Coefficient Of Determination In Prediction Research Articles

Rapid and Non-Invasive Assessment of Texture Profile Analysis of Common Carp (Cyprinus carpio L.) Using Hyperspectral Imaging and Machine Learning.

Hyperspectral imaging (HSI) has been applied to assess the texture profile analysis (TPA) of processed meat. However, whether the texture profiles of live fish muscle could be assessed using HSI has not been determined. In this study, we evaluated the texture profile of four muscle regions of live common carp by scanning the corresponding skin regions using HSI. We collected skin hyperspectral information from four regions of 387 scaled and live common carp. Eight texture indicators of the muscle corresponding to each skin region were measured. With the skin HSI of live common carp, six machine learning (ML) models were used to predict the muscle texture indicators. Backpropagation artificial neural network (BP-ANN), partial least-square regression (PLSR), and least-square support vector machine (LS-SVM) were identified as the optimal models for predicting the texture parameters of the dorsal (coefficients of determination for prediction (rp) ranged from 0.9191 to 0.9847, and the root-mean-square error for prediction ranged from 0.1070 to 0.3165), pectoral (rp ranged from 0.9033 to 0.9574, and RMSEP ranged from 0.2285 to 0.3930), abdominal (rp ranged from 0.9070 to 0.9776, and RMSEP ranged from 0.1649 to 0.3601), and gluteal (rp ranged from 0.8726 to 0.9768, and RMSEP ranged from 0.1804 to 0.3938) regions. The optimal ML models and skin HSI data were employed to generate visual prediction maps of TPA values in common carp muscles. These results demonstrated that skin HSI and the optimal models can be used to rapidly and accurately determine the texture qualities of different muscle regions in common carp.

Non-Targeted Detection and Quantification of Food Adulteration of High-Quality Stingless Bee Honey (SBH) via a Portable LED-Based Fluorescence Spectroscopy.

Stingless bee honey (SBH) is rich in phenolic compounds and available in limited quantities. Authentication of SBH is important to protect SBH from adulteration and retain the reputation and sustainability of SBH production. In this research, we use portable LED-based fluorescence spectroscopy to generate and measure the fluorescence intensity of pure SBH and adulterated samples. The spectrometer is equipped with four UV-LED lamps (peaking at 365 nm) as an excitation source. Heterotrigona itama, a popular SBH, was used as a sample. 100 samples of pure SBH and 240 samples of adulterated SBH (levels of adulteration ranging from 10 to 60%) were prepared. Fluorescence spectral acquisition was measured for both the pure and adulterated SBH samples. Principal component analysis (PCA) demonstrated that a clear separation between the pure and adulterated SBH samples could be established from the first two principal components (PCs). A supervised classification based on soft independent modeling of class analogy (SIMCA) achieved an excellent classification result with 100% accuracy, sensitivity, specificity, and precision. Principal component regression (PCR) was superior to partial least squares regression (PLSR) and multiple linear regression (MLR) methods, with a coefficient of determination in prediction (R2p) = 0.9627, root mean squared error of prediction (RMSEP) = 4.1579%, ratio prediction to deviation (RPD) = 5.36, and range error ratio (RER) = 14.81. The LOD and LOQ obtained were higher compared to several previous studies. However, most predicted samples were very close to the regression line, which indicates that the developed PLSR, PCR, and MLR models could be used to detect HFCS adulteration of pure SBH samples. These results showed the proposed portable LED-based fluorescence spectroscopy has a high potential to detect and quantify food adulteration in SBH, with the additional advantages of being an accurate, affordable, and fast measurement with minimum sample preparation.

Application of Hyperspectral Imaging as a Nondestructive Technology for Identifying Tomato Maturity and Quantitatively Predicting Lycopene Content.

Maturity is a crucial indicator in assessing the quality of tomatoes, and it is closely related to lycopene content. Using hyperspectral imaging, this study aimed to monitor tomato maturity and predict its lycopene content at different maturity stages. Standard normal variable (SNV) transformation was applied to preprocess the hyperspectral data. Then, using competitive adaptive reweighted sampling (CARS), the characteristic wavelengths were selected to simplify the calibration models. Based on the full and characteristic wavelengths, a support vector classifier (SVC) model was developed to determine tomato maturity qualitatively. The results demonstrated that the classification accuracy using the characteristic wavelength led to the obtention of better results with an accuracy of 95.83%. In addition, the support vector regression (SVR) and partial least squares regression (PLSR) models were utilized to predict lycopene content. With a coefficient of determination for prediction (R2P) of 0.9652 and a root mean square error for prediction (RMSEP) of 0.0166 mg/kg, the SVR model exhibited the best quantitative prediction capacity based on the characteristic wavelengths. Following this, a visual distribution map was created to evaluate the lycopene content in tomato fruit intuitively. The results demonstrated the viability of hyperspectral imaging for detecting tomato maturity and quantitatively predicting the lycopene content during storage.

Detection of the Adulteration of Dendrobium Huoshanense with Dendrobium Henanense by UV-Vis-Shortwave Near-Infrared Diffuse Reflectance Spectroscopy Combined with Chemometrics.

Dendrobium huoshanense (DHS) is a classic traditional Chinese medicine (TCM) with distinctive medicinal benefits and great economic worth; nevertheless, because of similar tastes and looks, it is simple to adulterate with less expensive substitutes (such as Dendrobium henanense [DHN]). This work aimed to develop a reliable tool to detect and quantify the adulteration of DHS with DHN by using UV-Vis-shortwave near-infrared diffuse reflectance spectroscopy (UV-Vis-SWNIR DRS) combined with chemometrics. Adulterated samples prepared in varying concentrations (0-100%, w/w) were analyzed with UV-Vis-SWNIR DRS methods. Partial least-square-discriminant analysis (PLS-DA) and partial least-squares (PLS) regression techniques were used for the differentiation of adulterated DHN from pure DHS and the prediction of adulteration levels. The PLS-DA classification models successfully differentiated adulterated and nonadulterated DHS with an over 100% correct classification rate. UV-Vis-SWNIR DRS data were also successfully used to predict adulteration levels with a high coefficient of determination for calibration (0.9924) and prediction (0.9906) models and low error values for calibration (3.863%) and prediction (5.067%). UV-Vis-SWNIR DRS, as a fast and environmentally friendly tool, has great potential for both the identification and quantification of adulteration practices involving herbal medicines and foods. UV-Vis-SWNIR DRS combined with chemometrics can be applied to identify and quantify the adulteration of herbal medicines and foods.

Potato flour content determination of potato–wheat flour mixture based on hyperspectral imaging

SummaryPotato–wheat flour mixture (PWFM) has important significance for the development of potato staple food products. However, conventional chemical methods are unable to detect the content of potato flour. Hyperspectral imaging (HSI) technology combined with chemometrics was investigated to predict the feasibility of potato flour content in PWFM. In this study, seven pretreatment algorithms were performed to process the raw spectral data. The results showed that the standard normalised variables (SNV) to establish a partial least square regression (PLSR) model had the most predictive accuracy with the determination coefficient of prediction () of 0.9729. The characteristic wavelengths of raw spectral information were extracted using three algorithms to reduce the model complexity. Eventually, the extracted characteristic wavelengths of potato flour content combine with SNV to establish PLSR, principal component regression (PCR) and support vector regression (SVR) models. The results revealed that the optimal model was SNV‐competitive adaptive reweighted sampling (CARS)‐PLSR with the values of of 0.9853. These results showed that HSI determination of potato flour content in PWFM was feasible and provided a non‐destructive method.

Determination of watermelon soluble solids content based on visible/near infrared spectroscopy with convolutional neural network

The soluble solids content（SSC）of fruits is an essential indicator of fruit taste and flavor. The near-infrared spectroscopy (NIRS) is widely used in fruit SSC detection. A common method to deal with such predictive modelling is the partial least-squares (PLSR). Wavelength selection algorithms are often employed to eliminate redundant wavelengths before constructing the model. However, the wavelength selection algorithms can not only increase the model complexity but also may lose valuable information. In this work, 1D-CNN was used to improve the prediction model of the watermelon SSC. First, the best parameter combination for 1D-CNN was found. The root mean square error of prediction (RMSEP) was 0.21 and the determination coefficient of prediction (Rp2) was 0.97. Then, the performance of PLSR and backpropagation neural network (BPNN) are compared. The results show that the Rp2 of 1D-CNN is improved by 14.1% and 6.6%, respectively. Finally, a gradient-based method for visualizing features of CNN regression models, namely regression activation mapping (RAM), was proposed. The results show that the features of 1D-CNN are consistent with the feature peaks of the spectrum, while the features of the BPNN and PLSR are not obvious.

Development of new fruit quality indices through aggregation of fruit quality parameters and their predictions using near-infrared spectroscopy

This study introduces a flexible approach to aggregate several quality-related parameters to provide new fruit quality indices (FQIs) with the aim of evaluating the overall quality of fruits. The calculations were based on the aggregation of selected fruit quality parameters, such as total soluble solids (TSS), titratable acidity (TA), pH, firmness, dry matter (DM), and lipid content. The fruit quality index 1 (FQI1) and fruit quality index 2 (FQI2) were calculated, respectively, as geometric and weighted arithmetic means of the scaled fruit quality parameters. Both calculations resulted in numerical scores corresponding to a quality rank ranging from 0 to 100. For rapid and non-destructive detection, near-infrared (NIR) spectra were calibrated for predictions of the developed indices using partial least squares (PLS). The predictive performance was evaluated based on several metrics, including root mean square errors of calibration (RMSEC) and prediction (RMSEP), coefficients of determination for calibration (R2) and prediction (Q2), the ratio of RMSEP and RMSEC (RP/C) and the ratio of prediction to deviation (RPD). Mango, tangerine, and avocado were used in the demonstration. The FQI evaluations offer flexibility in the number of aggregate parameters, making them applicable to various types of fruits. With the NIR detection, the developed indices resulted in a significant reduction in the measurements of quality-related parameters but still provided the overall quality of the fruit samples.

Characterization of ash content in wheat flour using data fusion

Ash detection played an important role in wheat flour quality testing. In this work, we proposed a method for the ash content detection in wheat flour, which based on hyperspectral (HSI) method fused with terahertz (THz) technology. Standard Normal Variable Correction (SNV) and Multiple Scattering Correction (MSC) were used for the pretreatment of HSI and THz data. Moreover, feature wavelengths were extracted by the Successive Projections Algorithm (SPA) and Feature weighting algorithms (Relieff), respectively. Hierarchical Extreme Learning Machine (H-ELM) model were used for the analysis of two spectral data, which combined with data fusion strategy. The prediction coefficient of determination (r2) and the root mean square error of prediction (RMSEP) were employed to evaluate the performance of the model effectively. Results suggested that the model accuracy of data fusion was better than that of single spectrum model. Compared to other fused method, this model obtained better results at r2 = 0.989 and RMSEP = 0.015, which based on the SPA-selected HSI feature data fused with the Relieff-selected THz feature data. This study demonstrates that data fusion analysis offers a way to detect ash content in wheat flour, which based on HSI method and THz technology.

Quality Assessment and Ripeness Prediction of Table Grapes Using Visible-Near-Infrared Spectroscopy.

Ripeness significantly affects the commercial values and sales of fruits. In order to monitor the change of grapes' quality parameters during ripening, a rapid and nondestructive method of visible-near-infrared spectral (Vis-NIR) technology was utilized in this study. Firstly, the physicochemical properties of grapes at four different ripening stages were explored. Data evidenced increasing color in redness/greenness (a*) and Chroma (C*) and soluble solids (SSC) content and decreasing values in color of lightness (L*), yellowness/blueness (b*) and Hue angle (h*), hardness, and total acid (TA) content as ripening advanced. Based on these results, spectral prediction models for SSC and TA in grapes were established. Effective wavelengths were selected by the competitive adaptive weighting algorithm (CARS), and six common preprocessing methods were applied to pretreat the spectra data. Partial least squares regression (PLSR) was applied to establish models on the basis of effective wavelengths and full spectra. The predictive PLSR models built with full spectra data and 1st derivative preprocessing provided the best values of performance parameters for both SSC and TA. For SSC, the model showed the coefficients of determination for calibration (RCal2) and prediction (RPre2) set of 0.97 and 0.93, respectively, the root mean square error for calibration set (RMSEC) and prediction set (RMSEP) of 0.62 and 1.27, respectively; and the RPD equal to 4.09. As for TA, the optimum values of RCal2, RPre2, RMSEC, RMSEP and RPD were 0.97, 0.94, 0.88, 1.96 and 4.55, respectively. The results indicated that Vis-NIR spectroscopy is an effective tool for the rapid and non-destructive detection of SSC and TA in grapes.

Post-fire assessment of heating temperatures experienced by concrete using short video imaging, hyperspectral imaging and laser-induced breakdown spectroscopy

This study develops rapid post-fire analysis methods to predict the heating temperature to which the concrete was exposed. Short video imaging (SVI), hyperspectral imaging (HSI) and laser-induced breakdown spectroscopy (LIBS) were used for the first time to obtain spectra of concrete after high-temperature exposure (100–800 °C). The differences in colour levels and spectroscopic signals due to varying temperatures were observed. To handle the complex relationship between spectra and temperatures, machine learning models were used to extract meaningful information from spectra for the quantification of temperature. Furthermore, domain knowledge related to concrete composition and LIBS signal was integrated into machine learning to improve quantification performance. The highest coefficients of determination for prediction achieved based on SVI, HSI and LIBS measurements were 91.4, 94.8 and 98.6, respectively. These results demonstrate that SVI, HSI and LIBS can be fast and viable methods for assessing the fire temperature that the concrete has experienced.

Detection of antioxidants in edible oil by two-dimensional correlation spectroscopy combined with convolutional neural network

In this study, the qualitative identification and quantitative prediction of antioxidants in edible oil were achieved by the two-dimensional correlation spectroscopy combined with convolutional neural network (CNN). The CNN model obtained classification accuracy of 97.56%, which is significantly higher than that of the partial least squares discriminant analysis (PLS-DA) model. Comparing the performance of the established partial least squares (PLS), CNN, and CNN combined with PLS (CNN_PLS) regression models, it is found that the CNN model has the best quantitative performance among the three regression models, with a root mean square errors for prediction (RMSEP) of 0.0232 and a coefficient of determination for prediction (R2p) of 0.9703. At the same time, it is found that the prediction ability of the CNN_PLS model is affected by the feature extraction ability of CNN models and the output dimension of convolution layers in CNN models. The results demonstrate the potential of the proposed method for the detection of antioxidant in edible oils.

Comparison of the performance of different one-dimensional convolutional neural network models-based near-infrared spectra for determination of chlorpyrifos residues in corn oil

This study introduces a fast analytical approach for detecting chlorpyrifos residues in corn oil, based on a one-dimensional convolutional neural network (1D-CNN) structure for near-infrared (NIR) spectral deep learning models. Data augmentation algorithms were introduced to effectively expand the database of corn oil samples obtained in the experiment, ensuring sufficient training of the deep learning network. A well-designed 1D-CNN structure was implemented to create a multivariate calibration model. This model can be used to quantify chlorpyrifos residues in corn oil. The study found that using data augmentation with a 1D-CNN model led to improved performance compared to using the original spectra calibration in the model. Particularly, the 1D-CNN model’s best overall performance was achieved using data augmented with varying degrees of signal-to-noise ratio (SNR) algorithms, with a prediction coefficient of determination (RP2) of 0.9492 and a relative percent deviation (RPD) of 4.4569. The study demonstrates the feasibility of using NIR spectral deep learning models for quantitative analysis of pesticide residues in edible oils. Furthermore, data augmentation methods can effectively improve the accuracy of deep learning algorithms in NIR spectral chemometrics model calibration.

Synthesis, Characterization, and Evaluation of Co-MOF Based ZIF-67 for CO2 Corrosion Inhibition of X65 Steel: Insights from Electrochemical Studies and a Machine Learning Algorithm

Co-MOF based metal organic framework was synthesized by reacting a metal ion (cobalt nitrate hexahydrate) with an organic ligand (2-methylimidazole) via a wet chemical method. The resulting material was characterized using detailed analytical methods and further was used as a self-assembly corrosion inhibitor in sweet corrosive environment. The empirical data set via electrochemical studies was modeled using adaptive neuro fuzzy inference system (ANFIS). The observed results showed that Co-MOF could significantly impede the corrosion rate of X65 steel and protect it from CO2 corrosion. Increasing the concentration of Co-MOF in the test solution increased the inhibition efficiency up to 97% at 0.1 wt % Co-MOF with a mixed-type inhibition mechanism. In addition, the DFT/MD-simulation approach evidenced the adsorption disposition of Co-MOF in aqueous and gas phase which complement with the empirical findings. Also, the prognostic capability of the proposed algorithm based on the statistical parameters such as root-mean-square error (RMSE), chi square (χ2), model predictive error (MPE) and coefficient of determination (R2) were appraised. From the viewpoint of statistics, the explanatory model aligned credibly with the ANFIS algorithm. The overall findings confirmed a dense hybrid coating of the synthesized Co-MOF on X65 steel as responsible for the inhibition of the sweet corrosion.

Study of coffee sensory attributes by ordered predictors selection applied to 1H NMR spectroscopy

The determination of sensory attributes of coffee samples through trained cupping tasters is one of the main methodologies for coffee quality control. However, this analysis may suffer some distortions due to different ways of interpreting quality from the tasters' perspective. Thus, other, and complementary have been developed as alternative ways to determine sensory attributes. Hydrogen nuclear magnetic resonance (1H NMR) is a technique that allows the chemical study of compounds present in organic matrices. Through 1H NMR it is possible to predict a sensory attribute using chemometric methods. However, 1H NMR generates many variables per sample, making it necessary to use variable selection methods to find the most useful information. Ordered predictors selection (OPS) is a variable selection method developed to search, sort, and select the variables in order of importance. In this study, six sensory attributes from 42 coffee samples were predicted by partial least squares (PLS) and support vector regression (SVR) methods and OPS as variable selection in 1H NMR data set. The integration of areas of the 1H NMR spectra and the full data sets were also used to compare the prediction models. OPS-PLS model was the best strategy to predict aftertaste, balance, and fragrance with root mean squared error of prediction (RMSEP) of 0.24, 0.35, and 0.20, respectively. The coefficients of determination for prediction (R2p) of these models were 0.71, 0.60, and 0.77, respectively. OPS-SVR predominated as the best strategy to predict acidity, body, and flavor with RMSEP of 0.23, 0.21, and 0.22, and R2p of 0.89, 0.75, and 0.83, respectively. None of the models chosen as the best showed the presence of trends in residuals above 5% of significance. Variable selection by OPS can improve the prediction of regression models.

Non-destructive evaluation of soluble solid content in fruits with various skin thicknesses using visible–shortwave near-infrared spectroscopy

Abstract Visible–shortwave near-infrared spectroscopy has been used for internal quality measurement, but the optical penetration to the thickness of fruit skin becomes a challenge. This research aimed to develop partial least square regression model for the soluble solid content (SSC) measurement of fruits having various skin thicknesses, namely dragon fruit, tomato, guava, sapodilla, and banana. The spectra of each fruit were taken in a reflectance mode over a wavelength range of 400–1,000 nm. The best models obtained from banana and sapodilla yielded determination coefficient of prediction (R 2 p) of 0.88 and 0.90 and root mean square error of prediction (RMSEP) 0.39 and 0.38°Brix, respectively. The banana and sapodilla SSC prediction models should be able to be used carefully in a variety of applications. Tomato and guava had moderately thinner skin but had the lower R 2 p of 0.64 and 0.76 and the RMSEP of 0.17 and 0.26°Brix, respectively. The poorest model was yielded by dragon fruit, which had the thickest skin with the R 2 p of 0.59 and the RMSEP of 0.40°Brix. The model for guava, although having low R 2 p, can still be utilized as a screening criterion and in some other ‘approximate’ applications. However, the SSC prediction model for tomatoes and dragon fruit is not recommended to use and requires additional research. In addition to the effect of skin thickness, other fruit morphological influences the result of this study. Internal structure and seed number influence the reflection optical geometry, which also affects the SSC prediction model.

Prediction and Online Optimization of Strip Shape in Hot Strip Rolling Process Using Sparrow Search Algorithm‐Online Sequential‐Deep Multilayer Extreme Learning Machine Algorithm

In the hot strip process, the prediction of strip shape is a key factor to improve the quality of products. However, strip‐shape prediction models based on traditional machine learning algorithms with relatively simple network structures often rely on data preprocessing and feature selection. Herein, five strip‐shape prediction models are proposed by combining sparrow search algorithm (SSA), particle swarm optimization algorithm (PSO), extreme learning machine (ELM), and deep multilayer extreme learning machine (DELM). The prediction experiments show that the SSA‐DELM model has highest accuracy, and the determination coefficient (R2) of crown prediction and flatness prediction of SSA‐DELM model is 0.971 and 0.979. 100% of the samples have a prediction error of less than ±7 μm and ±7 IU. Furthermore, to solve the problem of concept drift affecting prediction accuracy in industrial processes, online optimization method is proposed. Especially, online sequential deep ELM model (OS‐DELM) optimized by SSA and guided by double window drift detection is proposed to fill the gap. Compared with other online optimization methods, the update time with this method can be reduced by up to 83.05% averagely, which is more suitable for online strip‐shape prediction in hot rolling process.

Hyperspectral imaging and chemometrics assessment of intramuscular fat in pork Longissimus thoracic et lumborum primal cut

To assess the intramuscular fat (IMF) of Longissimus thoracis et lumborum (LTL) primal cut excised from an animal carcass, rib sections are dissected for chemical or subjective evaluation. Dissection destroys the integrity of the LTL. This study examined the feasibility of developing a method based on hyperspectral imaging to predict the IMF of pork LTL using hyperspectral imaging. Spectral information from different tissues was collected at the cranial (Serratus ventralis, Spinalis dorsi, longissimus , backfat), and the caudal ( Gluteus medius, Psoas major ) ends of the LTL. The spectral information and the IMF content chemically extracted from the mid-loin (3rd and 4th last rib of the LTL) were used to develop regression models for the prediction of the IMF content in the 3rd and 4th. The individual results of the analysis from the various tissues at both the cranial and caudal ends show that models exhibited performances for IMF prediction with root-mean-square-error (RMSEP) ranging from 0.36 to 0.92% and coefficient of determination in prediction ranging from 0.43 to 0.81. Gluteus medius showed the highest accuracy. This study has demonstrated that hyperspectral imaging could be used to accurately predict the IMF content in the mid-loin by using spectral data from Gluteus medius . The result could be useful in segregating pork LTL based on IMF content. • Intramuscular fat in whole pork Longissimus thoracic et lumborum was evaluated. • Muscles from the cranial and caudal of the Longissimus thoracic et lumborum were scanned. • PLSR was used to develop models between tissues and intramuscular fat at 3rd/4th last ribs. • The Gluteus medius muscle predicted intramuscular fat accurately.

Quantitative analysis of index factors in agricultural compost by infrared spectroscopy

Hyperspectral technology, with its high spectrum resolution and nanometer continuous spectral information acquisition ability, provide a possibility for rapidly and nondestructive evaluating compost maturity. In this study, the near-infrared spectroscopy (NIRS) analysis techniques was used to analyze quantitatively organic matter (OM) content, total nitrogen (TN) content and carbon-nitrogen (C/N) ratio in compost based on two different composting procedures. In the basis of spectra preprocessing and strategies of variable selection, the nonlinear modeling LBC-siPLS-PLSR for OM, MSC-SPA-PLSR for TN and R-SPA-PLSR for C/N ratio was respectively constructed using partial least squares regression (PLSR). LBC-siPLS-PLSR, MSC-SPA-PLSR and R-SPA-PLSR provided a better prediction capability with root mean square error of prediction, the coefficient of determination for prediction and residual predictive deviation values of 4.061, 0.746 and 2.02 for OM, values of 0.205, 0.65 and 1.71 for TN and values of 1.11, 0.706 and 2.07 for C/N ratio, respectively. These results showed that the NIRS technique could be fitted to each element, using specific spectrum pretreatment, in order to achieve an acceptable accuracy in the prediction.

Nondestructive Detection of Moisture Content in Palm Oil by Using Portable Vibrational Spectroscopy and Optimal Prediction Algorithms.

Rapid and nondestructive measurement of moisture content in crude palm oil is essential for promoting the shelf-stability and quality. In this research, micro NIR spectrometer coupled with a multivariate calibration model was used to collect and analyse fingerprinted information from palm oil samples at different moisture contents. Several preprocessing methods such as standard normal variant (SNV), multiplicative scatter correction (MSC), Savitzky-Golay first derivative (SGD1), Savitzky-Golay second derivative (SGD2) together with partial least square (PLS) regression techniques, full PLS, interval PLS (iPLS), synergy interval PLS (SiPLS), genetic algorithm PLS (GAPLS), and successive projection algorithm PLS (SPA-PLS) were comparatively employed to construct an optimum quantitative prediction model for moisture content in crude palm oil. The models were evaluated according to the coefficient of determination and root mean square error in calibration (Rc and RMSEC) and prediction (Rp and RMSEC) set, respectively. The model SGD1 + SiPLS was the optimal novel algorithm obtained among the others with the performance of Rc = 0.968 and RMSEC = 0.468 in the calibration set and Rp = 0.956 and RMSEP = 0.361 in the prediction set. The results showed that rapid and nondestructive determination of moisture content in palm oil is feasible and this would go a long way to facilitating quality control of crude palm oil.

Pedotransfer functions for predicting bulk density of coastal soils in East China

Soil bulk density (BD) is not only an important physical property but is also an essential factor for weight-to-volume conversion. However, this parameter is often missing from soil databases because its direct measurement is labor-intensive, time-consuming, and sometimes impractical, particularly on a large scale. Therefore, pedotransfer functions (PTFs) have been developed to predict BD for several decades. In this study, six previously revised PTFs (including five basic functions and stepwise multiple linear regression (SMLR)), partial least squares regression (PLSR), and support vector machine regression (SVMR) were used to develop BD PTFs for coastal soil in East China. The independent variables included soil organic carbon (SOC) and particle size distribution (PSD). To compare the robustness and reliability of various methods, the calibration and prediction processes were performed 1,000 times using the calibration and validation sets divided by a random sampling algorithm. The results showed that SOC was the most important predictor, and the revised PTFs performed reasonably, although only SOC was included. The PSD data were useful for a better prediction of BD, and the sand and clay fractions were the second and third most important properties for the prediction of BD. The PLSR showed slightly better PTFs for the study area (the average adjusted coefficient of determination for prediction was 0.581). These results suggest that PLSR with SOC and PSD data can be used for PTFs to fill in the missing BD data in coastal soil databases and provide important information that can be used to estimate coastal carbon storage, which will further improve our understanding of sea-land interactions under global warming.