• Journal of Biosystems Engineering
• /
• v.26 no.5
• /
• pp.475-480
• /
• 2001

Sensing soil organic matter is crucial for precision farming and environment friendly agriculture. Near infra-red(NIR) was utilized to measure the soil organic matter. Multivariate calibration methods, including stepwise multiple linear regression(MLR), principal components recession(PCR) and partial least squares regression(PLS), were applied to soil spectral reflectance data to predict the organic matter content. The effect of soil particle size and water content was studied. The range of soil organic matter contents was from 0.5 to 11%. Near infrared (NIR) region from 700 to 2,500nm was applied. For uniform soil particle size, result had good correlation (R$\^$2/ = 0.984, standard error of prediction= 0.596). The effect of soil particle size could be eliminated with 1st order derivative of the NIR signal. However. moist soil had a little lower correlation. R$\^$2/ was 0.95 and standard error of prediction was 0.94% using the PLS method. The results showed the possibility of soil organic matter measurement using NIR reflectance on the field.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.40-40
• /
• 2017

본 연구는 빛의 파장대가 넓어 보다 다양한 접근과 검출이 가능한 초분광 카메라 (VNIR spectral camera PS, SPECIN Filand)를 이용하여 정식시기가 다른 배추를 생육단계별로 영상을 취득한 후 배추 캐노피의 전 파장 (400~1000nm)으로 생육 추정모델을 개발하기 위해 수행하였다. 정식시기가 다른 배추를 생육단계별로 초분광 카메라로 영상을 취득한 후 취득된 영상 ($348{\times}1040$)을 ENVI (ver. 5.2, Exelis Visual Information Solutions, USA) 프로그램을 이용하여 식생지수 NDVI로 작물과 배경을 구분하였다. 배추 캐노피 영역에 전 파장을 산출한 후 반사판 영역의 전 파장을 이용하여 광 보정된 반사율을 산출하였다. 통계 프로그램인 R Project (ver.3.3.3, Development Core Team, Vienna, Austria)를 이용하여 배추의 반사율과 계측한 생육 정보를 PLSR (Partial least squares regression) 분석하여 정확도($R^2$) 및 정밀도 (RMSE [g,cm,count], RE [%])로 나타내었고 그 모델은 full-cross validation (FV) 하여 타당성을 검증하였다. 정식시기가 다른 배추의 모든 생육단계의 생육정보를 이용하여 PLSR (Partial least squares regression) 결과 엽장을 추정한 모델의 $R^2$는 84% 이상의 정확도와 RMSE 3.2cm 이하의 좋은 정밀도를 보였다. 엽폭을 추정한 모델의 $R^2$는 73% 이상의 정확도와 RMSE 3.5cm 이하의 정밀도를 보였고 엽수를 추정한 모델의 $R^2$는 93% 이상의 정확도와 RMSE 6.3Count 이하의 정밀도로 보여 캐노피의 전 파장을 이용해 생육을 추정하는 것이 가능하다고 판단되었으며 이 모델들의 타당성 검증에서도 좋은 정확도와 정밀도를 보였다. 그러나 배추의 중요한 생육인자 중 생체중을 추정한 모델의 $R^2$는 89% 이상으로 정확도가 높았으나 RMSE 571.1g 이하로 낮은 정밀도를 보여 생체중을 정확히 추정하기 어려웠다. 따라서 다른 통계분석방법으로 전 파장과 생육정보를 분석하거나 특정 밴드를 선택하여 산출한 식생지수를 이용한 추정 모델의 개발을 통하여 오차를 개선할 필요가 있다고 사료된다. 추후 반복 실험하여 분석한 추정 모델과 비교 분석하여 다양한 환경 및 생물 조건에 범용성을 가진 모델을 개발할 필요가 있다.

• Journal of the Korean Wood Science and Technology
• /
• v.43 no.3
• /
• pp.311-319
• /
• 2015

Near infrared (NIR) reflectance spectroscopy was employed to develop moisture content prediction model of pitch pine (Pinus rigida), red pine (Pinus densiflora), Korean pine (Pinus koraiensis), yellow poplar (Liriodendron tulipifera) wood below fiber saturation point. NIR reflectance spectra of specimens ranging from 1000 nm to 2400 nm were acquired after humidifying specimens to reach several equilibrium moisture contents. To determine the optimal moisture contents prediction model, 5 mathematical preprocessing methods (moving average (smoothing point: 3), baseline, standard normal variate (SNV), mean normalization, Savitzky-Golay $2^{nd}$ derivatives (polynomial order: 3, smoothing point: 11)) were applied to reflectance spectra of each specimen as 8 combinations. After finishing mathematical preprocessings, partial least squares (PLS) regression analysis was performed to each modified spectra. Consequently, the mathematical preprocessing methods deriving optimal moisture content prediction were 1) moving average/SNV for pitch pine and red pine, 2) moving average/SNV/Savitzky-golay $2^{nd}$ derivatives for Korean pine and yellow poplar. Every model contained three principal components.

• Journal of the Korean Wood Science and Technology
• /
• v.43 no.3
• /
• pp.304-310
• /
• 2015

The moisture content of sawdust must be measured accurately and controlled appropriately during storage and transportation because biological degradation could be caused by improper moisture. In this study, to measure the moisture contents of Larix kaempferi sawdust, the near-infrared reflectance spectra (Wavelength 1000-2400 nm) of sawdust were used as detection parameter. After acquiring the NIR reflection spectrum of specimens which were humidified at each relative humidity condition ($25^{\circ}C$, RH 30~99%), moisture content prediction model was developed using mathematical preprocessings (e.g. smoothing, standard normal variate) and partial least squares (PLS) analysis with the acquired spectrum data. High reliability of the MC regression model with NIR spectroscopy was verified by cross validation test ($R^2$ = 0.94, RMSEP = 1.544). The results of this study show that NIR spectroscopy could be used as a convenient and accurate method for the nondestructive determination of moisture content of sawdust, which could lead to optimize wood utilization.

• 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.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.53 no.3
• /
• pp.244-250
• /
• 2008

The purpose of this study was to measure fundamental data required for the prediction of milling ratios, and to develop regression models to predict the head rice ratio of milled rice using NIR spectra of hulled rice. A total of 81 rice samples used in this study were collected from Jeongeup, Jeonbuk province in 2006. NIR spectra were measured using one mode of measurement, reflection. The reflectance spectra were measured in the wavelength region of 400-2500 nm with an NIR spectrophotometer "NIRSystems 6500" (Foss, Silverspring, USA). Calibration equations were developed by the modified partial least squares (MPLS), partial least squares (PLS), and principal components regression (PCR). Math treatments were 1-4-4-1, 1-10-10-1, 2-4-4-1, and 2-10-10-1. The software used was WinISI (Infrasoft International, State College, USA). Automatic head rice production and quality checking system used was "SY2000-AHRPQCS" (Ssangyong, Korea). The calibration was made with the first derivative and the spectrum designated was in 8 nm interval. The determination coefficients of head rice ratios were 0.8353, 0.8416 and 0.5277 for the MPLS, PLS and PCR, respectively. Those obtained with 20 nm interval were 0.8144, 0.8354 and 0.6908 for the MPLS, PLS and PCR, respectively. The calibration was made with second derivative that spectrum designated was 8 nm in interval. The determination coefficients of head rice ratios were 0.7994, 0.8017 and 0.4473 for the MPLS, PLS and PCR, respectively. Those with 20 nm interval were 0.8004, 0.8493 and 0.6609 for the MPLS, PLS and PCR, respectively. These results indicate that the accuracy of determination coefficient for MPLS and PLS is higher than that of PCR.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.53 no.1
• /
• pp.15-20
• /
• 2008

Near infrared reflectance spectroscopy (NIRS) is a rapid and accurate analytical method for determining the composition of agricultural products and feeds. This study was conducted to measure anthocyanin contents in black colored soybean by using NIRS system. Total 300 seed coat of black colored soybean samples previously analyzed by HPLC were scanned by NIRS and over 250 samples were selected for calibration and validation equation. A calibration equation calculated by MPLS(modified partial least squares) regression technique was developed in which the coefficient of determination for anthocyanin pigment C3G, D3G and Pt3G content was 0.952, 0.936, and 0.833, respectively. Each calibration equation was applied to validation set that was performed with the remaining samples not included in the calibration set, which showed high positive correlation both in C3G and D3G content file. In case Pt3G, the prediction model was needed more accuracy because of low $R^2$ value in validation set. This results demonstrate that the developed NIRS equation can be practically used as a rapid screening method for quantification of C3G and D3G contents in black colored soybean.

• Korean Journal of Optics and Photonics
• /
• v.20 no.6
• /
• pp.346-353
• /
• 2009

Glucose and protein in urine are among the important substances for urine analysis and have generally been measured based on a reagent strip test. In this study, these two substances were measured using mid-infrared absorption spectroscopy. Samples were prepared from a commercial synthetic urine product. Glucose and albumin were added as well as red blood cells, which are expected to create the most spectroscopic interference of any substance. Concentrations of these substances were varied independently. Optimal wavelength regions were determined from a partial least squares regression analysis (glucose 980 - 1150/cm, albumin 1400 - 1570/cm). Interference by other substances increased the differences between measured and predicted values. Albumin measurement in particular weres heavily influenced by the presence of glucose and red blood cells. Depending on the inference by other substances, measurement errors were 29.85${\sim}$45.19 mg/dl for a glucose level between 0 and 1000 mg/dl and 14.0${\sim}$93.11 mg/dl for an albumin level of 0 ${\sim}$ 500 mg/dl. Our study proposes an alternative to the chemical test-strip analysis, which shows only discrete concentration levels.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.4
• /
• pp.497-502
• /
• 2012

This study investigates the prediction of soil OM on Korean soils using the Visible-Near Infrared (Vis-NIR) spectroscopy. The ASD Field Spec Pro was used to acquire the reflectance of soil samples to visible to near-infrared radiation (350 to 2500 nm). A total of 503 soil samples from 61 Korean soil series were scanned using the instrument and OM was measured using the Walkley and Black method. For data analysis, the spectra were resampled from 500-2450 nm with 4 nm spacing and converted to the $1^{st}$ derivative of absorbance (log (1/R)). Partial least squares regression (PLSR) and regression rules model (Cubist) were applied to predict soil OM. Regression rules model estimates the target value by building conditional rules, and each rule contains a linear expression predicting OM from selected absorbance values. The regression rules model was shown to give a better prediction compared to PLSR. Although the prediction for Andisols had a larger error, soil order was not found to be useful in stratifying the prediction model. The stratification used by Cubist was mainly based on absorbance at wavelengths of 850 and 2320 nm, which corresponds to the organic absorption bands. These results showed that there could be more information on soil properties useful to classify or group OM data from Korean soils. In conclusion, this study shows it is possible to develop good prediction model of OM from Korean soils and provide data to reexamine the existing prediction models for more accurate prediction.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1245-1245
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145-154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.