Visible And Shortwave Near Infrared Research Articles

Identification of Maize with Different Moldy Levels Based on Catalase Activity and Data Fusion of Hyperspectral Images.

Maize is susceptible to mold infection during growth and storage due to its large embryo and high moisture content. Therefore, it is essential to distinguish the moldy sample from healthy groups to prevent the spread of mold and avoid huger economic losses. Catalase is a metabolite in the growth of microorganisms; hence, all maize samples were accurately divided into four moldy grades (health, mild, moderate, and severe levels) by determining their catalase activity. The visible and shortwave near-infrared (Vis-SWNIR) and longwave near-infrared (LWNIR) hyperspectral images were investigated to jointly identify the moldy levels of maize. Spectra and texture information of each maize sample were extracted and used to build the classification models of maize with different moldy levels in pixel-level fusion and feature-level fusion. The result showed that the feature-level fusion of spectral and texture within Vis-SWNIR and LWNIR regions achieved the best results, overall prediction accuracy reached 95.00% for each moldy level, all healthy maize was correctly classified, and none of the moldy samples were misclassified as healthy level. This study illustrated that two hyperspectral image systems, with complementary spectral ranges, combined with feature selection and data fusion strategies, could be used synergistically to improve the classification accuracy of maize with different moldy levels.

Feature Wavelength Selection Based on the Combination of Image and Spectrum for Aflatoxin B1 Concentration Classification in Single Maize Kernels

Aflatoxin B1 (AFB1) is a very strong carcinogen, maize kernels are easily infected by this toxin during storage. Rapid and accurate identification of AFB1 is of great significance to ensure food safety. In this study, a novel method for classification of AFB1 in single maize kernels was developed. Four groups of maize kernel samples with different AFB1 concentrations (10, 20, 50, and 100 ppb) were prepared by artificial inoculation of toxin. In addition, one group of maize kernel samples without AFB1 were prepared as control, each group with 70 samples. The visible and short wave near-infrared (Vis-SWNIR) region (500–1000 nm) and long wave near-infrared (LWNIR) region (1000–2000 nm) hyperspectral images of all samples were obtained respectively, and the hyperspectral images in 500–2000 nm range was obtained after spectral pretreatment and fusion. Kennard-Stone algorithm was used to divide the samples into calibration set or prediction set. Competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to roughly select the characteristic wavelengths of the calibration set samples, and 25 and 26 effective wavelengths were obtained respectively. Based on the roughly selected wavelengths, a method of fine selection of the characteristic wavelengths was proposed by using the gray-value difference of image (GDI), and a few number of characteristic wavelengths were further selected. Under the LDA classification model, 10 characteristic wavelengths were selected to test the prediction set and the independent verification samples, and the ideal result were obtained with an accuracy of 94.46% and 91.11%, respectively. This study provides a new approach for AFB1 concentration classification of single maize kernels.

Qualitative Characterization of Astringent and De-astringed Intact ‘Xichu’ Persimmon Fruit Using VIS/SWNIR and Chemometrics

Astringency removal is considered as a key process before commercialize persimmon cv. ‘Xichu’, due to its high content of soluble tannins. Application of carbon dioxide treatment effective in removing astringency and widely used as a commercial postharvest practice for astringent persimmon fruit. The aim of this research is study to the application of visible and shortwave near infrared (VIS/SWNIR) spectroscopy in the spectral data of 400-1100 nm to discriminate astringent (A) and de-astringed (DA) fruit non-destructively based on the sensorial perception as 0.10% soluble tannin of fresh weight. The highest classifi cation accuracy score was obtained from QDA model combined with 2D preprocessing technique as 98.99% in the external validation set. Therefore, the results obtained in this study can be considered as a non-destructive analytical method to monitoring the effectiveness of the astringency removal treatment in ‘Xichu’ persimmon fruit.

Integrating Vis-SWNIR spectrometer in a conveyor system for in-line measurement of dry matter content and soluble solids content of durian pulp

The prediction of dry matter content (DMC) and soluble solids content (SSC) in durian pulp were performed using a small laboratory scale in-line visible and short wave near infrared (Vis-SWNIR) spectroscopic system. The fiber optic diode array spectrometer with a charged coupled device (CCD) detector in a wavelength range of 450−1000 nm was used for spectral data acquisition. The spectra of the sample were acquired on the moving conveyor belt in two different orientations, including scanning in the upright position of pulps collected in 2018 and the stable position by scanning on the side of the pulps collected in 2019. Partial least squares regression (PLSR) was used to establish the relationship between the spectra and observed DMC and SSC values using the different wavelength ranges, including 450−1000, 700−1000, and 800−1000 nm for the comparison. The results showed that the durian pulp should be scanned in the upright position at the center of the pulp. Moving average smoothing preprocessing combined with the standard normal variate (SNV) for DMC and multiple scatter correction (MSC) for SSC gave the best result. The suitable wavelength range for model development to predict the DMC and SSC was 700−1000 nm and 800−1000 nm, respectively. After comparing the results, the optimum model showed the coefficient of determination of calibration (RC2), and prediction (RP2), root mean square error of prediction (RMSEP), bias, and the ratio of performance to interquartile distance (RPIQ) of 0.88, 0.83, 4.32 %, 1.25 %, and 3.52 for DMC and 0.70, 0.70, 4.0 %, 0.4 %, and 2.2 for SSC prediction.

Measurement of cross link densities of prevulcanized natural rubber latex and latex products using low-cost near infrared spectrometer

The objective of this project is to use the four models to predict the crosslink densities based on reference method of PRM 300% using portable low-cost visible and shortwave near-infrared (Vis/SW-NIR) spectrometer across wavelengths of 350-1100 nm. The degrees of crosslink reflect on the properties of the prevulcanized (PV) latices and latex products produced and hence useful for quality control in the process of production. The four models were optimized using partial least squares regression (PLSR) that the spectra were collected from PV, PV50, thin and thick films. The use of thin and thick films was to emulate the latex products that used the PV latices. The results showed that there were almost no difference in the PV and PV50 models by the coefficient of determination (R2) and root mean square error of calibration (RMSEC) of 0.70 and 9.04 × 104 N/m2 and 0.75 and 8.59 × 104 N/m2, respectively. Among the four models, thin and thick film models had poor results indicated by the coefficient of determination (R2) and root mean square error of calibration (RMSEC) of 0.02 and 17.31 × 104 N/m2 and 0.05 and 16.63 × 104 N/m2, respectively. Based on these results, only the models of prevulcanized (PV) latices could be used for quality assessment. Hence the Vis/SW-NIR spectrometer could be a cheap alternative for crosslink density determination of PV latices and would be a beneficial tool for monitoring the process of vulcanization in the rubber industry.

Non-destructive visible and short-wave near-infrared spectroscopic data estimation of various physicochemical properties of Fuji apple (Malus pumila) fruits at different maturation stages

measurement of physicochemical properties of fruits during maturation stages can help having proper fruit management. Spectroscopy data analyzing and processing is among the commonly used methods that enable non-destructive accurate property estimation. Non-destructive linear (partial least squares regression, PSLR) and non-linear (artificial neural network, ANN) regression estimation of different physicochemical properties including firmness, acidity (pH) and starch content of 160 Fuji (Malus pumila) apple fruit samples at various maturity stages using visible and short wave near infrared (VSWIR) spectroscopic data in wavelength range 400–1000 ​nm is investigated with the following steps: (1) harvesting 160 Fuji apple samples at four different maturation levels; (2) extracting spectral data in wavelength range of 400–1000 ​nm; extracting physicochemical properties of tissue firmness, acidity (pH) and starch content; (3) pre-processing the reflectance spectra from each sample; (4) selecting effective wavelength values for each chemical property; and (5) non-destructive estimation of tissue firmness, acidity (pH) and starch content using spectral data range 400–1000 ​nm and spectral data based on effective wavelengths, by means of an ensemble average artificial neural network method. Results show that the neural ensemble reached similar results when using VSWIR spectral data content (wavelength range) and fixed effective selected NIR wavelengths. Correlation coefficients estimating tissue firmness, acidity (pH), and starch content were 0.800, 0.919, and 0.940 for VSWIR spectral data (linear PLS regression), 0.826, 0.947, and 0.969 for VSWIR spectral data (non-linear ANN), 0.827, 0.946, and 0.969 for fixed NIR effective wavelengths (non-linear ANN). Mean ​± ​std. regression coefficients (R) for tissue firmness, acidity (pH), and starch content were 0.717 ​± ​0.113, 0.786 ​± ​0.131, and 0.941 ​± ​0.013 for Vis/NIR spectral data (linear PLS regression), 0.849 ​± ​0.017, 0.930 ​± ​0.017, and 0.967 ​± ​0.007 for Vis/NIR spectral data (non-linear ANN), 0.852 ​± ​0.016, 0.929 ​± ​0.015, and 0.966 ​± ​0.006 for fixed effective NIR wavelengths (non-linear ANN).

Adaptation of visible and short wave Near Infrared (VIS-SW-NIR) common PLS model for quantifying paddy hardness

Hardness of paddy is an indicator of preserved quality of rice as it maintains the integrity of grain to avoid falling-off during milling. Most of the prevailing methods carter to determine the hardness are destructive and time consuming. Though, use of Near Infrared (NIR) is nondestructive, its conventional approach implies separate Partial Least Square (PLS) model for each new paddy type to be predicted successfully. Therefore, this study evaluates NIR spectroscopy (588–1091 nm) to be used as a common PLS model for quantifying a range of paddy varieties and processing conditions in rapid and non-destructive mode. The acquired NIR spectra were used to construct PLS calibration models by using Pirouette 4.5 software. As a result, the lowest standard error of validation (SEV = 1.711) and highest correlation coefficient of validation (R2 = 0.936) were obtained. The research has successfully demonstrated that the potential possibility of NIR spectroscopy to be used as a common PLS model for quantifying hardness of paddy from new varieties and conditions.

A comparative study of mango solar drying methods by visible and near-infrared spectroscopy coupled with ANOVA-simultaneous component analysis (ASCA)

The effect of mango solar drying methods (traditional and tunnel dryers) on the quality of dried mango slices was investigated by visible (VIS) and near-infrared (NIR) spectroscopy combined with the chemometric analysis methods of principal component analysis (PCA) and ANOVA-simultaneous component analysis (ASCA). Five batches of mango were investigated, each subjected to two/three different positions of three different types of dryers: electrical (reference), traditional, and tunnel dryers. The results of the visible and near-infrared spectra showed that the quality of the mango samples obtained from the electrical dryer (reference method) was the most uniform and conserved the highest content of carotenoids and chlorophyll pigments. The samples from the traditional dryer had the highest variation and content of residual water. ASCA analysis of visible and shortwave near-infrared (VIS-NIR) (including color information) showed that the batch effect was most dominant with a significance effect of 47.5%, whereas longwave near-infrared (NIR) spectra (chemistry) showed that the dryer effect was the most dominant with a significance effect of 38.3%. The factor of the fruit positions in the dryers proved not to be significant. The VIS-NIR spectrum is thus well adapted to measure the fruit maturity and the NIR spectrum has great potential to investigate and control the dryer performance. The latter clearly demonstrated that the tunnel dryer provides much more gentle and consistent drying process compared to the traditional dryer. In contrast, the samples from the traditional dryer showed chemical changes/decomposition.

Assessment of tomato soluble solids content and pH by spatially-resolved and conventional Vis/NIR spectroscopy

Spatially-resolved spectroscopy (SRS) enables better interrogation of tissue properties at different depths, and it thus has the potential for enhancing quality assessment of horticultural products like tomato, which are heterogeneous in structure and chemical composition. This research was aimed at assessing quality of tomato fruit by using a newly developed SRS system with 30 detection optic fibers covering the wavelength range of 550–1650 nm and comparing its performance with two conventional single-point (SP) spectroscopic instruments covering the visible and shortwave near-infrared (Vis/SWNIR) (400–1100 nm) and near-infrared (NIR) (900–1300 nm) regions, respectively. Spatially-resolved (SR) spectra and SP interactance spectra were acquired for 600 ‘Sun Bright’ tomato fruit. Partial least squares (PLS) models for individual SR spectra and their combinations and for SP Vis/SWNIR and NIR spectra were developed for prediction of soluble solids content (SSC) and pH. Results showed that SSC and pH predictions by SRS varied depending on the light source-detector distance, with the correlation coefficient of prediction (rp) ranging 0.608–0.791 and 0.688–0.800, respectively. Combinations of two or more SR spectra resulted in better, more consistent SSC and pH predictions. SR predictions of pH (rp = 0.819) were better than for SP Vis/SWNIR (rp = 0.743) and NIR (rp = 0.741) predictions, whereas SR predictions of SSC (rp = 0.800) were comparable to SP NIR predictions (rp = 0.810) but better than SP Vis/SWNIR predictions (rp = 0.729). This research showed that owning to its ability of acquiring spatially-resolved spectral information, the SRS technique has advantages over conventional SP spectroscopy for enhancing quality assessment of tomatoes.

Prediction of firmness parameters of tomatoes by portable visible and near-infrared spectroscopy

Firmness is an important parameter for determining maturity/ripeness and postharvest processing quality of tomatoes. This paper reports on the prediction of different fruit firmness parameters of tomatoes by using visible and near-infrared spectroscopy. Interactance spectra were taken from 600 freshly harvested tomatoes of six maturity stages, using two portable spectrometers which cover the two commonly used spectral regions, i.e., the visible and short-wave near-infrared (Vis/SWNIR) range of 400–1100 nm and the near-infrared (NIR) range of 900–1700 nm, respectively. Different firmness parameters for the tomatoes were measured using acoustic, impact, compression and puncture tests. Partial least squares (PLS) regression models, coupled with four preprocessing methods (i.e., original, logarithmic, autoscale, and logarithmic plus autoscale), were developed to predict the firmness parameters of tomato fruit. The PLS models gave better predictions of impact firmness, compression area and puncture slope for the tomato fruit, with the correlation coefficients for prediction of 0.899, 0.917 and 0.935 for Vis/SWNIR, and 0.846, 0.831 and 0.853 for NIR. Overall, autoscale preprocessing performed better for both Vis/SWNIR and NIR spectra. Visible and near-infrared spectroscopy in interactance mode can be useful for nondestructive assessment of tomato firmness measured by both destructive and nondestructive reference methods.

Predicting bruise susceptibility in apples using Vis/SWNIR technique combined with ensemble learning

Bruise susceptibility in fruits is an important indicator in evaluating risk factors for bruising caused by external factors. Prediction of the bruising susceptibility of fruit can provide useful information for proper postharvest handling and storage operations. In this study, visible and shortwave near-infrared (Vis/SWNIR) technique was used to develop nondestructive method for predicting the bruise susceptibility of apples. Vis/SWNIR spectra covering 400-1100 nm were collected for 300 ‘Golden Delicious’ apples over a time period of three weeks after harvest. A pendulum-like device was used to simulate impact bruise at three impact energy levels of 1.11 J, 0.66 J and 0.33 J. Bruise volumes were estimated from the digital images of the bruised apples by using the bruise thickness model. Three prediction models, i.e. partial least squares model (PLS), partial least squares model combined with successful projection algorithm (SPA-PLS), and selective ensemble learning based on feature selection (SELFS), for bruise susceptibility were developed for each impact energy level as well as for the pooled data. Compared with PLS and SPA-PLS model, SELFS gave the better prediction results for bruise susceptibility, with the correlation coefficient of Rp=0.800-0.886 for the prediction set, the root-mean-square error of 38.7- 62.1 mm3/J for the prediction set (RMSEP), and the residual predictive deviation (RPD) of 1.78-2.14 for three impact energy level. For three impact energy levels, the RMSEP and RPD value obtained by SELFS model improved by 14.8%-20.0% and 15.0%-24.5% compared to PLS model, and 11.4%-21.2% and 11.5%-27.1% compared to SPA-PLS model, respectively. The SELFS model achieved relatively lower prediction accuracies for the pooled data, with the Rp values of 0.731, RMSEP of 85.46 mm3/J, and RPD of 1.46, which were also better than that of PLS model and SPA-PLS model. This research demonstrated that Vis/SWNIR technique combined with ensemble learning is promising technique for rapid assessment of bruise susceptibility of fruit, which would be useful for postharvest handling of fruit. Keywords: apple, nondestructive detection, bruise susceptibility, visible/short-wave near-infrared technique, ensemble learning DOI: 10.25165/j.ijabe.20171005.2888 Citation: Yao J, Guan J Y, Zhu Q B. Predicting bruise susceptibility in apples using Vis/SWNIR technique combined with ensemble learning. Int J Agric & Biol Eng, 2017; 10(5): 144–153.

FIRST DERIVATIVE PREDICTION OF RAW BROILER SHEAR FORCE USING VISIBLE SHORT WAVE NEAR INFRARED SPECTROSCOPY

A non-destructive,fast, reliable and low cost technique which is Near-Infrared Spectroscopy (NIRS) is required to replace conventional destructive texture analyser in shear force measurement. The combination of visible and shortwave near infrared (VIS-SWNIR) spectrometer and principal component regression (PCR) to assess the quality attribute of raw broiler meat texture (shear force value (kg)) was investigated. Wavelength region of visible and shortwave 662-1005 nm was selected for prediction after pre-processing. Absorbance spectra was pre-processed using the optimal Savitzky-Golay smoothing mode with 1st order derivative, 2nd degree polynomial and 31 filter points to remove the baseline shift effect. Potential outliers were identified through externally studentised residual approach. The PCR model were trained with 90 samples in calibration and validated with 44 samples in prediction datasets. From the PCR analysis, correlation coefficient of calibration (RC), the root mean square calibration (RMSEC), correlation coefficient of prediction (RP) and the root mean square prediction (RMSEP) of visible and shortwave (662-1005 nm) with 4 principal components were 0.4645,0.0898, 0.4231 and 0.0945. The predicted results can be improved by applying the 2nd order derivative and the non-linear model.

Classification of different tomato seed cultivars by multispectral visible-near infrared spectroscopy and chemometrics

The feasibility of rapid and non-destructive classification of five different tomato seed cultivars was investigated by using visible and short-wave near infrared (Vis-NIR) spectra combined with chemometric approaches. Vis-NIR spectra containing 19 different wavelengths ranging from 375 nm to 970 nm were extracted from multispectral images of tomato seeds. Principal component analysis (PCA) was used for data exploration, while partial least squares discriminant analysis (PLS-DA) and support vector machine discriminant analysis (SVM-DA) were used to classify the five different tomato cultivars. The results showed very good classification accuracy for two independent test sets ranging from 94% to 100% for all tomato cultivars irrespective of chemometric methods. The overall classification error rates were 3.2% and 0.4% for the PLS-DA and SVM-DA calibration models, respectively. The results indicate that Vis-NIR spectra have the potential to be used for non-destructive discrimination of tomato seed cultivars with an opportunity to integrate them into plant genetic resource management, plant variety protection or registration programmes.

Influence of the Peel on Predicting Soluble Solids Content of Navel Oranges Using Visible and Near-Infrared Spectroscopy

Abstract. The peel of orange was proven to influence light propagation within the fruit; thus, this study was aimed at investigating the influence of the peel on absorption spectra and calibration models within the wavelength range from 520 to 2200 nm. To investigate this effect further, the correlation between pulp soluble solids content (SSC) and peel SSC of the same oranges was studied. Spectra of 86 oranges with peel and peeled were collected using a commercial spectrometer, and partial least squares regression was used to develop calibration models. Results showed that for intact oranges, the calibration model using the visible and shortwave near-infrared (Vis-SWNIR) region (520-1100 nm) performed similarly to that using the Vis-NIR region (520-2200 nm), and the broader Vis-NIR region did not improve the calibration models. With respect to the influence of the peel, within the Vis-SWNIR and Vis-NIR regions, the models elaborated using peeled samples performed slightly better, but not significantly. In the NIR region, better results were obtained for models using intact samples. In addition, a linear correlation was found between pulp SSC and peel SSC, with a coefficient of determination (R 2 ) of 0.5047, which could be used to explain why the peel did not have significantly negative influence on prediction performance. It was concluded that the peel of navel orange did not have significant influence on the SSC determination using Vis/NIR spectroscopy, and the .

Grading of apples based on firmness and soluble solids content using Vis/SWNIR spectroscopy and spectral scattering techniques

Sorting of apple fruit based on internal quality can enhance the industry’s competiveness and profitability and assure consumer satisfaction. In this research, visible and shortwave near-infrared (Vis/SWNIR) spectroscopy (460–1100nm) and spectral scattering (450–1050nm) were used for sorting three varieties of apple (i.e., ‘Delicious’, ‘Golden Delicious’ and ‘Jonagold’) into two quality grades based on firmness, soluble solids content (SSC), or both firmness and SSC. Vis/SWNIR spectra were obtained in interactance mode under stationery condition, whereas spectral scattering images were acquired online at a conveyor speed of 82mm/s. A total of 8491 apples for the three varieties harvested from the same orchard in 2009, 2010 and 2011 were used for analysis. First derivative spectra were obtained from the Vis/SWNIR data, while the scattering images were first preprocessed by computing mean reflectance spectra and then performing continuous wavelet transform decompositions. Sorting algorithms were developed using sequential forward selection and linear discriminant analysis, and the classification models were compared in terms of their overall performance and local confusion matrices. A sensitivity analysis was also performed to assess the effect of using different quality threshold criteria on the sorting performance. Overall, consistent and relatively good sorting results for firmness (ranging between 77.9% and 98.2%) and moderate results for SSC (ranging between 62.0% and 91.7%) were obtained using scattering technique. Vis/SWNIR technique showed slightly better sorting results for firmness (ranging between 87.3% and 97.6%) and SSC (ranging between 77.1% and 92.3%). When the classification was performed based on both firmness and SSC, the sorting accuracies generally decreased to between 75.7% and 90.1% for Vis/SWNIR and between 69.7% and 91.5% for spectral scattering. Vis/SWNIR and spectral scattering techniques have potential for online sorting and grading of apples by firmness and SSC.

Prediction and classification of sugar content of sugarcane based on skin scanning using visible and shortwave near infrared

The potential application of a visible and shortwave near infrared (Vis/SWNIR) spectroscopic technique as a low cost alternative to predict sugar content based on skin scanning was evaluated. Two hundred and ninety one internode samples representing three different commercial sugarcane varieties were used. Each sample was scanned at four scanning points to obtain the spectra data which was later correlated with its °Brix (soluble solids content) values. Partial least square (PLS) model was developed and applied to both calibration and prediction samples. Using reflectance spectra data, the model had a coefficient of determination (R2) of 0.91 and root means square error of predictions (RMSEP) of 0.721 °Brix. The artificial neural network (ANN) was also applied to classify spectra data into five °Brix categories. The ANN has yielded good classification performance, ranging from 50 to 100% accuracy with an average accuracy of 83.1%. These results demonstrated that the Vis/SWNIR spectroscopy technique could be applied to predict sugarcane °Brix in the field based skin scanning method.

Comparison and fusion of four nondestructive sensors for predicting apple fruit firmness and soluble solids content

Four nondestructive technologies (i.e., acoustic firmness, bioyield firmness, visible and shortwave near infrared (Vis-SWNIR) spectroscopy, and spectral scattering) have been developed in recent years for assessing the firmness and/or soluble solids content (SSC) of apples. Each of these technologies has its merits and limitations in predicting the two quality parameters. With the concept of multi-sensor data fusion, different sensors would work synergistically and complementarily to improve the quality prediction of apples. In this research, the four sensing systems were evaluated and combined for nondestructive prediction of the firmness and SSC of ‘Jonagold’ (JG), ‘Golden Delicious’ (GD), and ‘Delicious’ (RD) apples. A total of 6535 apples harvested in 2009 and 2010 were used for analysis. Better predictions of the firmness and, in most cases, of the SSC were obtained using sensors fusion than using individual sensors, as measured by correlation coefficient and standard error of prediction (SEP). The SEPs for the firmness of JG, GD and RD using the best combination of two-sensor data were reduced by 13.5%, 20.0% and 7.3% for the 2009 data and 14.6%, 14.2% and 6.2% for the 2010 data; and using the best three or four fused sensor data by 19.1%, 24.9% and 13.9% in 2009, and 15.7%, 23.6%, and 8.9% in 2010, respectively. The combination of Vis-SWNIR and scattering data improved SSC predictions for RD apples, with the SEP values being reduced by 5.8% and 6.0% for 2009 and 2010, respectively. This research demonstrated that the fused systems provided more complete and complementary information and, thus, were more effective than individual sensors in prediction of apple quality.

Neural network and principal component regression in non-destructive soluble solids content assessment: a comparison

Visible and near infrared spectroscopy is a non-destructive, green, and rapid technology that can be utilized to estimate the components of interest without conditioning it, as compared with classical analytical methods. The objective of this paper is to compare the performance of artificial neural network (ANN) (a nonlinear model) and principal component regression (PCR) (a linear model) based on visible and shortwave near infrared (VIS-SWNIR) (400-1000 nm) spectra in the non-destructive soluble solids content measurement of an apple. First, we used multiplicative scattering correction to pre-process the spectral data. Second, PCR was applied to estimate the optimal number of input variables. Third, the input variables with an optimal amount were used as the inputs of both multiple linear regression and ANN models. The initial weights and the number of hidden neurons were adjusted to optimize the performance of ANN. Findings suggest that the predictive performance of ANN with two hidden neurons outperforms that of PCR.

Uninformative variable elimination for improvement of successive projections algorithm on spectral multivariable selection with different calibration algorithms for the rapid and non-destructive determination of protein content in dried laver

The potential of using partial least square based uninformative variable elimination algorithm (UVEPLS) on successive projections algorithm (SPA) for spectral multivariable selection was evaluated. A case study was done on the visible and shortwave-near infrared (Vis-SNIR) spectroscopy for the rapid and non-destructive determination of protein content in dried laver. Three calibration algorithms, namely multiple linear regression (MLR), partial least square regression (PLS) and least-square support vector machine (LS-SVM), were used for the model establishment based on the selected variables of SPA, UVEPLS and UVEPLS-SPA, respectively. A total of 175 samples were prepared for the calibration (n = 117) and prediction (n = 58) sets. The performances of different pretreatments were compared. Both linear calibration algorithms of MLR and PLS and non-linear calibration algorithms of LS-SVM with linear kernel and RBF kernel obtained similar results based on certain variable selection strategies of SPA, UVEPLS and UVEPLS-SPA. The average improvement percentage of RPD values of four calibration algorithms was 38.66% by calculating SPA on UVEPLS processed variables. Therefore there was much improvement of using UVEPLS on SPA spectral multivariable selection with both linear and nonlinear calibration algorithms in this case. Moreover, the RPD values of both linear and non-linear models based on the thirteen selected variables of UVEPLS-SPA show that coarse quantitative predictions of the protein determination in dried laver is possible based on Vis-SNIR spectra. We hope that the results obtained in this study will help both further chemometric (multivariate selection and calibration analysis) investigations and investigations in the sphere of applied vibrational (Near infrared, Mid-infrared and Raman) spectroscopy of sophisticated multicomponent systems.

Nondestructive detection of internal insect infestation in jujubes using visible and near-infrared spectroscopy

This paper reports on a study comparing three spectroscopic measurements (interactance, reflectance, and transmittance) in the Vis/NIR range for the detection of internal insect infestation with different damaged levels in jujubes ( Hovenia acerba Lindl.). Stepwise discriminant analysis was used to derive the discriminant functions based on the effective wavelengths that had maximum discriminatory potential for the different internal conditions. The results show that both interactance in the long-wave NIR (LWNIR) and transmission in the visible and short-wave near-infrared (VSWNIR) wavelength ranges have an obvious advantage over reflectance for every range in completely distinguishing infested from intact jujubes. However, interactance and reflectance in the VSWNIR wavelength range exhibited higher classification accuracies in sorting severely damaged jujubes from slightly infested and intact samples. Furthermore, transmission had clear advantages over both interactance and reflectance for distinguishing slightly infested jujubes from intact jujubes in the VSWNIR range.