
Optionally, in a third embodiment of the first aspect of the present invention, the processed standard spectral data is normalized
Wherein s is second For filtered standard spectral data, E s For mathematical expectation of filtered standard spectral data, σ s 2 E is the variance of the standard spectral data after filtering processing and is the base number of a natural logarithm function;
standardized test spectral data
Wherein, t second For the filtered test spectral data, E t For mathematical expectation of filtered standard spectral data, σ t 2 Is the variance of the filtered standard spectral data.
Optionally, in a fourth embodiment of the first aspect of the present invention, the calculating the weighted correlation coefficient between the test spectrum and the standard spectrum uses the following formula:
weighted correlation coefficient
Wherein s is i Is the ith data point, t, in the normalized standard spectrum data i For the ith data point in the normalized test spectrum data,
ω i is the weight of the ith data point, <' >>
And k is a self-defined parameter.
Optionally, in a fifth embodiment of the first aspect of the present invention, k is 0.01 or 0.5.
Optionally, in a sixth embodiment of the first aspect of the present invention, the test sample comprises a sample of the same substance in a standard library of spectra and a sample of a substance in a non-standard library of spectra.
Optionally, in a seventh embodiment of the first aspect of the present invention, the sample to be tested includes drugs and explosives.
The present invention provides in a second aspect an infrared spectroscopy-based sample identification apparatus, the sample identification apparatus comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the sample identification device to perform an infrared spectroscopy-based sample identification method as described in any one of the above.
A third aspect of the invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method for infrared spectroscopy-based sample identification as defined in any one of the above.
Has the advantages that: the invention provides a sample identification method, equipment and a storage medium based on infrared spectroscopy, wherein the sample identification method comprises the steps of establishing a standard spectrum library of substances on the basis of infrared spectroscopy of a series of standard substances, wherein each piece of spectrum data in the standard spectrum library is called as a standard spectrum; constructing a series of test samples, carrying out infrared spectrum scanning on the test samples, and extracting each piece of spectrum data of the test samples to be used as a test spectrum; calculating a weighted correlation coefficient of the test spectrum and the standard spectrum, setting a similar interval according to the weighted correlation coefficient, and establishing an infrared spectrum identification model; performing infrared spectrum scanning on a sample to be detected to obtain spectral data of the sample to be detected; and inputting the spectral data into an infrared spectrum recognition model to recognize the sample to be detected. The sample identification method disclosed by the invention adopts an infrared spectrum technology, and compared with instruments such as a mass spectrum and the like, the sample identification method does not use a chemical reagent, is green and environment-friendly, applies a weighted correlation coefficient in an identification model, and has high identification accuracy and high detection efficiency.
Drawings
FIG. 1 is a flow chart of one embodiment of a method for infrared spectroscopy-based sample identification of the present invention;
FIG. 2 is an infrared scanning raw spectrum of a substance in a standard spectrum library;
FIG. 3 is a material distribution diagram of a standard spectrum to which the highest correlation coefficient between a test spectrum and the standard spectrum belongs;
fig. 4 is a schematic diagram of an embodiment of an infrared spectrum-based sample identification apparatus according to the present invention.
Detailed Description
The embodiment of the invention provides a sample identification method and device based on infrared spectroscopy and a storage medium.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a detailed flow chart of an embodiment of the present invention is described below, with reference to fig. 1, in which a first aspect of the present invention is a method for sample identification based on infrared spectroscopy, the method for sample identification based on infrared spectroscopy comprising:
s100, establishing a standard spectrum library of substances on the basis of infrared spectrums of a series of standard substances, wherein each piece of spectrum data in the standard spectrum library is called as a standard spectrum;
s200, constructing a series of test samples, carrying out infrared spectrum scanning on the test samples, and extracting each piece of spectrum data of the test samples to be used as a test spectrum;
s300, calculating a weighted correlation coefficient of the test spectrum and the standard spectrum, setting a similar interval according to the weighted correlation coefficient, and establishing an infrared spectrum identification model;
s400, performing infrared spectrum scanning on a sample to be detected to obtain spectral data of the sample to be detected;
s500, inputting the spectral data into the infrared spectrum recognition model to recognize the sample to be detected.
The sample identification method based on the infrared spectrum is characterized in that an infrared spectrum identification model is firstly established, the infrared spectrum of a sample is identified by the infrared spectrum identification model, the model is based on the infrared spectrum of a series of standard substances, a standard spectrum library of the substances is established, each piece of spectrum data in the standard spectrum library is called as a standard spectrum, and then an identification matching model is established through a weighted correlation coefficient. According to the invention, the similarity of the infrared spectrum is measured through the weighted correlation coefficient, the weighted correlation coefficient can effectively use the spectrum characteristics for similarity calculation, so that the reliability of the result is improved, the test spectrum of the test sample is highly similar to but different from the standard spectrum of the substances in the standard spectrum library, the common characteristics are reflected, and the individual difference is reflected. Therefore, a similar interval of the spectrum similarity is determined, products in the interval are similar substances, and otherwise, the products are non-similar substances or abnormal samples.
In an alternative embodiment of the first aspect of the present invention, in the standard spectrum library, the average value of m data points corresponding to p pieces of spectral data of the same substance measured in different batches is used as the standard spectrum s of the substance original ，
In an alternative embodiment of the first aspect of the present invention, the calculating the weighted correlation coefficients of the test spectrum and the standard spectrum comprises:
filtering the test spectrum and the standard spectrum, and calculating to obtain mathematical expectation and variance of the standard spectrum data after filtering and mathematical expectation and variance of the test spectrum data after filtering;
and standardizing the standard spectrum data after the filtering processing and the test spectrum data after the filtering processing.
In this embodiment, both the test spectrum and the standard spectrum need to be preprocessed, where the preprocessing includes filtering the spectrum data, and further, the preprocessing needs to be standardized to obtain the finally needed standard spectrum data and test spectrum data.
In an alternative embodiment of the first aspect of the present invention, the processed standard spectral data is normalized
Wherein s is second For filtered standard spectral data, E s For mathematical expectation of filtered standard spectral data, σ s 2 E is the variance of the standard spectral data after filtering processing and is the base number of a natural logarithm function;
standardized test spectral data
Wherein, t second For the filtered test spectral data, E t For mathematical expectation of filtered standard spectral data, σ t 2 Is the variance of the filtered standard spectral data.
In an alternative embodiment of the first aspect of the present invention, the calculating the weighted correlation coefficient between the test spectrum and the standard spectrum uses the following formula:
weighted correlation coefficient
Wherein s is i Is the ith data point, t, in the normalized standard spectrum data i For the ith data point in the standardized test spectral data, based on the normalization process>
ω i Is the weight of the ith data point, <' >>
And k is a custom parameter.
In an alternative embodiment of the first aspect of the present invention, k is 0.01 or 0.5. In the embodiment, the weight formula contains a parameter k which needs to be specified by a user, and the parameter k is the only parameter to be considered by the algorithm model of the weighted correlation coefficient method, when k =0.5, most data is used for the algorithm model, and when k =0.01, only few local points participate in the algorithm model.
In an alternative embodiment of the first aspect of the present invention, the test sample comprises a sample of the same substance in a standard library of spectra and a sample of a substance in a non-standard library of spectra. In this embodiment, the test sample is used to determine a weighted correlation coefficient, the weighted correlation coefficient of the test spectrum of the sample of the same substance in the standard spectrum library with the standard spectrum of the substance is the highest, and the highest weighted correlation coefficient of other substances in the standard spectrum library with the substance in the standard spectrum library is lower, so that a threshold value of the weighted correlation coefficient can be determined, wherein the substance belonging to the standard spectrum library is represented by the threshold value, and of course, the threshold value can be adjusted according to the selected test sample.
In an alternative embodiment of the first aspect of the present invention, the sample to be tested includes drugs and explosives. More specifically, the sample to be tested comprises cocaine, heroin, methamphetamine, morphine, tai-an, cannabis and nitroglycerin.
The first aspect of the invention is a specific example of a sample identification method based on infrared spectroscopy, as follows:
The infrared spectrum signal comprises an infrared spectrum in a certain waveband range, specifically an infrared absorbance curve or other spectral parameters derived from formula deformation, and is acquired by a Fourier infrared spectrometer produced by BRUKER company (Germany).
Taking the average value of m data points corresponding to p spectral data of the same substance measured in different batches as the standard spectrum s of the substance original ，
The spectrum comprises a standard spectrum s original And a test spectrum t original (ii) a The preprocessing comprises filtering the spectral data, further performing standardization, and obtaining the final standard spectral data s and the test spectral data t.
The spectrum pretreatment comprises the following steps:
3.1 spectral filtering treatment, wherein S-G smoothing filtering is mainly used;
3.2 obtaining the spectral data s obtained after filtering second Or t second Mathematical expectation of (E) s Or E t Sum variance σ s 2 Or σ t 2 ；
3.3 normalization
Step 4, establishing a weighted correlation coefficient algorithm model
Specifically, calculating a weighted correlation coefficient r of the test spectrum t and a standard spectrum s, wherein s is standard spectrum data finally obtained in the step 3, and s in s is i Is the ith data point in the standard spectral data. t in t i Is the ith data point in the test spectrum data.
ω i Is the weight of the ith data point. />
In the above expression of the weighted correlation coefficient r, the weight ω i The corresponding expression is as follows:
the above formula contains a parameter k which needs to be specified by a user, and this is also the only parameter to be considered by the weighted correlation coefficient algorithm model, and k =0.5 in this embodiment.
Testing the test spectrum of each substance in the standard library for multiple times, and obtaining a correlation coefficient between the test spectrum and each standard spectrum in the standard library; and testing the test spectrum of the non-existing substance in the standard library for multiple times, obtaining the correlation coefficient between the test spectrum and the standard spectrum of each substance in the standard library, and counting the distribution of the correlation coefficient of each test spectrum, thereby setting a reasonable similar interval for each standard spectrum substance in the standard library.
In this embodiment, referring to fig. 2, fig. 2 is an infrared scanning raw spectrum of 10 substances in a standard spectrum library, referring to fig. 3, and a sample label 0,1, \82309in ordinate in fig. 3 represents a substance distribution of a standard spectrum to which a highest correlation coefficient between a test spectrum and 10 standard spectra in the standard spectrum library belongs. The test spectra of 10 substances in the standard spectrum library are tested, 20 (200 in total) test spectra of the substances in the standard spectrum library and 200 test spectra of substances outside the standard spectrum library are tested, and the 10 different substances in the standard spectrum library and the substances outside the standard spectrum library are marked by 11 marks with different shapes. And (3) respectively calculating correlation coefficients of all the test spectra t and the standard spectra of 10 substances in the standard spectrum library, and obtaining the highest correlation coefficient between each test spectrum and 10 standard spectra, the distribution of the highest correlation coefficient and the substance distribution of the corresponding standard spectrum, as shown in fig. 3. It is easy to see that the correlation coefficient of the test spectrum of the sample of the same substance in the standard spectrum library and the standard spectrum of the substance is the highest and is higher than 0.85. The highest correlation coefficient of other substances except the standard spectrum library and 10 substances in the standard spectrum library is lower than 0.85. The threshold value of substantially each substance may be set to approximately 0.85. The similarity interval is [ 0.85,1 ]. Of course, the threshold value can be fine-tuned in a targeted manner according to the distribution of the correlation coefficients of the substances. The highest correlation coefficient between all the test spectra and 10 standard spectra forms a highest correlation coefficient matrix, the expression is r, in this embodiment, n =10, h =400, and if rjv is in the correlation coefficient similarity interval of the jth substance, the substance to which the test spectrum belongs is judged as the jth substance. Otherwise, judging the sample to belong to other substances outside the standard spectrum library.
Fig. 4 is a schematic structural diagram of an infrared spectrum-based sample identification device according to an embodiment of the present invention, which may have relatively large differences due to different configurations or performances, and may include one or more processors 10 (CPUs) (e.g., one or more processors) and a memory 20, and one or more storage media 30 (e.g., one or more mass storage devices) for storing applications or data. The memory and storage medium may be, among other things, transient or persistent storage. The program stored on the storage medium may include one or more modules (not shown), each of which may include a series of instruction operations in the sample identification device. Still further, the processor may be configured to communicate with a storage medium, and execute a series of instruction operations in the storage medium on the answer sheet segmentation apparatus.
The infrared spectroscopy-based sample identification apparatus may also include one or more power supplies 40, one or more wired or wireless network interfaces 50, one or more input-output interfaces 60, and/or one or more operating systems, such as Windows Server, mac OS X, unix, linux, freeBSD, etc. Those skilled in the art will appreciate that the infrared spectroscopy-based sample identification apparatus configuration shown in fig. 4 does not constitute a limitation of the sample identification apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and which may also be a volatile computer readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the infrared spectroscopy-based sample identification method.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses, and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A sample identification method based on infrared spectroscopy is characterized by comprising the following steps:
establishing a standard spectrum library of substances based on infrared spectra of a series of standard substances, wherein each piece of spectral data in the standard spectrum library is called as a standard spectrum;
constructing a series of test samples, carrying out infrared spectrum scanning on the test samples, and extracting each piece of spectrum data of the test samples to be used as a test spectrum;
calculating the weighted correlation coefficient of the test spectrum and the standard spectrum, setting a similar interval according to the weighted correlation coefficient, and establishing an infrared spectrum identification model;
performing infrared spectrum scanning on a sample to be detected to obtain spectral data of the sample to be detected;
inputting the spectral data into the infrared spectrum recognition model to recognize the sample to be detected;
the calculating of the weighted correlation coefficient of the test spectrum and the standard spectrum comprises:
filtering the test spectrum and the standard spectrum, and calculating to obtain mathematical expectation and variance of the standard spectrum data after filtering and mathematical expectation and variance of the test spectrum data after filtering;
standardizing the standard spectrum data after filtering and the test spectrum data after filtering;
normalized standard spectral data
Wherein s is second For filtered standard spectral data, E s For mathematical expectation of filtered standard spectral data, σ s 2 E is the variance of the standard spectral data after filtering processing and is the base number of a natural logarithm function;
standardized test spectral data
Wherein, t second For the filtered test spectral data, E t For mathematical expectation of filtered standard spectral data, σ t 2 The variance of the standard spectrum data after filtering processing is obtained;
said calculation ofThe weighted correlation coefficient of the test spectrum and the standard spectrum adopts the following formula: weighted correlation coefficient
Wherein s is i Is the ith data point, t, in the normalized standard spectrum data i For the ith data point in the standardized test spectral data, a value is determined which is based on the value of the reference value>
ω i Is the weight of the ith data point, based on the sum of the weights in the previous frame and the sum of the weights in the previous frame>
And k is a custom parameter.
2. The method for identifying a sample according to claim 1, wherein the standard spectrum s of a substance is the average value of m data points corresponding to p spectral data of the same substance measured in different batches in the standard spectrum library original ，
3. The method for sample identification based on infrared spectroscopy of claim 1 wherein k is 0.01 or 0.5.
4. The method for infrared spectrum based sample identification as claimed in claim 1, wherein the test samples comprise samples of the same species in a standard spectral library and samples of species in a non-standard spectral library.
5. The method for identifying a sample according to claim 1, wherein the sample to be tested comprises drugs and explosives.
6. An infrared spectroscopy-based sample identification apparatus, the sample identification apparatus comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the sample identification device to perform the infrared spectroscopy-based sample identification method of any one of claims 1-5.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for infrared spectroscopy-based sample identification as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036604.1A CN112834451B (en) | 2021-01-12 | 2021-01-12 | Sample identification method and device based on infrared spectrum and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036604.1A CN112834451B (en) | 2021-01-12 | 2021-01-12 | Sample identification method and device based on infrared spectrum and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112834451A CN112834451A (en) | 2021-05-25 |
| CN112834451B true CN112834451B (en) | 2023-04-18 |
Family
ID=75929592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110036604.1A Active CN112834451B (en) | 2021-01-12 | 2021-01-12 | Sample identification method and device based on infrared spectrum and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112834451B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114414478B (en) * | 2021-12-21 | 2022-09-02 | 北京智创芯源科技有限公司 | Sample testing device and testing method for cadmium zinc telluride sample |
| EP4467944B1 (en) * | 2023-05-24 | 2025-02-19 | Bruker Switzerland AG | Systems and methods for identifying substances contained in a sample |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101949824A (en) * | 2009-06-30 | 2011-01-19 | 武汉矽感科技有限公司 | Method and system device for detecting commodity according to spectral information of substance |
| CN102445712B (en) * | 2011-11-22 | 2013-05-01 | 成都理工大学 | Character window weighting related spectrum matching method facing rocks and minerals |
| CN103760126B (en) * | 2013-12-16 | 2016-01-27 | 青海春天药用资源科技利用有限公司 | The Infrared spectroscopy authentication method of Cordyceps sinensis polypide |
| CN105717066B (en) * | 2016-01-29 | 2018-09-18 | 广西中烟工业有限责任公司 | A kind of near infrared spectrum identification model based on weighted correlation coefficient |
| CN108254351B (en) * | 2016-12-29 | 2023-08-01 | 同方威视技术股份有限公司 | Raman spectrum detection method for checking articles |
| CN108362662B (en) * | 2018-02-12 | 2020-01-14 | 山东大学 | Near infrared spectrum similarity calculation method and device and substance qualitative analysis system |
-
2021
- 2021-01-12 CN CN202110036604.1A patent/CN112834451B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112834451A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108362662B (en) | Near infrared spectrum similarity calculation method and device and substance qualitative analysis system | |
| CN105389593B (en) | Image object recognition methods based on SURF feature | |
| CN107092829B (en) | Malicious code detection method based on image matching | |
| WO2018121122A1 (en) | Raman spectroscopy detection method for checking goods, and electronic device | |
| CN112834451B (en) | Sample identification method and device based on infrared spectrum and storage medium | |
| CN103150498B (en) | Based on the hardware Trojan horse recognition method of single category support vector machines | |
| CN110068544A (en) | Material identification network model training method and tera-hertz spectra substance identification | |
| CN113128567A (en) | Abnormal electricity consumption behavior identification method based on electricity consumption data | |
| CN116935384B (en) | Intelligent detection method for cell abnormality sample | |
| CN108072626B (en) | Asphalt brand identification method | |
| CN108844917A (en) | A kind of Near Infrared Spectroscopy Data Analysis based on significance tests and Partial Least Squares | |
| CN117132778A (en) | Spectrum measurement correction calculation method and system | |
| CN113008805A (en) | Radix angelicae decoction piece quality prediction method based on hyperspectral imaging depth analysis | |
| CN104376325A (en) | Method for building near-infrared qualitative analysis model | |
| CN109060371A (en) | A kind of auto parts and components abnormal sound detection device | |
| CN110414549B (en) | Tea near infrared spectrum classification method for fuzzy orthogonal linear discriminant analysis | |
| CN111426657B (en) | Identification comparison method of three-dimensional fluorescence spectrogram of soluble organic matter | |
| CN118471348B (en) | Human body fluid spectrum analysis method and system based on artificial intelligence | |
| CN113310934A (en) | Method for quickly identifying milk cow milk mixed in camel milk and mixing proportion thereof | |
| CN117929356B (en) | LIBS quantitative analysis method based on Gaussian process regression | |
| CN113791062A (en) | Method for judging fixed substance type based on Raman spectrum | |
| CN118837328A (en) | Quality detection method and system for dimethylphenol monomer rectification process | |
| CN112801172A (en) | Chinese cabbage pesticide residue qualitative analysis method based on fuzzy pattern recognition | |
| CN109325551B (en) | Terahertz Spectral Identification Method Combining Radial Basis Function and Kernel Principal Component Analysis | |
| CN114997243B (en) | Identification method of Chinese herbal medicine based on ID3 decision tree algorithm and fuzzy discrimination |
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 |