• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.391-404
• /
• 2021

This study developed a long-term prediction model for the potential yield of garlic based on a genetic algorithm (GA) by utilizing global climate reanalysis data. The GA is used for digging the inherent signals from global climate reanalysis data which are both directly and indirectly connected with the garlic yield potential. Our results indicate that both deterministic and probabilistic forecasts reasonably capture the inter-annual variability of crop yields with temporal correlation coefficients significant at 99% confidence level and superior categorical forecast skill with a hit rate of 93.3% for 2 × 2 and 73.3% for 3 × 3 contingency tables. Furthermore, the GA method, which considers linear and non-linear relationships between predictors and predictands, shows superiority of forecast skill in terms of both stability and skill scores compared with linear method. Since our result can predict the potential yield before the start of farming, it is expected to help establish a long-term plan to stabilize the demand and price of agricultural products and prepare countermeasures for possible problems in advance.

• Proceedings of the Technology Innovation Conference
• /
• 2003.02a
• /
• pp.173-190
• /
• 2003

Demand forecasting is essential in establishing national and corporate strategy as well as the management of their resource. We forecast demand for multi-generation product using discrete choice model combining diffusion model The discrete choice model generally captures consumers'valuation of the product's qualify in the framework of a cross-sectional analysis. We incorporate diffusion effects into a discrete choice model in order to capture the dynamics of demand for multi-generation products. As an empirical application, we forecast demand for worldwide DRAM (dynamic random access memory) and each of its generations from 1999 to 2005. In so doing, we use the method of 'Technological Forecasting'for DRAM Density and Price of the generations based on the Moore's law and learning by doing, respectively. Since we perform our analysis at the market level, we adopt the inversion routine in using the discrete choice model and find that our model performs well in explaining the current market situation, and also in forecasting new product diffusion in multi-generation product markets.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.1
• /
• pp.87-94
• /
• 2012

The apartment reconstruction projects have the proper functions such as residential environment improvement and the new housing allocation system; however, intention of the projects are distorted by the combination of factors, like failure of relocation of the original occupants and income redistribution, speculation in real estate, sharp rise in housing price, disputation between various interested parties, inadequate system and etc and it makes the projects unable to go well. Disputations and litigations are due to spread of the small conflict. As a result of the problems, it could not going smoothly and that lead to increase or stop the period and cost. This study is to estimate the period and cost using the conflict index so as to prevent and solve the problem which is among the conflict in the reverse functions. The conflict index has estimated focus on the conflict impact and the period and cost has been estimated using an variable independent including the conflict index. Also, estimated the conflict index and estimate of the period and cost are able to succeed with a minimum of disputation and money.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.227-239
• /
• 2020

This paper introduces a method for predicting the maximum power demand despite communication errors in industrial sites. Due to the recent policy of de-nuclearization in Korea, the price of electricity is inevitable, and the amount of electricity used and maximum load management for the management of power demand are becoming important issues. Accordingly, it is important to predict and manage peak power. However, problems such as loss and modulation of measured power data occur at industrial sites due to noise generated by various facilities and sensors. It is difficult to predict the exact value when measured effective power data are lost. The study presents a model for predicting and correcting anomalies and missing values when measured effective power data are lost. The models used in this study are expected to be useful in predicting peak power demand in the event of communication errors at industrial sites.

• The Korean Journal of Financial Management
• /
• v.16 no.2
• /
• pp.285-308
• /
• 1999

증권의 가격형성에 유리한 뉴스와 불리한 뉴스가 도착할 때 이 뉴스가 주가의 변동성에 미치는 영향의 정도는 차이가 있다. 불리한 뉴스가 변동성에 미치는 영향도가 유리한 뉴스가 변동성에 미치는 영향도보다 크다. 따라서 불리한 뉴스가 발생할 때 형성되는 변동성의 양이 유리한 뉴스의 도착시보다 크다. 그리고 충격의 크기에 따라 이 충격이 야기하는 변동성의 양의 크기에도 차이가 존재한다. 일반 자기회귀 조건부 이분산 과정은 유리한 뉴스와 불리한 뉴스를 대칭적으로 반영하고 있다. 이 뉴스들을 비대칭적으로 포착하는 자기회귀 조건부 이분산 과정의 모형들을 실증적으로 분석하였다. 뉴스의 비대칭성과 규모를 적절히 포착하고 있는 모형들이 비선형 일반 자기회귀 조건부 이분산 과정, 지수 일반 자기회귀 조건부 이분산 과정과 정보 포착 자기회귀 조건부 이분간 과정임이 발견되었다. 이 중 비선형 일반 자기회귀 조건부 이분산 과정이 가장 좋은 모형으로 보인다. 비선형 일반 자기회귀 조건부 이분산 과정의 경우 예측오차의 승멱(power)이 약 1.5이다. 따라서 일반 자기회귀 조건부 이분산 과정의 예측오차의 승멱인 2에 비하여 작다. 이 사실은 일반 자기회귀 조건부 이분산의 예측오차의 승멱이 과도하게 측정되고 없음을 알 수 있다. 뉴스의 비대칭성과 규모를 반영하고 있는 모형들은 한결같이 예측오차의 크기에 적절한 가중치를 부여하여 예측오차의 크기를 조정하고 있다. 이 모형의 성질과 실증분석의 결과에 의하여 예측오차의 승멱은 2 이하로 수정하여 사용해야 한다는 점이 시사되고 있다. 음의 충격이 양의 충격보다 주가의 변동성을 크게 하고 없음이 발견되었다. 주가형성에 유리한 뉴스와 불리한 뉴스가 주가의 변동성에 미치는 영향의 차이와 충격의 중대성을 양으로 표시하는 규모의 차이를 반영해주는 변수들의 추정된 계수가 미국과 일본보다 절대값에 있어서 상당히 작다. 이 현상은 뉴스의 비대칭성과 규모보다는 발생하는 충격, 즉 뉴스 자체에 보다 민감하게 반응하고 있음을 보여주고 있다. 물론 투자자들이 뉴스의 비대칭성과 규모를 완전히 무시하고 투자활동을 전개하고 있다는 것을 의미하는 것은 아니다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.3
• /
• pp.233-241
• /
• 2021

As increasing the feasibility of the eVTOL UAM(electric vertical take-off and landing urban air mobility), numerous corporations and laboratories are conducting researches. In the aircraft development process, estimating the cost of the aircraft is essential part in terms of budgeting and commercial viability analysis. However, it is difficult to predict the cost of an eVTOL UAM owing to various configurations and little open cost information. This paper presents a novel method to predict the vehicle cost of various eVTOL configurations by modifying previous studies of the aircraft cost estimation. A vehicle cost of Wisk Cora is calculated by the presented method as an example to illuminate the method. The method is indirectly validated by comparing the vehicle costs of six representative eVTOL aircraft with those from the UAM study reports.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.23-30
• /
• 2022

Deep learning analyzes data to discover a series of rules and anticipates the future, helping us in various ways in our lives. For example, prediction of stock prices and agricultural prices. In this research, the results of solar photovoltaic power generation accompanied by weather are analyzed through deep learning in situations where the importance of solar energy use increases, and the amount of power generation is predicted. In this research, we propose a model using LSTM(Long Short Term Memory network) that stand out in time series data prediction. And we compare LSTM's performance with CNN(Convolutional Neural Network), which is used to analyze various dimensions of data, including images, and CNN-LSTM, which combines the two models. The performance of the three models was compared by calculating the MSE, RMSE, R-Squared with the actual value of the solar photovoltaic power generation performance and the predicted value. As a result, it was found that the performance of the LSTM model was the best. Therefor, this research proposes predicting solar photovoltaic power generation using LSTM.

• Korea Trade Review
• /
• v.48 no.2
• /
• pp.27-43
• /
• 2023

The maritime industry is playing an increasingly vital part in global economic expansion. Specifically, the Baltic Dry Index is highly correlated with global commodity prices. Hence, the importance of BDI prediction research increases. But, since the global situation has become more volatile, it has become methodologically more difficult to predict the BDI accurately. This paper proposes an integrated machine-learning strategy for accurately forecasting BDI trends. This study combines the benefits of a convolutional neural network (CNN) and long short-term memory neural network (LSTM) for research on prediction. We collected daily BDI data for over 27 years for model fitting. The research findings indicate that CNN successfully extracts BDI data features. On this basis, LSTM predicts BDI accurately. Model R2 attains 94.7 percent. Our research offers a novel, machine-learning-integrated approach to the field of shipping economic indicators research. In addition, this study provides a foundation for risk management decision-making in the fields of shipping institutions and financial investment.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.16 no.4
• /
• pp.309-315
• /
• 2014

Summer cabbages in an alpine area are very sensitive to the fluctuations in supply and demand. Yield variability due to weather conditions dictates the market fluctuations of cabbage price. This study reports an empirical relationship based on weather conditions to estimate the growth and harvestable biomass of cabbages, factors that are critical for supply of summer cabbages. Based on experimental results testing sowing date effects over the two years from 1997 to 1998, a logistic equation was parameterized to predict leaf area expansion of summer cabbages. This logistic model for leaf area expansion was then combined with an empirical allometric relationship to predict total biomass. The final equation for estimating fresh weight accumulation of Chinese cabbage is given by: $$Fresh\;weight=3500/(1+{\exp}(5.175-1.153{\times}(6/(1+{\exp}(6.367-0.0064{\times}PHU)))))$$ Where PHU is potential heat units ($^{\circ}C$). The model performance was tested using weather data from 2003 to 2006 to predict fresh harvestable biomass. Overall the model performance was satisfactory with the correlation efficient ranging between 0.89 and 0.94 for each year.

• The Journal of Society for e-Business Studies
• /
• v.9 no.4
• /
• pp.103-116
• /
• 2004

It is needed to transfer the technology actively which has already developed to improve a up-to-date technology and foster the technological innovation. The technology transfer also can bring about a commercial success. To promote the technology transfer, it is needed to develop a new technology valuation model for a specific technology from a objective point of view, as well as to equip an institution such as the technology transfer center. The technology valuation from a objective point of view is of importance as the basic information for the price negotiation between a technology-buyer and a technology-seller. This paper takes aim at investigating a new technology valuation model and developing a technology valuation system for promoting the technology transfer. A new technology valuation system is developed as a web-enabling base. Using this users are able to estimate the value of specific technology on a real time efficiently.