Apparatus and method for measuring substance concentration based on spectrum learning

Abstract

A method for generating a concentration prediction model for predicting the concentration of a target substance by machine learning is disclosed. The method for generating a concentration prediction model includes a learning data generation step of generating an optimally transformed spectrum as learning data by transforming a basic spectrum of a substance whose concentration is known based on a predetermined transformation condition, and a concentration prediction model generation step of generating a concentration prediction model by machine learning the optimally transformed spectrum transformed based on the predetermined transformation condition generated in the learning data generation step and the actual concentrations of the substances corresponding to the optimally transformed spectrum, thereby suppressing spectral changes due to compounds other than the analyte to be predicted and maximizing spectral changes corresponding to the concentration of the analyte, thereby improving accuracy in predicting the concentration of the substance.

Description

[Technical field]

[0001] The present invention relates to a method for checking the concentration of a substance in a solution in real time, and more particularly, to a method for accurately predicting the concentration of a substance to be analyzed by learning a real-time optical analysis spectrum of a process solution in which the concentration of the substance changes based on a concentration prediction algorithm. [Background technology]

[0002] In order to obtain chemical information of a substance in a solution, a spectrum can be obtained using optical analysis methods using a spectrometer, such as infrared spectroscopy (IR), Raman spectroscopy, or ultraviolet-visible (UV-vis) spectroscopy. Based on the obtained spectrum, chemical information of the substance can be extracted and the concentration can be calculated.

[0003] In the case of analyzing the concentration of a substance using a conventional optical analysis method, it is difficult to distinguish the chemical information of the substance according to the components due to the mixed state of a wide variety of chemical substances, and it takes a long time to distinguish and analyze them, so that it is difficult to measure the concentration of the target analyte in real time. In order to solve this problem, the conventional technology predicts the concentration of the analyte by performing multivariate linear combination by using a machine learning-based multi-regression analysis, polynomial regression analysis, partial least squares (PLS) or net analyte signal (NAS) algorithm. Such a method is disclosed in Patent Document 1. However, when the relationship between the concentration of the analyte and the spectrum obtained from the spectrometer is not linear, there is a problem that the accuracy of the formation of the algorithm model and the prediction of the concentration is low. In addition, when the change in the spectrum according to the concentration of the analyte in the solution is slight, there is a problem that the learning rate of the model decreases.

[0004] Meanwhile, the concentration of an analyte can be predicted from the spectrum of the analyte using a decision tree, a random forest, a support vector machine, deep learning, etc., which are capable of performing nonlinear regression learning based on machine learning. However, these methods generate a prediction model only by adjusting learning parameters related to the spectrum, and the accuracy of predicting the concentration of a target substance is low due to the wide variety of substance information contained in the spectrum.

[0005] In order to improve this problem, Patent Document 2 attempts to predict the concentration more accurately by spectrum transformation using background signals, comparison of similarity intervals, and the like.

[0006] However, these prior art techniques predict concentrations by simply modifying the spectrum, and the spectrum pre-processing techniques for optimal concentration prediction are insufficient. In order to solve the above problems, the present invention aims to provide a method and system for predicting the concentration of an analyte, which can improve the accuracy of the concentration prediction model by performing machine learning using the modified spectrum of the substance to generate a concentration prediction model, and modifying the spectrum of the analyte and inputting it into the generated concentration prediction model.

[0007] Related prior art includes the following patent documents: [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Republic of Korea Publication Patent No. 2020-0018177 [Patent Document 2] Japanese Patent No. 6871195 Summary of the Invention [Problem to be solved by the invention]

[0009] The present invention has been devised to solve the above-mentioned problems, and its purpose is to provide a method for predicting an analyte concentration, which can improve the accuracy of concentration prediction by adding an analyte spectrum transformation algorithm to a concentration prediction model. [Means for solving the problem]

[0010] In order to achieve the above-mentioned object, the present invention provides a method for generating a concentration prediction model for predicting the concentration of a target substance by machine learning, the method including: a learning data generation step of generating, as learning data, an optimally transformed spectrum obtained by transforming a basic spectrum of a substance whose concentration is known based on predetermined transformation conditions; and a concentration prediction model generation step of performing machine learning on the optimally transformed spectrum generated in the learning data generation step, transformed based on the predetermined transformation conditions, and the optimally transformed spectrum and the actual concentrations of the substances corresponding to each of them, to generate a concentration prediction model.

[0011] The predetermined transformation condition may be an optimal transformation condition derived by a spectral transformation and combination step of transforming a basic spectrum based on two or more mutually different transformation conditions to generate a transformed spectrum, and an optimal transformation condition derivation step of deriving an optimal transformation condition from the transformed spectrum.

[0012] The optimal transformation condition derivation step may be characterized in that it calculates a standard deviation of the reference similarity of the transformed spectrum generated in the spectral transformation and combination step, a correlation coefficient with an actual concentration, and a multivariate ratio before and after the spectral transformation, and derives the transformation condition that maximizes the sum of these as the optimal transformation condition.

[0013] In addition, in order to achieve the above-mentioned object, the present invention provides a computer recording medium on which a concentration prediction model generation algorithm is recorded, the computer recording medium including: a spectrum transformation module that transforms a basic spectrum based on two or more transformation conditions to generate a transformed spectrum corresponding to the basic spectrum; an optimal transformed spectrum calculation module that calculates the standard deviation of the reference similarity of the transformed spectra based on each of the transformation conditions, the correlation coefficient with the actual concentration of the substance corresponding to each transformed spectrum, and the multivariate ratio before and after the spectral transformation, and calculates an optimal transformed spectrum transformed based on the transformation condition that maximizes the sum of these; and a machine learning module that performs machine learning on the optimal transformed spectrum and the actual concentration of the substance corresponding to the optimal transformed spectrum as learning data to generate a concentration prediction model.

[0014] Furthermore, in order to achieve the above-mentioned object, the present invention provides a concentration prediction method for predicting the concentration of an analyte, comprising: a predicted spectrum acquisition step of acquiring a predicted spectrum of a substance whose concentration is to be predicted; an optimally modified predicted spectrum generation step of transforming the acquired predicted spectrum under optimal transformation conditions to generate an optimally modified predicted spectrum; and a predicted concentration output step of inputting the optimally modified predicted spectrum into a concentration prediction model and outputting a predicted concentration value, wherein the optimal transformation conditions are transformation conditions derived by a spectrum transformation and combination step of transforming a basic spectrum of a predetermined substance, the actual measured concentration value of which is known, based on two or more mutually different transformation conditions to generate a modified spectrum, and an optimal transformation condition derivation step of deriving optimal transformation conditions from the generated modified spectrum, and wherein the concentration prediction model is a neural network or a concentration prediction algorithm trained to calculate a predicted concentration value from the optimally modified spectrum by machine learning an optimally modified spectrum obtained by transforming the basic spectrum under the optimal transformation conditions and a corresponding actual measured concentration value.

[0015] The optimal transformation condition derivation step may be characterized in that it calculates a standard deviation of the reference similarity of the transformed spectrum generated in the spectral transformation and combination step, a correlation coefficient with an actual concentration, and a multivariate ratio before and after the spectral transformation, and derives the transformation condition that maximizes the sum of these as the optimal transformation condition.

[0016] Furthermore, in order to achieve the above-mentioned object, the present invention provides a concentration prediction system for predicting the concentration of an analyte, comprising: a spectral data acquisition unit that acquires a basic spectrum of a substance for generating learning data, or a predicted spectrum, which is the spectrum of a substance whose concentration is to be measured; a substance concentration data acquisition unit that acquires already acquired concentration data of the substance and an actual concentration of the substance to be measured using a known concentration measuring device; a calculation and control unit that generates modified spectra of the basic spectrum and the predicted spectrum, calculates optimal modification conditions, performs machine learning, and generates a concentration prediction model; and a memory that stores the basic spectrum of the analyte acquired in the spectral data acquisition unit, the actual substance concentration value acquired in the substance concentration data acquisition unit, and the concentration prediction model generated in the calculation and control unit.

[0017] The calculation and control device may be characterized in that it transforms and combines the spectra acquired in the spectral data acquisition unit based on a spectral transformation algorithm, derives from the transformed spectra a transformed spectrum that indicates an optimal accuracy of concentration prediction as an optimal transformed spectrum, performs machine learning using the optimal transformed spectrum and the actual measured concentration of the corresponding substance as learning data to generate a concentration prediction model, and inputs the predicted spectrum into the generated concentration prediction model to predict the concentration.

[0018] The memory may include a spectrum transformation and combination module that transforms the spectrum acquired in the spectrum acquisition unit based on transformation conditions, an optimal spectrum derivation module that acquires an optimal spectrum from the transformed spectra that indicates an optimal accuracy of concentration prediction and derives optimal transformation conditions, a machine learning module that utilizes the optimal transformed spectrum and the measured substance concentrations as learning data to advance machine learning and generate a concentration prediction model, and a concentration prediction module that calculates a concentration prediction value using the predicted spectrum as input data.

[0019] Furthermore, in order to achieve the above-mentioned object, the present invention provides a computer recording medium having recorded thereon a concentration prediction algorithm comprising: a spectrum transformation module that transforms a predicted spectrum of a substance whose concentration is to be predicted to generate a transformed spectrum; an optimal spectrum derivation module that calls the spectrum transformation module and calculates an optimal transformed predicted spectrum by transforming the predicted spectrum based on optimal transformation conditions; and a concentration prediction module that receives an input of the optimal transformed predicted spectrum and calculates a predicted concentration value, wherein the concentration prediction module is generated by machine learning based on the spectrum transformed based on the optimal transformation conditions and the actual concentration of the corresponding substance.

[0020] Furthermore, in order to achieve the above-mentioned object, the present invention provides a concentration measuring device for predicting the concentration of an analyte, comprising: a spectral data acquisition unit for acquiring a predicted spectrum, which is the spectrum of the analyte; a memory device equipped with a spectral transformation module for transforming the predicted spectrum based on optimal transformation conditions and a concentration prediction module for calculating a predicted concentration value from an optimally transformed predicted spectrum obtained by transforming the predicted spectrum based on the optimal transformation conditions; and an arithmetic and control device for reading the concentration prediction module equipped in the memory device and controlling it to calculate the predicted concentration value from the predicted spectrum whose concentration is to be predicted.

[0021] The concentration measuring instrument may be provided with a data connection unit for connecting an external memory device and receiving input and output of data from an external device, and the memory device may be connected to the data connection unit in a removable form.

[0022] The concentration measuring instrument may include a data connection unit for connecting an external memory device and receiving input and output of data from the external device, and the memory device may receive and store a spectrum transformation module that transforms the predicted spectrum based on optimal transformation conditions and a concentration prediction module that calculates a predicted concentration value from an optimally transformed predicted spectrum obtained by transforming the predicted spectrum based on the optimal transformation conditions from the external device via the data connection unit.

[0023] The data connection unit may be configured integrally with the spectral data acquisition unit. Effect of the Invention

[0024] The present invention can improve the accuracy of a concentration prediction model by performing machine learning on a modified spectrum of a substance to generate a concentration prediction model, and by modifying the spectrum of an analyte and inputting it into the generated concentration prediction model.

[0025] Furthermore, the present invention derives an optimal transformation method (transformation conditions) from among various transformation methods when transforming a spectrum, generates a concentration prediction model from a transformed spectrum transformed using the derived optimal transformation method (transformation conditions), and uses this to predict concentrations, thereby improving the accuracy of predicting substance concentrations. [Brief description of the drawings]

[0026] [Figure 1] FIG. 1 illustrates a concentration prediction system and device for predicting the concentration of an analyte of the present invention. [Diagram 2] 1 is a block diagram of a concentration measuring device according to an embodiment of the present invention. [Diagram 3]1 is a spectrum transformation method using an inverse transformation method according to an embodiment of the present invention. [Figure 4] 2 is a diagram illustrating a spectrum transformation method using a filtering transformation method according to an embodiment of the present invention; [Diagram 5] 1 is a spectrum modification method using a baseline removal modification scheme according to an embodiment of the present invention; [Figure 6] 2 is a diagram showing a spectrum transformation method using an interval averaging transformation method according to an embodiment of the present invention; [Figure 7] 2 is a diagram showing a spectrum transformation method using an interval elimination transformation method according to an embodiment of the present invention; [Figure 8] FIG. 2 is a flow chart showing a concentration prediction method of the present invention for generating a concentration prediction model and predicting the concentration of an analyte. [Figure 9] 1 is a graph showing the mean square error based on the optimal spectrum transformation conditions of the present invention. [Figure 10] 1 is a graph showing the concentration prediction results of a conventional concentration prediction method. [Figure 11] 1 is a graph showing a concentration prediction result of the concentration prediction method of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0027] Hereinafter, the embodiments of the present invention will be described in detail with reference to the accompanying drawings so that a person having ordinary skill in the art to which the present invention pertains can easily carry out the present invention. However, the present invention can be embodied in various different forms and is not limited to the embodiments described herein. In the drawings, in order to clearly explain the present invention, parts that are not related to the description are omitted, and similar parts are denoted by similar reference numerals throughout the specification.

[0028] The present invention will now be described in detail with reference to the accompanying drawings.

[0029] The present invention relates to a method for predicting an analyte concentration.

[0030] More specifically, the present invention relates to a system and method for predicting the concentration of a substance with improved accuracy by adding a spectral transformation algorithm to a substance concentration prediction model.

[0031] 1. Creation of concentration prediction model and concentration prediction method of the present invention

[0032] The concentration prediction model of the present invention is generated by machine learning to transform the spectrum of a substance whose concentration is known or whose concentration can be experimentally measured, either by obtaining the concentration from a device capable of obtaining the spectrum of the substance, such as a known spectrometer, and to learn the transformed spectrum to predict the concentration value.

[0033] 1.1. Training data generation step

[0034] The present invention uses, as learning data, a transformed spectrum obtained by transforming the spectrum of the above-mentioned substance whose concentration is known and the actual measured concentration of the substance. Furthermore, in order to generate an optimal prediction model, the present invention finds optimal spectrum transformation conditions that generate an optimal prediction model from among various spectrum transformation methods and spectrum transformation conditions resulting from combinations of these, and uses, as learning data, the transformed spectrum data transformed under the optimal spectrum transformation conditions and the actual measured concentration of the substance.

[0035] 1.1.1. Step of Acquiring Fundamental Spectral Si Data (S10)

[0036] In the present invention, the i fundamental spectra to be used as training data are denoted as Si. In the present invention, the fundamental spectra refer to the initial spectral data acquired using a known spectrometer or the like. In the present invention, the i acquired spectra S are denoted as S1, S2, ..., Si.

[0037] 1.1.2. Measured substance concentration LC i Data acquisition step (S20)

[0038] The actual concentration data LCi of the substance corresponding to each of the fundamental spectra described above is obtained. When a fundamental spectrum Si is obtained for a substance whose concentration is already known, the concentration data LCi of each substance may be a value obtained by experimentally measuring the concentration of the substance whose fundamental spectrum has been obtained using a known concentration measuring device linked to the concentration measuring system of the present invention, using the known substance concentration data.

[0039] 1.1.3. Step of obtaining optimal deformation spectrum MoSi (S30)

[0040] The modified spectrum used as the learning data of the present invention is a spectrum obtained by modifying the above-mentioned basic spectrum based on the modification conditions described below.

[0041] In the present invention, for the purpose of explanation, k types of spectral transformation conditions can be set according to the transformation conditions and their combinations described below, and the first, second, ..., kth transformation conditions are denoted as M1, M2, ..., Mk, respectively, and the optimal transformation condition for generating the optimal concentration prediction model is denoted as Mo.

[0042] It should be obvious to any ordinary engineer that the spectrum transformed under each transformation condition can be expressed as M1S1, M1S2, ... M1Si when the basic spectrum (Si, i = 1, 2, ..., n) is transformed under transformation condition M1, and the spectrum transformed under transformation condition Mk can be expressed as MkSi (k = 1, 2, ..., n, i = 1, 2, ..., M).

[0043] In the present invention, of these modified spectra MkSi, the modified spectrum MoSi, which is modified under Mo, which is the optimum modification condition showing the optimum accuracy of concentration prediction, is used as learning data.

[0044] (1) Spectral transformation and combination step

[0045] This is a step of modifying and combining the fundamental spectrum Si based on a wide variety of modification conditions in order to derive the optimal modification condition.

[0046] The following are examples of the five basic spectral transformation conditions used in the present invention. In the present invention, if any one of the following five transformation methods can be used, at least two or more of them can be selectively combined and used as the spectral transformation conditions, but the present invention is not limited to these five methods and their combinations, and any spectral transformation conditions and their combinations known before the filing date of the present invention can be used as the spectral transformation conditions.

[0047] (i) Transformation condition 1: Inverse transformation

[0048] FIG. 3 shows a spectrum transformation method using the inverse transformation method according to an embodiment of the present invention. The inverse transformation refers to a transformation in which the data values ​​of the acquired spectrum are inversely transformed. For example, the intensity of the spectrum is transformed into the inverse x Then, the intensity of the spectrum represented by the inverse transformation can be transformed to: where R is a variable that removes large deviations from the spectrum, so that the deviations of the data of the obtained inverse transformation spectrum do not appear larger than a certain level.

[0049] (ii) Transformation condition 2: Filtering transformation

[0050] 4 shows a spectrum modification method using a filtering modification method according to an embodiment of the present invention. Filtering modification refers to a modification in which a part of the acquired spectrum is selectively blocked and the rest is transmitted. By filtering out peaks in the spectrum that are unrelated to the analyte, the relationship between the actual analyte and the acquired spectrum can be improved.

[0051] (iii) Transformation condition 3: Baseline removal transformation

[0052] FIG. 5 shows a spectrum modification method of the baseline removal modification method according to an embodiment of the present invention. When a spectrum is acquired using a spectrometer, the spectrum data cannot have an ideal baseline due to noise caused by the characteristics of the system and variations in the measured substance sample. Therefore, the relationship between the concentration of the measured substance and the spectrum can be improved by removing the baseline to remove the influence of baseline movement from the spectrum data. In the case of baseline removal modification, the similarity of data between spectra may increase, so that the use of the baseline removal modification can be determined according to the type of measured substance or the analysis method.

[0053] (iv) Transformation condition 4: Interval averaging transformation

[0054] 6 shows a spectrum modification method using the interval averaging modification method according to an embodiment of the present invention. The interval averaging modification refers to a modification in which data values ​​in a predetermined interval are averaged in an acquired spectrum. In this case, not only the spectral data in the predetermined interval but also all variables are averaged. The interval averaging modification can also remove noise peaks caused by the noise of the spectrometer system to improve the relationship between the measured substance concentration and the spectrum.

[0055] (v) Transformation condition 5: Interval removal transformation

[0056] 7 shows a spectrum transformation method using an interval elimination transformation method according to an embodiment of the present invention. The interval elimination transformation refers to a transformation in which data values ​​in a predetermined interval are deleted from an acquired spectrum. When peaks or data in a spectrum include peaks or data that are unrelated to an analyte to be measured, the relationship between the concentration of the analyte in the entire interval and the spectrum can be improved by performing the interval elimination transformation.

[0057] (2) Derivation of the optimal deformation condition Mo

[0058] This is the step of deriving the optimal deformation conditions according to the procedure described below.

[0059] The inventors of the present invention discovered that an optimal prediction model is generated when the optimal transformation conditions are set to those that maximize the standard deviation (Ak) of the reference similarity of the transformed spectra (M1Si, M2S2, ..., MkSi) transformed under each transformation condition, the correlation coefficient with concentration (Bk), and the function value of the multivariate ratio (Ck), and applied this to the present invention.

[0060] In particular, the optimal transformation condition was set to the transformation condition that maximizes the value of Fk(Ak,Bk,Ck)=aAk+bBk+cCk, which is expressed as a linear function of the Ak,Bk,Ck values. Here, when transformation is performed under transformation condition M1, the linear function is expressed as F1(A1,B1,C1), where a, b, and c are constant values ​​set by the user and can be omitted.

[0061] That is, in the present invention, the optimal transformation condition means deriving k for which Fk(Ak, Bk, Ck) is maximized, and the value Fo(Ao, Bo, Co) = Ao + Ao + Co for a spectrum transformed under the optimal transformation condition Mo is the maximum value among the Fk (k = 1, 2, ..., n) values.

[0062] Preferably, in the present invention, the optimal transformation condition means deriving k at which Fk(Ak, Bk, Ck) is maximized, and the Fo(Ao, Bo, Co)=aAo+bAo+cCo value for a spectrum transformed under the optimal transformation condition Mo is the maximum value among the Fk(k=1, 2, ..., n) values, and in this case, the constant values ​​a, b, and c may be values ​​selected from the ranges of 6.5 to 7.7, 0.5 to 2.0, and 2.5 to 4.0, and more preferably, a, b, and c may be selected as 6.69, 1.52, and 3.59, respectively.

[0063] For example, in the spectrum optimal transformation condition derivation unit of the present invention, i spectra Si acquired as learning data are transformed using the above-mentioned transformation conditions 1 to 10, respectively, and the Fk value is calculated for the combined k types of transformed spectra, and the kth transformation condition Mk showing the largest Fk is derived as the optimal transformation condition Mo.

[0064] In the following, the standard deviation of the reference similarity of the deformed spectrum (Ak), the correlation coefficient with the concentration (Bk), and the multivariate ratio (Ck) will be explained.

[0065] (i) Standard deviation of the baseline similarity (A)

[0066] In order to derive the optimum spectrum transformation conditions, the standard deviation of the reference similarity between the reference spectrum and each transformed spectrum, which is transformed according to the above spectrum transformation methods or a combination thereof and has different transformation conditions, is calculated.

[0067] Here, the reference spectrum is a linear spectrum with an intensity of K (a constant other than 0) in all wavelength bands. Therefore, the standard deviation of the reference similarity is calculated by calculating the standard deviation of the reference similarity between all the transformed spectra and the reference spectrum. For example, if there are 10 samples of the basic spectrum before transformation (S1, S2, ..., S 10 ), and there are 10 types of transformation combination methods (M1, M2, …, M 10 ), we get 100 transformed spectra (M1S 1, …,M1S 10 ,M2S1,…,M2S 10 ,…M 10 S 10 ) is generated, and 100 reference similarities can be calculated based on the reference spectrum.

[0068] A reference similarity of the transformed spectrum based on each of the transformation conditions is calculated.

[0069] For example, the standard deviation (A1) of the reference similarity is calculated for a transformed spectrum M1Si transformed based on the transformation condition M1, and the standard deviation (Ak) of the reference similarity is calculated for a transformed spectrum M2Si, ..., MkSi transformed based on the transformation conditions M2, ..., Mk in the same manner.

[0070] The standard deviation of the reference similarity is obtained by calculating the cosine similarity of the transformed spectrum with different transformation conditions compared to the reference spectrum, and the cosine similarity indicates the similarity that can be obtained using a linear reference spectrum and a transformed spectrum, i.e., the cosine angle between the two spectra, and it can be determined that the closer the value is to 1, the higher the similarity. The reference similarity is calculated according to the following Equation 1.

[0071]

number

[0072] In the above formula 1, α denotes the combined intensity of the combined transformed spectra, and β denotes the combined intensity of the reference spectra, which is an adjustable constant having a constant value for all multivariates.

[0073] According to the above Equation 1, the reference similarity value between the modified spectrum and the reference spectrum based on each modification condition is calculated, and the standard deviation of the reference similarity is the result value (Ak) of calculating the standard deviation between the reference similarities. In another embodiment, when the number of modified spectra is greater than a predetermined standard, the result value (Ak) of dividing the standard deviation between the similarities by the average similarity is calculated.

number

[0074] Therefore, the standard deviation A of the reference similarity calculated in the present invention is a value that allows the degree of difference between each of the deformed spectra to be analogized, and allows the shape difference between the deformed spectra to be sensitively recognized.

[0075] Deformed spectrum M1S deformed under deformation condition M1 i Let A1 be the standard deviation of the reference similarity for the deformation spectra M1S1, M1S2, …, M1S i of

number

[0076] It is calculated as:

[0077] In this way, the deformation condition M k The deformed spectrum M k S i Calculate the standard deviation (Ak) of the reference similarity for

[0078] (ii) Correlation coefficient with substance concentration (B)

[0079] The relationship with the substance concentration means a normalized value (B) obtained by normalizing the covariance value indicating the relationship between the reference similarity of the spectrum and the corresponding actual substance concentration (actually measured concentration LCi) to a maximum value of 1. The value obtained by normalizing the covariance value to a maximum value of 1 is the same as the correlation coefficient of covariance, which is characterized by having a range from -1 to +1, so the result value is the same even if the correlation coefficient of covariance is used for calculation. In other words, the calculation of the relationship with the target substance concentration can estimate the relationship between the shape of the deformed spectrum and the corresponding substance concentration using B.

[0080] The normalized value of covariance or the correlation coefficient of covariance is calculated according to the following Equation 2, and the resulting values ​​are all in the range of -1 or more and +1 or less.

[0081]

number

[0082] In the above Equation 2, X represents the reference similarity and Y represents the actual substance concentration of the analyte.

[0083] Furthermore, Cov(X,Y) denotes the covariance value between the reference similarity (X) and the corresponding concentration of the analyte (Y), and Var(X) and Var(Y) denote the variance values ​​between the reference similarity (X) and the corresponding concentration of the analyte (Y).

[0084] In the above, the actual concentration of a substance means the actual concentration of a substance measured by oneself through an experiment or other method, or the actual concentration of a known substance. This process is a process of reflecting the relationship between the concentration of an actual substance and the deformation spectrum as a learning element.

[0085] The LCi value, which is the actual concentration value of the spectrum-corresponding substance previously acquired as learning data, is input as the Y value in the above formula 2. As the X value, the previously calculated reference similarity value is input.

[0086] The normalized value (Bk) of the covariance value calculated according to the above formula is calculated according to the combination of the modified spectrum. For example, in the modified combination method M k A reference similarity is calculated for the transformed spectrum M1Si, and a normalized value (Bk) of the covariance value is calculated based on the actual concentration value LCi of the corresponding substance.

[0087] (iii) Multivariate ratios before and after spectral transformation (C)

[0088] In the present invention, a multivariate ratio (C) is calculated as another variable of the optimal spectrum transformation condition. The multivariate ratio is

number

[0089] The number of multivariates in the present invention means the number of data acquired in a predetermined wavelength band corresponding to the X-axis of the acquired spectrum. For example, if a spectrum in a wavelength band of 1000 nm to 3000 nm is acquired in increments of 1 nm in a spectrometer, the number of multivariates at this time is (3000-1000), which is 2000. If the spectrum of 1000-1500 nm is removed using the interval removal transformation among the transformation methods, the number of multivariates after transformation is (3000-1500), which is a total of 1500 multivariates. As another example, when an interval averaging transformation is performed, the number of multivariates is reduced to the number of set intervals.

[0090] Using this method, the number of multivariates after spectral transformation compared to the number of multivariates before spectral transformation can be calculated to obtain a C value, where C can be used to estimate the degrees of freedom for the number of variables after spectral transformation when learning about spectral transformation using an ML model.

[0091] The multivariate ratio (Ck) calculated according to the above formula varies depending on the data values ​​before and after the spectrum transformation, and therefore indicates a representative value of the degree of freedom for the data values ​​due to the spectrum transformation.

[0092] (3) Calculation of optimal deformation spectrum MoSi data

[0093] After determining Mo, which is the transformation condition that maximizes Fk(Ak, Bk, Ck) for the i*k transformed spectra MkSi using the above-mentioned method, the basic spectrum Si is transformed using the transformation condition Mo to calculate optimal transformed spectrum MoSi data. The optimal transformed spectrum MoSi data may be the transformed spectrum MoSi data with k=o previously generated in the calculation process of Fk(Ak, Bk, Ck) as is.

[0094] 1.2. Machine learning and concentration prediction model generation step (S40)

[0095] In the present invention, a concentration prediction model is generated by machine learning the optimal transformed spectrum MoSi obtained by transforming the above-mentioned fundamental spectrum Si under the optimal transformation condition Mo and the measured concentrations LCi of the corresponding substances as learning data.

[0096] The neural network and learning model used to train the concentration prediction model generated in the present invention are not limited to one specific type, and any neural network and learning model that generates a concentration prediction model from publicly known spectral data may be used.

[0097] In this way, the concentration prediction model generated by learning using the optimal deformed spectrum MoSi is used to predict concentration in a concentration prediction step described later.

[0098] 1.3. Concentration prediction step

[0099] The concentration of a new substance is predicted using the generated concentration prediction model. The concentration prediction includes an acquisition step of a predicted spectrum PS, an optimally transformed predicted spectrum generation step of transforming the acquired predicted spectrum under the above-mentioned optimal transformation condition to generate an optimally transformed predicted spectrum P.MoS, and an optimally transformed predicted spectrum P.MoS data is input to the generated concentration prediction model to output a predicted concentration value PLC.

[0100] (1) Step of obtaining predicted spectrum PS (P10)

[0101] This is a step in which the spectrum of the substance whose concentration is to be predicted is acquired by the spectrum acquisition unit.

[0102] (2) Generation step of optimal deformation prediction spectrum P.MoS (P20)

[0103] This is a step of modifying the predicted spectrum under the above-mentioned optimum modification conditions to generate an optimally modified predicted spectrum.

[0104] (3) Predicted concentration PLC output step (P30)

[0105] This is a step in which the above-mentioned optimal deformation predicted spectrum is input to a concentration prediction model generated by machine learning using the above-mentioned optimal deformation spectrum set, and the concentration predicted value PLC, which is the output, is obtained.

[0106] <Verification of the performance of the prediction model based on the detection of the optimal deformation condition of the present invention>

[0107] Figure 9 shows the mean squared error based on the spectral transformation conditions. The graph shows the log(MSE mean) based on F(A,B,C). -1 where MSE stands for Mean Square Error. In FIG. 9, the higher F(A,B,C), the higher the log(MSE average). -1 It can be seen that the mean square error tends to be high. The lower the mean square error, the smaller the difference in the concentration prediction value using the ML model, and therefore the higher the accuracy of the generated ML model. That is, the lower the MSE average, the more favorable it is to generate a ML model with high accuracy using the spectral transformation.

[0108] 10 and 11 are graphs showing the results of prediction of concentration by the conventional concentration prediction method and the present invention, respectively. Fig. 10 shows the results of verification for a model in which deep neural network (DNN) learning was performed without performing spectral transformation according to the conventional technology, and Fig. 11 shows the results of verification for a model in which optimal spectral transformation was performed according to the present invention and DNN learning was performed.

[0109] In the present invention, the data used for generating and verifying the learning model was a model for predicting the concentration of glucose used as a substrate from the real-time spectrum of the process solution in the culture vessel, and the prediction and results were verified. In this verification, the Fo(Ao,Bo,Co)=aAo+bAo+cCo value for the spectrum transformed under the optimal transformation condition Mo was the maximum value among the Fk (k=1,2,...,n) values, and a, b, and c were applied as 6.69, 1.52, and 3.59, respectively.

[0110] R 2 The line drawn with indicates the regression coefficient of determination, the higher its value, the better the predictive results of the model.

[0111] In order to evaluate the trained and generated concentration prediction ML model, data is excluded in advance so as not to be used in the training and generation of the concentration prediction ML model, and the performance of the model is tested using this excluded data, which is called validation data. In the graph, the fimse shown by green dots indicates the result of evaluating the mean squared error based on the validation data not used in the training and generation of the ML model. In addition, in the graph, the mmse shown by black dots indicates the result of evaluating the mean squared error (MSE) based on the training data used in the training and generation of the ML model, and the pmse shown by red dots indicates the result of evaluating the mean squared error based on the input data not used in the training and formation of the ML model.

[0112] The accuracy of concentration prediction of the ML model generated using the optimal spectrum transformation process of the present invention in FIG. 11 is higher than that of the conventional technique in FIG. 2 It can be seen that the values ​​are higher and that the pmse and fimse point data are also more precisely and accurately distributed above the predicted validation line.

[0113] 2. Substance concentration prediction system 100 according to the present invention

[0114] FIG. 1 is a diagram showing a substance concentration prediction system 100 according to the present invention.

[0115] 1, the present invention is based on a spectrometer for an optical analysis method, and the spectrometer is used to obtain spectra of a substance whose concentration is known and a substance whose concentration is to be predicted, and the obtained spectra are analyzed to output a concentration value of the substance. In addition, the detected spectra and the concentration value of the analyte are applied as learning data for a concentration prediction model, and the optimal transformation condition of the spectrum for more accurate concentration prediction is derived using the concentration prediction model, and the concentration prediction model transforms the spectrum according to the optimal transformation condition to predict the concentration of the analyte to be predicted.

[0116] In FIG. 1, the data flow indicated by solid lines indicates the data flow used to generate a concentration prediction model, and the data flow indicated by dotted lines indicates the data flow associated with the procedure of predicting the concentration of a substance using the generated concentration prediction model.

[0117] The substance concentration prediction system 100 of the present invention comprises a spectrum data acquisition section 10, a concentration data acquisition section 20, a calculation section 30, and a memory 40. Each of the components will be described below.

[0118] 2.1. Spectral data acquisition unit 10

[0119] The spectrum acquisition unit may be a known spectrometer or spectrometer for optical analysis. The spectrum of the analyte whose concentration is to be measured is acquired using the spectrometer, and the acquired spectrum can be calculated as the concentration value of the analyte by using an analysis method according to the type of spectrometer.

[0120] The spectrum acquisition unit of the present invention acquires a basic spectrum Si for learning data and a predicted spectrum PSi for predicting a concentration. The spectrum acquisition unit 10 can acquire a basic spectrum or a predicted spectrum from an external device such as a spectrometer, an external spectrum generating device, a memory 40, etc., and may include a data connection unit 11 for connecting data.

[0121] (1) Acquisition of the fundamental spectrum Si

[0122] The spectrum data acquisition unit 10 acquires fundamental spectra from a spectroscope of a substance whose concentration is known, and uses the acquired fundamental spectrum set as learning data. In the present invention, the acquired i spectra S are denoted as S1, S2, ..., S i The basic spectrum is the basis for generating a transformed spectrum MSi to be used as learning data in the machine learning module 43 described later.

[0123] The fundamental spectrum S i may be stored in advance in the memory in the form of already acquired spectrum data. In this case, the spectrum acquisition unit acquires the fundamental spectrum S i from the memory.

[0124] (2) Obtaining predicted spectrum PSi

[0125] The spectral data acquisition unit 10 also acquires a predicted spectrum PSi of the substance to be used as an input of the generated concentration prediction model to predict the concentration. The acquired predicted spectrum data is transformed into a predicted optimally transformed spectrum PMoSi based on the optimal transformation conditions, and is input to the concentration prediction model generated according to the above-mentioned procedure to be used for predicting the concentration of the substance.

[0126] 2.2. Substance concentration LCi data acquisition unit 20

[0127] This is a component that acquires the concentration data LCi of the substance corresponding to each of the fundamental spectra described above. In the case of a concentration of a known substance, the concentration data LCi is stored in a memory and can be acquired by reading the memory in the substance concentration LCi data acquisition unit 20. Alternatively, the concentration data LCi of the substance corresponding to the fundamental spectrum is acquired by measuring the concentration using a known concentration measuring device (not shown) that is linked to the concentration measurement system of the present invention or by measuring experimentally.

[0128] The concentration data acquisition unit 20 can acquire known or experimentally measured concentration data from an external concentration measuring device, an external experimental data storage, memory 40, etc., and may be equipped with a data connection unit 21 for connecting the data.

[0129] 2.3. Calculation and Control Unit 30

[0130] The calculation and control device 30 of the present invention may be a single CPU or microprocessor, or a terminal device, computer device, computer server, or the like that is equipped with the same.

[0131] The calculation and control device 30 controls the overall operation of the system, acquires and stores data, performs machine learning and generates concentration prediction models, and manages the concentration prediction models generated as a result of the machine learning.

[0132] The calculation and control device 30 also controls the transformation of the spectrum in the present invention, the derivation of optimal transformation conditions using the transformed spectrum, the generation of a transformed spectrum based on the optimal transformation conditions, and the learning of a concentration prediction model utilizing the transformed spectrum, as well as the generation of a concentration prediction model.

[0133] The calculation and control device of the present invention can utilize a computer program that controls each function stored in a memory when performing these operations, stores the generated concentration prediction model in the memory, and when performing a concentration prediction, reads the concentration prediction model from the memory again to perform the prediction calculation. It will be easily understood by those skilled in the art that the computer programs that perform each of these functions are stored as separate modules in a memory device described later, and that when the calculation and control device is needed, these can be read from the memory to perform the function of each module.

[0134] Each operation performed by the arithmetic and control device of the present invention will now be described.

[0135] (1) Spectral transformation and combination

[0136] The fundamental spectrum Si acquired by the spectrum acquisition unit is transformed and combined to generate a transformed spectrum MkSi. This operation is as described above in Section 1.1.3. In performing this procedure, the arithmetic and control device can load a spectrum transformation and combination module or transformation algorithm stored in the memory in the form of software / program.

[0137] In the present invention, the spectral transformation and combination procedure may be configured as a separate spectral transformation and combination unit to perform the spectral transformation and combination procedure based on a spectral transformation algorithm by a microprocessor or the like configured as a separate module in the arithmetic and control device.

[0138] (2) Derivation of the optimal deformation spectrum

[0139] The optimal deformation conditions are derived from the above-mentioned deformation spectrum MkSi. The specific procedure for deriving the optimal deformation conditions is as explained in Section 1.1.3., and can be performed by loading the optimal spectrum derivation module installed in the form of software / program in the memory described later.

[0140] (i) The optimal transformed spectrum used as learning data to generate a concentration prediction model is calculated by determining optimal transformation conditions from a transformed spectrum for the basic spectrum S and transforming the basic spectrum S under the optimal transformation conditions, or by selecting a transformed spectrum that matches the optimal transformation conditions from among the transformed spectra already generated. The derived optimal transformed spectrum is used as input data for machine learning, which will be described later.

[0141] The derived optimal deformation condition Mo may be stored in a memory for future use.

[0142] (ii) When a concentration is to be predicted, the calculation and control device transforms the predicted spectrum PSi of the target substance using the previously calculated optimal transformation conditions Mo to generate an optimal transformed predicted spectrum MoPSi. The optimal transformed predicted spectrum MoPSi is input to a concentration prediction module 44 to calculate a concentration prediction value PLC.

[0143] In another embodiment of the present invention, the spectrum transformation and combination unit may be separately configured using a separate microprocessor or the like to perform the procedure for deriving the optimal transformed spectrum.

[0144] (3) Machine learning and generation of concentration prediction model

[0145] As described above in Section 1.2, the control and calculation unit of the present invention performs machine learning using the optimal transformed spectrum MoSi obtained by transforming the fundamental spectrum Si under the optimal transformation condition Mo and the corresponding actual measured concentrations LCi of the substances as learning data to generate a concentration prediction model. The generated concentration prediction model may be stored in a memory in the form of a software program or an algorithm.

[0146] (4) Concentration prediction

[0147] The previously generated optimal deformation prediction spectrum MoPSi is input to the generated concentration prediction model to calculate the concentration prediction value PLC.

[0148] Memory Device 40

[0149] The memory device 40 in the concentration prediction system of the present invention can be used as a data storage for storing in advance concentration value data LCi of substances whose concentrations are known and used as training data, and their basic spectra Si, and is equipped with the following computer software modules in the form of computer programs / software to perform the various functions of the system of the present invention. The memory device 40 also stores the optimal transformation conditions Mo calculated in the control and calculation unit.

[0150] Meanwhile, the concentration prediction system of the present invention may be configured by installing each of the following software modules, and each module may be configured by separating them into separate memory locations. The memory device 40 in the present invention is not necessarily limited to one physical memory location.

[0151] In addition, the memory of the present invention may be replaced by a memory device of a computer system, a server system, etc., or may be realized as a removable memory device having a separate CD, hard disk, USB, etc. that contains each program module or each software algorithm described below.

[0152] Each "module" described below may refer to a series of computer software algorithms configured to perform a given function.

[0153] (1) Spectral Transformation and Combination Module 41

[0154] The memory of the present invention stores each transformation method and computer software module or transformation algorithm for performing the step of transforming and combining spectra (1) described in the step of obtaining the optimal transformed spectrum in Section 1.1.3 above.

[0155] (2) Optimal spectrum derivation module 42

[0156] The memory of the present invention is equipped with a computer software module that performs the (2) optimal transformation condition derivation step described in the optimal transformed spectrum acquisition step in Section 1.1.3 above, and calls the spectral transformation and combination module to calculate the optimal transformed spectrum based on the optimal transformation conditions.

[0157] (3) Machine Learning Module 43

[0158] The memory of the present invention is equipped with a computer software module that serves as a machine learning module that calculates (3) the optimal deformed spectral data described in the optimal deformed spectrum acquisition step in Section 1.1.3 above, uses this as learning data together with the concentration value data LCi of substances with known concentrations, and proceeds with the machine learning process described in Section 1.2 above to generate a concentration prediction model.

[0159] (4) Concentration Prediction Module 44

[0160] A computer software module is installed that executes the concentration prediction model generated by the machine learning module 43 described above.

[0161] When predicting the concentration of a specified substance, the calculation and control device 30 inputs the predicted spectrum PSi of the substance whose concentration is to be predicted as input data, and inputs its modified spectrum, that is, the optimal modified predicted spectrum PMoSi, into the concentration prediction module 44 of the prediction memory, and the concentration prediction module 44 calculates the concentration prediction value PLCi.

[0162] The concentration measurement system of the present invention may be configured to change and set the optimal transformation conditions so as to correspond to the optimal transformation conditions that are set differently depending on the type of substance to be measured. The calculation and control device 30 receives the input of the predetermined optimal transformation conditions determined by the selection input displayed on the screen display unit (not shown) of the system or the selection input input from a physical switch (not shown), calls up the corresponding spectrum transformation module from the memory 40 to transform the spectrum, and inputs it again into the concentration prediction model called up from the memory 40 to output the predicted concentration value. In this case, it will be obvious to those skilled in the art that the memory 40 can generate and store concentration prediction modules 44 corresponding to a number of concentration prediction models each corresponding to a specific optimal transformation condition according to the above-mentioned concentration prediction model generation method.

[0163] 3. Concentration measuring device according to the present invention

[0164] Taking FIG. 2 as an example, a concentration measuring device equipped with a concentration prediction module 44 created based on the technical concept of the present invention will be described.

[0165] The concentration measuring device of the present invention is equipped with the spectrum data acquiring unit 10 described in the previous two sections, the calculation and control device 30, and the memory device 40. Each component can be configured differently from the concentration measuring system described in the previous two sections, which will be described in detail below.

[0166] (1) Spectral data acquisition unit 10

[0167] The spectral data acquisition unit 10 of the concentration measuring instrument of the present invention acquires predicted spectral data PSi of a target substance. The input includes data output by a known spectrometer, spectroscope, optical sensor, etc. that outputs spectral data of a substance whose concentration is to be measured by contact or non-contact.

[0168] (2) Memory device 40

[0169] The memory device 40 of the concentration measuring device of the present invention is equipped with the (1) spectrum transformation and combination module mounted in the memory device 40 described in Section 2.4, the (4) concentration prediction module 44 based on the derived optimal transformation condition Mo and the already learned optimal transformed spectrum.

[0170] Depending on the application, the memory device 40 of the concentration measuring instrument may be configured to include only a spectral transformation module based on the already calculated optimal transformation conditions among the spectral transformation and combination modules, and in this case, the concentration prediction module 44 installed is similarly a concentration prediction module 44 that has already been trained using the optimal transformed spectrum as training data.

[0171] (3) Calculation and control device 30

[0172] The calculation and control device 30 of the concentration measuring instrument of the present invention utilizes the optimal transformation conditions, the spectrum transformation and combination module, and the concentration prediction module 44 mounted in the memory device 40 to calculate the concentration prediction value PLCi from the acquired predicted spectrum PSi data of the target substance.

[0173] The concentration measuring device of the present invention is configured to change and set the optimum transformation conditions so as to correspond to the optimum transformation conditions that are set differently depending on the type of substance to be measured. The calculation and control device 30 receives the input of a predetermined optimum transformation condition determined in advance by receiving a selection input displayed on a screen display unit (not shown) or a selection input input from a physical switch (not shown), calls up a spectrum transformation module corresponding to the transformation from the memory device 40, transforms the spectrum, and inputs the transformed spectrum to a concentration prediction model called up from the memory device 40 again to output a predicted concentration value. In this case, it is obvious to a person skilled in the art that the concentration prediction modules 44 corresponding to a number of concentration prediction models each corresponding to a specific optimum transformation condition may be generated and stored in the memory device 40 by the above-mentioned method, and the concentration prediction module 44 corresponding to the corresponding substance may be called up to calculate the predicted concentration. Meanwhile, the concentration prediction module 44 may not be generated by learning a specific transformed spectrum, but may be a general-purpose spectrum concentration prediction model.

[0174] (4) Data connection unit 21

[0175] On the other hand, the concentration measuring device of the present invention may further include a data connection section for connecting an external memory device 40 and for receiving input and output of data from an external device.

[0176] The data connection section is configured integrally with the spectrum data acquisition section 10, and can also receive input of data other than spectrum data from an external device.

[0177] The spectrum transformation and combination module 41, the optimum transformation conditions, and the concentration prediction model that have already been generated can be received via the data connection unit and stored in the memory device 40. With this configuration, the optimum transformation conditions, the spectrum transformation and combination module 41, and the concentration prediction model that are set differently depending on the characteristics of the substance whose concentration is to be measured can be stored in the memory device 40 of the concentration measuring device and applied to the measurement of the concentration.

[0178] The data connection unit may be configured to be capable of connecting an externally removable memory device 40. In this case, the spectral transformation and combination module 41, optimal transformation conditions, and the already generated concentration prediction model are stored in the external memory device 40, which is connected in addition to or in place of the memory device 40, and the calculation and control device 30 is configured to read them and use them for concentration prediction. [Explanation of symbols]

[0179] The names of the symbols used in the specification and drawings of the present invention are as follows.

[0180] 100: Concentration prediction system 10: Spectral data acquisition section 20: Substance concentration data acquisition section 30: Calculation and control device 40: Memory device 41: Spectral transformation and combination module 42: Optimal spectrum derivation module 43: Machine learning module 44: Concentration prediction module

Claims

1. A method for generating a concentration prediction model for predicting a concentration of a target substance by machine learning, comprising: a training data generating step of generating, as training data, an optimally transformed spectrum obtained by transforming a basic spectrum of a substance having a known concentration based on a predetermined transformation condition; a concentration prediction model generation step of performing machine learning on the optimally deformed spectrum, which is deformed based on a predetermined deformation condition and which is generated in the learning data generation step, and the actual measured concentrations of substances corresponding to the optimally deformed spectrum, to generate a concentration prediction model; A method for generating a concentration prediction model, comprising:

2. The predetermined deformation condition is a spectrum transformation and combination step of transforming the basic spectrum based on two or more mutually different transformation conditions to generate a transformed spectrum; an optimal deformation condition derivation step of deriving optimal deformation conditions from the deformation spectrum; The method for generating a concentration prediction model according to claim 1 , wherein the optimal transformation condition is derived by:

3. The optimal deformation condition derivation step includes:

3. The method for generating a concentration prediction model according to claim 2, further comprising: calculating a standard deviation of a reference similarity of the transformed spectrum generated in the spectral transformation and combination step, a correlation coefficient with an actual concentration, and a multivariate ratio before and after the spectral transformation; and deriving the transformation condition that maximizes the sum of these as the optimal transformation condition.

4. The optimal deformation condition derivation step includes: the standard deviation (Ak) of the reference similarity, which is the standard deviation between the reference similarities of the transformed spectra for each transformation condition generated in the spectrum transformation and combination step, the correlation coefficient (Bk) with the measured concentration, and the multivariate ratio (Ck) before and after the spectrum transformation are calculated, and the transformation condition that maximizes the value of a linear function of these, Fk(Ak, Bk, Ck)=aAk+bBk+cCk (a, b, c are constant values), is derived as the optimal transformation condition; 3. The method for generating a concentration prediction model according to claim 2, wherein the reference similarity for calculating the standard deviation of the reference similarity, the correlation coefficient with the measured concentration, and the multivariate ratio before and after the spectrum transformation are calculated by the following Equations 1, 2, and 3, respectively. [006] (α is the combined transformation spectrum intensity combination, and β is the reference spectrum intensity combination.) [0070] (X is the reference similarity, Y is the actual substance concentration of the analyte, Cov(X,Y) is the covariance of the reference similarity (X) and the corresponding concentration of the analyte (Y), and Var(X) and Var(Y) are the variances of the reference similarity (X) and the corresponding concentration of the analyte (Y).) [0080] (The number of multivariates is the number of data acquired in a given wavelength band corresponding to the X-axis of the acquired spectrum.)

5. a spectrum transformation module that transforms a base spectrum based on two or more transformation conditions to generate a transformed spectrum corresponding to the base spectrum; an optimal modified spectrum calculation module that calculates a standard deviation of the reference similarity of the modified spectrum based on each of the modification conditions, a correlation coefficient with an actual concentration of a substance corresponding to each of the modified spectra, and a multivariate ratio before and after the spectral modification, and calculates an optimal modified spectrum modified based on the modification conditions that maximize the sum of these values; a machine learning module that performs machine learning on the actual measured concentration of the substance corresponding to the optimal deformation spectrum as learning data to generate a concentration prediction model; A computer-recorded medium having a concentration prediction model generation algorithm recorded thereon, comprising:

6. 1. A method for predicting a concentration of an analyte, comprising: A predicted spectrum acquisition step of acquiring a predicted spectrum of a substance whose concentration is to be predicted; an optimally modified predicted spectrum generating step of modifying the obtained predicted spectrum under optimal modification conditions to generate an optimally modified predicted spectrum; a predicted concentration output step of inputting the optimal deformation predicted spectrum to a concentration prediction model and outputting a predicted concentration value; comprising The optimal deformation condition is a spectrum modification and combination step of modifying a basic spectrum of a predetermined substance having a known measured concentration based on two or more different modification conditions to generate a modified spectrum; an optimal deformation condition derivation step of deriving optimal deformation conditions from the generated deformation spectrum; The deformation condition is derived by The concentration prediction model is a neural network or concentration prediction algorithm trained to calculate a predicted concentration value from an optimally transformed spectrum obtained by transforming the fundamental spectrum under the optimal transformation conditions and the corresponding measured concentration value through machine learning.

7. The optimal deformation condition derivation step includes:

7. The method for predicting a concentration according to claim 6, further comprising: calculating a standard deviation of a reference similarity of the transformed spectrum generated in the spectral transformation and combination step, a correlation coefficient with an actual concentration, and a multivariate ratio before and after the spectral transformation; and deriving, as an optimal transformation condition, a transformation condition that maximizes the sum of these.

8. The optimal deformation condition derivation step includes: a standard deviation (Ak) of the reference similarity, which is the standard deviation between the reference similarities of the transformed spectra for each transformation condition generated in the spectrum transformation and combination step, a correlation coefficient (Bk) with the measured concentration, and a multivariate ratio (Ck) before and after the spectrum transformation are calculated, and the transformation condition that maximizes the value of a linear function of these, Fk(Ak, Bk, Ck)=aAk+bBk+cCk (a, b, c are constant values), is derived as the optimal transformation condition, 7. The method for predicting a concentration according to claim 6, wherein the reference similarity for calculating a standard deviation of the reference similarity, the correlation coefficient with the actually measured concentration, and the multivariate ratio before and after the spectrum transformation are calculated by the following formulas 1, 2, and 3, respectively. [0097] (α is the combined transformation spectrum intensity combination, and β is the reference spectrum intensity combination.) [0010] (X is the reference similarity, Y is the actual substance concentration of the analyte, Cov(X,Y) is the covariance of the reference similarity (X) and the corresponding concentration of the analyte (Y), and Var(X) and Var(Y) are the variances of the reference similarity (X) and the corresponding concentration of the analyte (Y).) ##EQU00011## (The number of multivariates is the number of data acquired in a given wavelength band corresponding to the X-axis of the acquired spectrum.)

9. 1. A concentration prediction system for predicting a concentration of an analyte, comprising: a spectrum data acquisition unit for acquiring a basic spectrum of a substance for generating learning data or a predicted spectrum, which is a spectrum of a substance whose concentration is to be measured; a substance concentration data acquisition unit for acquiring already acquired substance concentration data and an actual measured concentration of a substance to be measured using a known concentration measuring device; A calculation and control device that generates a modified spectrum of the basic spectrum and the predicted spectrum, calculates an optimal modification condition, performs machine learning, and generates a concentration prediction model; a memory for storing the fundamental spectrum of the analyte obtained by the spectrum data acquisition unit, the measured substance concentration value obtained by the substance concentration data acquisition unit, and the concentration prediction model generated by the calculation and control device; A concentration prediction system comprising:

10. The arithmetic and control device includes: The spectra acquired in the spectrum data acquisition unit are transformed and combined based on a spectrum transformation algorithm; Among the transformed spectra, a transformed spectrum that shows the best accuracy of concentration prediction is derived as an optimal transformed spectrum; performing machine learning using the optimal deformation spectrum and the corresponding measured concentration of the substance as learning data to generate a concentration prediction model; The concentration prediction system according to claim 9 , further comprising: inputting the predicted spectrum into a generated concentration prediction model to predict the concentration.

11. The memory includes: a spectrum transformation and combination module that transforms the spectrum acquired by the spectrum acquisition unit based on a transformation condition; an optimal spectrum derivation module for obtaining an optimal spectrum that indicates an optimal accuracy of concentration prediction from among the transformed spectra, and deriving an optimal transformation condition; a machine learning module that uses the optimal deformation spectrum and the measured substance concentration as learning data to perform machine learning and generate a concentration prediction model; a concentration prediction module for calculating a concentration prediction value using the predicted spectrum as input data; The concentration prediction system of claim 9 .

12. a spectrum transformation module for transforming a predicted spectrum of a substance whose concentration is to be predicted to generate a transformed spectrum; an optimal spectrum derivation module that calls the spectrum transformation module and calculates an optimal transformed predicted spectrum by transforming the predicted spectrum based on an optimal transformation condition; a concentration prediction module for receiving the optimal deformation predicted spectrum and calculating a predicted concentration value; comprising The concentration prediction module includes: A computer-recording medium having recorded thereon a concentration prediction algorithm generated by machine learning based on the spectrum transformed based on the optimal transformation conditions and the actual measured concentration of the corresponding substance.

13. 1. A concentration measuring device for predicting a concentration of an analyte, comprising: a spectrum data acquisition unit for acquiring a predicted spectrum, which is a spectrum of an analyte; a memory device including a spectrum transformation module that transforms a predicted spectrum based on an optimal transformation condition and a concentration prediction module that calculates a predicted concentration value from the optimal transformed predicted spectrum obtained by transforming the predicted spectrum based on the optimal transformation condition; an arithmetic and control device that reads the concentration prediction module mounted on the memory device and controls the module to calculate a concentration prediction value from a prediction spectrum for which a concentration is to be predicted; A concentration measuring device comprising:

14. The concentration measuring device is Further comprising a data connection section for connecting an external memory device or receiving data input / output from an external device; The memory device includes:

14. The concentration measuring device of claim 13, removably connected to the data connection.

15. Further comprising a data connection section for connecting an external memory device or receiving data input / output from an external device; The memory device includes:

14. The concentration measuring instrument according to claim 13, further comprising: a spectrum transformation module that transforms the predicted spectrum based on optimal transformation conditions; and a concentration prediction module that calculates a predicted concentration value from an optimally transformed predicted spectrum obtained by transforming the predicted spectrum based on the optimal transformation conditions, the concentration prediction module receiving the predicted spectrum from an external device via the data connection unit and storing the data.

16. 15. The concentration measuring device of claim 14, wherein the data connection unit is integral with the spectral data acquisition unit.

Images