• Journal of Biosystems Engineering
• /
• v.40 no.2
• /
• pp.153-158
• /
• 2015

Purpose: The research presented in this paper applied the chemometric analysis to the near-infrared spectral data from line-scanned hyperspectral images of beef and fish meals in animal feeds. The chemometric statistical models were developed to distinguish beef meals from fish ones. Methods: The meal samples of 40 fish meals and 15 beef meals were line-scanned to obtain hyperspectral images. The spectral data were retrieved from each of 3600 pixels in the Region of Interest (ROI) of every sample image. The wavebands spanning 969 nm to 1551 nm (across 176 spectral bands) were selected for chemometric analysis. The partial least squares regression (PLSR) and the principal component analysis (PCA) methods of the chemometric analysis were applied to the model development. The purpose of the models was to correctly classify as many beef pixels as possible while misclassified fish pixels in an acceptable amount. Results: The results showed that the success classification rates were 97.9% for beef samples and 99.4% for fish samples by the PLSR model, and 85.1% for beef samples and 88.2% for fish samples by the PCA model. Conclusion: The chemometric analysis-based PLSR and PCA models for the hyperspectral image analysis could differentiate beef meals from fish ones in animal feeds.

• Journal of Biosystems Engineering
• /
• v.34 no.3
• /
• pp.197-203
• /
• 2009

This study was performed to develop a nondestructive determination technology for sugar content in sweet persimmons, and the main research results included the following. In order to determine sugar content in sweet persimmons, a dual side reflex was adopted, and the study was to measure sugar content using a reflectance spectrum for 2 parts because it was difficult to determine representative sugar content due to a great deviation in sugar content according to the part of sweet persimmons. To predict sugar contents of sweet persimmon, PLSR and PCR models were compared with a few preprocess methods. As a result, PLSR had $R^2$=0.67, SEP=0.42 brix, LV=11, and PCR had $R^2$=0.65, SEP=0.41 brix, PC=16. SNV method was the best among preprocess methods for predicting sugar contents.

• Korean Journal of Agricultural Science
• /
• v.50 no.4
• /
• pp.675-696
• /
• 2023

Terpenoids, also referred to as terpenes, are a large family of naturally occurring chemical compounds present in the essential oils extracted from medicinal plants. In this study, a nondestructive methodology was created by combining ATR-FT-IR (attenuated total reflectance-Fourier transform infrared), and Raman spectroscopy for the terpenoids assessment in medicinal plants essential oils from ten different geographical locations. Partial least squares regression (PLSR) and support vector regression (SVR) were used as machine learning methodologies. However, a deep learning based model called as one-dimensional convolutional neural network (1D CNN) were also developed for models comparison. With a correlation coefficient (R²) of 0.999 and a lowest RMSEP (root mean squared error of prediction) of 0.006% for the prediction datasets, the SVR model created for FT-IR spectral data outperformed both the PLSR and 1 D CNN models. On the other hand, for the classification of essential oils derived from plants collected from various geographical regions, the created SVM (support vector machine) classification model for Raman spectroscopic data obtained an overall classification accuracy of 0.997% which was superior than the FT-IR (0.986%) data. Based on the results we propose that FT-IR spectroscopy, when coupled with the SVR model, has a significant potential for the non-destructive identification of terpenoids in essential oils compared with destructive chemical analysis methods.

• Korean Journal of Agricultural Science
• /
• v.39 no.4
• /
• pp.603-612
• /
• 2012

In this research, the feasibility of non-destructive measurement technique of pungency measurement was investigated for the red-pepper powders produced in different domestic areas in South Korea. The near-infrared absorption spectra in the range of 1100 nm~2300 nm was used to measure capsaicinoids content in red-pepper powders by using a NIR spectroscopy equipped with Acousto-optic tunable filters (AOTF). Fourth three different red-pepper powders from 14 different locations were collected and separated in three different particle size (below 0.425 mm, 0.425~0.71 mm, 0.71~1.4 mm) for the spectral measurements. The partial least square regression (PLSR) models to predict the capsaicinoids content depends on particle size were developed with the measured spectra. The determinant coefficients and standard errors of the developed models for the red-pepper powders of below 0.425 mm, 0.425~0.71 mm, and 0.71~1.4 mm were in the range of 0.859~0.887 and 12.90~12.99 mg/100 g, respectively. The PLS model with the pretreatment of Standard Normal Variate (SNV) for the red-pepper powders below 1.4 mm particle size showed the best performance with the determinant coefficient of 0.844 and the standard error of 14.63 mg/100 g.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_1
• /
• pp.559-570
• /
• 2017

A partial least squares regression (PLSR) model was developed to map the internal soluble solids content (SSC) of apples using a ground-based hyperspectral scanner that could simultaneously acquire outdoor data and capture images of large quantities of apples. We evaluated the applicability of various preprocessing techniques to construct an optimal prediction model and calculated the optimal band through a variable importance in projection (VIP)score. From the 515 bands of hyperspectral images extracted at wavelengths of 360-1019 nm, 70 reflectance spectra of apples were extracted, and the SSC ($^{\circ}Brix$) was measured using a digital photometer. The optimal prediction model wasselected considering the root-mean-square error of cross-validation (RMSECV), root-mean-square error of prediction (RMSEP) and coefficient of determination of prediction $r_p^2$. As a result, multiplicative scatter correction (MSC)-based preprocessing methods were better than others. For example, when a combination of MSC and standard normal variate (SNV) was used, RMSECV and RMSEP were the lowest at 0.8551 and 0.8561 and $r_c^2$ and $r_p^2$ were the highest at 0.8533 and 0.6546; wavelength ranges of 360-380, 546-690, 760, 915, 931-939, 942, 953, 971, 978, 981, 988, and 992-1019 nm were most influential for SSC determination. The PLSR model with the spectral value of the corresponding region confirmed that the RMSEP decreased to 0.6841 and $r_p^2$ increased to 0.7795 as compared to the values of the entire wavelength band. In this study, we confirmed the feasibility of using a hyperspectral scanner image obtained from outdoors for the SSC measurement of apples. These results indicate that the application of field data and sensors could possibly expand in the future.

• YAKHAK HOEJI
• /
• v.47 no.6
• /
• pp.461-468
• /
• 2003

A method is described for measuring clinically relevant levels of glucose in a pH 7.4 phosphate buffer by nearinfrared (NIR) absorption spectroscopy. Three types of NIR spectrometer, dispersive type, photo-diode array (PDA) type, and fourier transform (FT) type spectrometer were used and the performance was compared. Spectra were collected with a cuvette cell or quartz liquid fiber of 1 mm or 2 mm optical pathlength as transmittance method. Glucose absorption band appeared at second overtone, first overtone, and combination region for all systems. By use of the multivariate technigue of partial least squares (PLS) regression, glucose concentrations can be determined with a 16, 44, and 9.1 mg/d l standard error of prediction for dispersive type, photo-diode array type, and fourier transform type system, respectively. Sensitivity of spectrometer was evaluated by absorbance for the difference of 10 mg/d l glucose. Three absorption bands, second overtone, first overtone, and combination region were suited to three types systems, dispersive type, photo-diode array type, and fourier transform type systems, respectively. This investigation showed that three types NIR spectrometer were proper method for identification and quantitative analysis of glucose and possible for noninvasive blood glucose monitoring.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.208-213
• /
• 2021

There is a lack of studies comparing the internal quality of fruit with its external quality. However, issues of internal quality of fruit such as internal browning are important. We propose a method of classifying normal apples and internally browned apples using a near-infrared (NIR) non-destructive system. Specifically, we found the optimal wavelength and characteristics of the spectra for determining the internal browning of Fuji apples. The NIR spectra of apples were obtained in the wavelength range of 470-1150 nm. A group of normal apples and a group of internally browned apples were identified using principal component analysis (PCA), and a partial least squares regression (PLSR) analysis was performed to develop and evaluate the discriminant model. The PCA analysis revealed a clear difference between the normal and internally browned apples. From the PLSR, the correlation coefficient of the predictive model without pretreatment was determined to be 0.902 with an RMSE value of 0.157. The correlation coefficient of the predictive model with pretreatment was 0.906 with an RMSE value of 0.154. The results show that this model is suitable for classifying normal and internally browned apples and that it can be applied for the sorting and evaluation of agricultural products for internal and external defects.

• Journal of the Korean Society of Food Culture
• /
• v.32 no.2
• /
• pp.150-161
• /
• 2017

This study was conducted to identify sensory characteristics of soy-meat samples by trained panels and to observe the relationship between these sensory characteristics and consumer acceptability of the samples. Descriptive analysis was performed on eight samples; four types of patty style soy-meat samples (Soy-meat Patty; SP) made with a Ddukgalbi recipe (YSP, VSP, LSP, and SSP) and four types of Bulgogi style soy-meat samples (Soy-meat Bulgogi; SB) made with a Bulgogi recipe (YSB, VSB, LSB, and SSB). Seven panelists were trained, and they evaluated the appearance, odor/aroma, flavor/taste, texture/mouth feel, and after taste attributes of these samples. Forty attributes were generated by panelists, and 37 attributes were significantly different across products (p<0.05). The SB group was characterized by beef, leek, and garlic flavor as well a sweetness, denseness, slipperiness, chewiness, and pepper after taste. The SP group was characterized by roughness, particle size, rancid oil flavor, raw bean flavor, astringent, sourness, and adhesiveness. Consumer test (n=125) showed that the VSB sample had the highest scores for acceptability of appearance, flavor, texture, and overall liking. The PLSR results show that the attributes that were more positively associated with acceptance of soy-meat samples were beef taste, wetness, and chewiness, whereas the raw bean smell and rancid oil flavor attributes were negative.

• Journal of Animal Environmental Science
• /
• v.20 no.3
• /
• pp.117-124
• /
• 2014

The objectives were to assess the use of near-infrared reflectance spectroscopy (NIRS) as a tool for estimating nutrient compositions of corn kernel, and to apply an NIRS-based indium gallium arsenide array detector to the system for collecting spectra and analyzing calibration equations using equipments designed for field application. Partial Least Squares Regression (PLSR) was employed to develop calibration equations based on representative data sets. The kennard-stone algorithm was applied to induce a calibration set and a validation set. As a result, the method for structuring a calibration set significantly affected prediction accuracy. The prediction of chemical composition of corn kernel resulted in the following (kennard-stone algorithm: relative) moisture ($R^2=0.82$, RMSEP=0.183), crude protein ($R^2=0.80$, RMSEP=0.142), crude fat ($R^2=0.84$, RMSEP=0.098), crude fiber ($R^2=0.74$, RMSEP=0.098), and crude ash ($R^2=0.81$, RMSEP=0.048). Result of this experiment showed the potential of NIRS to predict the chemical composition of corn kernel.

• Korean Journal of Soil Science and Fertilizer
• /
• v.37 no.4
• /
• pp.259-265
• /
• 2004

A quicker method was developed for foliar analysis in diagnosis of nitrogen in apple trees based on multivariate calibration procedure using partial least squares regression (PLSR) and principal component regression (PCR) to establish the relationship between reflectance spectra in the near infrared region and nitrogen content of fresh- and dry-leaf. Several spectral pre-processing methods such as smoothing, mean normalization, multiplicative scatter correction (MSC) and derivatives were used to improve the robustness and performance of the calibration models. Norris first derivative with a seven point segment and a gap of six points on MSC gave the best result of partial least squares-1 PLS-1) model for dry-leaf samples with root mean square error of prediction (RMSEP) equal to $0.699g\;kg^{-1}$, and that the Savitzky-Golay first derivate with a seven point convolution and a quadratic polynomial on MSC gave the best results of PLS-1 model for fresh-samples with RMSEP of $1.202g\;kg^{-1}$. The best PCR model was obtained with Savitzky-Golay first derivative using a seven point convolution and a quadratic polynomial on mean normalization for dry leaf samples with RMSEP of $0.553g\;kg^{-1}$, and obtained with the Savitzky-Golay first derivate using a seven point convolution and a quadratic polynomial for fresh samples with RMSEP of $1.047g\;kg^{-1}$. The results indicate that nitrogen can be determined by the near infrared reflectance (NIR) technology for fresh- and dry-leaf of apple.