• Journal of People, Plants, and Environment
• /
• v.24 no.6
• /
• pp.629-638
• /
• 2021

Background and objective: This study was conducted to develop diameter growth models for thinned Quercus glauca Thunb. (QGT) stands to inform production goals for treatment and provide the information necessary for the systematic management of this stands. Methods: This study was conducted on QGT stands, of which initial thinning was completed in 2013 to develop a treatment system. To analyze the tree growth and trait response for each thinning treatment, forestry surveys were conducted in 2014 and 2021, and a one-way analysis of variance (ANOVA) was executed. In addition, non-linear least squares regression of the PROC NLIN procedure was used to develop an optimal diameter growth model. Results: Based on growth and trait analyses, the height and height-to-diameter (H/D) ratio were not different according to treatment plot (p > .05). For the diameter of basal height (DBH), the heavy thinning (HT) treatment plot was significantly larger than the control plot (p < .05). As a result of the development of diameter growth models by treatment plot, the mean squared error (MSE) of the Gompertz polymorphic equation (control: 2.2381, light thinning: 0.8478, and heavy thinning: 0.8679) was the lowest in all treatment plots, and the Shapiro-Wilk statistic was found to follow a normal distribution (p > .95), so it was selected as an equation fit for the diameter growth model. Conclusion: The findings of this study provide basic data for the systematic management of Quercus glauca Thunb. stands. It is necessary to construct permanent sample plots (PSP) that consider stand status, location conditions, and climatic environments.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.575-580
• /
• 2024

Detecting the status of websites, normal or phishing, is necessary to defend against intelligent phishing attacks. We propose a machine learning-based classification to predict the status of websites. First, we collect information about 'URL', convert it into numerical data, and remove outliers. Second, we apply VIF(Variance Inflation Factors) to understand the correlation and independence between variables. Finally, we develop a phishing website detection model with machine learning-based classifications, which predicts website status. In the test datasets, Random Forest showed the best performance, with precision of 93.74%, recall of 92.26%, and accuracy of 93.14%. In the future, we expect to apply our model to detect various phishing crimes.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.157-163
• /
• 2022

As the online game market grows, the use of game bots is causing the most serious problem for game services. We propose a harvest coordinate analysis model to detect harvesting bots among game bots of the Massively Multiplayer Online Role-Playing Games(MMORPGs) genre. The proposed model analyzes the player's harvesting behavior using the coordinate data. Game bots can obtain in-game goods and items more easily than normal players and are not affected by realistic restrictions such as sleep time and character manipulation fatigue. As a result, there is a difference in harvesting coordinates between normal players and game bots. We divided the coordinate zones and used these coordinate zone differences to distinguish between game bot players and normal players. We created a dataset with NCSoft's AION log and applied it to a random forest model to detect game bots, and as a result, we derived performance with a recall of 0.72 and a precision of 0.92.

• Journal of the Korean Wood Science and Technology
• /
• v.45 no.4
• /
• pp.399-408
• /
• 2017

Research on the rapid and accurate prediction of physical properties of wood using near-infrared (NIR) spectroscopy has attracted recent attention. In this study, partial least squares analysis was performed between NIR spectra and air-dried specific gravity of five domestic conifer species including larch (Larix kaempferi), Korean pine (Pinus koraiensis), red pine (Pinus densiflora), cedar (Cryptomeria japonica), and cypress (Chamaecyparis obtusa). Fifty different lumbers per species were purchased from the five National Forestry Cooperative Federations of Korea. The air-dried specific gravity of 100 knot- and defect-free specimens of each species was determined by NIR spectroscopy in the range of 680-2500 nm. Spectral data preprocessing including standard normal variate, detrend and forward first derivative (gap size = 8, smoothing = 8) were applied to all the NIR spectra of the specimens. Partial least squares analysis including cross-validation (five groups) was performed with the air-dried specific gravity and NIR spectra. When the performance of the regression model was expressed as $R^2$ (coefficient of determination) and root mean square error of calibration (RMSEC), $R^2$ and RMSEC were 0.63 and 0.027 for larch, 0.68 and 0.033 for Korean pine, 0.62 and 0.033 for red pine, 0.76 and 0.022 for cedar, and 0.79 and 0.027 for cypress, respectively. For the calibration model, which contained all species in this study, the $R^2$ was 0.75 and the RMSEC was 0.37.

• Asia pacific journal of information systems
• /
• v.28 no.4
• /
• pp.308-319
• /
• 2018

This paper aims at providing valuable insights on Financial Fraud Detection on a mobile money transactional activity. We have predicted and classified the transaction as normal or fraud with a small sample and massive data set using Azure and Spark ML, which are traditional systems and Big Data respectively. Experimenting with sample dataset in Azure, we found that the Decision Forest model is the most accurate to proceed in terms of the recall value. For the massive data set using Spark ML, it is found that the Random Forest classifier algorithm of the classification model proves to be the best algorithm. It is presented that the Spark cluster gets much faster to build and evaluate models as adding more servers to the cluster with the same accuracy, which proves that the large scale data set can be predictable using Big Data platform. Finally, we reached a recall score with 0.73, which implies a satisfying prediction quality in predicting fraudulent transactions.

• Journal of Korean Society of Forest Science
• /
• v.88 no.3
• /
• pp.400-407
• /
• 1999

The purpose of thin paper is to test difference of the two question formats, open-ended and dichotomous choice formats, in the contingent valuation method using the estimated recreational benefits. The data were collected from the visitors at the Songnisan National Park. The recreational benefit based on the equivalent variation. The two question formats, but the same content, were asked of the same individuals. In this analysis, it was used travel cost and monthly income as the exogenous variables, which assumed a linear functional form for the WTP equation. The model assumed a bivariate normal distribution on the basis of the probit and tobit model concerning the censored zero WTP. The result showed no differences in the recreational benefits from the different question formats under a same respondent. The mean benefit was estimated 25.556 Won per 5 years per visitors.

• Journal of the Korean Wood Science and Technology
• /
• v.43 no.3
• /
• pp.304-310
• /
• 2015

The moisture content of sawdust must be measured accurately and controlled appropriately during storage and transportation because biological degradation could be caused by improper moisture. In this study, to measure the moisture contents of Larix kaempferi sawdust, the near-infrared reflectance spectra (Wavelength 1000-2400 nm) of sawdust were used as detection parameter. After acquiring the NIR reflection spectrum of specimens which were humidified at each relative humidity condition ($25^{\circ}C$, RH 30~99%), moisture content prediction model was developed using mathematical preprocessings (e.g. smoothing, standard normal variate) and partial least squares (PLS) analysis with the acquired spectrum data. High reliability of the MC regression model with NIR spectroscopy was verified by cross validation test ($R^2$ = 0.94, RMSEP = 1.544). The results of this study show that NIR spectroscopy could be used as a convenient and accurate method for the nondestructive determination of moisture content of sawdust, which could lead to optimize wood utilization.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.83-93
• /
• 2013

Land Suitability Assessment can help to evaluate whether to preserve or to develop through analysis of various land characteristics. So, the evaluation index and method are very important for making the best result. The principle objective of this dissertation is to identify effective method that can make up for the distortion of land suitability value in the forest bordering the management area. The objective area of this study is comparative flat Jeungpyeong-gun. The procedures of the study are as follows. First, implement land suitability assessment as the normal index on Guideline. Second, verify land suitability grade about the forest bordering the management area. The third, redo land suitability assessment as two alternative index on $^*$Guideline. The fourth, identify effective method between normal index and alternative index. The results of this tests show that the development suitability value is higher than preservation suitability value in the forest bordering the management area near existing development area. For that reason, this study needed to use substitution index in order to make up for the weakness. The level of land price and distance from road were main considerations. Finally, the derivative model is as follows. The derivative model confirmed the best assessment method in the forest bordering the management area near existing development area.

• Journal of Korean Society of Forest Science
• /
• v.94 no.4 s.161
• /
• pp.281-286
• /
• 2005

Trees enhance slope stability against down slope mass movement through the removal of soil water by transpiration and by the mechanical reinforcement of their roots. To assess the magnitude of this reinforcement on natural slope stability, direct shear tests were made on dry sand reinforced with different array types of roots. Pinus koraiensis was used as root specimens. The peak shear resistance at each normal stress level was measured on the rooted and unrooted soil specimens. Increased soil resistance(${\Delta}S$) by roots was calculated using parameters like internal friction angle and cohesion of tested soil and also evaluated the effects of root array in tested soil. As results, we find that shear resistance increased in tested soil shear box as diameters and arrayed numbers of root specimen increased and cross root array in tested soil had a much greater reinforcing effect than other root arrays. Comparison of traditional root-soil model with experiments showed that simulated reinforce strength by the model was different with those obtained by the experiment due to its linearity.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.30 no.5
• /
• pp.98-106
• /
• 2002

This study was designed to present a river model with the aim of restoring the ecosystem and improving the landscape along the urban rivers on the basin of the Namhanl river, a core life channel for the National Capital regin. The revelation of botanical status, transition trend and correlation of plants might lead to providing the urban river restoration projects and ecological river formation projects with basic data for a model of ideal aquatic ecology and landscape. The outcomes of this study could be summed up as follows: 1. The plant communities of river flora found on the basin of the Namhan river could be categorized largely into 39 plant communities 2. Most diverse plants were distributed in the rivers lower reaches such as Unsim-ri where the protected zone of Paldang reservoir for city water borders the body of Jodae swamp where natural streams flow nearby. 3. One of the greatest threats to the biomass of the River Namhan is that the communities of such invasive alien plants as Panicum dichotomiflorum and Ambrosia artemisiifolia var. elatior dominate most parts of the area, a fact that has resulted in a reduced variety of plants and will, sooner or later, be likely to cause an ecological imbalance in the hitherto healthy Aquatic plant life. It is highly advisable to gradually diversify the species of trees and to return the plants bark to their original state since, besides the naturalized plants, plantations afforested with Erigeron canadensis and Erigeron annuus stocks in buckwheat field, Robinia Pseudo-accacia in riverside forest, Pinus rigida in terrestrial forest on the river basin and Larix leptolepis are anticipated to act as interceptors of normal migrations of the fluvial and terrestrial ecosystems. Finally, it seems also desirable to continue to explore the relationship between fluvial and terrestrial ecologies with the purpose of building up a model of natural streams in urban areas based on the surveyed factors for plant life, soil and landscape and, moreover, on the forecasting for overall influences derived from the rotation upon the ecosystem.