Moving Window Partial Least Squares Research Articles

Improving Raman-Based Models for Real-Time Monitoring the CHO Cell Culture Process with Effective Variable Selection Strategies

Research has shown that Raman spectroscopy could be applied to monitor various components in mammalian cell culture in real time. In the process of application, it is necessary to ensure the performance of the Raman-based model. The variable selection strategy is an effective method that significantly influences the model performance and simplification. In this study, different variable selection strategies were evaluated, and the optimal variable selection strategy was determined for monitoring the CHO cell culture process. Firstly, a wide variety of spectral regions involving the Raman fingerprinting region and the C-H stretching region were investigated. Secondly, six different variable selection algorithms were meticulously assessed. Thirdly, the combination of different variable selection algorithms was used to improve model performance and simplify the model. Finally, the monitoring of cell culture processes was implemented. The findings underscored that commonly used spectral regions could improve the model performance but could not simplify the model well. Moving-window partial least square (MWPLS), genetic algorithm (GA), and random frog (RF) are more suitable for Raman modeling of the cell culture process, but they must be used after the spectral region selection. The combination of three variable selection algorithms (MWPLS-GA-RF) improved the model’s performance by 16–70% by selecting 30–60 variables, effectively simplifying the model. For glucose, lactate, viable cell density, and ammonium ion, real-time monitoring was performed well. This study will be helpful for researchers to select suitable variable selection strategies for building models for the real-time monitoring of cell culture.

Quantitative determination of TVB-N content for different types of refrigerated grass carp fillets using near-infrared spectroscopy combined with machine learning

This research aims to accurately forecast the freshness indicators (TVB-N) of skinned and skinless grass carp fillets by integrating near-infrared spectroscopy (NIR) with machine learning algorithms. By comparing the predictive accuracy of machine learning models for the two types of grass carp fillets, the most effective modeling method is identified. Methodologically, the study first applies orthogonal signal correction (OSC) and the first derivative among other algorithms for spectral pre-processing. Subsequently, competitive adaptive reweighted sampling (CARS), moving window partial least squares (MWPLS), and random frog (RF) are used for the selection of variables. Lastly, partial least squares regression (PLSR), support vector regression (SVR), backpropagation neural networks (BPNN), and particle swarm optimization-enhanced BP neural networks (PSO-BP) are employed to quantitatively analyze the NIR data. The most relevant results reveal that the (OSC+D1)-CARS-PSO-BP model exhibits superior predictive capabilities. Especially when applied to skin-on fish fillets (R2P =0.988, RMSEP=0.092), this model surpasses that for skinless fish fillet data (R2P =0.987, RMSEP=0.096). Therefore, combining near-infrared with machine learning to predict the freshness (TVB-N) of grass carp fillets based on skin-on samples is a more effective non-destructive testing method.

Interval interaction moving window partial least squares for wavelength interval selection in near infrared spectroscopy

Variable selection is a highly effective approach to improve model performance when analyzing and modeling data from near-infrared spectroscopy. Moving window partial least squares (MWPLS), a well-known and classical wavelength interval selection algorithm, was widely used in the field of near-infrared spectroscopy. However, it has gradually faded from the spotlight due to its limitations. In this study, a modified MWPLS method called interval interaction moving window partial least squares (iMWPLS), was proposed to improve some limitations of MWPLS, including the lack of consideration for the combination effects of variables, the tendency to select redundant wavelength intervals, and the need for artificial intervention. By utilizing the framework of MWPLS, it could iteratively search, test, and add the intervals with the local minimum errors to the set of basic intervals. The method has high sensitivity to the combination effects of variables and enables accurate selection of intervals. Three NIR datasets, including corn starch, pharmaceutical tablets, and soil dataset were tested to evaluate the performance of iMWPLS. The results show that iMWPLS has better performance than other seven wavelength selection methods, including MWPLS, SEPA-MWPLS, fiPLS, biPLS, siPLS, iVISSA, and iRF.

Predicting the Quality of Tangerines Using the GCNN-LSTM-AT Network Based on Vis–NIR Spectroscopy

Fruit quality assessment plays a crucial role in determining their market value, consumer acceptance, and post-harvest management. In recent years, spectroscopic techniques have gained significant attention as non-destructive methods for evaluating fruit quality. In this study, we propose a novel deep-learning network, called GCNN-LSTM-AT, for the prediction of five important parameters of tangerines using visible and near-infrared spectroscopy (Vis–NIR). The quality attributes include soluble solid content (SSC), total acidity (TA), acid–sugar ratio (A/S), firmness, and Vitamin C (VC). The proposed model combines the strengths of graph convolutional network (GCN), convolutional neural networks (CNNs), and long short-term memory (LSTM) to capture both spatial and sequential dependencies in the spectra data, and incorporates an attention mechanism to enhance the discriminative ability of the model. To investigate the effectiveness and stability of the model, comparisons with three traditional machine-learning algorithms—moving window partial least squares (MWPLS), random forest (RF), and support vector regression (SVR)—and two deep neural networks—DeepSpectra2D and CNN-AT—are provided. The results have shown that the GCNN-LSTM-AT network outperforms other algorithms and models, achieving accurate predictions for SSC (R2: 0.9885, RMSECV: 0.1430 ∘Brix), TA (R2: 0.8075, RMSECV: 0.0868%), A/S (R2: 0.9014, RMSECV: 1.9984), firmness (R2: 0.9472, RMSECV: 0.0294 kg), and VC (R2: 0.7386, RMSECV: 29.4104 mg/100 g) of tangerines.

Novel comprehensive variable selection algorithm based on multi-weight vector optimal selection and bootstrapping soft shrinkage

The dimensionality of spectral data is increasing with the advancements in spectral technology. Therefore, there is an urgent need to develop high-performance variable selection algorithms for chemometrics applications. This study proposes a novel multi-weight optimal-bootstrap soft shrinkage (MWO-BOSS) method for variable selection based on the bootstrap soft shrinkage (BOSS) algorithm, comprising three effective improvement strategies. First, the optimal weight vector of six weight vectors are used as weights of the selection variables, rather than the absolute value of the regression coefficients based only on a single weight vector. Second, in each loop, a step-by-step strategy is implemented to determine the optimal set of variables. Finally, a smoothing operation is added to the weight vector to improve the anti-noise performance of the algorithm. The performance of the MWO-BOSS algorithm was tested on the four spectral datasets corn protein, corn oil, soil, and beer and compared with six high-performance algorithms, namely interval partial least squares (iPLS), Moving Window Partial Least-Squares(MWPLS), competitive adaptive reweighted sampling (CARS), variable combinatorial population analysis (VCPA), VCPA-IRIV and BOSS. The results show that the MWO-BOSS algorithm effectively improves the predictive ability of the model, with MWO-BOSS-Step-S providing the best results among the four tested datasets.

Characterization of Apple Juice Adulteration by Attenuated Total Reflection–Mid-Infrared Spectroscopy and Partial Least Squares

Juice counterfeiting not only affects product quality but also deceives consumers into buying low-quality goods at high prices. Here is explored the feasibility of combining attenuated total reflection–mid-infrared (ATR-MIR) spectroscopy and interval-based partial least squares (PLS) and full-spectrum PLS models for identifying the adulteration of apple juice. A sample set composed of 41 concentrations of diluted juice was prepared. The adulteration concentration was obtained based on the juice spectrum and the corresponding model. The changeable moving window PLS model was shown to provide the best performance and may be an alternative to traditional approaches for quality control of juice.

Estimation of Aboveground Biomass of Potatoes Based on Characteristic Variables Extracted from UAV Hyperspectral Imagery

Aboveground biomass (AGB) is an important indicator for crop-growth monitoring and yield prediction, and accurate monitoring of AGB is beneficial to agricultural fertilization management and optimization of planting patterns. Imaging spectrometer sensors mounted on unmanned aerial vehicle (UAV) remote-sensing platforms have become an important technical method for monitoring AGB because the method is convenient, rapidly collects data and provides image data with high spatial and spectral resolution. To confirm the feasibility of UAV hyperspectral remote-sensing technology to estimate AGB, this study acquired hyperspectral images and measured AGB data over the potato bud, tuber formation, tuber growth, and starch-storage periods. The canopy spectrum obtained in each growth period was smoothed by using the Savitzky–Golay filtering method, and the spectral-reflection feature parameters, spectral-location feature parameters, and vegetation indexes were extracted. First, a Pearson correlation analysis was performed between the three types of characteristic spectral parameters and AGB, and the spectral parameters that reached a significant level of 0.01 in each growth period were selected. Next, the spectral parameters reaching a significance of 0.01 were optimized and screened by moving window partial least squares (MWPLS), Monte Carlo uninformative variable elimination (MC-UVE), and random frog (RF) methods, and the final model parameters were determined according to the thresholds of the root mean square error of cross-validation (RMSEcv), the reliability index, and the selected probability. Finally, the three optimal characteristic spectral parameters and their combinations were used to estimate the potato AGB in each growth period by combining the partial least squares regression (PLSR) and Gaussian process regression (GPR) methods. The results show that, (i) ranked from high to low, vegetation indexes, spectral-location feature parameters, and spectral-reflection feature parameters in each growth period are correlated with the AGB, and these correlations all first improve and then degrade in going from the budding period to the starch-storage period. (ii) The AGB estimation model based on the characteristic variables screened by the three methods in each growth period is most accurate with RF, less so with MC-UVE, and least accurate with MWPLS. (iii) Estimating the AGB with the same variables combined with the PLSR method in each growth period is more accurate than the corresponding GPR method, but the estimations produced by the two methods both show a trend of first improving and then worsening from the budding period to the starch-accumulation period. The accuracy of the estimation models constructed by PLSR and GPR from high to low is based on comprehensive variables, vegetation indexes, spectral-location feature parameters and spectral-reflection feature parameters. (iv) When combined with the RF-PLSR method to estimate AGB in each growth period, the best R2 values are 0.65, 0.68, 0.72, and 0.67, the corresponding RMSE values are 167.76, 162.98, 160.77, and 169.24 kg/hm2, and the corresponding NRMSE values are 19.76%, 16.01%, 15.04%, and 16.84%. The results of this study show that a variety of characteristic spectral parameters may be extracted from UAV hyperspectral images, that the RF method may be used for optimizing and screening, and that PLSR regression provides accurate estimates of the potato AGB. The proposed approach thus provides a rapid, accurate, and nondestructive way to monitor the growth status of potatoes.

Measurement of nitrogen content in rice plant using near infrared spectroscopy combined with different PLS algorithms

Nitrogen plays an important role in rice growth, and determination of nitrogen content in rice plants is of great significance in assessing plant nutritional status and allowing precision cultivation. Traditional chemical methods for determining nitrogen content have the disadvantages of destructive sampling and lengthy analysis times. Here, the feasibility of rapid nitrogen content analysis by near-infrared (NIR) spectroscopy of rice plants was studied. Spectral data from 447 rice samples at several growth stages were used to establish a predictive model. Different spectral preprocessing methods and characteristic selection methods were compared, such as interval partial least-squares (iPLS), synergy interval partial least-squares (SiPLS), and moving-window partial least-squares (mwPLS). The SiPLS method exhibited better performance than mwPLS or iPLS. Specifically, the combination of four subintervals (7, 26, 27, and 28), with characteristic bands at 5299–4451 cm−1 and 10445–10423 cm−1, resulted in the best model. The optimal SiPLS model had a correlation coefficient of 0.9533 and a root mean square error of prediction (RMSEP) of 0.1952 on the prediction set. Compared to using the full spectra, using SiPLS reduced the number of characteristics by 87 % in the model, and RMSEP was reduced from 0.2284 to 0.1952. The results demonstrate that NIR spectroscopy combined with the SiPLS algorithm can be applied to quickly determine nitrogen content in rice plants. This study provides a technical framework to guide future precision agriculture efforts with respect to nitrogen application.

Wavelength Selection Method Based on Absorbance Value Optimization to Near-Infrared Spectroscopic Analysis

Regarding absorption spectrum, high absorption corresponds to low light transmittance and relatively loud noise, whereas low absorption corresponds to low information content, which interferes with the modeling of spectral analysis. Appropriate absorbance level is necessary to improve spectral information content and reduces noise level. In this study, based on the selection of the upper and lower bounds of absorbance, the absorbance value optimization partial least squares (AVO-PLS) method was proposed for appropriate wavelength model selection. Near-infrared spectroscopic analysis of hyperlipidemia indicators, namely, total cholesterol (TC), and triglyceride (TG), was conducted to validate the predicted performance of AVO-PLS. Well-performed wavelength selection methods, namely, moving-window PLS (MW-PLS) of continuous type-and successive projections algorithm (SPA) of discrete type, were also conducted for comparison. The spectra were first corrected using Savitzky–Golay smoothing. Modeling was performed based on the multiple partitioning of calibration and prediction sets to avoid data over-fitting and achieve parameter stability. The selected absorbance ranged from 0.45 to 0.86 for TC and from 0.45 to 0.92 for TG, and the corresponding waveband combinations were 1,376–1,388 and 1,560–1840 nm for TC and 1,376–1,390 and 1,552–1,846 nm for TG. Among them, the waveband combination of TG covers TC’s one, and can be used for the high-precision cooperativity analysis of the two indicators. Using the independent validation samples, the RMSEP and RP of 0.164 mmol l−1 and 0.990 for TC and 0.096 mmol l−1 and 0.997 for TG were obtained by the cooperativity model. And the sensitivity and specificity for hyperlipidemia were 98.0 and 100%, respectively. These values were better than those of MW-PLS and SPA. Importantly, the proposed AVO-PLS is a novel multi-band optimization approach for improving prediction performance and applicability. This method is expected to obtain more applications.

Developing variable moving window PLS models: Using case of NOx emission prediction of coal-fired power plants

The efficiency of selective catalytic reduction denitrification heavily depends on the amount of ammonia injection, which is determined by the emission of nitrogen oxides (NOx) in flue gas. To accurately predict NOx emission of the coal-fired boiler with strong variable correlations, nonlinear and time-varying characteristics for determining the amount of injected ammonia, a soft sensor modeling method based on the moving window partial least squares (MWPLS) and locally weighted regression, referred to as variable exponentially weighted MWPLS (VEW-MWPLS), is proposed. It adjusts the window size in disguised form by automatically strengthen or weaken the information in the selected window according to the prediction errors of the current model. In this work, with the added new sample and the removed old sample, a series of rank-1 modification formulations are used to calculate both, the means and standard deviations among the input and output variables and the covariance and cross-covariance matrices so that a quick and adaptive update can be done for the PLS model. The numerical results have demonstrated that VEW-MWPLS algorithm can reduce the mean and standard deviation of prediction errors by one order of magnitude, and reduce the computational complexity by two orders of magnitude when being compared with other algorithms. Thus the proposed VEW-MWPLS is more suitable for predicting NOx emission online.

Rapid Detection of Adulteration in Dendrobium Huoshanense with Dendrobium Henanense by ATR-FTIR Combined with Multivariate Methods.

Dendrobium huoshanense (DHS) has long been used to make tea drink, soup, and porridge to protect eye and liver in many Southeast Asian countries for centuries. As a rare and endangered functional food, adulteration in DHS with visually similar but cheaper and more accessible plants such as Dendrobium henanense (DHN) because of their similarities in morphology has become prevalent in the market. In this study, the Attenuated Total Reflectance Fourier transform Infrared Spectroscopy (ATR-FTIR) combined with chemometric methods was established to detect fraudulent addition in DHS with DHN. The partial least squares (PLS) models based on the ATR-FTIR files of DHS mixed with different proportions of DHN were built under cross validation and tested with different independent data sets. To reduce the variables’ lack of information and increase the accuracy of the model, different wavelength selection methods including Moving Window Partial Least Squares (MW-PLS), Monte Carlo-uninformative variable elimination (MC-UVE), and interval random frog (iRF) were compared.The results showed that iRF performed the most perfectly with the number of latent variables (nLVs = 7), the lowest Root Mean Square Error of Cross-Validation (RMSECV = 7.37), and the maximum determination coefficients (R2 = 0.9721). The excellent performance of the model was proved by the low RMSEP value of 6.44% and the high R2 value of 0.9556. The developed method could rapidly quantify the adulteration DHN in DHS, and our study might provide an efficient and great potential technique tool for the rapid, green, low-cost, and nondestructive identification and quantification for DHS adulterated with DHN.

Optimal partner wavelength combination method applied to NIR spectroscopic analysis of human serum globulin

Human serum globulin (GLB), which contains various antibodies in healthy human serum, is of great significance for clinical trials and disease diagnosis. In this study, the GLB in human serum was rapidly analyzed by near infrared (NIR) spectroscopy without chemical reagents. Optimal partner wavelength combination (OPWC) method was employed for selecting discrete information wavelength. For the OPWC, the redundant wavelengths were removed by repeated projection iteration based on binary linear regression, and the result converged to stable number of wavelengths. By the way, the convergence of algorithm was proved theoretically. Moving window partial least squares (MW-PLS) and Monte Carlo uninformative variable elimination PLS (MC-UVE-PLS) methods, which are two well-performed wavelength selection methods, were also performed for comparison. The optimal models were obtained by the three methods, and the corresponding root-mean-square error of cross validation and correlation coefficient of prediction (SECV, RP,CV) were 0.813 g L−1 and 0.978 with OPWC combined with PLS (OPWC-PLS), and 0.804 g L−1 and 0.979 with MW-PLS, and 1.153 g L−1 and 0.948 with MC-UVE-PLS, respectively. The OPWC-PLS and MW-PLS methods achieved almost the same good results. However, the OPWC only contained 28 wavelengths, so it had obvious lower model complexity. Thus it can be seen that the OPWC-PLS has great prediction performance for GLB and its algorithm is convergent and rapid. The results provide important technical support for the rapid detection of serum.

A novel wavelength selection strategy for chlorophyll prediction by MWPLS and GA

The research proposed a novel wavelength selection strategy by the combination of moving window partial least squares (MWPLS) and genetic algorithm (GA) for the chlorophyll content detection of winter wheat canopy using spectroscopy technology. Firstly, the original spectral dataset was pre-processed by wavelet denosing, multiple scatter correction. Then, abnormal data samples were removed by Pauta Criterion and the dataset was divided into modeling set and validation set by SPXY. Finally, the sensitive wavebands were selected using MWPLS method and MWPLS+GA respectively and partial least squares (PLS) models were established for chlorophyll content prediction. For the model established by using all the wavebands in the region of 400-900 nm, its Rc2 and Rv2 were 0.4468 and 0.3821 respectively; its modeling root mean square error (RMSEM) and verification root mean square error (RMSEV) were 2.9057 and 1.7589 respectively. For the model established by using 151 wavebands selected by MWPLS, its Rc2 and Rv2 were 0.6210 and 0.5901 respectively; its RMSEM and RMSEV were 2.4007 and 1.6408 respectively. For the model established by using 36 wavebands selected by MWPLS+GA, its Rc2 and Rv2 were 0.7805 and 0.7497 respectively; its RMSEM and RMSEV were 1.8504 and 1.1315 respectively. The results show that wavelength selection can remove redundant information and improve model performance. The strategy of combining MWPLS with GA has also been proved to work well in selecting sensitive wavebands for chlorophyll content prediction. Keywords: MWPLS, GA, canopy spectral reflectance, Chlorophyll content prediction DOI: 10.25165/j.ijabe.20191205.4033 Citation: Liu H J, Li M Z, Zhang J Y , Gao D H , Sun H , Zhang M, et al. A novel wavelength selection strategy for chlorophyll prediction by MWPLS and GA. Int J Agric & Biol Eng, 2019; 12(5): 149–155.

The determination of plasma voriconazole concentration by surface-enhanced Raman spectroscopy combining chemometrics

In this study, a simple detection method was constructed using gold nanoparticles as a substrate in surface-enhanced Raman scattering that combined chemometrics to measure plasma voriconazole concentration. In this application, an adaptive, iteratively reweighted, penalized least squares (air-PLS) method was utilized to deduct matrix background and correct baseline spectral drift. A moving window partial least squares (MWPLS) method was used to select the optimal wavelength combination to construct a concentration prediction model. Evaluation of the results demonstrated that the final model had an excellent capability for prediction of plasma voriconazole concentration, applicable over the concentration range 3 × 10−3–200 μg/mL with a correlation coefficient of above 0.99. In conclusion, using surface enhanced Raman spectroscopy with chemometrics, we propose a novel and efficient approach that plasma voriconazole concentration can be measured in tens of seconds with a simple pretreatment.

Small moving window calibration models for soft sensing processes with limited history

While many soft-sensing strategies have been developed for monitoring chemical processes, most require extensive historical data to train the soft sensor calibration. Many of these strategies involve very complex models to account for drift and other effects in the process. When a process changes, perhaps because of some upset or a change in process parameters, it is often necessary to rebuild the soft-sensing model, a process that can take considerable time. This paper focuses on use of simple models that can be used to provide soft-sensing with minimal calibration data, and with minimal training of hyperparameters to permit process monitoring while a more complex model is rebuilt. The goal of this study was to explore simple soft sensing strategies for the case where a new process has been put online with limited history. Five soft sensor methodologies with two update conditions were compared on two experimentally-obtained datasets and one simulated dataset. The soft sensors investigated were moving window partial least squares regression (and a recursive variant), moving window random forest regression, the mean moving window of the property y, and a novel random forest partial least squares regression ensemble (RF-PLS), all of which can be used with small sample sizes so that they can be rapidly placed online. It was found that, on two of the datasets studied, small window sizes led to the lowest prediction errors for all of the moving window methods studied. On the majority of datasets studied, the RF-PLS calibration method offered the lowest one-step-ahead prediction errors compared to those of the other methods, and it demonstrated greater predictive stability at larger time delays than moving window PLS alone. Both the random forest and RF-PLS methods most adequately modeled datasets that did not feature purely monotonic increases in property values, but both methods performed more poorly than moving window PLS models on one dataset with purely monotonic property values. Other data dependent findings are presented and discussed.

A novel variable selection method based on stability and variable permutation for multivariate calibration

A novel variable selection method named stability and variable permutation (SVP) is proposed based on evolutionary principles of ‘intraspecific competition’ and ‘survival of the fittest’. In SVP, variables are selected in an iterative and competitive manner. In each iteration, Monte Carlo sampling (MCS) runs in sample space and variable space for stability and variable permutation, respectively. Variables are divided into elite variables and normal variables according to stability by adaptive reweighted sampling (ARS). Then, combining variable permutation analysis, exponentially decreasing function (EDF) is employed to select important variables from normal variables. Elite variables and important variables construct a new variable subset for the next iteration. After the selection iterations are terminated, a number of sub-models were generated by Monte Carlo cross validation (MCCV) for each variable subset. The optimal variable subset was considered to be the one with the minimum mean value and relatively low standard deviation of root mean square error of MCCV. The performance of SVP is evaluated by three near-infrared (NIR) datasets: corn oil dataset, diesel fuel total aromatics dataset and wheat protein dataset. Compared with methods of moving window PLS (MWPLS), Monte Carlo uninformative variable elimination (MCUVE), competitive adaptive reweighted sampling (CARS), stability competitive adaptive reweighted sampling (SCARS), variable permutation population analysis (VPPA) and genetic algorithm (GA), SVP shows better prediction results.

Analysis of paclitaxel concentration in rat plasma by Raman spectrums combined with partial least square

Partial least square (PLS) combining with Raman spectroscopy was applied to develop predictive models for plasma paclitaxel concentration detection. In this experiment, 312 samples were scanned by Raman spectroscopy. High performance liquid chromatography (HPLC) was applied to determine the paclitaxel concentration in 312 rat plasma samples. Monte Carlo partial least square (MCPLS) method was successfully performed to identify the outliers and the numbers of calibration set. Based on the values of degree of approach ( D a ), moving window partial least square (MWPLS) was used to choose the suitable preprocessing method, optimum wavelength variables and the number of latent variables. The correlation coefficients between reference values and predictive values in both calibration set ( R c2) and validation set ( R p2) of optimum PLS model were 0.933 1 and 0.926 4, respectively. Furthermore, an independent verification test was performed on the prediction model. The results showed that the correlation error of the 20 validation samples was 9.36%±2.03%, which confirmed the well predictive ability of established PLS quantitative analysis model.

Novel near-infrared spectrum analysis tool: Synergy adaptive moving window model based on immune clone algorithm

This paper presents a novel spectrum analysis tool named synergy adaptive moving window modeling based on immune clone algorithm (SA-MWM-ICA) considering the tedious and inconvenient labor involved in the selection of pre-processing methods and spectral variables by prior experience. In this work, immune clone algorithm is first introduced into the spectrum analysis field as a new optimization strategy, covering the shortage of the relative traditional methods. Based on the working principle of the human immune system, the performance of the quantitative model is regarded as antigen, and a special vector corresponding to the above mentioned antigen is regarded as antibody. The antibody contains a pre-processing method optimization region which is created by 11 decimal digits, and a spectrum variable optimization region which is formed by some moving windows with changeable width and position. A set of original antibodies are created by modeling with this algorithm. After calculating the affinity of these antibodies, those with high affinity will be selected to clone. The regulation for cloning is that the higher the affinity, the more copies will be. In the next step, another import operation named hyper-mutation is applied to the antibodies after cloning. Moreover, the regulation for hyper-mutation is that the lower the affinity, the more possibility will be. Several antibodies with high affinity will be created on the basis of these steps. Groups of simulated dataset, gasoline near-infrared spectra dataset, and soil near-infrared spectra dataset are employed to verify and illustrate the performance of SA-MWM-ICA. Analysis results show that the performance of the quantitative models adopted by SA-MWM-ICA are better especially for structures with relatively complex spectra than traditional models such as partial least squares (PLS), moving window PLS (MWPLS), genetic algorithm PLS (GAPLS), and pretreatment method classification and adjustable parameter changeable size moving window PLS (CA-CSMWPLS). The selected pre-processing methods and spectrum variables are easily explained. The proposed method will converge in few generations and can be used not only for near-infrared spectroscopy analysis but also for other similar spectral analysis, such as infrared spectroscopy.

Grid search parametric optimization for FT-NIR quantitative analysis of solid soluble content in strawberry samples

Grid search technology is proposed to choose the influencing parameters for interval partial least squares (iPLS) and moving window partial least squares (MWPLS) models in the Fourier transform near infrared (FT-NIR) spectrometric quantitative determination of solid soluble content (SSC) in strawberry samples. The objective of grid search is to find out a robust way to ensure that the selected parameters of iPLS and MWPLS would output the informative wavebands leading to improved modeling results. For the improvement of model accuracy, the grid search technique is designed for locating the informative wavebands via influential algorithmic parameters on FT-NIR regions corresponding to different spectral responses of molecule vibration. The commonly used iPLS and MWPLS algorithms are modified in cooperation with the grid search technique, to identify the informative wavebands for the improvement of the model prediction performances. A further integration of the wavebands from different regions could obtain some more accurate models based on the calibrating-validating-testing (CVT) sample division framework. The optimized parameters have the potential to be applied to the development of online and realtime measurement for fruit industry.

Vis-NIR spectroscopy with moving-window PLS method applied to rapid analysis of whole blood viscosity.

A rapid analytical method of human whole blood viscosity with low, medium, and high shear rates [WBV(L), WBV(M), and WBV(H), respectively] was developed using visible and near-infrared (Vis-NIR) spectroscopy combined with a moving-window partial least squares (MW-PLS) method. Two groups of peripheral blood samples were collected for modeling and validation. Separate analytical models were established for male and female groups to avoid interference in different gender groups and improve the homogeneity and prediction accuracy. Modeling was performed for multiple divisions of calibration and prediction sets to avoid over-fitting and achieve parameter stability. The joint analysis models for three indicators were selected through comprehensive evaluation of MW-PLS. The selected joint analysis models were 812-1278nm for males and 670-1146nm for females. The root-mean-square errors (SEP) and the correlation coefficients of prediction (RP) for all validation samples were 0.54mPa•s and 0.91 for WBV(L), 0.25mPa•s and 0.92 for WBV(M), and 0.22mPa•s and 0.90 for WBV(H). Results indicated high prediction accuracy, with prediction values similar to the clinically measured values. Overall, the findings confirmed the feasibility of whole blood viscosity quantification based on Vis-NIR spectroscopy with MW-PLS. The proposed rapid and simple technique is a promising tool for surveillance, control, and treatment of cardio-cerebrovascular diseases in large populations. Graphical Abstract The caption/legend of the online abstract figure: The selected wavebands and the prediction effects for the three indicators of whole blood viscosity.