• Korean Journal of Construction Engineering and Management
• /
• v.16 no.4
• /
• pp.50-59
• /
• 2015

While the international construction industry for Korean companies have grown in market size exponentially in the recent years, the profit rate of small and medium sized construction companies (SMCCs) are incomparably lower than those of large construction companies. Furthermore, small and medium size companies, especially subcontractor, lacks the judgement of project involvement appropriateness, which leads to an unpredictable profit rate. Therefore, this research aims to create a profit rate prediction model for the international construction project focusing on SMCCs. First, the factors that influence the profit rate and the area of profit zone are defined by using a total of 8,637 projects since the year 1965. Seconds, an extensive literature review is conducted to derive 10 influencing factors. Multiple regression analysis and corresponding judgement technique are used to derive the weight of each factor. Third, cased based reasoning (CBR) methodology is applied to develop the model for profit rate analysis in the project participation review stage. Using 120 validation data set, the developed model showed 11% (14 data sets) of error rate for type 1 and type 2 error. In utilizing the result, project decision makers are able to make decision based on authentic results instead of intuitive based decisions. The model additionally give guidance to the Korean subcontractors when advancing into the international construction based on the model result that shows the profit distribution and checks in advance for the quality of the project to secure a sound profit in each project.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.43-58
• /
• 2014

As the use of trading systems has increased rapidly, many researchers have become interested in developing effective stock market prediction models using artificial intelligence techniques. Stock market prediction involves multifaceted interactions between market-controlling factors and unknown random processes. A successful stock prediction model achieves the most accurate result from minimum input data with the least complex model. In this research, we develop a combination model of ${\pi}$-fuzzy logic and support vector machine (SVM) models, using a genetic algorithm to optimize the parameters of the SVM and ${\pi}$-fuzzy functions, as well as feature subset selection to improve the performance of stock market prediction. To evaluate the performance of our proposed model, we compare the performance of our model to other comparative models, including the logistic regression, multiple discriminant analysis, classification and regression tree, artificial neural network, SVM, and fuzzy SVM models, with the same data. The results show that our model outperforms all other comparative models in prediction accuracy as well as return on investment.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.16 no.1
• /
• pp.11-20
• /
• 2010

Oyster production is playing an important role in domestic aquaculture, but facing some problems such as exports decrease, a slowdown in domestic demand and marine environmental deterioration. In order to obtain the suitable and sustainable oyster production, suitable sites selection is an important step in oyster aquaculture. This study was conducted to identify the suitable sites for lunging culture of oyster using Geographic Information System(GIS)-based multi-criteria evaluation methods. Most of the parameters were extracted by Inverse Distance Weighted(IDW) methods in GIS and eight parameters were grouped into two basic sub-models for oyster aquaculture, namely oyster growth sub-model(Sea Temperature, Salinity, Hydrodynamics, Chlorophyll-a) and environment sub-model(Bottom DO, TOC, Sediment AVS, Benthic Diversity). Suitability scores were ranked on a scale from 1(leased suitable) and 8(most suitable), and about 80.1% of the total potential area had the highest scores 5 and 6. These areas were shown to have the optimum condition for oyster culture in GeojeHansan Bay. This method to identify suitable sites for oyster culture may be used to develop bivalve culture management system for supporting a decision making.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.2
• /
• pp.765-774
• /
• 2011

The purpose of this study is to provide informative statistics which can be used for effective Diabetes Management Programs. We collected and analyzed the data of 666 diabetic people who had participated in Korean National Health and Nutrition Examination Survey in 2007 and 2008. Group classification on management behavior of Diabetic Mellitus is based on the K-means clustering method. The Decision Tree method and Multiple Regression Analysis were used to study factors of the management behavior of Diabetic Mellitus. Diabetic people were largely classified into three categories: Health Behavior Program Group, Focused Management Program Group, and Complication Test Program Group. First, Health Behavior Program Group means that even though drug therapy and complication test are being well performed, people should still need to improve their health behavior such as exercising regularly and avoid drinking and smoking. Second, Focused Management Program Group means that they show an uncooperative attitude about treatment and complication test and also take a passive action to improve their health behavior. Third, Complication Test Program Group means that they take a positive attitude about treatment and improving their health behavior but they pay no attention to complication test to detect acute and chronic disease early. The main factor for group classification was to prove whether they have hyperlipidemia or not. This varied widely with an individual's gender, income, age, occupation, and self rated health. To improve the rate of diabetic management, specialized diabetic management programs should be applied depending on each group's character.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.2
• /
• pp.108-117
• /
• 2011

In drafting the standards on changes in current conditions, the height or the number of stories is applied in a restrictive manner by limiting to securing the distance to vertical surface for cultural properties within the influence investigation area, but this is expected to have a negative impact on the surrounding sceneries as well as results in the dwarfing phenomenon for precious cultural properties. That is, the preparation for supplementing the insufficient objectivity that is likely to take place during the process of drafting the standards on changes in current conditions. Thus the author attempts to suggest the analytic method for the decision making related to objective and reasonable determination and regulation of the changes in current conditions through computer based simulation work that considers the cultural properties and surrounding environments under investigation. In order to achieve such research objectives, the author reviewed the subject sites where the cultural property dwarfing phenomenon was expected to occur in case of the permission for the changes in current conditions or where the impact of natural landscape and natural feature on the earth is less than architectural building or artificial structure or where the new policy program is likely to be adopted due to incomplete establishment of current condition change standard within influence investigation area, among other cultural properties with architectural building or artificial structure nearby located in Cheonan city and then selected Cheonansaji Dangganjiju(flag poles) and Jiksanhyun Gwana(government office). The author then undertook the quantitative visibility analysis in order to determine the comprehensive prospect rights for the cultural properties and surrounding environments concerned.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.603-612
• /
• 2022

The study aims were to evaluate a machine-learning, algorithm-based, forest biomass-estimation model to estimate subnational forest biomass and to comparatively analyze REDD+ forest reference emission levels. Time-series Landsat satellite imagery and ESA Biomass Climate Change Initiative information were used to build a machine-learning-based biomass estimation model. The k-nearest neighbors algorithm (kNN), which is a non-parametric learning model, and the tree-based random forest (RF) model were applied to the machine-learning algorithm, and the estimated biomasses were compared with the forest reference emission levels (FREL) data, which was provided by the Paraguayan government. The root mean square error (RMSE), which was the optimum parameter of the kNN model, was 35.9, and the RMSE of the RF model was lower at 34.41, showing that the RF model was superior. As a result of separately using the FREL, kNN, and RF methods to set the reference emission levels, the gradient was set to approximately -33,000 tons, -253,000 tons, and -92,000 tons, respectively. These results showed that the machine learning-based estimation model was more suitable than the existing methods for setting reference emission levels.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.16 no.4
• /
• pp.153-165
• /
• 2021

With the disappearance of boundaries between online and offline, the O2O(online to offline) platform service is rapidly growing. Unlike general products, freshness is an important decision-making factor for agri-food, and there are many limiting factors for growth as an open market among O2O platforms due to the characteristics of difficult refunds and exchanges compared to other items and new transaction methods. In order to overcome these obstacles, consumer innovation must be considered. The purpose of this study was to investigate the influence of O2O(online to offline) platform characteristics perception on agri-food repurchase intentions. And an empirical survey of the hypothesis is made that innovation will show a moderating effect between agri-food O2O platform characteristics and repurchase intention. And an empirical survey of the hypothesis is made that innovation will show a moderating effect between agri-food O2O platform characteristics and repurchase intention. For this purpose, Using a convenience sampling technique, an online survey was conducted through Google survey from April 1 to April 15, 2021. A total of final analysis data were collected from a total of 270 purchase experienced of agri-food O2O(online to offline) platform. The SPSS program was used for analysis, and multiple regression analysis was used for hypothesis verification. The results showed that Economic, Interaction, and Playfulness had a significant positive effect on agri-food repurchase intend. Also, Interactivity × innovation, playfulness × innovation were found to have a significant positive (+) effect on repurchase intention. The results of this study show that innovation reduces the burden on consumers for new systems and mobile transactions. The results of this study suggest that convenient interface design is important for activating O2O transactions of agri-food. In addition, education and support are needed to strengthen the IT competency of farmers. The results of this study will be able to contribute to the establishment of infrastructure for agri-food open market shopping malls. In future studies, the influence of the O2O platform type on the purchase intention should be studied continuously.