• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2018

The study is based on machine learning techniques to increase the accuracy of the forest fire predictive model. It used 14 years of data from 2003 to 2016 in Gang-won-do where forest fire were the most frequent. To reduce weather data errors, Gang-won-do was divided into nine areas and weather data from each region was used. However, dividing the forest fire forecast model into nine zones would make a large difference between the date of occurrence and the date of not occurring. Imbalance issues can degrade model performance. To address this, several sampling methods were applied. To increase the accuracy of the model, five indices in the Canadian Frost Fire Weather Index (FWI) were used as derived variable. The modeling method used statistical methods for logistic regression and machine learning methods for random forest and xgboost. The selection criteria for each zone's final model were set in consideration of accuracy, sensitivity and specificity, and the prediction of the nine zones resulted in 80 of the 104 fires that occurred, and 7426 of the 9758 non-fires. Overall accuracy was 76.1%.

• Korean Journal of Breeding Science
• /
• v.50 no.4
• /
• pp.529-533
• /
• 2018

Hyowon6, a mid-late maturing, good eating quality rice variety with multi-resistance, was developed by the rice breeding team of Pusan National University in 2013. This variety was derived from a cross between Hwayeong (as a multi-resistant parent) and Koshihikari (as a good eating quality parent). Selection by the pedigree breeding method was carried out until the $F_8$ generation. A promising line, JS14-12-36-8-5-3-1-1-1, was developed and designated as HY103 in 2013. This variety headed on August 22, which was 11 days later than that of Hwayeong. The culm length and panicle length of Hyowon6 was 85.7 cm and 21.1 cm, respectively. The number of panicles per hill was 14.5 and the number of grains per panicle was 101.7. The ratio of ripened grain was approximately 92% and the 1,000-grain weight was approximately 21.36 g for brown rice, which were similar to those of Hwayeong. Hyowon6 was moderately resistant to lodging and also to neck blast, leaf blight, and stripe virus. The glossiness value of Hyowon6 was 83, which was considerably higher than that of Hwayeong.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.206-217
• /
• 2021

Purpose: Recently, a series of large social disasters have led to a lot of research to prevent social disasters as well as natural disasters and reduce damage. However, this paper aims to select the types of social disasters that local governments should focus on and create basic data for effective countermeasures and mitigation efforts. Method: Among 43 types of disasters announced by the Ministry of Public Administration and Security, 11 types of disasters were selected and collected to select the main types of disasters, and risk types were derived by region with risk maps. In order to derive the risk map, each detailed index was rescheduled to be 0-1 and weights were determined through entropy technique. Result: As a result, about 41% of the major disasters announced by the Ministry of Public Administration and Security were consistent, and the rest of the major types were disasters that could not be obtained or have not occurred in the past 20 years. Conclusion: Therefore, in order to establish an effective prevention and recovery plan for social disasters through this study, it was intended to present social disaster-focused disasters for each local government.

• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.355-363
• /
• 2021

The purpose of this research is to explore the selection attributes that the director of a taekwondo gym places importance on when purchasing a work of taekwon gymnastics for the competition. We conducted in-depth interviews with 6 participants using qualitative case study techniques, and analyzed data using Creswell's (2015) spiral analysis method. The data analysis results show music, trainees, characteristics of the work, criteria for evaluating the competition, producer competence, and price factors. As a result of the research, music should be produced around diverse and differentiated genres and music preferred by the trainees, and the appropriate theme should be selected considering the expressiveness and level of the trainees. The work should be considered creative works that harmonize the movement ratio of Taekwondo movements and dance, and the length of the work should be adjusted according to the purpose of the buyer, and the construction of the work should be based on the regulations of the competition. The manufacturer should ensure smooth communication with the buyer, including coaching ability and experience at the convention site. Prices will be affordable and affordable, and prices will need to be calculated based on special prices or mentoring periods for a small number of buyers.

• Journal of Bio-Environment Control
• /
• v.28 no.4
• /
• pp.311-321
• /
• 2019

Greenhouse farmers often use thermal screens to reduce greenhouse heating expenses during the winter, and for shade during hot, sunny days in the summer, as it is an inexpensive solution to temperature control relative to other available options. However, accurate measurements of their emitted and absorbed radiations are important for the selection of suitable screens that offer maximum performance. Material's ability to save energy is highly dependent on these properties. Limited studies have investigated the measurement of these properties under natural conditions, but they are only applicable to materials having partial porosities. In this work, we describe a new radiation balance method for determining emissive power and absorptive capacity, as well as reflectivity, transmissivity and emissivity of materials having complete and partial transparency by using pyrgeometer and net radiometer. In this study, four materials with zero porosity, were tested. The emissivity value of PE, LD-13, LD-15 and PH-20 was $0.439{\pm}0.020$, $0.460{\pm}0.010$, $0.454{\pm}0.004$, and $0.499{\pm}0.006$, respectively. All tested samples showed high emitted radiation as compared to absorbed radiation.

• Journal of the Korean Society for information Management
• /
• v.37 no.4
• /
• pp.1-26
• /
• 2020

In today's increasingly data-intensive academic environment, data is becoming the foundation of academic communication as a research outcome rather than a research by-product. However, there is a limit to guaranteeing actual data reuse only by expanding the data supply or securing accessibility. In order to overcome this, it is necessary to understand the data reuse behavior and data needs in-depth. Therefore, this study attempted to identify the major data reuse behavior and data needs among researchers. To this end, the authors of KCI papers among the data reuse documents of the Korea Social Science Data Archive (KOSSDA) for the past 3 years were targeted. An in-depth interview was conducted with 12 researchers who accepted the interview. As a result, factors considered when reusing data were personal, economic, technical, and social aspects, and it was found that the data itself was used or contextual information of the data was used depending on the purpose of data reuse. The path to acquiring data is a web-based source of information, and a path through informal communication can also be found. In terms of the data needs, it was found that they prefer English, the United States, and institutional producers. Also they have a clear preference for quantitative data from an interviewer-filled interpersonal interview survey method, rich metadata along with raw data, and data that contains identification information. However, due to the lack of confidence in the value, it is negative for the use of data with controlled access and use, and it is difficult to confirm a clear preference because there is no similar data available for selection in terms of size and freshness.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.560-567
• /
• 2021

The purpose of this study is to examine the concepts of cultural administration and art management, their context, and elements that each concept pursues, and to establish the domains and systems of cultural administration and art management in Jeju. Seven values were selected through the consideration of commonalities and differences and previous studies, and sub-indicators of each value were determined. Factors were analyzed using the AHP method. Cultural administration is based on the areas of publicity, equity, and transparency, while art management is based on productivity, publicity, and responsiveness. Cultural administration needs to focus on a system for the preservation and utilization of local culture, co-evolution of culture, and expansion of culture and arts education. Art management needs to focus on the level of achievement of goals, the level of output versus input, and the system for preserving and utilizing local culture. In addition, it was found that there is a need to establish a system in Jeju with a common aim of the co-evolution of culture and preservation and the utilization of local culture.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.527-535
• /
• 2021

Traditional business intelligence (BI) systems have been used widely as tools for better decision-making on time. On the other hand, building a data warehouse (DW) for the efficient analysis of rapidly growing data is time-consuming and complex. In particular, the ETL (Extract, Transform, and Load) process required to build a data warehouse has become much more complex as the BI platform moves to a cloud environment. Various BI solutions based on the NoSQL database, such as MongoDB, have been proposed to overcome these ETL issues. Decision-makers want easy access to data without the help of IT departments or BI experts. Recently, self-service BI (SSBI) has emerged as a way to solve these BI issues. This paper proposes a self-service BI system with farming data using the MongoDB cloud as DW to support the selection of new crops by return-farmers. The proposed system includes functions to provide insights to decision-makers, including data visualization using MongoDB charts, reporting for advanced data search, and monitoring for real-time data analysis. Decision makers can access data directly in various ways and can analyze data in a self-service method using the functions of the proposed system.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.4
• /
• pp.78-86
• /
• 2011

The recovering of historical mountain fortress needs the maintenance of forest scape for achieving visibility. In the study, the methods for the maintenance of the forest around the fortress were proposed. The Cumulative Visibility Analysis and Multiple Sight Surface Analysis were tested to verify the methods using GIS on the Myeong-hwal Fortress in Kyungju. The results of the study are as follows. First, the Cumulative Visibility Analysis was made on the Myeong-hwal Fortress from surrounding major viewpoints. The Cumulative Visibility Analysis enables the selection of excellent visibility sectors on the fortress. The 6 excellent visibility sectors were 1,937m(which occupied 41.2% of the area). Second, two cases of pine tree height were compared in the Cumulative Visibility Analysis. One used the average height of pines and the other used the maximum growth height. The comparative result demonstrated that the case of average height would be more effective for deciding the pine removal zone as well as achieving visibility to the mountain fortress. Third, to examine the feasibility of the management method, the tree removal plan and removal execution were compared on the A zone which showed high visibility frequency. Asa comparative result, there was insignificant difference(3.3%) in area between the tree removal plan($10,935m^2$) and removal execution($11,296m^2$). This study proved the Cumulative Visibility Analysis and Multiple Sight Surface Analysis to be effective for forest scape maintenance around a mountain fortress.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.309-327
• /
• 2021

Dynamic treatment regimes (DTRs) are decision-making rules designed to provide personalized treatment to individuals in multi-stage randomized trials. Unlike classical methods, in which all individuals are prescribed the same type of treatment, DTRs prescribe patient-tailored treatments which take into account individual characteristics that may change over time. The Q-learning method, one of regression-based algorithms to figure out optimal treatment rules, becomes more popular as it can be easily implemented. However, the performance of the Q-learning algorithm heavily relies on the correct specification of the Q-function for response, especially in observational studies. In this article, we examine a number of double-robust weighted least-squares estimating methods for Q-learning in high-dimensional settings, where treatment models for propensity score and penalization for sparse estimation are also investigated. We further consider flexible ensemble machine learning methods for the treatment model to achieve double-robustness, so that optimal decision rule can be correctly estimated as long as at least one of the outcome model or treatment model is correct. Extensive simulation studies show that the proposed methods work well with practical sample sizes. The practical utility of the proposed methods is proven with real data example.