본 연구는 메꽃과 6종의 식물에 대해 신속하고 비파괴적으로 분류하기 위해 근적외선 (Vis-NIR) 스펙트럼을 이용하였고 데이터의 전처리와 머신러닝 기술을 적용하였다. 전국적으로 분포하는 메꽃과 6종에 대해 야외에서 휴대용 분광기를 이용하여 판별하였다. 식물의 잎의 표면에서 400~1,075 nm의 근적외선 스펙트럼 (1.5 nm)을 수집하였 다. 수집된 스펙트럼 데이터는 3가지의 전처리와 raw데이터를 이용하였고 4종류의 머신러닝 모델을 적용하여 높은 판별 정확도를 확인하였다. 전처리와 머신러닝 모델의 조합을 통해 분석된 판별의 정확도는 43~99%의 범위로 분석되었고, standard normal variate 전처리와 support vector machine 머신러닝 모델의 조합에서 판별 정확도가 98.6% 로 가장 높게 나타났다. 본 연구에서 수집된 스펙트럼은 식물의 성장단계, 다양한 측정 지역 및 잎에서의 측정 위치 등과 같은 요인과 더불어 데이터 분석을 위한 조건으로 최 적의 전처리와 머신러닝 기술을 적용한다면 메꽃과 식물의 야외에서의 정확한 분류가 가능하고 이들 식물의 효과적인 관리와 모니터링에 활용할 수 있을 것으로 판단되었다.

Near infrared reflectance spectroscopy (NIRS) is routinely used for the determination of nutrient components of forages. However, little is known about the impact of sample preparation and wavelength on the accuracy of the calibration to predict minerals. This study was conducted to assess the effect of sample preparation and wavelength of near infrared spectrum for the improvement of calibration and prediction accuracy of Calcium (Ca) and Phosphorus (P) in imported hay using NIRS. The samples were scanned in reflectance in a monochromator instrument (680–2,500 nm). Calibration models (n = 126) were developed using partial least squares regression (PLS) based on cross-validation. The optimum calibrations were selected based on the highest coefficients of determination in cross validation (R2) and the lowest standard error of cross-validation (SECV). The highest R2 and the lowest SECV were obtained using oven-dry grinded sample preparation and 1,100-2,500 nm wavelength. The calibration (R2) and SECV were 0.99 (SECV: 468.6) for Ca and 0.91 (SECV: 224.7) for P in mg/kg DM on a dry weight, respectively. Results of this experiment showed the possibility of NIRS method to predict mineral (Ca and P) concentration of imported hay in Korea for routine analysis method to evaluate the feed value.

The aim of this study was to investigate the feasibility of discrimination 12 different cultivar of sorghum × sudangrass hybrid (Sorghum genus) seed through near infrared spectroscopy (NIRS). The amount of samples for develop to the best discriminant equation was 360. Whole samples were applied different three spectra range (visible, NIR and full range) within 680-2500 nm wavelength and the spectrastar 2500 Near near infrared was used to measure spectra. The calibration equation for discriminant analysis was developed partial least square (PLS) regression and discrimination equation (DE) analysis. The PLS discriminant analysis model for three spectra range developed with mathematic pretreatment 1,8,8,1 successfully discriminated 12 different sorghum genus. External validation indicated that all samples were discriminated correctly. The whole discriminant accuracy shown 82 ~ 100 % in NIR full range spectra. The results demonstrated the usefulness of NIRS combined with chemometrics as a rapid method for discrimination of sorghum × sudangrass hybrid cultivar through seed.

In this study, whole crop rice samples were used to develop near-infrared reflectance (NIR) equations to estimate six forage quality parameters: Moisture, crude protein (CP), neutral detergent fiber (NDF), acid detergent fiber (ADF), Ash and relative feed value (RFV). A population of 564 whole crop rice representing a wide range in chemical parameters was used in this study. Undried finely chopped whole crop rice samples were scanned at 1 nm intervals over the wavelength range 680–2500 nm and the optical data recorded as log 1/Reflectance (log 1/R). NIRS calibrations were developed by means of partial least-squares (PLS) regression. The correlation coefficients of cross-validation (R2 cv) and standard error of cross-validation (SECV) for whole crop rice calibration were 0.98 (SECV 1.81%) for moisture, 0.89 (SECV 0.50%) for CP, 0.86 (SECV 1.79%) for NDF, 0.89 (SECV 0.86%) for ash, and 0.84 (SECV 5.21%) for RFV on a dry matter (%), respectively. The NIRS calibration equations developed in this study will be useful in predicting whole crop rice quality for these six quality parameters.

Near infrared reflectance spectroscopy (NIRS) has become increasingly used as a rapid and accurate method of evaluating some chemical compositions in forages. The objective of this study was to evaluate the potential of NIRS, applied to imported forage, to estimate the moisture and chemical parameters for imported hays. A population of 392 imported hay representing a wide range in chemical parameters was used in this study. Samples of forage were scanned at 1 nm intervals over the wavelength range 680-2500nm and the optical data was recorded as log 1/Reflectance(log 1/R), which scanned in intact fresh condition. The spectral data were regressed against a range of chemical parameters using partial least squares(PLS) multivariate analysis in conjunction with spectral math treatments to reduced the effect of extraneous noise. The optimum calibrations were selected based on the highest coefficients of determination in cross validation(R2) and the lowest standard error of cross-validation(SECV). The results of this study showed that NIRS predicted the chemical parameters with very high degree of accuracy. The R2 and SECV for imported hay calibration were 0.92(SECV 0.61%) for moisture, 0.98(SECV 0.65%) for acid detergent fiber, 0.97(SECV 0.40%) for neutral detergent fiber, 0.99(SECV 0.06%) for crude protein and 0.97(SECV 3.04%) for relative feed value on a dry matter(%), respectively. Results of this experiment showed the possibility of NIRS method to predict the moisture and chemical composition of imported hay in Korea for routine analysis method to evaluate the feed value.

This study was carried out to explore the accuracy of near infrared spectroscopy(NIRS) for the prediction of moisture content and chemical parameters on winter annual forage crops. A population of 2454 winter annual forages representing a wide range in chemical parameters was used in this study. Samples of forage were scanned at 1nm intervals over the wavelength range 680-2500nm and the optical data was recorded as log 1/Reflectance(log 1/R), which scanned in intact fresh condition. The spectral data were regressed against a range of chemical parameters using partial least squares(PLS) multivariate analysis in conjunction with spectral math treatments to reduced the effect of extraneous noise. The optimum calibrations were selected based on the highest coefficients of determination in cross validation(R2) and the lowest standard error of cross-validation(SECV). The results of this study showed that NIRS calibration model to predict the moisture contents and chemical parameters had very high degree of accuracy except for barely. The R2 and SECV for integrated winter annual forages calibration were 0.99(SECV 1.59%) for moisture, 0.89(SECV 1.15%) for acid detergent fiber, 0.86(SECV 1.43%) for neutral detergent fiber, 0.93(SECV 0.61%) for crude protein, 0.90(SECV 0.45%) for crude ash, and 0.82(SECV 3.76%) for relative feed value on a dry matter(%), respectively. Results of this experiment showed the possibility of NIRS method to predict the moisture and chemical composition of winter annual forage for routine analysis method to evaluate the feed value.

This study was conducted to find out an alternative way of rapid and accurate analysis of chemical composition of permanent pastures in hilly grazing area. Near reflectance infrared spectroscopy (NIRS) was used to evaluate the potential for predicting proximate analysis of permanent pastures in a vegetative stage. 386 pasture samples obtained from hilly grazing area in 2015 and 2016 were scanned for their visible–NIR spectra from 400~2,400nm. 163 samples with different spectral characteristics were selected and analysed for moisture, crude protein (CP), crude ash (CA), acid detergent fiber (ADF) and neutral detergent fiber (NDF). Multiple linear regression was used with wet analysis data and spectra for developing the calibration and validation mode1. Wavelength of 400 to 2500nm and near infrared range with different critical T outlier value 2.5 and 1.5 were used for developing the most suitable equation. The important index in this experiment was SEC and SEP. The R2 value for moisture, CP, CA, CF, Ash, ADF, NDF in calibration set was 0.86, 0.94, 0.91, 0.88, 0.48 and 0.93, respectively. The value in validation set was 0.66, 0.86, 0.83, 0.71, 0.35 and 0.88, respectively. The results of this experiment indicate that NIRS is a reliable analytical method to assess forage quality for CP, CF, NDF except ADF and moisture in permanent pastures when proper samples incorporated into the equation development.

This study was conducted to determine the effect of mathematical transformation on near infrared spectroscopy (NIRS) calibrations for the prediction of chemical composition and fermentation parameters in corn silage. Corn silage samples (n=407) were collected from cattle farms and feed companies in Korea between 2014 and 2015. Samples of silage were scanned at 1 nm intervals over the wavelength range of 680~2,500 nm. The optical data were recorded as log 1/Reflectance (log 1/R) and scanned in intact fresh condition. The spectral data were regressed against a range of chemical parameters using partial least squares (PLS) multivariate analysis in conjunction with several spectral math treatments to reduce the effect of extraneous noise. The optimum calibrations were selected based on the highest coefficients of determination in cross validation (R2 cv) and the lowest standard error of cross validation (SECV). Results of this study revealed that the NIRS method could be used to predict chemical constituents accurately (correlation coefficient of cross validation, R2 cv, ranging from 0.77 to 0.91). The best mathematical treatment for moisture and crude protein (CP) was first-order derivatives (1, 16, 16, and 1, 4, 4), whereas the best mathematical treatment for neutral detergent fiber (NDF) and acid detergent fiber (ADF) was 2, 16, 16. The calibration models for fermentation parameters had lower predictive accuracy than chemical constituents. However, pH and lactic acids were predicted with considerable accuracy (R2 cv 0.74 to 0.77). The best mathematical treatment for them was 1, 8, 8 and 2, 16, 16, respectively. Results of this experiment demonstrate that it is possible to use NIRS method to predict the chemical composition and fermentation quality of fresh corn silages as a routine analysis method for feeding value evaluation to give advice to farmers.

본 연구는 근적외선분광법을 이용하여 우리나라에서 재배되고 있는 목초류 중 외형적 특성이 유사한 이탈리안 라이그라스, 페레니얼 라이그라스와 톨 페스큐 종자의 초종 판별 가능성을 검토하고자 수행되었다. 근적외선분광기를 이용하여 목초류 종자를 가시파장 대역대(680~1,099 nm), NIRS 파장 대역대(1,100-2,500 nm) 및 NIRS 전체 파장 대역대(680-2,500 nm)로 구분하여 스펙트라를 얻은 후 1차 미분과 8 nm gap으로 수 처리를 수행하였으며 부분최소자승(PLS) 회귀분석법을 통해 초종판별 검량식을 개발하고 판별 정확성을 검증하였다. 목초류의 초종판별 정확성은 가시파장대역에서 SECV 1.732, R2CV 0.96으로 가장 판별 정확성이 낮았으며 NIRS 전체 파장대역에서 SECV 1.182, R2CV 0.98로 가장 높은 판별 정확성을 나타내었다. 파장대역별 예측 정확성은 NIR 파장대역(1,100-2,500 nm)에서 교차검증오차(SECV) 1.319에서 예측 오차(SEP) 1.288로 낮아졌으며 가시영역대(680~1,099)는 SECV 1.732에서 SEP 1.749로 약간 높아졌다. Discrimination equation 분석법에 의한 NIRS 전체 파장대역별 목초류 초종의 판별 결과는 초종간에 판별 정확성의 차이가 크게 나타났으며 이탈리안 라이그라스의 ‘Hits’는 68%로 가장 낮았으며 페레니얼 라이그라스가 78%의 정확성으로 가장 높게 나타났다. 따라서 NIRS를 이용한 목초류 초종의 판별분석이 가능할 것으로 판단되었다.