Root Mean Square Error Of Cross-validation Research Articles

Quantification of low-content encapsulated active cosmetic ingredients in complex semi-solid formulations by means of attenuated total reflectance-infrared spectroscopy.

Attenuated total reflectance-infrared (ATR-IR) spectroscopy is a robust tool for molecular characterisation of matter. Applied to semi-solid formulations, it enables rapid and reliable data collection without pre-analytical requirements. Based on nano-encapsulated Omegalight®, a skin-lightening active cosmetic ingredient (ACI), incorporated in a hydrogel, it is first demonstrated that, despite the high water content and the chemical complexity of the samples (i.e. number of ingredients), the spectral features of the ACI can be detected and monitored. Secondly, with a total of 105 samples divided into a training set (n = 60) and an unknown set (n = 45) covering a 0.5% w/w-5% w/w concentration range, the study further investigates the quantitative performance of ATR-IR coupled with partial least squares regression (PLSR). Througha step-by-step approach in testing different cross-validation protocols, accuracy (root mean square error of cross-validation (RMSECV)) and linearity between the experimental and predicted concentrations (R2) of ATR-IR are consistently evaluated to be respectively 0.097% (w/w) and 0.995 with a lower LOD = 0.067% (w/w). Subsequently, further evaluation of the accuracy (relative error of the predicted concentration compared with the true value, expressed as %) of the analysis was undertaken with the 45 unknown samples that were defined asunknown and analysed by PLSR. The outcome of the analysis demonstrates the ruggedness and the consistency of the determination performed using the ATR-IR data. With an average relative error of 2.5% w/w and only 5 samples out of 45 blind samples exhibiting a relative error above the 5% threshold, high accuracy quantification of the nano-encapsulated ACI can be unambiguously achieved by means of the label-free and non-destructive technique of ATR-IR spectroscopy. Ultimately, the study demonstrates that the analytical capabilities of ATR-IR hold significant potential for applications in the cosmetics industry, and although the path remains long, the present study is one step further to support validation of the technique, albeit for the specific case of Omegalight®.

Infrared Spectroscopy with a Fiber-Coupled Quantum Cascade Laser for Attenuated Total Reflection Measurements Towards Biomedical Applications.

The development of rapid and accurate biomedical laser spectroscopy systems in the mid-infrared has been enabled by the commercial availability of external-cavity quantum cascade lasers (EC-QCLs). EC-QCLs are a preferable alternative to benchtop instruments such as Fourier transform infrared spectrometers for sensor development as they are small and have high spectral power density. They also allow for the investigation of multiple analytes due to their broad tuneability and through the use of multivariate analysis. This article presents an in vitro investigation with two fiber-coupled measurement setups based on attenuated total reflection spectroscopy and direct transmission spectroscopy for sensing. A pulsed EC-QCL (1200–900 cm) was used for measurements of glucose and albumin in aqueous solutions, with lactate and urea as interferents. This analyte composition was chosen as an example of a complex aqueous solution with relevance for biomedical sensors. Glucose concentrations were determined in both setup types with root-mean-square error of cross-validation (RMSECV) of less than 20 mg/dL using partial least-squares (PLS) regression. These results demonstrate accurate analyte measurements, and are promising for further development of fiber-coupled, miniaturised in vivo sensors based on mid-infrared spectroscopy.

Non-invasive measurements of ‘Yunhe’ pears by vis-NIRS technology coupled with deviation fusion modeling approach

Abstract Visible-near infrared spectroscopy (vis-NIRS) technology has been broadly and effectively implemented in the measurements of internal quality for food and agricultural products, coupled with the most common partial least square (PLS) modeling method. However, only the top latent variables (LVs) are employed in this optimized PLS model, and the residual LVs are discarded, resulting in the loss of spectral information. In this study, soluble solids content (SSC) of ‘Yunhe’ pears was non-invasively measured by a miniature vis-NIRS device in interactance spectral reading mode, coupled with a fusion modeling strategy based on two member models. One model was the optimized PLS model with the first 12 LVs, generally aiming at minimizing the root mean square errors of cross-validation (RMSECV) in the stage of calibrating the model, and the other was the derived multiple linear regression (MLR) model, which was developed with the remaining 8 LVs. These 20 LVs utilized in the PLS model accumulated over 99.99 % of the original spectral information. Two fusion strategies, including stacked fusion and the deviation fusion, were comparatively employed to fuse the above two member models. The deviation consensus model provided the weightings of 0.9077 and 0.0923 for the PLS and MLR model, respectively, and performed better than that of any univocal model or the stacked model, with an rp of 0.9026, as well as a root mean square errors of prediction (RMSEP) of 0.59, decreasing the RMSEP of 7.5 % compared to that of the optimal PLS member model. It can be concluded that the strategy of deviation consensus modeling can use the spectral information from two member models, and can improve the model prediction overall.

Online monitoring of horseradish peroxidase structural changes by Near Infrared (NIR) Spectroscopy

The development of online monitoring techniques is of great relevance for understanding the structural changes of proteins under different conditions in order to maximize their catalytic activity. This study aimed to evaluate the potential of the NIR (near-infrared spectroscopy) technique for the monitoring of alterations of secondary and tertiary structures of Horseradish peroxidase (HRP), an oxidoreductase that has several applications in the industrial environment, food industry and bioremediation. The NIR associated to the multivariate calibration, through the PLS (partial least square) method allowed the construction of a robust model for the prediction of the analysis. The values of the correlation coefficient (R²), root mean square error of calibration (RMSEC), root mean square error of prediction (RMSEP) and root mean square error of cross validation (RMSECV) for secondary structure analysis using circular dichroism (CD) data as reference (actual values) were 0.9681, 0.647 (mdeg), 0.945 (mdeg), and 1.12 (mdeg), respectively. For tertiary structure analysis, fluorescence spectroscopy (FL) data were used as reference. R2, RMSEC, RMSEP and RMSECV were, respectively 0.9999, 1.95 (a.u.), 2.09 (a.u.); and 2.19 (a.u.). NIR combined multivariate calibration showed promising results for sctructural changes monitoring of HRP.

Data Fusion of Raman and Near-Infrared Spectroscopies for the Rapid Quantitative Analysis of Methanol Content in Methanol–Gasoline

Rapid analysis of methanol content in methanol–gasoline is of great significance to monitor the methanol–gasoline quality. In this work, two different data-fusion strategies based on Raman and near-infrared (NIR) spectroscopies coupled with partial least square (PLS) were constructed and applied for a rapid and accurate analysis of the methanol content in methanol–gasoline. The Raman and NIR spectra of 49 methanol–gasoline samples were recorded, and the characteristic peaks of the methanol–gasoline samples in Raman and NIR spectroscopies were identified. For spectral data fusion, two different data-fusion strategies based on Raman and NIR spectroscopies coupled with PLS were proposed; normalization was used for low-level data fusion, and variable importance in projection (VIP) was used for mid-level data fusion. The different spectra pretreatment methods, latent variables, and variable importance thresholds of VIP were explored and optimized by 5-fold cross-validation (CV) to optimize the PLS calibration model for methanol content analysis. To further prove the predictive performance and stability of the PLS calibration model based on two data-fusion strategies, four PLS calibration models based on Raman, NIR, and two data-fusion strategies were applied to the quantitative analysis of methanol content in methanol–gasoline. The results show that the predictive performance of PLS calibration models based on the two data-fusion strategies is improved, and the PLS calibration model based on mid-level data fusion strategy gave an excellent predictive performance in methanol content analysis, with coefficients of determination of cross-validation (Rcᵥ²) and validation set (Rᵥ²) of 0.9988 and 0.9905, respectively, and root mean square error of cross-validation (RMSECV) and validation set (RMSEV) of 0.0068 and 0.0288%, respectively. Therefore, data fusion based on Raman and NIR spectroscopies coupled with PLS can give a rapid and accurate quantitative analysis of the methanol content in methanol–gasoline.

Quantitative analysis of Pb in soil by femtosecond-nanosecond double-pulse laser-induced breakdown spectroscopy

The effects of inter-pulse delay on the quantitative analysis of femtosecond-nanosecond double-pulsed laser-induced breakdown spectroscopy (fs-ns DP-LIBS) for assessing Pb in soil have been systematically studied in this work. A femtosecond pulse laser was focused to produce a filament, which was used to ablate the soil sample and produce an appreciable amount of aerosol particles ejected from the soil surface at a low density. Scattering images of the soil particles ejected from the soil surface were obtained, and the soil particles were found to have a delay of 800 µs. After an inter-pulse delay, a nanosecond Nd:YAG laser re-ablated the soil particles and obtained a spectral enhancement and a narrow line width. The quantitative analysis based on DP-LIBS for Pb in soil was strongly dependent on the inter-pulse delay time. With an inter-pulse delay time of 10 µs for DP-LIBS, the R-square factor (R2), relative standard deviation (RSD), root mean square error of cross-validation (RMSECV), and limit of detection (LOD) were 99.42%, 2.99%, 0.42 wt%, and 8.13 mg/kg, respectively. These findings demonstrate that DP-LIBS can be applied as an efficient spectroscopic tool to improve the quantitative analysis of Pb heavy metal in soil.

Multivariate determination of 10B isotopic ratio by laser-induced breakdown spectroscopy using multiple BO molecular emissions

Measurements of boron isotopic ratios have been investigated using LIBS, and combined LIBS and Molecular laser-induced fluorescence (MLIF). Mixtures of various ratios of research grade H310BO3 and H311BO3 in pellet form were interrogated with a Q-switched Nd:YAG laser operating at 532 nm. The resulting plasma was examined for their BO molecular bands in the 254–262 nm and 266–276 nm wavelength ranges. A minimum of three band heads of the β system B2Σ → X2Σ transitions were identified. The rovibronic isotopic shifts of the corresponding bands were measured and were conclusively compared to the literature. MLIF was applied to LIBS emission lines covering 253–271 nm to enhance some band heads, selectively. Both LIBS and LIBS-MLIF emissions were subject to multivariate statistical analysis to predict 10B isotopic ratios. Two PLS regression calibration models were examined to better examine the effects, sensitivity, accuracy of the laser-produced plasma excitation modalities based models through the figure of merit. For the full calibration set (21 samples), the root mean square error of cross-validation (RMSECV), the pseudo univariate LOD (LODpu) and the LOD interval ([LODmin,LODmax]) for 10B isotopes were improved from 1.61%, 4.81%, [2.64%, 3.49%] 10B isotopic ratio, respectively for LIBS to 0.98%, 2.40%, [2.19%, 2.81%] 10B isotopic ratio, respectively for LIBS-MLIF. However, using a random subset of the samples (14) as a calibration set and the rest as a test set, the root mean square error of prediction of 10B isotopic ratio in the test set improved from 2.95% to 1.16% 10B isotopic ratio, respectively for LIBS and LIBS-MLIF; and the LOD interval improved from [2.45%, 2.69%] to [1.88%, 2.12%] 10B isotopic ratio when calculated with cross-validated residual variance. Moreover, the prediction error of a test set improved from 2.95% for LIBS to 1.16% for LIBS-MLIF.

In-Line Monitoring the Degradation of Polypropylene under Multiple Extrusions Based on Raman Spectroscopy.

Polymer degradation is a common problem in the extrusion process. In this work, Raman spectroscopy, a robust, rapid, and non-destructive tool for in-line monitoring, was utilized to in-line monitor the degradation of polypropylene (PP) under multiple extrusions. Raw spectra were pretreated by chemometrics methods to extract variations of spectra and eliminate noise. The variation of Raman intensity with the increasing number of extrusions was caused by the scission of PP chains and oxidative degradation, and the variation trend of Raman intensity indicated that long chains were more likely to be damaged by the extrusion. For the quantitative analysis of degradation, the partial least square was used to build a model to predict the degree of PP degradation measured by gel permeation chromatography (GPC). For the calibration set, the coefficient of determination (R2) and the root mean square error of cross-validation (RMSECV) were 0.9859 and 1.2676%, and for the prediction set, R2 and the root mean square error of prediction (RMSEP) were 0.9752 and 1.7228%, which demonstrated the accuracy of the proposed model. The in-line Raman spectroscopy combined with the chemometrics methods was proved to be an accurate and highly effective tool, which can monitor the degradation of polymer in real time.

Vis/NIR reflectance spectroscopy for hybrid rice variety identification and chlorophyll content evaluation for different nitrogen fertilizer levels.

Nitrogen is one of the most important nutrient indicators for the growth of crops, and is closely related to the chlorophyll content of leaves and thus influences the photosynthetic ability of the crops. In this study, five hybrid rice varieties were cultivated during one entire growing period in one experimental field supplied with six nitrogen fertilizer levels. Visible and near infrared (vis/NIR) reflectance spectroscopy combined with multivariate analysis was used to identify hybrid rice varieties and nitrogen fertilizer levels, as well as to detect chlorophyll content associated with nitrogen levels. The support vector machine (SVM) algorithm was applied to identify five varieties of hybrid rice and six levels of nitrogen fertilizer. The results demonstrated that different varieties of hybrid rice for each nitrogen level can be well distinguished except for the highest nitrogen level, and no nitrogen level for each rice variety can be completely identified from the other five nitrogen levels. Further, 12 spectral indices combined with partial least square (PLS) analysis were applied for estimating chlorophyll content of rice leaves from plants subjected to different nitrogen levels, and a root mean square error of cross-validation (RMSECV) of 0.506, a coefficient of determination (R2) of 97.8% and a ratio of performance to deviation (RPD) of 4.6 for all rice varieties indicated this as a preferable procedure. This study demonstrates that Vis/NIR spectroscopy can have a great potential for identification of rice varieties and evaluation of nitrogen fertilizer levels.

Quantification of a cocrystal and its dissociated compounds in solid dosage form using transmission Raman spectroscopy

The performance of transmission Raman spectroscopy (TRS) for quantifying a cocrystal and its dissociation in solid dosage form was investigated. Some tablets containing 0%–20% (w/w) of a cocrystal of carbamazepine (CBZ)/succinic acid (SUC), 0%–4% of CBZ, 0%–4% of SUC, and 75%–99% of D-mannitol were prepared. The Raman spectra of these tablets were preprocessed using the standard normal variate (SNV) or multiplicative scatter correction (MSC) as well as the Savitzky Golay second derivative, and then, these were used to generate calibration models using partial least squares (PLS) regression. The performance of the model was superior when the MSC preprocessing spectra of the cocrystal between 200 and 1800 cm−1 were used for calibration. The determination coefficient of the PLS calibration curve for the CBZ/SUC cocrystal between 200 and 1800 cm−1 with MSC was 0.97, root mean square error of cross validation (RMSECV) was 1.16, and root mean square error of prediction (RMSEP) was 1.10. As in the case of the CBZ/SUC cocrystal, the performance of the model was superior when the MSC preprocessing spectra of CBZ and SUC between 200 and 1800 cm−1 were used for calibration. These data suggest that TRS is useful for quantifying a cocrystal and its dissociation compounds in solid dosage forms.

Estimation of the age of human semen stains by attenuated total reflection Fourier transform infrared spectroscopy: a preliminary study

Semen stain is one of the most important biological evidence at sexual crime scenes. Age estimation of human semen stains plays an important role in forensic work, and it is rarely studied due to lack of well-established methods. In this study, the technique called attenuated total reflection Fourier transform infrared spectroscopy (ATR-FTIR) coupled with advanced chemometric methods was employed to determine the age of semen stains on three different substrates: glass slides, tissues and fabric made of regenerated cellulose fibres up to 6 d. Partial least squares regression (PLSR) was used in conjunction with spectral analysis for age estimation, and the results generated high R2 values (cross-validation: 0.81, external validation: 0.74) but a narrow margin of error for root mean square error (RMSE) (RMSE of cross-validation: 0.77 d, RMSE of prediction: 1.02 d). Additionally, our results indicated the robustness of PLSR model was not weaken by the influence of different substrates in this study. Our results indicate that ATR-FTIR, combined with chemometric methods, shows great potential as a convenient and efficient tool for age estimation of semen stains. Moreover, the method could be applied to routine forensic investigations in the future.

Potentiality of using front face fluorescence spectroscopy for quantitative analysis of cow milk adulteration in buffalo milk.

In current study, synchronous front-face fluorescence spectroscopy together with partial least squares regression (PLSR) is used to predict the adulteration of cow and buffalo milk quantitatively. Fresh (unprocessed milk) samples of cow and buffalo were collected from local dairy farms. Fluorescence emission from milk samples mixed in different concentrations, show intensity variations at wavelengths 370-380 nm, 410 nm, 442 nm and 520-560 nm. Among them, the emissions at band position of 442 nm and 525 nm are highly selective between the two species and could help in finding adulteration of cow milk in buffalo milk and vice versa. The emissions at these wavelength positions correspond to fat-soluble vitamin-A as well as β-carotene. PLS regression is used as a statistical prediction model, which is developed by training with the emission spectra of milk samples having known level of adulterations. The developed model predicts the unknown level of adulterations by means of their spectral data. The goodness of the model is determined by the correlation coefficient R-square (r2) value, which in our case is 0.99. Furthermore, the model root mean square error in cross validation (RMSECV) and in prediction (RMSECP) remains 1.16 and 6.24 respectively. This approach can effectively be applied to determine milk adulterations among other species as well as in detecting external agents (fraudulent) added into milk and other dairy products by further studies.

A newly developed ocean significant wave height retrieval method from Envisat ASAR wave mode imagery

The main objective of this paper is to propose a newly developed ocean Significant Wave Height (SWH) retrieval method from Envisat Advanced Synthetic Aperture Radar (ASAR) imagery. A series of wave mode imagery from January, April and May of 2011 are collocated with ERA-Interim reanalysis SWH data. Based on the matched datasets, a simplified empirical relationship between 22 types of SAR imagery parameters and SWH products is developed with the Genetic Algorithms Partial Least-Squares (GA-PLS) model. Two major features of the backscattering coefficient S10 and the frequency parameter S10 are chosen as the optimal training feature subset of SWH retrieval by using cross validation. In addition, we also present a comparison of the retrieval results of the simplified empirical relationship with the collocated ERA-Interim data. The results show that the assessment index of the correlation coefficient, the bias, the root-mean-square error of cross validation (RMSECV) and the scattering index (SI) are 0.78, 0.07 m, 0.76 m and 0.5, respectively. In addition, the comparison of the retrieved SWH data between our simplifying model and the Jason-2 radar altimeter data is proposed in our study. Moreover, we also make a comparison of the retrieval of SWH data between our developed model and the wellknown CWAVE_ENV model. The results show that satisfying retrieval results are acquired in the low-moderate sea state, but major bias appears in the high sea state, especially for SWH>5 m.

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.

A quantitative analysis method assisted by image features in laser-induced breakdown spectroscopy

The determination accuracy of alloying elements in high alloy steel is generally poor in laser-induced breakdown spectroscopy (LIBS) due to their matrix effect. To solve this problem, an image quantitative analysis (IQA) method was proposed and verified by determining nickel (Ni) in 17 stainless steel samples in this work. The results showed that the coefficient of determination (R2) was increased from 0.9833 of a conventional spectrum quantitative analysis (SQA) method to 0.9996 of the IQA method, and the average relative error of cross-validation (ARECV) and root mean squared error of cross-validation (RMSECV) were decreased from 56.80% and 1.0818 wt% to 15.93% and 0.9866 wt%, respectively. Besides, the determinations of chromium (Cr) and silicon (Si) demonstrated the generalization ability of the IQA. This study provides an effective approach to improving the quantitative performance of LIBS through the combination of image processing and computer vision technology.

Evaluation of pH of curry soup containing coconut milk by near infrared spectroscopy

The pH is the important parameters to characterize the food deterioration and an indicative of food spoilage. The aim of this research was to apply the near infrared (NIR) spectroscopy to evaluate pH of curry soup containing coconut milk. The soup samples from mixing tank, water content adjusted tank, UHT pipe and laminated containers in the production line were collected. There were also the pH adjusted samples where the curry was made from the same recipe but increasing placed time for 2, 4 and 6 hr after 0 hr. There are 73 samples in total. The sample was scanned with FT-NIR spectrometer. A prediction model for pH was established using NIR spectral data in conjunction with partial least squares regression, which was validated using leave one out cross validation and test set validation. After validated by unknown samples, the leave one out cross validation model showed better prediction performance. The best model developed using first derivative spectra in 9403.8-7498.3, 6102-5446.3 and 4605.4-4242.9 cm−1 provided an coefficient of determination (r2), root mean square error of cross validation (RMSECV), bias and ratio of performance to interquartile (RPIQ) of 0.73, 0.28, 0.01 and 1.89. The model was usable for screening and some other “approximate” calibrations. The model could be improved for further development of robust model using more natural samples in evaluation of pH in the curry soup

Hyperspectral Imaging for the Nondestructive Quality Assessment of the Firmness of Nanguo Pears Under Different Freezing/Thawing Conditions.

Firmness changes in Nanguo pears under different freezing/thawing conditions have been characterized by hyperspectral imaging (HSI). Four different freezing/thawing conditions (the critical temperatures, numbers of cycles, holding time and cooling rates) were set in this experiment. Four different pretreatment methods were used: multivariate scattering correction (MSC), standard normal variate (SNV), Savitzky-Golay standard normal variate (S-G-SNV) and Savitzky-Golay multiplicative scattering correction (S-G-MSC). Combined with competitive adaptive reweighted sampling (CARS) to identify characteristic wavelengths, firmness prediction models of Nanguo pears under different freezing/thawing conditions were established by partial least squares (PLS) regression. The performance of the firmness model was analyzed quantitatively by the correlation coefficient (R), the root mean square error of calibration (RMSEC), the root mean square error of prediction (RMSEP) and the root mean square error of cross validation (RMSECV). The results showed that the MSC-PLS model has the highest accuracy at different cooling rates and holding times; the correlation coefficients of the calibration set (Rc) were 0.899 and 0.927, respectively, and the correlation coefficients of the validation set (Rp) were 0.911 and 0.948, respectively. The accuracy of the SNV-PLS model was the highest at different numbers of cycles, and the Rc and the Rp were 0.861 and 0.848, respectively. The RMSEC was 65.189, and the RMSEP was 65.404. The accuracy of the S-G-SNV-PLS model was the highest at different critical temperatures, with Rc and Rp values of 0.854 and 0.819, respectively, and RMSEC and RMSEP values of 74.567 and 79.158, respectively.

Spectroscopic determination of leaf chlorophyll content and color for genetic selection on Sassafras tzumu

BackgroundReflectance spectroscopy, like IR, VIS–NIR, combined with chemometric, has been widely used in plant leaf chemical analysis. But less studies have been made on the application of NIR reflectance spectroscopy to plant leaf color and pigments analysis and the possibility of using it for genetic breeding selection. Here, we examine the ability of NIR reflectance spectroscopy to determine the plant leaf color and chlorophyll content in Sassafras tzumu leaves and use the prediction results for genetic selection. Fresh and living tree leaves were used for NIR spectra collection, leaf color parameters (a*, b* and L*) and chlorophyll content were measured with standard analytical methods, partial least squares regression (PLSR) were used for model construction, the coefficient of determination (R2) [cross-validation ({text{R}}^{2}_{text{CV}}) and validation ({text{R}}^{2}_{text{V}})] and root mean square error (RMSE) [cross-validation (RMSECV) and validation (RMSEV)] were used for model performance evaluation, significant Multivariate Correlation algorithm was applied for model improvement, to find out the most important region related to the leaf color parameters and chlorophyll model, which have been simulated 100 times for accuracy estimation.ResultsLeaf color parameters (a*, b* and L*) and chlorophyll content were well predicted by NIR reflectance spectroscopy on fresh leaves in vivo. The mean {text{R}}^{2}_{text{CV}} and RMSECV of a*, b*, L* and chlorophyll content were (0.82, 4.43), (0.63, 3.72), (0.61, 2.35) and (0.86, 0.13%) respectively. Three most important NIR regions, including 1087, 1215 and 2219 nm, which were highly related to a*, b*, L* and chlorophyll content were found. NIR reflectance spectra technology can be successfully used for genetic breeding program. High heritability of a*, b*, L* and chlorophyll content (h2 = 0.77, 0.89, 0.78, 0.81 respectively) were estimated. Several families with bright red color or bright yellow color were selected.ConclusionsNIR spectroscopy is promising for the rapid prediction of leaf color and chlorophyll content of living fresh leaves. It has the ability to simultaneously measure multiple plant leaf traits, potentially allowing for quick and economic prediction in situ.

A novel hybrid feature selection strategy in quantitative analysis of laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy (LIBS) has been recognized as a significant tool for quantitative analysis of elements with its unique advantages, especially in combination with multivariate calibration methods. However, LIBS spectra typically include large amounts of high-dimensional data that affect the predictive accuracy of multivariate calibration based on LIBS. Feature selection, as an important preprocessing step in data mining, can improve the performance of the multivariate calibration model by eliminating the redundant and irrelevant features. In this study, a hybrid feature selection method based on V-WSP-PSO was proposed to improve the accuracy of LIBS analysis. The proposed method combines the advantages of V-WSP based filter method and particle swarm optimization (PSO) based wrapper method. The uncorrelated and redundant features were first eliminated by V-WSP method to form a simplified input subset, and then the retained features were further refined by PSO method to find a small set of features with high predictive accuracy. In order to evaluate the performance of proposed method, LIBS experiments were performed using 28 coal samples, and a nonlinear multivariate calibration method based on kernel extreme learning machine (KELM) was selected to implement the proposed hybrid feature selection method for calorific value determination of coal. Comparing the proposed method with several other feature selection methods shows that the V-WSP-PSO method is best in terms of number of selected features and predictive accuracy. Finally, 114 features were selected from full spectrum (27620 features) by V-WSP-PSO method and the best root mean square error of cross validation (RMSECV) and determination coefficient of cross validation (RCV2) were 0.4013 MJ/kg and 0.9908, root mean square error of prediction (RMSEP) and determination coefficient of prediction (RP2) were 0.3534 MJ/kg and 0.9894. The overall results demonstrate that the V-WSP-PSO method is more efficient to reduce the redundant features, calculation time and improve the model performance, and it is a good alternative for feature selection in multivariate calibration.

FT-NIR: a tool for rapid intracellular lipid quantification in oleaginous yeasts

BackgroundLipid extraction for quantification of fat content in oleaginous yeasts often requires strong acids and harmful organic solvents; it is laborious and time-consuming. Therefore, in most cases just endpoint measurements of lipid accumulation are performed and kinetics of intracellular lipid accumulation is difficult to follow. To address this, we created a prediction model using Fourier-transform near-infrared (FT-NIR) spectroscopy. This method allows to measure lipid content in yeast.MethodsThe FT-NIR calibration sets were constructed from spectra of freeze-dried cells of the oleaginous yeasts Rhodotorula toruloides CBS 14, Lipomyces starkeyi CBS 1807 and Yarrowia lipolytica CBS 6114. The yeast cells were obtained from different cultivation conditions. Freeze-dried cell pellets were scanned using FT-NIR in the Multi Purpose Analyser (MPA) from Bruker. The obtained spectra were assigned corresponding to total fat content, obtained from lipid extraction using a modified Folch method. Quantification models using partial least squares (PLS) regression were built, and the calibration sets were validated on independently cultivated samples. The R. toruloides model was additionally tested on Rhodotorula babjevae DBVPG 8058 and Rhodotorula glutinis CBS 2387.ResultsThe R2 of the FT-NIR model for R. toruloides was 98%, and the root mean square error of cross-validation (RMSECV) was 1.53. The model was validated using a separate set of R. toruloides samples with a root mean square error of prediction (RMSEP) of 3.21. The R2 of the Lipomyces model was 96%, with RMSECV 2.4 and RMSEP 3.8. The R2 of the mixed model, including all tested yeast strains, was 90.5%, with RMSECV 2.76 and RMSEP 3.22, respectively. The models were verified by predicting the total fat content in newly cultivated and freeze-dried samples. Additionally, the kinetics of lipid accumulation of a culture were followed and compared with standard lipid extraction methods.ConclusionsUsing FT-NIR spectroscopy, we have developed a faster, less laborious and non-destructive quantification of yeast intracellular lipid content compared to methods using lipid extraction.