Synergy Interval Research Articles

Determination of 10-HDA in royal jelly by ATR-FTMIR and NIR spectral combining with data fusion strategy

The attenuated total reflectance-Fourier transform mid-infrared (ATR-FTMIR) and near-infrared (NIR) spectra of royal jelly samples were collected. Low- and mid-level data fusion strategies in combination with the partial least squares (PLS) regression algorithm were used for quantitative modeling analysis of 10-hydroxy-2-decenoic acid (10-HDA) content in royal jelly samples. In low-level data fusion, each raw spectrum was pre-processed before splicing into a new data matrix for PLS model construction and analysis. In the mid-level data fusion, synergy interval (SI)-PLS was used for variable selection and principal component analysis/independent component analysis was used for feature extraction to obtain variables. The extracted variables were spliced before inputting into the PLS model for modeling and analysis. The results showed that the PLS analysis model constructed by mid-level data fusion is better than the PLS models constructed by independent data and low-level data fusion. Among these models, the PLS model that was constructed by the mid-level data fusion after SI-PLS variable selection had the best 10-HDA content prediction accuracy, with RMSEP = 0.1118(%) and RP = 0.9585. Therefore, a mid-level data fusion strategy based on the ATR-FTMIR and NIR spectra can be used as a reliable tool for 10-HDA quantitation.

Rapid detection model of Bacillus subtilis in solid‐state fermentation of rapeseed meal

AbstractThe main objective of this research was to monitor variety in the content of Bacillus subtilis 10160 during solid‐state fermentation (SSF) of rapeseed meal by near infrared (NIR) spectroscopy and chemometrics. Observations showed the coefficient of determination (R2) value was 0.9401 and root‐mean‐square deviation was 0.639 log (CFU/g) for viable cell content by synergies between four intervals 5,203.003–5,600.267, 5,604.124–6,001.388, 6,807.487–7,204.751 and 8,411.972–8,809.235 cm−1. The determination coefficient of prediction (Rp2) and root‐mean‐square deviation of prediction in an external validation set could reach 0.9532 and 0.628 log (CFU/g) by the viable B. subtilis model. These findings suggest that rapid detection of B. subtilis in SSF is achieved by the combination of synergy interval partial least squares and NIR spectroscopy.

Identification of rice storage time based on colorimetric sensor array combined hyperspectral imaging technology

The study reports a novel colorimetric sensor array (CSA) based hyperspectral imaging (HSI) system and chemometrics algorithms for the identification of rice storage time. CSA fabricated by boron-dipyrromethene (BODIPY) dyes was used to capture the volatile organic compounds (VOCs) of rice samples. CSA hypercube before and after the reaction were obtained with HSI. Genetic synergy interval partial least square algorithm (GA-Si-PLS) was used to filter spectral information. Fifty-four spectral data variables and five dominant wavelength images was selected from CSA hypercube. Then three grayscale difference values were extracted from each dominant wavelength image, thus totaling to 15 variables as imaging data variables. Linear discriminant analysis (LDA) and k-Nearest Neighbor (KNN) model were established to comparing the performance of spectral variables, imaging variables and combined datasets. The result showed the optimal model was linear discriminant analysis (LDA) model built by using spectral variables and the correct rate of calibration set for rice storage time discrimination was 92.73% and the obtained rate of prediction set was 90.91%. It is indicated the applicability of the proposed CSA combined with HSI technology towards rice storage time identification.

Application of siSVR-Vis/NIR to the nondestructive determination of acid detergent fiber content in corn straw

Determining acid detergent fiber (ADF) content in corn straw with Visible/Near-Infrared (Vis/NIR) spectroscopy, associated suitable chemometrics methods, is both feasible and relevant for the corn breeding. The work demonstrated that Vis/NIR combined with support vector regression (SVR) realized the nondestructive determination of ADF content. Herein, after optimized spectra and model parameters by pretreatment methods and genetic algorithm (GA), the preeminent SVR model was confirmed. For selecting feature bands, the modified synergy interval (si) algorithm was applied to unevenly divide full-spectra into seven subintervals, the performance of 128 siSVR models with different combinations was investigated. It turned out that the determination coefficient (R2), root mean square error of prediction (RMSEP), residual predictive deviation (RPD), relative standard deviation (RSD) of test set of SVR model successively reached 0.9897, 0.4037, 9.8689, 0.0094. Meanwhile, the performance of siSVR model was proven to further improve when the penalty parameter C and kernel function parameter g respectively were 99.9904, 0.0051, the group of [2,3,5,6] was determined. Besides, the second subinterval were subdivided into I, II, III sub-bands to further dimension reduction. As expected that siSVR model reached for best level when the suited group was [2(I, III), 3, 5, 6], R2, RMSEP, RPD, RSD were 0.9943, 0.2885, 13.2688, 0.0066, respectively. Finally, compared with other models, the results of external validation indicated that the proposed method presented the excellent performance, which could meet the requirements of ADF analysis.

Measurement of total free amino acids content in black tea using electronic tongue technology coupled with chemometrics

The potential of cyclic voltammetry electronic tongue (CVET) coupled to chemometrics was investigated for measuring total free amino acids (FAA) content in black tea. Two working electrodes - glassy carbon electrode and platinum electrode were comparative and syncretic in prediction of total FAA content. Synergy interval partial least square (Si-PLS) combined with variable combination population analysis (VCPA), namely Si-VCPA-PLS, was creatively employed for searching characteristic variables selection from the whole cyclic voltammetry data set. Cyclic voltammetry signals coupled Si-VCPA-PLS model results represented its feasibility in estimating total FAA content in black tea, achieved with Rp = 0.8185 for the glassy carbon electrode; Rp = 0.8366 for the platinum electrode; and Rp = 0.8414 for their data fusion. The extracted characteristic variables were only occupying about 0.2% of the origin. This work confirmed that the cyclic voltammetry electronic tongue could be as a fast, low-cost, efficient and complementary approach for predicting total FAA content in black tea.

Investigation into crystal size effect on sodium chloride uptake and water activity of pork meat using hyperspectral imaging

In this study, impact of crystal size on salt (NaCl) uptake and water activity (aw) of dry-cured pork was investigated by hyperspectral imaging. Three grades of NaCl labeled fine flake, medium flake, and large flakes were used during the 3 day salting period. Spectra and spatial information were extracted from three subsurfaces labeled surface-1, surface-2, and surface-3 for each sample and prediction models were established based on partial least squares regression, synergy interval partial least squares, and competitive adaptive reweighted sampling partial least squares. The overall results indicated that processing with NaCl of different crystal sizes influenced NaCl uptake and aw of pork samples. Distribution maps based on spatial analysis further revealed that crystal size impacted NaCl uptake to a large extent. Thus, in the drive to process meat with lower NaCl content, crystal morphology may be considered in further studies in dry-cured meat processing. Practical applications Meat preservation with salt (NaCl) is a widely applied traditional technique of safe-guiding meat from microbial invasion because of its effectiveness and the ease of accessing the commodity. Yet, several studies have associated noncommunicable diseases, including hypertension, cardiovascular disease, and stroke to the high intake of NaCl. As a result, several strategies are being developed for reducing NaCl contents in processed foods in a bid to avert these health-related concerns. Some of these strategies involved studying the dissolution characteristics of salt crystals in saliva, brining with high-powered ultrasound, among others. Dry-cured pork is a worldwide delicacy. Thus, for the purposes of understanding how crystal size influence total NaCl levels in dry-cured pork, this investigation was carried out. The outcome of this study may be considered in the formulation of future research needs in the drive to achieving sodium reduction in salted meat while maintaining quality and salt intensity.

Quantification of Jatropha methyl biodiesel in mixtures with diesel using mid-infrared spectrometry and interval variable selection methods

The use of mid-infrared spectrometry with horizontal attenuated total reflectance and Fourier transform, along with methods of variable selection by intervals, that is, interval partial least-squares (iPLS), backward interval partial least-squares (biPLS), and synergy interval partial least-squares (siPLS), were evaluated in order to quantify the Jatropha methyl biodiesel content in mixtures with diesel in the range from 0.25 to 30.00% (v/v). The spectral data were obtained in quintuplicate and corrected using the baseline technique. The constructed variable selection models were compared with the global partial least-squares (PLS) model by applying the F test to the root mean square error of prediction (RMSEP) value. The model with the best predictive capacity was iPLS24 (i.e., dividing the full spectrum into 24 equidistant intervals) constructed in the region from 650 to 750 cm−1 with 101 variables. The parameters obtained were the root mean square error of calibration (RMSEC) of 0.22%, the root mean square error of cross-validation (RMSECV) of 0.25%, RMSEP of 0.24%, limit of detection (LD) of 0.40% (v/v) and limit of quantification (LQ) of 0.13% (v/v). Therefore, the interval variable selection method was efficient in obtaining a spectral region that provided better predictive capacity than the global PLS model. In addition, with the selection of a smaller number of variables, it is possible to build portable equipment at a lower cost for use by fuel quality control agencies.

Fast determination of oxides content in cement raw meal using NIR spectroscopy combined with synergy interval partial least square and different preprocessing methods

Near infrared (NIR) diffuse reflectance spectroscopy, combined with chemometrics techniques was proposed as a fast and accurate method applied for determination of main components (CaO, SiO2, Al2O3, Fe2O3) in cement raw meal. The analyses were implemented by correlation of NIR spectra with reference method made by X-ray Fluorescence (XRF), using different regression methods such as partial least square (PLS), interval PLS (iPLS) and synergy interval PLS (siPLS) with multiple pretreatment methods. The optimal models obtained by using siPLS algorithm showed root-mean-square-error-of-prediction (RMSEP) from 0.0379 to 0.1715, the correlation coefficient (Rp) from 0.7294 to 0.9304 and average prediction error from 0.03% to 0.13%. The proposed method is cheaper and safer, and it takes much less time (3–5 min) than the XRF method (40–60 min) for each measurement. Our results demonstrate that NIR diffuse reflectance spectroscopy technology can be applied to quantitative determination of the four oxides in cement raw meal.

A newly developed method to extract the optimal hyperspectral feature for monitoring leaf biomass in wheat

Hyperspectral image provides a plethora of information, some of which may be redundant. Therefore, reducing information’s dimensionality using feature selection methods becomes essential. Here, we proposed a new technique, named synergy interval partial least squares (SIPLS) with successive projections algorithm (SPA) (SIPLS-SPA), combining SIPLS and SPA, to efficiently extract optimal spectral features of wheat biomass from hyperspectral image data. In this study, hyperspectral images and leaf biomass were acquired from two-year wheat field experiments with varied nitrogen rates, planting densities, and cultivars. The results showed that eight wavelengths (706, 724, 734, 806, 808, 810, 812, and 816 nm) were selected as the sensitive input variables to establish partial least squares regression (PLSR) model for wheat leaf biomass. The SIPLS-SPA biomass model performed better with higher Rc2 (0.79) in calibration, lower RMSEv (0.059 kg/m2) and RRMSEv (38.55%) in validation. Compared with other state-of-the-art feature selection techniques, the SIPLS-SPA method provided significantly fewer unrelated, collinear spectral variables, and showed a promising application in terms of lower overall complexity, reduced computational complexity, and shorter running time. Furthermore, this work demonstrates the potential of SIPLS-SPA method for extracting other plant traits from hyperspectral data in future agricultural applications.

Optimized prediction of sugar content in ‘Snow’ pear using near-infrared diffuse reflectance spectroscopy combined with chemometrics

In near-infrared spectroscopy applications, the original spectra often contain redundant information, which will seriously affect the performance of chemometric models. Therefore, preprocessing, effective wavelengths selection, and appropriate regression models are essential. The objective of this study was to optimize the nondestructive determination multivariate calibration model of sugar content in ‘Snow’ pears, using near-infrared diffuse reflectance spectroscopy combined with chemometrics. All data (sugar content reference values and spectra data) from three measuring positions (P1, P2, and P3, marked around the pear’s equator at angular distances of approximately 120°) were divided into four grouped datasets, namely Set-1 (P1), Set-2 (P2), Set-3 (P3), and Set-4 (average of the three measuring positions). All subsequent optimized processes were performed based on each grouped dataset. First, different preprocessing methods were tested and an optimal method was determined. Then, synergy interval partial least squares and synergy interval partial least squares-competitive adaptive reweighted sampling were applied to select effective regions and effective wavelengths from all wavelengths, respectively, and partial least squares regression models were established and analyzed. In addition, support vector regression models were also established for comparative study. After comprehensive analysis of prediction accuracy and model complexity, the partial least squares regression model based on the 16 selected effective wavelengths for Set-4 was optimal, with the correlation coefficient for prediction, root-mean-square error of prediction, and residual predictive deviation of 0.9701, 0.2311, and 4.12, respectively. The results indicated that with these optimized processes, the multivariate calibration model of sugar content in ‘Snow’ pears was effectively optimized for each dataset. In addition, it is concluded that partial least squares regression was superior to support vector regression in this study, although some other researches had found different results in related fields.

Determination of API Gravity and Total and Basic Nitrogen Content by Mid- and Near-Infrared Spectroscopy in Crude Oil with Multivariate Regression and Variable Selection Tools

American Petroleum Institute (API) gravity is an important parameter in the crude oil industry and the nitrogen compounds are related to the toxic effects of the oil in refineries and the environment. In this paper, 194 crude oil samples with API gravities ranging from 11.4 to 57.5 were used for the purpose of estimating the physicochemical properties: API gravity, total nitrogen content (TNC) and basic nitrogen content (BNC). Initially, infrared spectra in the mid and near regions (MIR and NIR) were collected, then full-spectral partial least squares (PLS) and the orthogonal projections to latent structures (OPLS) chemometric models were developed and validated, as well as models using interval PLS (iPLS), synergy interval PLS (siPLS) and competitive adaptive reweighted sampling PLS (CARSPLS) as variable selection tools. For API gravity and TNC, the best calibration technique is the NIR CARSPLS with a root mean square error of prediction (RMSEP) values of 0.9 and 0.0275 wt%, respectively. For BNC, the best technique is MIR siPLS with a prediction error of 0.0134 wt%. The results were validated based on the evaluation of the figures of merit, a statistical evaluation of the accuracy, characterization of the systematic error and measurement for errors in the residues. The results were satisfactory considering the high variability of the data and the diversity of the samples, demonstrating suitable applicability for practical analysis.

Simultaneous determination of sulfur, nitrogen and ash for vegetable tannins using ATR-FTIR spectroscopy and multivariate regression

The quantification of sulfur, nitrogen and ash content in tannins of mimosa (Acacia mearnsii) and quebracho (Schinopsis sp.) is of fundamental importance for its industrial use. Thus, an analytical method capable of identifying these properties by attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) was developed using multivariate regression methods. Partial least squares regression (PLS) method was used as well as the interval partial least squares (iPLS) and the synergy interval partial least squares (siPLS). The developed models were compared based on the root of the mean square errors (RMSE) and determination coefficients (R2). The results showed that both the iPLS and the siPLS, using the infrared data, obtained satisfactory results, but having a small improvement with the use of the siPLS. In general, the proposed method does not require reagent consumption, being much faster than traditional techniques, allowing potential applications for simultaneous determination of sulfur, nitrogen and ash contents for routine analysis of plant tannins by FTIR data.

Rapid and Nondestructive Quantification of Trimethylamine by FT-NIR Coupled with Chemometric Techniques

This paper focused on the quick and nondestructive evaluation of trimethylamine (TMA-N) in fish storage which is sequent to its freshness, the key for controlling the quality and safety of fish products by combining Fourier transform near-infrared (FT-NIR) and chemometric techniques. Calibration models of fish freshness were established using three multivariate chemometric methods—partial least square (PLS), synergy interval PLS (Si-PLS), and genetic algorithm PLS (GA-PLS) for quantitative prediction of TMA-N in fish. Results of the developed model were estimated using the correlation coefficients of the prediction (Rp) and calibration (Rc); root mean square error of prediction (RMSEP) and the ratio of sample standard deviation to RMSEP (RPD). The established model’s performance achieved 0.943 ≤ Rp ≤ 0.977 and 4.25 ≤ RPD ≤ 4.30. The model’s prediction strength improved in the order PLS < Si-PLS < GA-PLS. GA-PLS significantly improved the prediction of TMA-N prediction with RMSEC = 5.08 and Rc = 98.28 for the calibration data whereas the prediction set gave an RMSEP = 5.10 and Rp = 97.70. FT-NIR spectroscopy combined with GA-PLS technique may be employed for rapid and non-invasive quantification of TMA-N in fish for monitoring safety and quality.

Determination of physicochemical properties of petroleum using 1H NMR spectroscopy combined with multivariate calibration

This paper proposes a methodology to characterize the following petroleum properties: UOP characterization factor (K), nitrogen content, solubility parameter, sulfur content, maximum and minimum pour point, and kinematic viscosity (at 20 °C, 30 °C, 40 °C and 50 °C), in petroleum within a single 1H NMR (proton nuclear magnetic resonance) spectra. Multivariate calibration tools, such as partial least squares (PLS), orthogonal projections to latent structures (OPLS) (with variable selection), interval PLS (iPLS), synergy interval PLS (siPLS) and model population analysis (MPA), were applied to 138 samples. The models were evaluated by coefficient of determination (R2), root mean square error of prediction (RMSEP), and residuals. In general, model population analysis had better results in the determination of petroleum's physicochemical properties than PLS and OPS. Thus, MPA provided models with better accuracy in the determination of the following properties: UOP characterization factor (0.06), nitrogen content (0.048 wt%), kinematic viscosity at 40 °C (relative error of 21.9%) and pour point (14.58 °C and 19.2 °C, respectively). The sulfur content was estimated with a 0.09 wt% mean error of prediction, using the PLS model, and the solubility parameter with a 1.06 (MPa)1/2 mean error of prediction, using the OPLS model.

A feature-based soft sensor for spectroscopic data analysis

In the last few decades, spectroscopic techniques such as near-infrared (NIR) and UV/vis spectroscopies have gained wide applications. As a result, various soft sensors have been developed to predict sample properties from its spectroscopic readings. Because the readings at different wavelengths are highly correlated, it has been shown that variable selection could significantly improve a soft sensor’s prediction performance and reduce the model complexity. Currently, almost all variable selection methods focus on how to select the variables (i.e., wavelengths or wavelength segments) that are strongly correlated with the dependent variable to improve the prediction performance. Although many successful applications have been reported, such variable selection methods do have their limitations, such as high sensitivity to the choice of training data, and deteriorated performance when testing on new samples. One possible reason is the removal of useful wavelengths or segments of wavelengths during the calibration process, which could be “tilted” to overfit or capture the noise or unknown disturbances contained in the calibration data. As a result, the model prediction performance may deteriorate significantly when the model is extrapolated or applied to new samples. To address this limitation, we propose a feature-based soft sensor approach utilizing statistics pattern analysis (SPA). Instead of selecting certain wavelengths or wavelength segments, the SPA-based method considers the whole spectrum which is divided into segments, and extracts different features over each spectrum segment to build the soft sensor. In other words, the SPA model contains the complete information from the full spectrum without any selection or removal, which we believe is the main reason for the high robustness of the SPA-based method. In addition, we propose a Monte Carlo validation and testing (MCVT) procedure and three MCVT-based performance indices for consistent and fair comparison of different soft sensor methods across different datasets. The MCVT procedure and indices are generally applicable for model comparison in other applications. Four case studies are presented to demonstrate the performance of the feature-based soft sensor and to compare it with a full partial least squares (PLS), a least absolute shrinkage and selection operator (Lasso), and a synergy interval PLS (SiPLS) based models following the proposed MCVT procedure. In addition, we examine the potential of kernel PLS (KPLS) based soft sensor approaches, examine their performances, and discuss their pros and cons.

Quantitative assessment of zearalenone in maize using multivariate algorithms coupled to Raman spectroscopy

Zearalenone is a contaminant in food and feed products which are hazardous to humans and animals. This study explored the feasibility of the Raman rapid screening technique for zearalenone in contaminated maize. For representative Raman spectra acquisition, the ground maize samples were collected by extended sample area to avoid the adverse effect of heterogeneous component. Regression models were built with partial least squares (PLS) and compared with those built with other variable selection algorithms such as synergy interval PLS (siPLS), ant colony optimization PLS (ACO-PLS) and siPLS-ACO. SiPLS-ACO algorithm was superior to others in terms of predictive power performance for zearalenone analysis. The best model based on siPLS-ACO achieved coefficients of correlation (Rp) of 0.9260 and RMSEP of 87.9132 μg/kg in the prediction set, respectively. Raman spectroscopy combined multivariate calibration showed promising results for the rapid screening large numbers of zearalenone maize contaminations in bulk quantities without sample-extraction steps.

Research on Detection of Multi-adulteration of Sesame Oils by Near-infrared Spectroscopy

Aiming at the adulteration of sesame oil, our research is focused on using near-infrared spectroscopy combined with chemometrics to achieve rapid detection. The near-infrared spectrum of the sample was collected, and the data analysis and modeling were conducted on MATLAB. The raw spectral data was pretreated using multiplicative scatter correction (MSC) and standard normal variate (SNV). Support vector machine (SNM) model was established by using competitive adaptive reweighed sampling (CARS) and combined synergy interval partial least squares (SiPLS) to select characteristic spectral data. The highest correct recognition rate of the qualitative model is 100%, the mean square error MSE of the quantitative model is 0.0829, and the correlation error R is 99.0772%. The results prove that the support vector machine classification model established by near-infrared spectroscopy combined with chemometrics can qualitatively detect whether sesame oil is adulterated. In the meanwhile, the SNM model can quantitatively predict the content of active components.

Evaluation of moisture content in processed apple chips using NIRS and wavelength selection techniques

Rapid determination of moisture content during processing period of apple chips is of great significance for their real-time quality control. In this study, near infrared spectroscopy (NIRS) combined with chemometric techniques were used to measure moisture content of apple chips during processing period. Interval partial least squares (iPLS), synergy interval partial least squares (siPLS) and genetic algorithm (GA) were utilized to select efficient wavelength regions, respectively, and partial least squares regression (PLSR) was applied to develop prediction model. The performance of models was evaluated by three types of parameters, including the root mean square error (RMSE), correlation coefficient (R) and the residual prediction deviation (RPD). The results demonstrated that, in contrast to classical PLS, iPLS and GA-PLS model, siPLS model for the prediction of moisture content had superior performance with RMSEC = 0.0877, Rc = 0.9540, RMSEP = 0.0627, Rp = 0.9747, and RPD = 4.37. Therefore, the application of NIRS and wavelength selection techniques in this study provides a feasibility of a non-destructive and rapid way to enhance the efficiency of quality assurance and control investment.

Total polyphenol quantitation using integrated NIR and MIR spectroscopy: A case study of Chinese dates (Ziziphus jujuba).

Polyphenols are the foremost measure of phytochemicals in Chinese dates due to their many potential health benefits such as averting cancers, reducing the risk of coronary artery disease, diuretic activity, myocardial stimulant, coronary dilator and muscle relaxant. To quantitate the polyphenols in Chinese dates using a data fusion approach with near-infrared (NIR) and mid-infrared (MIR) spectroscopy. A total of 80 Chinese dates samples were used for data acquisition from both NIR and MIR spectroscopy. The efficient spectral intervals were extracted by the synergy interval partial least square (Si-PLS) algorithm as input variables for NIR-MIR fusion model. A genetic algorithm (GA) was used to construct the model based on NIR-MIR fusion. The performance of the developed models was evaluated using correlation coefficients of calibration (R2 ) and prediction (r2 ), root mean square error of prediction (RMSEP), bias and residual prediction deviation (RPD). The data fusion model based on the GA was superior compared to NIR and MIR build model. The optimal GA-fusion model yielded R2 =0.9621, r2 =0.9451, RPD=2.44, calibration set bias=0.004 and prediction set bias=0.061, computing only 15 variables. These findings reveal that integration of NIR and MIR is possible for the prediction of total polyphenol content in Chinese dates.

Quantitative analysis of volatile organic compound using novel chemoselective response dye based on Vis-NIRS coupled Si-PLS

Quantitative analysis of volatile organic compounds (VOCs) using spectroscopy technology has invariably been a formidable problem. In this paper, chemoselective response dyes were employed as probes to capture VOCs, including a novel chemoselective response dye called BODIPY. The spectral data of distinct sensor color difference pattern due to the rapid chemical reaction between the dye molecule and organic compound molecule was collected by portable Visible-Near Infrared Spectroscopy (Vis-NIRS) equipment. Afterward, the synergy interval partial least squares (Si-PLS) algorithm was used to process spectral data and establish predictive models for pure VOCs in the mixture and actual samples with the high correlation coefficient of determination of the prediction set (Rp) value and the low root mean square error of prediction (RMSEP) value. This new method formed by a color-sensitive sensor made of chemoselective dye combined with Vis-NIRS technology not only achieves quantitative detection of VOCs but also address the limitations of spectrum technology in this field. Finally, we obtained the expected results, the average prediction rate of the concentration of the six pure VOCs counted as 107 ± 20%, the average prediction rate of pure VOCs in the mixture counted as 101 ± 12%. Meanwhile, the average prediction rate of VOCs in the actual samples counted as 108 ± 31%, when this new method was applied to the detection of VOCs.