Spatter Rate Estimation of GMAW-S based on Partial Least Square Regression

This paper analyzes the drop transfer process in gas metal arc welding in short-circuit transfer mode （GMAW-S） in order to develop an optimized spatter rate model that can be used on line. According to thermodynamic characters and practical behavior, a complete arcing process is divided into three sub-processes： arc re-ignition, energy output and shorting preparation. Shorting process is then divided as drop spread, bridge sustention and bridge destabilization. Nine process variables and their distribution are analyzed based on welding experiments with high-speed photos and synchronous current and voltage signals. Method of variation coefficient is used to reflect process consistency and to design characteristic parameters. Partial least square regression （PLSR） is utilized to set up spatter rate model because of severe correlativity among the above characteristic parameters. PLSR is a new multivariate statistical analysis method, in which regression modeling, data simplification and relativity analysis are included in a single algorithm. Experiment results show that the regression equation based on PLSR is effective for on-line predicting spatter rate of its corresponding welding condition.

Estimating canopy closure density and above-ground tree biomass using partial least square methods in Chinese boreal forests

Boreal forests play an important role in global environment systems. Understanding boreal forest ecosystem structure and function requires accurate monitoring and estimating of forest canopy and biomass. We used partial least square regression （PLSR） models to relate forest parameters, i.e. canopy closure density and above ground tree biomass, to Landsat ETM＋ data. The established models were optimized according to the variable importance for projection （VIP） criterion and the bootstrap method, and their performance was compared using several statistical indices. All variables selected by the VIP criterion passed the bootstrap test （p〈0.05）. The simplified models without insignificant variables （VIP 〈1） performed as well as the full model but with less computation time. The relative root mean square error （RMSE%） was 29% for canopy closure density, and 58% for above ground tree biomass. We conclude that PLSR can be an effective method for estimating canopy closure density and above ground biomass.

NIR Hyperspectral Imaging Measurement of Sugar Content in Peach Using PLS Regression

Near infrared （NIR） hyperspectral imaging measurement of sugar content in peach was introauced. NIR spectral images （650～1 000 nm, resolution： 2 nm） of peach samples were captured with developed hyperspectral imaging setup. Partial least square （PLS） regression prediction model was developed to estimate the sugar content in peach; step-wise backward method was utilized to determine optimal wavelength subsets. Experimental results show that the calibration model with optimal wavelength subsets has a correlation coefficient of prediction of 0.97 and a standard error of prediction of 0.19, the prediction accuracy is higher than the calibration model applied over the whole wavelength, which proves that variable selection plays an important role in improving the prediction accuracy of PLS regression model.

Process Characterization of the Transesterification of Rapeseed Oil to Biodiesel Using Design of Experiments and Infrared Spectroscopy

For optimization of production processes and product quality,often knowledge of the factors influencing the process outcome is compulsory.Thus,process analytical technology(PAT)that allows deeper insight into the process and results in a mathematical description of the process behavior as a simple function based on the most important process factors can help to achieve higher production efficiency and quality.The present study aims at characterizing a well-known industrial process,the transesterification reaction of rapeseed oil with methanol to produce fatty acid methyl esters(FAME)for usage as biodiesel in a continuous micro reactor set-up.To this end,a design of experiment approach is applied,where the effects of two process factors,the molar ratio and the total flow rate of the reactants,are investigated.The optimized process target response is the FAME mass fraction in the purified nonpolar phase of the product as a measure of reaction yield.The quantification is performed using attenuated total reflection infrared spectroscopy in combination with partial least squares regression.The data retrieved during the conduction of the DoE experimental plan were used for statistical analysis.A non-linear model indicating a synergistic interaction between the studied factors describes the reactor behavior with a high coefficient of determination(R^(2))of 0.9608.Thus,we applied a PAT approach to generate further insight into this established industrial process.

A Comparison of CNN and PLSR for Glucose Monitoring Using Mid-Infrared Absorption Spectroscopy

With the development of mid-infrared (MIR) photoelectric devices, mid-infrared spectroscopy has become one of the important methods for non-invasive detection of blood glucose. The mid-infrared region (4000 - 400 cm-1) has the well-known fingerprint region (1200 - 800 cm-1) of glucose, which has clearer characteristic absorption peaks and better specificity. There is a lot of molecular information about glucose in the MIR. The non-invasive detection of blood glucose by mid-infrared spectroscopy needs to achieve certain accuracy, and the quantitative model is an important factor affecting the accuracy of glucose detection. In this paper, the samples of imitation solution containing only glucose and the samples of imitation mixed solution are taken as the research objects, and the mid-infrared spectral data of the samples are collected. The full spectrum partial least squares Regression (PLSR) model, SNV + Ctr-PLSR model, MSC + Ctr-PLSR model, and convolutional neural networks (CNN) model of 3000 - 900 cm-1 band were constructed. Full spectrum PLS model and CNN model of 1200 - 900 cm-1 band were constructed. The experimental results show that the optimal model of the two bands is CNN, then the correlation coefficient of prediction set (Rp) of 3000 - 900 cm-1 band is 0.95, and the root mean square error of pre-diction set (RMSEP) value is 22.10. The Rp of 1200 - 900 cm-1 band is 0.95, and the RMSEP value is 22.54. The research results show that CNN is a promising method, which has higher accuracy than PLSR, and is especially suitable for modeling human complex environment. In addition, the study provides a theoretical and practical basis for CNN in feature selection and model interpretation.

Application of NIR spectroscopy for firmness evaluation of peaches

The use of near infrared （NIR） spectroscopy was proved to be a useful tool for quality analysis of fruits. A bifurcated fiber type NIR spectrometer, with a detection range of 800-2500 nm by InGaAs detector, was used to evaluate the firmness of peaches. Anisotropy of NIR spectra and firmness of peaches in relation to detecting positions of different parts （including three latitudes and three longitudes） were investigated. Both spectra absorbency and firmness of peach were influenced by longitudes （i, ii, iii） and latitudes （A, B, C）. For modeling, two thirds of the samples were used as the calibration set and the remaining one third were used as the validation or prediction set. Partial least square regression （PLSR） models for different longitude and latitude spectra and for the whole fruit show that collecting several NIR spectra from different longitudes and latitudes of a fruit for NIR calibration modeling can improve the modeling performance. In addition, proper spectra pretreatments like scattering correction or derivative also can enhance the modeling performance. The best results obtained in this study were from the holistic model with multiplicative scattering correction （MSC） pretreatment, with correlation coefficient of cross-validation γcv=0.864, root mean square error of cross-validation RMSECV=6.71 N, correlation coefficient of calibration r=0.948, root mean square error of calibration RMSEC=4.21 N and root mean square error of prediction RMSEP=5.42 N. The results of this study are useful for further research and application that when applying NIR spectroscopy for objectives with anisotropic differences, spectra and quality indices are necessarily measured from several parts of each object to improve the modeling performance.

Spectroscopic Leaf Level Detection of Powdery Mildew for Winter Wheat Using Continuous Wavelet Analysis

Powdery mildew （Blumeria graminis） is one of the most destructive crop diseases infecting winter wheat plants, and has devastated millions of hectares of farmlands in China. The objective of this study is to detect the disease damage of powdery mildew on leaf level by means of the hyperspectral measurements, particularly using the continuous wavelet analysis. In May 2010, the reflectance spectra and the biochemical properties were measured for 114 leaf samples with various disease severity degrees. A hyperspectral imaging system was also employed for obtaining detailed hyperspectral information of the normal and the pustule areas within one diseased leaf. Based on these spectra data, a continuous wavelet analysis （CWA） was carried out in conjunction with a correlation analysis, which generated a so-called correlation scalogram that summarizes the correlations between disease severity and the wavelet power at different wavelengths and decomposition scales. By using a thresholding approach, seven wavelet features were isolated for developing models in determining disease severity. In addition, 22 conventional spectral features （SFs） were also tested and compared with wavelet features for their efficiency in estimating disease severity. The multivariate linear regression （MLR） analysis and the partial least square regression （PLSR） analysis were adopted as training methods in model mildew on leaf level were found to be closely related with the development. The spectral characteristics of the powdery spectral characteristics of the pustule area and the content of chlorophyll. The wavelet features performed better than the conventional SFs in capturing this spectral change. Moreover, the regression model composed by seven wavelet features outperformed （R2=0.77, relative root mean square error RRMSE=0.28） the model composed by 14 optimal conventional SFs （R2---0.69, RRMSE--0.32） in estimating the disease severity. The PLSR method yielded a higher accuracy than the MLR method. A combination of CWA and PLSR was found to be promising in providing relatively accurate estimates of disease severity of powdery mildew on leaf level.

Quantitative analysis of ammonium salts in coking industrial liquid waste treatment process based on Raman spectroscopy

Quantitative analysis of ammonium salts in the process of coking industrial liquid waste treatment is successfully performed based on a compact Raman spectrometer combined with partial least square(PLS) method. Two main components(NH4SCN and(NH4)2S2O3) of the industrial mixture are investigated. During the data preprocessing, wavelet denoising and an internal standard normalization method are employed to improve the predicting ability of PLS models. Moreover,the PLS models with different characteristic bands for each component are studied to choose a best resolution. The internal and external calibration results of the validated model show a mass percentage error below 1% for both components.Finally, the repeatabilities and reproducibilities of Raman and reference titration measurements are also discussed.

The use of milk Fourier transform midinfrared spectra and milk yield to estimate heat production as a measure of efficiency of dairy cows

Background:Transformation of feed energy ingested by ruminants into milk is accompanied by energy losses via fecal and urine excretions,fermentation gases and heat.Heat production may differ among dairy cows despite comparable milk yield and body weight.Therefore,heat production can be considered an indicator of metabolic efficiency and directly measured in respiration chambers.The latter is an accurate but time-consuming technique.In contrast,milk Fourier transform mid-infrared(FTIR)spectroscopy is an inexpensive high-throughput method and used to estimate different physiological traits in cows.Thus,this study aimed to develop a heat production prediction model using heat production measurements in respiration chambers,milk FTIR spectra and milk yield measurements from dairy cows.Methods:Heat production was computed based on the animal’s consumed oxygen,and produced carbon dioxide and methane in respiration chambers.Heat production data included 16824-h-observations from 64 German Holstein and 20 dual-purpose Simmental cows.Animals were milked twice daily at 07:00 and 16:30 h in the respiration chambers.Milk yield was determined to predict heat production using a linear regression.Milk samples were collected from each milking and FTIR spectra were obtained with MilkoScan FT 6000.The average or milk yield-weighted average of the absorption spectra from the morning and afternoon milking were calculated to obtain a computed spectrum.A total of 288 wavenumbers per spectrum and the corresponding milk yield were used to develop the heat production model using partial least squares(PLS)regression.Results:Measured heat production of studied animals ranged between 712 and 1470 kJ/kg BW0.75.The coefficient of determination for the linear regression between milk yield and heat production was 0.46,whereas it was 0.23 for the FTIR spectra-based PLS model.The PLS prediction model using weighted average spectra and milk yield resulted in a cross-validation variance of 57%and a root mean square error of prediction of 86.5 kJ/kg BW0.75.The ratio of performance to deviation(RPD)was 1.56.Conclusion:The PLS model using weighted average FTIR spectra and milk yield has higher potential to predict heat production of dairy cows than models applying FTIR spectra or milk yield only.

Milk Production of Sarda Suckler Cows with Different Calving Period

The study explored the relationship between the performance of calves and calving season in a Mediterranean rangeland-based beef livestock system.Twenty multiparous Sarda cows,grazing on a natural pasture,with two distinct calving periods(group A,11 animals,calving date 15/10/2016±16(means±s.d.),and group W,nine animals,calving date 26/01/2017±11)were used.Meteorological data,herbage quality,daily milk yield(DMY),total milk yield(TMY),body weight(BW)of cows and calf,body-weight daily gain(ADG)of calves,body condition score(BCS)and calving interval(CI)of cows were assessed.A mixed-effects model was used to DMY and ADG data while TMY,BCS,weaning weight(WW)and CI data were analyzed by a linear model.The most determining factors in the DMY and ADG were detected by means of partial least square regression(PLSR)procedure.Group W showed higher DMY(6.5±0.3 kg/d vs.4.5±0.3 kg/d,p<0.001)and TMY(1,189±70 kg vs.830±60 kg,p=0.002)than Group A,but this did not result in a greater ADG of calves(Group A:0.83±0.04 kg/d/animal and Group W:0.99±0.09 kg/d/animal,p-value not significant)or WW when adjusted for their age(Group A:216±14 kg/animal and Group W:250±22 kg/animal,p-value not significant).In contrast,the WW actually measured were higher in Group A than in Group W(257±7 kg vs.175±8 kg,p<0.001).The Group W cows experienced a minor CI than Group A cows(288±13 d vs.320±8 d,p=0.04).The results of PLSR suggest that the factors with utmost importance for both DMY and ADG were the age and the body-weight of cows,highlighting the excellent maternal ability of Sarda breed and its good adaptation to environment.

Evaluation of the Ability to Apply Near-Infrared Spectroscopy on Direct Assay of Acyclovir in Tablets

This paper aimed at developing a simple and fast approach using chemometrics processing for direct assay of acyclovir in tablets by NIR （near infrared） spectroscopy in diffuse reflectance mode. In making trials with 5 different tablet matrices, the experimental results showed that regardless the matrix variation, it was always possible to construct a quantitative model with suitable linear range, accuracy and precision for direct assay of acyclovir in tablet from NIR spectra. Therefore, the approach used in this study was suitable for on-site fast assay of APIs in tablets during manufacturing process or in post-marketing surveillance of drug quality.

Spatio-temporal assessment of soil salinization utilizing remote sensing derivatives,and prediction modeling:Implications for sustainable development

This study aims to investigate the combined use of multi-sensor datasets(Landsat 4–5&8 OLI satellite imagery,spatial resolution=30 m)coupled with field studies to evaluate spatio-temporal dynamics of soil salinization along the coastal belt in West Bengal,India.This study assesses soil salinization by mapping the salinity and electrical conductivity of saturation extract(ECe)and utilizing spectral signatures for estimating soil salinity.The SI change(%)was analyzed(2021–1995),categorizing increases in salinity levels into 5%,10%,and 50%changes possibly due to salt encrustation on the soil layers.The land use land cover(LULC)change map(2021–1995)demonstrates that the study area is continuously evolving in terms of urbanization.Moreover,in the study area,soil salinity ranges from 0.03 ppt to 3.87 ppt,and ECe varies from 0.35 dSm^(-1)to 52.85 dSm^(-1).Additionally,vulnerable saline soil locations were further identified.Classification of soil salinity based on ECe reveals that 26%of samples fall into the nonsaline category,while the rest belong to the saline category.The Spectral signatures of the soil samples(n=19)acquired from FieldSpec hand spectrometer show significant absorption features around 1400,1900,and 2250 nm and indicate salt minerals.The results of reflectance spectroscopy were crossvalidated using X-ray fluorescence and scanning electron microscopy.This study also employed partial least square regression(PLSR)approach to predict ECe(r^(2)=0.79,RMSE=3.29)and salinity parameters(r^(2)=0.75,RMSE=0.51),suggesting PLSR applicability in monitoring salt-affected soils globally.This study’s conclusion emphasizes that remote sensing data and multivariate analysis can be crucial tools for mapping spatial variations and predicting soil salinity.It has also been concluded that saline groundwater used for irrigation and aqua-cultural activities exacerbates soil salinization.The study will help policymakers/farmers identify the salt degradation problem more effectively and adopt immediate mitigation measures.

Ultrasonic concentration measurement of citrus pectin aqueous solutions using PC and PLS regression

This work demonstrated the use of multivariate statistical techniques called principal component(PC)and partial least squares(PLS)to extract the acoustic features of citrus pectin water solution.The concentration of citrus pectin water solution was predicted by PC and PLS regression method using the spectra of ultrasound pulse echoes travelling through mixtures.The values of root mean square error of validation(RMSEV)were 0.0675 g/100 g and 0.0662 g/100 g for PC and PLS regression model,respectively.Since the response variable was taken into account,PLS regression model was more accurate than PC regression model.Also,a method for temperature compensation was proposed to correct the impact of temperature variation on analyzed data.The proposed methods for pectin concentration measurement are easily adaptable to similar applications using existing hardware.

Application of Visible/Near-Infrared Spectra in Modeling of Soil Total Phosphorus

Overabundance of phosphorus (P) in soils and water is of great concern and has received much attention in Florida, USA. Therefore, it is essential to analyze and predict the distribution of P in soils across large areas. This study was undertaken to model the variation of soil total phosphorus (TP) in Florida. A total of 448 soil samples were collected from different soil types. Soil samples were analyzed by chemical reference method and scanned in the visible/near-infrared (VNIR) region of 350-2 500 nm. Partial least squares regression (PLSR) calibration model was developed between chemical reference values and VNIR values. The coefficient of determination (R2) and the root mean squares error (RMSE) of calibration and validation sets, and the residual prediction deviation (RPD) were used to evaluate the models. The R2in calibration and validation for log-transformed TP (log TP) were 0.69 and 0.65, respectively, indicating that VNIR calibration obtained in this study accounted for at least 65% of the variance in log TP using only VNIR spectra, and the high RPD of 2.82 obtained suggested that the spectral model derived in this study was suitable and robust to predict TP in a wide range of soil types, being representative of Florida soil conditions.

Determination of Soil Parameters in Apple-Growing Regions by Near-and Mid-Infrared Spectroscopy

Soil quality monitoring is important in precision agriculture.This study aimed to examine the possibility of assessing the soil parameters in apple-growing regions using spectroscopic methods.A total of 111 soil samples were collected from 11 typical sites of apple orchards,and the croplands surrounding them.Near-infrared(NIR) and mid-infrared(MIR) spectra,combined with partial least square regression,were used to predict the soil parameters,including organic matter(OM) content,pH,and the contents of As,Cu,Zn,Pb,and Cr.Organic matter and pH were closely correlated with As and the heavy metals.The NIR model showed a high prediction accuracy for the determination of OM,pH,and As,with correlation coefficients(r) of 0.89,0.89,and 0.90,respectively.The predictions of these three parameters by MIR showed reduced accuracy,with r values of 0.77,0.84,and 0.92,respectively.The heavy metals could also be measured by spectroscopy due to their correlation with organic matter.Both NIR and MIR had high correlation coefficients for the determination of Cu,Zn,and Cr,with standard errors of prediction of 2.95,10.48,and 9.49 mg kg-1 for NIR and 3.69,5.84,and 6.94 mg kg-1 for MIR,respectively.Pb content behaved differently from the other parameters.Both NIR and MIR underestimated Pb content,with r values of 0.67 and 0.56 and standard errors of prediction of 3.46 and 2.99,respectively.Cu and Zn had a higher correlation with OM and pH and were better predicted than Pb and Cr.Thus,NIR spectra could accurately predict several soil parameters,metallic and nonmetallic,simultaneously,and were more feasible than MIR in analyzing soil parameters in the study area.

Rapid detection of aflatoxin B_(1) in paddy rice as analytical quality assessment by near infrared spectroscopy

A rapid identification method for aflatoxin B_(1) in paddy rice samples was developed by using near infrared spectroscopy under a wavelength range of 1000-2500 nm.Eighty paddy rice samples were collected from both natural and artificial infection with aflatoxin B_(1) to build the calibration models based on the partial least square regression method.The best predictive model to detect aflatoxin B_(1) in paddy rice was obtained using standard normal variate detrending spectra,with a correlation of 0.850,and a standard error of prediction of 3.211%.Therefore,the result showed that near infrared spectroscopy could be a useful instrumental method for determining aflatoxin B_(1) in paddy rice.The near infrared spectroscopy methodology can be applied to the monitoring of aflatoxin fungal contamination in postharvest paddy rice during storage and may become a powerful tool for the safety of grain and grain products.

LW-NIR hyperspectral imaging for rapid prediction of TVC in chicken flesh

Total viable count(TVC)is often used as an important indicator for chicken freshness evaluation.In this study,112 fresh chicken flesh samples were acquired after slaughtered and their hyperspectral images were collected in the LW-NIR(900-1700 nm)range.The full LW-NIR spectra(486 wavebands)within the images were extracted and applied to related to reference TVC values measured in different storage periods,using partial least squares regression(PLSR)algorithm,resulting in high correlation coefficients(R)and low root mean square errors(RMSE),for either raw spectra or pretreatment spectra.By using regression coefficients(RC)method,20,18,17 and 20 optimal wavebands were respectively selected from raw spectra,baseline correction(BC)spectra,Savitzky-Golay convolution smoothing(SGCS)spectra and standard normal variate(SNV)spectra and applied for the optimization of original full waveband PLSR model.By comparison,RC-PLSR model based on the SGCS spectra showed a better performance in TVC prediction with RC of 0.98 and RMSEC of 0.35 log10 CFU/g in calibration set,and RP of 0.98 and RMSEP of 0.44 log10 CFU/g in prediction set.At last,by transferring the best RC-PLSR model,the dynamic TVC change during the storage was visualized by color maps to indicate the TVC spoilage degree.The overall study revealed that LW-NIR hyperspectral imaging combined with PLSR could be used to predict the freshness of chicken flesh.

Winter wheat biomass estimation based on canopy spectra

The winter wheat aboveground biomass is an important agronomic parameter to estimate the growth status,and evaluate the yield and quality.Spectrum technique provides a nondestructive and fast method for estimating the winter wheat biomass.In order to find the optimum model by analyzing the wheat canopy spectral characteristic during the whole growth period,field trails were conducted at the National Demonstration Base of Precision Agriculture in Beijing Xiaotangshan town.A portable spectrometer(200-1100 nm)was used to collect the wheat canopy spectra of different varieties at the different growth stages(green stage,jointing stage,booting stage,heading stage and filling stage),clipping the winter wheat at ground level at the same time.Regression and correlation analysis were used to establish the winter wheat biomass estimation models in this study.The results showed that the biggest different bands of the winter wheat canopy spectral reflection curves mainly lied along the blue and near-infrared bands.The spectral reflectance at 678 nm in the visible light range had the best correlation with the biomass(correlation=0.724).The monadic regression analysis,the multiple regression analysis and the partial least squares regression analysis were applied to establish the biomass estimation models,among which the partial least squares regression(PLS)model had higher modeling precision.The R2 of the calibration and validation were 0.916 and 0.911,respectively.The root-mean-square error(RMSE)of the calibration and validation were 0.090 kg and 0.094 kg(Sample area 50 cm×60 cm).The results indicated that the PLS model(400-1000 nm)could fully estimate the aboveground biomass in the whole growth period of wheat with a better measurement accuracy.

Volatile profile analysis and quality prediction of Longjing tea(Camellia sinensis) by HS-SPME/GC-MS

This study aimed to analyze the volatile chemical profile of Longjing tea, and further develop a prediction model for aroma quality of Longjing tea based on potent odorants. A total of 21 Longjing samples were analyzed by headspace solid phase microextraction (HS-SPME) coupled with gas chromatography-mass spectrometry (GC-MS).Pearson's linear correlation analysis and partial least square (PLS) regression were applied to investigate the relationship between sensory aroma scores and the volatile compounds. Results showed that 60 volatile compound scould be commonly detected in this famous green tea. Terpenes and esters were two major groups characterized,representing 33.89% and 15.53% of the total peak area respectively. Ten compounds were determined to contribute significantly to the perceived aroma quality of Longjing tea, especially linalool (0.701), nonanal (0.738), (Z)-3-hexenyl hexanoate (-0.785), and β-ionone (-0.763). On the basis of these 10 compounds, a model (correlation coefficient of89.4% and cross-validated correlation coefficient of 80.4%) was constructed to predict the aroma quality of Longjingtea. Summarily, this study has provided a novel option for quality prediction of green tea based on HS-SPME/GC-MStechnique.