• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2019.08a
• /
• pp.316-317
• /
• 2019

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2018.06a
• /
• pp.3-20
• /
• 2018

• Korean System Dynamics Review
• /
• v.15 no.3
• /
• pp.5-36
• /
• 2014

The purpose of this paper is to develop a System Dynamics model for estimating the volume of forest resources in the future and simulating the volume of function of public benefit linked to forest resources in dynamic manner. Also it is to analyze the impact when the volume of forest land conversion is controlled by policy using the SD model. The analysis was done at nation-wide for the simulation period 2000 to 2040. Estimated forest area was 6.2 million ha and estimated growing stock was $4.7\;billion\;m^3$ in 2040 from the future forecast without policies. Changing of forest resources, 13.9 billion tons of forest-ground-water storage was estimated, $1.8\;million\;m^3$ of erosion control of forest was estimated and 377 million tons of $CO_2$ absorption was estimated. As a result of simulation with two alternatives, forest area was less reduced and growing stock was bigger than do nothing policy. Also, function of public benefit reflected by changes of forest resources was enhanced. This study contributes to estimate the quantitatively measured volume of forest resources and function of public benefit over the 30 years in Korean forest land in scientific way. Using this SD model, decision maker would develop forest land policies more delicately for deserving forest resources and increasing the volume of function of public.

• Journal of Korean Society of Forest Science
• /
• v.97 no.6
• /
• pp.669-679
• /
• 2008

Jirisan National Park was designated on December 29, 1967 as the first national park in Korea and that caused continuous conflicts between the violation of the right to hold property in this area due to several regulations following the designation and the nature preservation for the value of heritage for descendants. Thus, the objective of this study is to find a proposal for making decision based on the rationality that is able to solve these conflicts. To achieve the objective of this study, this study applies a game theory that supports a reasonable decision making process for solving these conflicts between interest groups around Jirisan National Park in which the component of this game consists of Jirisan National Park, residents, and interest groups. The Nash equilibrium obtained by the analysis of the strategy of interest groups for the use and preservation of forests and its rewards from the strategy as an nonecooperative game showed a behavior that chases their own benefits and causes lots of troubles. However, in the case of the results obtained from a cooperative game based on the strategy that includes some public interests accepted by interest groups and its rewards, it represented an aspect that solves conflicts through achieving a strategical set, which shows a win-win outcome even though the results of this cooperative game may present less rewards than that of the Nash equilibrium. Whereas, if there exists the public interests accepted by interest groups and truth for protecting such public interests, it is considered that it becomes a way that solves present structural troubles in the National Parks in Korea due to the fact that there exist uncertainties caused by the human rationality.

• Journal of Korean Society of Forest Science
• /
• v.95 no.5
• /
• pp.569-579
• /
• 2006

This study focuses on the application of multi-criteria performance measures based on the concept of equifinality to the calibration of the rainfall-runoff model TOPMODEL in a small deciduous forest catchment. The performance of each parameter set was evaluated by six performance measures, individually, and each set was identified as a behavioral or non-behavioral parameter set by a given behavioral acceptance threshold. Many behavioral parameter sets were scattered throughout the parameter space, and the range of model behavior and the sensitivity for each parameter varied considerably between the different performance measures. Sensitivity was very high in some parameters, and varied depending on the kind of performance measure as well. Compatibilities of behavioral parameter sets between different performance measures also varied, and very few parameter sets were selected to be used in making god predictions for all performance measures. Since different behavioral parameter sets with different likelihood weights were obtained for each performance measure, the decision on which performance measure to be used may be very important to achieve the goal of study. Therefore, one or more suitable performance measures should be selected depending on the environment and the goal of a study, and this may lead to decrease model uncertainty.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.4
• /
• pp.1-11
• /
• 2006

This paper aims to develop a GIS(Geographic Information System) application model as a decision-making support system in order to evaluate the potential of forests according to their functions, or to classify forest functions. The forest functions analyzed in this study are as follows: production of timber, stable supply of water resources, forest hazards prevention, recreation in forests, conservation of living conditions and natural environment. Using a model possible to evaluate the potential of each forest function and to assort forest functions by making priority-based decisions according to the functions, as well as allowing for various possible analysis environments, its application has been reviewed. Factors for assessing the forest functions could be built by using the following three categories: four maps-topographical map, vegetation map, forest site map and basic forest land use map-whose quantitative drawings had already been made; other self-established maps, such as one indicating the location of sawmills, location map of expressway interchanges, and spatial data of national population distribution map; and attribute data of population and precipitation. The GIS application developed here contributes to the evaluation of forest functions in all the subject areas by map units and national forest management districts based upon the assessment system.

• Journal of Forest and Environmental Science
• /
• v.34 no.6
• /
• pp.461-471
• /
• 2018

In this study, the deforestation and forest degradation areas have been obtained in Myanmar using a land cover lamp (LCM) and a tree cover map (TCM) to get the $CO_2$ potential reduction and the strength of occurrence was evaluated by using the geostatistical technique. By applying a multiple criteria decision-making method to the regions having high strength of occurrence for the $CO_2$ potential reduction for the deforestation and forest degradation areas, the priority was selected for candidate lands for REDD+ project. The areas of deforestation and forest degradation were 609,690ha and 43,515ha each from 2010 to 2015. By township, Mong Kung had the highest among the area of deforestation with 3,069ha while Thlangtlang had the highest in the area of forest degradation with 9,213 ha. The number of $CO_2$ potential reduction hotspot areas among the deforestation areas was 15, taking up the $CO_2$ potential reduction of 192,000 ton in average, which is 6 times higher than that of all target areas. Especially, the township of Hsipaw inside the Shan region had a $CO_2$ potential reduction of about 772,000 tons, the largest reduction potential among the hotpot areas. There were many $CO_2$ potential reduction hot spot areas among the forest degradation area in the eastern part of the target region and has the $CO_2$ potential reduction of 1,164,000 tons, which was 27 times higher than that of the total area. AHP importance analysis showed that the topographic characteristic was 0.41 (0.40 for height from surface, 0.29 for the slope and 0.31 for the distance from water area) while the geographical characteristic was 0.59 (0.56 for the distance from road, 0.56 for the distance from settlement area and 0.19 for the distance from Capital). Yawunghwe, Kalaw, and Hsi Hseng were selected as the preferred locations for the REDD+ candidate region for the deforestation area while Einme, Tiddim, and Falam were selected as the preferred locations for the forest degradation area.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• Journal of radiological science and technology
• /
• v.46 no.2
• /
• pp.131-139
• /
• 2023

High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R² to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R² 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R² 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R² 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R² 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.445-452
• /
• 2022

Class distribution of unbalanced data is an important part of the digital world and is a significant part of cybersecurity. Abnormal activity of unbalanced data should be found and problems solved. Although a system capable of tracking patterns in all transactions is needed, machine learning with disproportionate data, which typically has abnormal patterns, can ignore and degrade performance for minority layers, and predictive models can be inaccurately biased. In this paper, we predict target variables and improve accuracy by combining estimates using Synthetic Minority Oversampling Technique (SMOTE) and Light GBM algorithms as an approach to address unbalanced datasets. Experimental results were compared with logistic regression, decision tree, KNN, Random Forest, and XGBoost algorithms. The performance was similar in accuracy and reproduction rate, but in precision, two algorithms performed at Random Forest 80.76% and Light GBM 97.16%, and in F1-score, Random Forest 84.67% and Light GBM 91.96%. As a result of this experiment, it was confirmed that Light GBM's performance was similar without deviation or improved by up to 16% compared to five algorithms.