• 농업과학연구
• /
• 제47권4호
• /
• pp.995-1010
• /
• 2020

In this study, a multivariate analysis model of partial least square regression (PLSR) was developed to predict the moisture content of green peppers using hyperspectral imaging (HSI). In HSI, illumination is essential for high-quality image acquisition and directly affects the analytical performance of the visible near-infrared hyperspectral imaging (VIS/NIR-HSI) system. When green pepper images were acquired using a direct lighting system, the specular reflection from the surface of the objects and their intensities fluctuated with time. The images include artifacts on the surface of the materials, thereby increasing the variability of data and affecting the obtained accuracy by generating false-positive results. Therefore, images without glare on the surface of the green peppers were created using a polarization filter at the front of the camera lens and by exposing the polarizer sheet at the front of the lighting systems simultaneously. The results obtained from the PLSR analysis yielded a high determination coefficient of 0.89 value. The regression coefficients yielded by the best PLSR model were further developed for moisture content mapping in green peppers based on the selected wavelengths. Accordingly, the polarization filter helped achieve an uniform illumination and the removal of gloss and artifact glare from the green pepper images. These results demonstrate that the HSI technique with a polarized lighting system combined with chemometrics can be effectively used for high-throughput prediction of moisture content and image-based visualization.

• 한국산학기술학회논문지
• /
• 제21권10호
• /
• pp.354-360
• /
• 2020

본 연구는 잡곡(조, 기장, 수수)의 물리적 특징 중 기하학적 특성, 산물밀도 및 종말속도를 함수율별로 분석하여 미곡가공시설의 선별 장치를 이용하여 잡곡의 선별의 가능성을 위한 기초자료로 활용하기 위하여 연구를 수행하였다. 조, 기장 및 수수의 초기함수율은 16.3, 19.8, 16.5 %(w.b.)로 나타났다. 잡곡은 5수준으로 건조하여 실험에 사용하였다. 잡곡의 기하학적 특성 중 원형율을 제외하고 단축, 장축 및 면적은 함수율이 높을수록 증가하는 것으로 나타났으며, 1차식 실험모델로 모두 표현이 가능하였다. 산물밀도는 조 및 기장은 함수율이 높을수록 증가하는 것으로 나타났으나 수수의 경우는 함수율과 무관하였다. 종말속도는 함수율이 높을수록 종말속도가 증가하는 것으로 나타났으며, 1차식 실험모델로 표현이 가능하였다. 잡곡별 측정한 물리적 특성은 함수율의 변화에 따른 1차식 실험모델로 표현이 가능하였으며, 기존 미곡선별장치를 이용할 경우 종말속도를 이용하는 장치는 사용이 가능하지만 기하하적 특성 및 산물밀도를 이용하는 공정은 잡곡에 따라 전용 공정의 설계가 별도로 필요하였다.

• Journal of Biosystems Engineering
• /
• 제21권2호
• /
• pp.198-207
• /
• 1996

To measure the moisture content, protein and viscosity of brown and milled rice with Near Infrared Reflectance(NIR) analyzer, the comparison and analysis of the data from the chemical analysis and NIR analyzer were conducted. The purpose of this study is to find out the fundamental data required for the prediction of rice qualify and taste rank, and to develop a measuring method of constituents and physical characteristics of domestic rice with NIR analyzer. The important results can be summarized as follows. 1. The $r^2$ and SEC of moisture calibration from brown rice powder were 0.87 and 0.09 respectively, those of milled rice powder were 0.95 and 0.08 respectively. 2. The $r^2$ and SEC of protein calibration from brown rice powder were 0.83 and 0.20 respectively, those of milled rice powder were 0.86 and 0.20 respectively. 3. The $r^2$ and SEC of viscosity calibration from brown rice powder were 0.36 and 15.50 respectively, those of milled rice powder were 0.55 and 12.98 respectively. Further study is required to develop better prediction model for viscosity. It is necessary the continuous study including wavelength selection, because $r^2$ is small for practical use. 4. The regression equation for one rice variety was nearly coincident with other. Therefore, it is required that the prediction model should be developed for the all rice samples.

• Journal of Biosystems Engineering
• /
• 제23권3호
• /
• pp.253-258
• /
• 1998

The part I was for developing regression models to predict the moisture content, protein content and viscosity of brown and milled rice using Near Infrared(NIR) Reflectance analyzer. The purpose of this study(part II) is to measure fundamental data required for the prediction of rice quality, and to develop regression models to predict the protein content of brown and milled rice, brown rice yield from undried paddy powder by using Near Infrared(NIR) Reflectance analyzer. The results of this study were summarized as follows : The predicted values of protein contents obtained from the undried paddy powder were well correlated to the measured values from brown and milled rice. The predicted yields of brown rice from undried paddy powder were not well correlated to the lab measured values from dried paddy. Continuous study in wavelength selection and of constituent relationship is necessary for practical application.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1998년도 하계 학술대회 논문집
• /
• pp.171-177
• /
• 1998

The part Ⅰ was for developing regression models to predict the moisture content, protein content and viscosity of brown and milled rice using Near Unfrared (NIR) Reflectance analyzer. The purpose of this study(part Ⅱ) is to measure fundamental data required for the prediction of rice quality , and to develop regression models to predict the protein content of brown and milled rice, brown rice yield from undreid paddy powder by using Near Infrared (NIR) Reflectance analyzer. The results of this study were summarized as follows . The predicted values of protein contents obtained from the undried paddy powder were will correlated to the measured values from brown and milled rice. The predicted yields of brown rice from undried paddy powder were not well correlated to be lab measured values from dried paddy. Continuous study in wavelength selection and of constituent relationship is necessary for practical application.

• 한국산림과학회지
• /
• 제112권4호
• /
• pp.490-501
• /
• 2023

본 연구에서는 강우의 침투과정 및 수분 재분포 현상을 분석하기 위하여 실내 컬럼실험을 수행하였으며, 토층 내 함수비를 효율적으로 측정하기 위하여 딥러닝 기법 중 하나인 합성곱신경망(Convolutional Neural Network, CNN)을 사용하여 함수비 예측 모델을 구축하였다. 컬럼실험으로부터 획득된 디지털 이미지를 구축된 CNN 모델에 적용한 결과 시간에 따른 토층별 함수비를 효과적으로 측정할 수 있었으며, 토층별로 설치된 함수비 센서에 따른 함수비와도 비교적 잘 일치하는 것으로 나타났다. 결과적으로 CNN을 활용하여 토층 내 연속적인 함수비 분포를 파악하는 것이 가능하였으며, 토성 및 지반 함수비 조건에 따른 침투 과정을 효과적으로 분석할 수 있었다.

• Journal of the Korean Wood Science and Technology
• /
• 제47권6호
• /
• pp.732-750
• /
• 2019

천연건조 중 목재의 함수율 변화 예측모형을 제시하기 위하여 15본의 소나무 원목에 대한 천연건조를 수행하였다. 초기함수율이 68.7%인 6본의 소나무 원목에 대하여 여름철에 천연건조를 시작한 후 약 880일이 경과한 후의 최종함수율은 17.4%이었다. 초기함수율이 35.8%인 9본의 소나무 원목에 대하여 겨울철에 천연건조를 시작한 후 약 760일이 경과한 후의 최종함수율은 16.0%이었다. 소나무 원목의 말구지름, 온도, 상대습도, 풍속을 독립변수로 결정하고, 천연건조 중 감소한 함수율을 종속변수로 다중회귀분석을 진행한 결과, 결정계수 0.925의 회귀모형을 얻을 수 있었다. 소나무 원목의 특성인 초기함수율과 말구지름이 기상조건인 온도, 상대습도, 풍속에 비하여 천연건조 중 함수율 감소에 미치는 영향이 더 크게 나타났다. 천연건조 중 내부함수율의 분포 및 함수율 변화를 예측하기 위하여 2차원 물질전달 해석을 수행하였다. 건조일수를 서로 다르게 적용하고, 수분확산계수 및 표면방사계수를 결정하는 기상조건을 다르게 적용한 2가지의 예측모형을 제시하였다. 2가지 적용 방법의 오차는 0.1 - 0.8%의 범위였으며, 측정값과의 차이는 2.2 - 3.6%의 범위였다. 다양한 초기함수율과 말구지름의 소나무 원목에 대한 천연건조 중 내부함수율을 측정하고, 각각의 기상조건에 대한 목재 내 수분이동계수를 산출하면 예측모형의 오차를 감소시킬 수 있을 것으로 판단된다.

• 약학회지
• /
• 제47권3호
• /
• pp.148-153
• /
• 2003

Skin moisture is an important factor in skin health. Measurement of moisture content can provide diagnostic information on the condition of skin. In this study, a portable near-infrared (NIR) system was newly integrated with a photo diode array detector that has no moving parts, and this system has been successfully applied for the evaluation of human skin moisture. Diffuse reflectance spectra were collected and transformed to absorbance using 1 nm step size over the wavelength range of 1100 nm to 2200 nm. Partial least squares regression (PLSR) was applied to develop a calibration model. For practical use for the evaluation of human skin moisture, the PLS model for human skin moisture was developed in vivo using the portable NIR system on the basis of the relative water content values of stratum corneum from the conventional capacitance method. The PLS model showed a good correlation. The calibration with the use of PLS model predicted human moisture with a standard error of prediction (SEP) of 3.5 at 1120∼1730 nm range. This study showed the possibility of skin moisture measurement using portable NIR system.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제26권6호
• /
• pp.106-117
• /
• 2021

The purpose of this study is prediction of landslide occurrence reflecting the subsurface flow characteristics within the soil layer in the future due to climate change in a large scale watershed. To do this, we considered the infinite slope stability theory to evaluate the landslide occurrence with predicted soil moisture content by SWAT model based on monitored data (rainfall-soil moisture-discharge). The correlation between the SWAT model and the monitoring data was performed using the coefficient of determination (R²) and the model's efficiency index (Nash and Sutcliffe model efficiency; NSE) and, an accuracy analysis of landslide prediction was performed using auROC (area under Receiver Operating Curve) analysis. In results comparing with the calculated discharge-soil moisture content by SWAT model vs. actual observation data, R² was 0.9 and NSE was 0.91 in discharge and, R² was 0.7 and NSE was 0.79 in soil moisture, respectively. As a result of performing infinite slope stability analysis in the area where landslides occurred in the past based on simulated data (SWAT analysis result of 0.7~0.8), AuROC showed 0.98, indicating that the suggested prediction method was resonable. Based on this, as a result of predicting the characteristics of landslide occurrence by 2050 using climate change scenario (RCP 8.5) data, it was calculated that four landslides could occur with a soil moisture content of more than 75% and rainfall over 250 mm/day during simulation. Although this study needs to be evaluated in various regions because of a case study, it was possible to determine the possibility of prediction through modeling of subsurface flow mechanism, one of the most important attributes in landslide occurrence.

• 한국식품저장유통학회지
• /
• 제30권2호
• /
• pp.224-234
• /
• 2023

We analyzed the major quality characteristics of red pepper powders from various regions and predicted these characteristics nondestructively using shortwave infrared hyperspectral imaging (HSI) technology. We conducted partial least squares regression analysis on 70% (n=71) of the acquired hyperspectral data of the red pepper powders to examine the major quality characteristics. R_c² values of ≥0.8 were obtained for the ASTA color value (0.9263) and capsaicinoid content (0.8310). The developed quality prediction model was validated using the remaining 30% (n=35) of the hyperspectral data; the highest accuracy was achieved for the ASTA color value (R_p²=0.8488), and similar validity levels were achieved for the capsaicinoid and moisture contents. To increase the accuracy of the quality prediction model, we conducted spectrum preprocessing using SNV, MSC, SG-1, and SG-2, and the model's accuracy was verified. The results indicated that the accuracy of the model was most significantly improved by the MSC method, and the prediction accuracy for the ASTA color value was the highest for all the spectrum preprocessing methods. Our findings suggest that the quality characteristics of red pepper powders, even powders that do not conform to specific variables such as particle size and moisture content, can be predicted via HSI.