• 대한조선학회논문집
• /
• 제56권6호
• /
• pp.488-496
• /
• 2019

The estimation of block erection work time at a dock is one of the important factors when establishing or managing the total shipbuilding schedule. In order to predict the work time, it is a natural approach that the existing block erection data would be used to solve the problem. Generally the work time per unit is the product of coefficient value, quantity, and product value. Previously, the work time per unit is determined statistically by unit load data. However, we estimate the work time per unit through work time coefficient value from series ships using machine learning. In machine learning, the outcome depends mainly on how the training data is organized. Therefore, in this study, we use 'Feature Engineering' to determine which one should be used as features, and to check their influence on the result. In order to get the coefficient value of each block, we try to solve this problem through the Ensemble learning methods which is actively used nowadays. Among the many techniques of Ensemble learning, the final model is constructed by Stacking Ensemble techniques, consisting of the existing Ensemble models (Decision Tree, Random Forest, Gradient Boost, Square Loss Gradient Boost, XG Boost), and the accuracy is maximized by selecting three candidates among all models. Finally, the results of this study are verified by the predicted total work time for one ship among the same series.

• Journal of the Korean Wood Science and Technology
• /
• 제48권5호
• /
• pp.651-665
• /
• 2020

Hydrolysis of biomass for the production of fermentable sugar can be improved by the addition of surfactants. In pulp and paper mills, lignin, which is a by-product of the pulping process, can be utilized as a fine chemical. In the hydrolysis process, lignin is one of the major inhibitors of the enzymatic breakdown cellulose into sugar monomer. Therefore, the conversion of lignin into a biosurfactant offers the opportunity to solve the waste problem and improve hydrolysis efficiency. In this study, lignin derivatives, a biosurfactant, was applied to enzymatic hydrolysis of various lignocellulosic biomass. This Biosurfactant can be prepared by reacting lignin with a hydrophilic polymer such as polyethylene glycol diglycidylethers (PEDGE). In this study, the effect of biosurfactants on the enzymatic hydrolysis of pretreated sweet sorghum bagasse (SSB), oil palm empty fruit bunch, and sugarcane trash with different lignin contents was investigated. The results show that lignin derivatives improve the enzymatic hydrolysis of the pretreated biomass with low lignin content, however, it has less influence on the enzymatic hydrolysis of other pretreated biomass with lignin content higher than 10% (w/w). The use of biosurfactant on SSB kraft pulp can increase the sugar yield from 45.57% to 81.49%.

• 미생물학회지
• /
• 제47권1호
• /
• pp.30-37
• /
• 2011

조류 인플루엔자 바이러스(AIV) 아형을 ultra-time PCR법(UPCR)을 이용하여 초스피드로 진단할 수 있는 방법을 고안하였다. 표적 대상의 프라이머는 AIV H5N1 아형의 hemagglutinin(HA) 유전자 중 가장 상보성이 높은 133 bp의 부위를 선택하였고, 실험의 안전을 위하여 인공합성의 방법으로 제작하였다. 압타머와 결합한 molecular beacon 기반 Mini-Opticon Q-PCR 기기를 사용한 UPCR법으로, 총 UPCR 반응액의 양을 10 ${\mu}l$으로, UPCR과 용융온도 분석시간을 15분 이내로 매우 짧게 단축시켰다. 민감도 측정에서 최소의 주형인 5분자의 HA 유전자만으로 정확히 AIV의 특이적 133 bp를 합성하였다. UPCR로 디자인된 이 PCR은 AIV 아형의 진단에 적용될 수 있을 뿐 아니라, UPCR이 기반되는 진단을 이용하여 다른 병원체에도 널리 적용 될 수 있을 것으로 기대된다.

• 한국농림기상학회지
• /
• 제6권4호
• /
• pp.235-241
• /
• 2004

1월의 최저기온을 대상으로 1951년부터 2000년까지 14개 지점의 관측자료를 분석한 결과 11개 지점에서 전반기(1951-1980)에 비해 후반기(1971-2000)의 연차 변이가 오히려 감소한 것으로 나타났다 표준편차로 표현할 경우 제주, 전주, 울릉도를 제외한 나머지 11개 지점에서 많게는 0.35(서울)에서 적게는 0.03(강릉)까지 고르게 연차변이가 감소하였다. 이는 최근의 난동화 경향과 함께 겨울철 최저기온의 연차변이가 더 심해지고 있다는 당초의 예상과 다른 결과이다 연차변이의 공간분포양상은 최저기온의 절대값과 정의 상관을, 관측점의 해발고도와는 부의 상관을 보였다. 이 관계를 이용하여 남한전역의 1월 최저기온 30년 표준 편차 분포도를 작성하였으며, 이를 토대로 재현기간별로 기대되는 전국의 극최저기온 분포도를 제작하여 지역별 동해위험 평가에 이용토록 하였다.

• 산업경영시스템학회지
• /
• 제47권1호
• /
• pp.41-50
• /
• 2024

Korea is facing a significant problem with historically low fertility rates, which is becoming a major social issue affecting the economy, labor force, and national security. This study analyzes the factors contributing to the regional gap in fertility rates and derives policy implications. The government and local authorities are implementing a range of policies to address the issue of low fertility. To establish an effective strategy, it is essential to identify the primary factors that contribute to regional disparities. This study identifies these factors and explores policy implications through machine learning and explainable artificial intelligence. The study also examines the influence of media and public opinion on childbirth in Korea by incorporating news and online community sentiment, as well as sentiment fear indices, as independent variables. To establish the relationship between regional fertility rates and factors, the study employs four machine learning models: multiple linear regression, XGBoost, Random Forest, and Support Vector Regression. Support Vector Regression, XGBoost, and Random Forest significantly outperform linear regression, highlighting the importance of machine learning models in explaining non-linear relationships with numerous variables. A factor analysis using SHAP is then conducted. The unemployment rate, Regional Gross Domestic Product per Capita, Women's Participation in Economic Activities, Number of Crimes Committed, Average Age of First Marriage, and Private Education Expenses significantly impact regional fertility rates. However, the degree of impact of the factors affecting fertility may vary by region, suggesting the need for policies tailored to the characteristics of each region, not just an overall ranking of factors.

• 대한원격탐사학회지
• /
• 제29권3호
• /
• pp.307-314
• /
• 2013

The Bidirectional Reflectance Distribution (BRD) effect is critical to interpret the surface information using remotely sensed data. This effect was caused by geometric relationship between sensor, target and solar that is inevitable effect for data of optical sensor. To remove the BRD effect, semi-empirical BRDF models are widely used. It is faster to calculate than physical models and demanded less observation than empirical models. In this study, Ross-Li kernel and Roujean kernel were used respectively in National Aeronautics and Space Administration (NASA) and European Organization for the Exploitation of Meteorological Satellites (EUMETSAT) that are used to compare each other. The semi-empirical model consists of three parts which are isotropic, geometric and volumetric scattering. Each part contained physical kernel and empirical coefficients that were calculated by statistical method. Red and NIR channel of SPOT/VEGETATION product were used to compute Nadir BRDF Adjusted Reflectance (NBAR) over East Asia area from January 2009 to December 2009. S1 product was provided by VITO that was conducted atmospheric correction using Simplified Method of Atmospheric Correction (SMAC). NBAR was calculated using corrected reflectance of red and NIR. Previous study has revealed that Roujean geometric kernel had unphysical values in large zenith angles. We extracted empirical coefficients in three parts and normalized reflectance to compare both BRDF models. Two points located forest in Korea peninsular and bare land in Gobi desert were selected for comparison. As results of time series analysis, both models showed similar reflectance change pattern and reasonable values. Whereas in case of empirical coefficients comparison, different changes pattern of values were showed in isotropic coefficients.

• 농촌계획
• /
• 제21권1호
• /
• pp.1-8
• /
• 2015

Population growth and increasing consumption of resources in the process of the industrial development has caused environmental pollution, climate change, and resource exhaustion. Therefore 'sustainable development' has become the important issue for the future. The sustainable development aims at effective resource use, less environmental impacts, and higher social security. Generally the rural area including agricultural fields and forest has various and plentiful natural resources which could make future development sustainable. To develop potential rural resources, the values for energy, environment and economy should be assessed considering the life-cycle of resources. The purposes of this study are to suggest the E3 (Energy, Environment, and Economy) assessment model for rural biomass considering life-cycle of resource and to apply the model to rice, the major agricultural product. As the results of this study, it turned out through E3 assessment that economic gain of rice cultivation is 578,374 won/10a, carbon absorption is $1,530kgCO_2/10a$, carbon emission is $926.65kgCO_2/10a$, and bio-energy potential of by-product is 394,028 kcal/10a. When E3 assessment was applied to by province, the results varied by regions because of the amount of input during cultivation. These results would be useful to realize the rural biomass and design regional resources plan in integrated E3 perspective.

• 한국지리정보학회지
• /
• 제11권2호
• /
• pp.61-72
• /
• 2008

엽면적 지수(LAI)는 지표 환경에 영향을 미치는 광합성, 증발, 그리고 에너지 균형과 같은 생물물리학적 변화 과정에 있어 매우 중요한 인자이며, 여러 가지 생태학적 모델의 입력 자료로서도 필수적이다. 이러한 중요성에 근거하여 더욱 정확하고 유용한 LAI 추정 기법의 개발이 요구되지만, 현실적으로 LAI는 광역적 실측이 어렵기 때문에 대부분 LAI 연구에서는 정규화식생지수(NDVI)와의 단순 관계식을 통해 추정되어져 왔다. 본 연구에서는 경안천 유역(561.12 $Km^2$)을 대상으로 MODIS LAI Product의 활용성을 평가하고자 NOAA AVHRR NDVI와의 관계식으로 추정된 LAI와 국립산림과학원의 실측 LAI (2003, 2004)를 MODIS LAI와 비교 분석하였다. 그 결과 MODIS LAI는 활엽수림에서는 실측치보다 약 14% 높게, NOAA LAI보다 약 15~30% 높게 추정되었다. 침엽수림에서는 2003년 실측치가 약 5% 높게 추정되었으며, NOAA는 4월을 제외하고 약 7%의 차이를 보였다. 이러한 결과는 일부 지점에서 이루어지는 실측과 MODIS LAI 추출 시 기준자료가 포함하는 공간해상도의 한계 및 토지피복분류의 부정확성 등으로부터 발생한다. 따라서 실측자료에 근거한 MODIS자료의 보정기술을 향상시킴으로써 향후 광역적인 식생정보 제공 및 물수지 모의를 위한 생태학 및 수문학적 모형의 입력자료 등으로의 활용범위가 더욱 확대 가능할 것이다.

• 펄프종이기술
• /
• 제30권2호
• /
• pp.13-23
• /
• 1998

Two major cellulase components purified with sephadex G-75 and DEAE sepharose were applied to bleached kraft pulp to inverstigate the change of fiber properties. Cellulose viscosity was very sensitive to $C_x$ component treatment (more than 15% drop was observed) while being little influenced by $C_1$, component (only 2% drop). Fiber fraction longer than 2mm was reduced by $C_x$ treatment while short fiber fraction was increased greatly by more than 15%. There was little change in fiber length distribution by combined treatment of $C_1$ 1 and $C_x$ at equal. In this case, fine contents increased by more than 2.5% at equivalent refining time. WRV and Density were increased as the amount of $C_1$ or $C_x$ treatment was increased. $C_{x}$ was main cause for increasing them. But the effect fell as enzyme dosage.

• 한국균학회지
• /
• 제31권2호
• /
• pp.89-93
• /
• 2003

송이균사의 대량배양에 적합한 공기부양식 생물반응기 형태를 찾고자 풍선형 및 칼럼형의 공기부양식 생물반응기와 external-loop형의 기포통기식 생물반응기에서 송이균사체를 심부배양하여, 반응기 형태별 송이균사체의 생장특성을 비교하였고, 반응기 형태가 세포에 주는 스트레스 정도를 비교하기 위하여 배양기 형태별 균사체의 에르고스테롤의 함량 변화를 비교하였다. 반응기 형태별 송이 균사체의 생산량은 풍선형 생물반응기에서 평균 12g, external-loop형의 기포통기식 생물반응기에서 평균 11.4g, 칼럼형 생물반응기는 평균 9.5g을 생산하여, 풍선형 생물반응기가 가장 우수하였다. 생장기간도 풍선형 생물반응기에서 균사 접종 후 16일 이후부터 정체기에 이르는 것으로 20일 이후에 나타난 칼럼형 및 기포통기형 생물반응기 보다 빠르게 생장하는 것으로 나타났다. 균사체의 생장시기별 에르고스테롤의 함량은 풍선형 공기부양식 생물반응기에서 가장 높이 나타났으며 이어서 칼럼형, 기포통기식 순으로 나타나, 송이 균사체 배양시 반응기 형태에 의한 물리적 스트레스는 풍선형 공기부양식 생물반응기가 가장 적게 받는 것으로 추정되었다. 송이 균사체 배양에 가장 적합한 공기부양식 생물반응기의 형태는 풍선형인 것으로 추정 할 수 있었다. 그러나 칼럼형 및 풍선형 공기부양식 생물반응기는 스파자 부근에서 균사체가 침적, 착생하여 점차 크게 뭉쳐 성장하면서 공기공급을 차단하는 현상이 있었으나 external-loop형의 기포통기식 생물반응기에서는 유체의 순환으로 이러한 현상은 적게 나타나 대용량의 송이 균사체 배양에 적합한 반응기 형태로는 배양기의 상부가 풍선형 반응기의 형태를 유지하고, 스파자가 위치한 하부는 external-loop형의 기포통기식 생물반응기의 유체 순환식 형태를 유지하도록하는 혼합형의 형태가 좋을 것으로 추정되었다.