• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.457-469
• /
• 2022

Purpose: The purpose of this study is to present the direction of improvement of safety management by reviewing the current status of forest fire accidents that are becoming larger throughout the year and the problems of the response system. Method: Domestic and foreign literature survey and statistics of recent forest fire accidents by Statistics Korea investigated and analyzed the cause, number of damage, and suggested ways to improve forest fire safety management through domestic and foreign forest fire response systems. Result: Through the analysis of the causes of recent wildfires and overseas response cases, measures to improve the safety management of wildfires in terms of hardware, software, and humanware were derived. Conclusion: The plan to improve forest fire safety management was classified into three main categories and presented, and it should be embodied through further related research.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.515-524
• /
• 2017

In this study, a measure of discrepancy based on MV (margin of victory) has been suggested that might be useful in determining the size of random forest for classification. Here MV is a scaled difference in the votes, at infinite random forest, of two most popular classes of current random forest. More specifically, max(-MV,0) is proposed as a reasonable measure of discrepancy by noting that negative MV values mean a discrepancy in two most popular classes between the current and infinite random forests. We propose an appropriate diagnostic statistic based on this measure that might be useful for the determination of random forest size, and then we derive its asymptotic distribution. Finally, a simulation study has been conducted to compare the performances, in finite samples, between this proposed statistic and other recently proposed diagnostic statistics.

• Journal of Forest and Environmental Science
• /
• v.39 no.2
• /
• pp.81-95
• /
• 2023

Due to the multiple ecosystem benefits that iconic large, old growth trees provide, forest managers are applying thinning treatments around these legacy trees to improve their vigor and reduce mortality, especially in the face of climate change and other forest health threats. One objectives of this study was to analyze sub-hourly stem fluctuations of legacy ponderosa (Pinus ponderosa Dougl. Ex P. & C. Laws) and sugar pines (Pinus lambertiana Dougl.) in the mixed-conifer forests of the Sierra Nevada in multiple different radius thinning treatments to assess the short-term effects of these treatments. Thinning treatments applied were: R30C0 (9.1 m radius), R30C2 (9.1 m radius leaving 2 competitors), and RD1.2 (radius equaling DBH multiplied by 1 ft/in multiplied by 1.25). The other objective was to assess climatic drivers of hourly stem fluctuations. Using the dendrometeR package, we gathered daily statistics (i.e. daily amplitude) of the stem fluctuations, as well as stem cycle statistics such as duration and magnitude of contraction, expansion, and stem radial increment. We then performed correlation analyses to assess the climatic drivers of stem fluctuations and to determine which radial thinning treatment was most effective at improving growth. We found an important role that mean solar radiation, air temperature, and relative humidity play in stem variations of both species. One of the main findings from a management perspective was that the RD1.2 treatment group allowed both species to contract less on warmer and higher solar radiation days. Furthermore, sugar pine put on more stem radial increment on higher solar radiation days. These findings suggest that the extended radius RD1.2 thinning treatment may be the most effective at releasing legacy sugar and ponderosa pine trees compared to the other forest management treatments applied.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.851-865
• /
• 2017

Ransomware such as WannaCry is a global issue and methods to defend against malware attacks are important. We have to be able to classify the malware types efficiently in order to minimize the damage from malwares. This study makes models to classify malware properly with various statistical techniques. Several classification techniques such as logistic regression, random forest, gradient boosting, and support vector machine are used to construct models. This study also helps us understand key variables to classify the type of malicious software.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• Journal of Korean Society of Forest Science
• /
• v.102 no.3
• /
• pp.437-445
• /
• 2013

This study was conducted to develop site index equations and to estimate productive areas of Quercus acutissima by ecoprovince in Korea using environmental factors. Using the large data set from both a digital forest site map and a climatic map, a total of 48 environmental factors including 19 climatic variables were regressed on site index to develop site index equations. Four to six environmental factors for Quercus acutissima by ecoprovince were selected as independent variables in the final site index equations. The result showed that the coefficients of determination for site index equations were ranged from 0.30 to 0.41, which seem to be relatively low but good enough for the estimation of forest stand productivity. The site index equations developed in this study were also verified by three evaluation statistics such as the estimation bias of model, precision of model, and mean square error of measurement. According to the evaluation statistics, it was found that the site index equations fitted well to the test data sets with relatively low bias and variation. As a result, it was concluded that the site index equations were well capable of estimating site quality. Based on the site index equations of Quercus acutissima by ecoprovince, the productive areas by ecoprovince were estimated by applying GIS technique to the digital forest site map and climate map. In addition, the distribution of productive areas by ecoprovince was illustrated by using GIS technique.

• Journal of Korean Society of Forest Science
• /
• v.101 no.3
• /
• pp.395-404
• /
• 2012

This study was conducted to develop site index equations and to estimate productive areas for major coniferous species in Korea such as Pinus densiflora Sieb. et. Zucc, Pinus densiflora for. erect, Larix leptolepis and Pinus koraiensis using environmental factors. Using the large data set from both a digital forest site map and a climatic map, a total of 43 environmental factors including 15 climatic variables were regressed on site index by tree species to develop site index equations. Six environmental factors by species were selected as independent variables in the final site index equations. The result showed that the coefficients of determination for site index equations by species were ranged from 0.36 to 0.56, which seem to be relatively low but good enough for the estimation of forest stand productivity. The site index equations developed in this study were also verified by three evaluation statistics such as the estimation bias of model, precision of model, and mean square error of measurement. According to the evaluation statistics, it was found that the site index equations by species fitted well to the test data sets with relatively low bias and variation. As a result, it was concluded that the site index equations by species were well capable of estimating site quality. Based on the site index equations, the productive areas by species for all forest areas were estimated by applying GIS technique to the digital forest site map and climate map. In addition, the distribution of productive areas by species was illustrated by using GIS technique.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1053-1065
• /
• 2019

Land use statistics calculation is very informative data as the activity data for calculating exact carbon absorption and emission in post-2020. To effective interpretation by land use category, This study classify automatically image interpretation by land use category applying forest aerial photography (FAP) to deep learning model and calculate national unit statistics. Dataset (DS) applied deep learning is divided into training dataset (training DS) and test dataset (test DS) by extracting image of FAP based national forest resource inventory permanent sample plot location. Training DS give label to image by definition of land use category and learn and verify deep learning model. When verified deep learning model, training accuracy of model is highest at epoch 1,500 with about 89%. As a result of applying the trained deep learning model to test DS, interpretation classification accuracy of image label was about 90%. When the estimating area of classification by category using sampling method and compare to national statistics, consistency also very high, so it judged that it is enough to be used for activity data of national GHG (Greenhouse Gas) inventory report of LULUCF sector in the future.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.723-734
• /
• 2021

Wind energy is one of the rapidly developing renewable energies which is being developed and invested in response to climate change. As renewable energy policies and power plant installations are promoted, the supply of wind power in Korea is gradually expanding and attempts to accurately predict demand are expanding. In this paper, the ARIMA and ARIMAX models which are Time series techniques and the SVR, Random Forest and XGBoost models which are machine learning models were compared and analyzed to predict wind power generation in the Jeonnam and Gyeongbuk regions. Mean absolute error (MAE) and mean absolute percentage error (MAPE) were used as indicators to compare the predicted results of the model. After subtracting the hourly raw data from January 1, 2018 to October 24, 2020, the model was trained to predict wind power generation for 168 hours from October 25, 2020 to October 31, 2020. As a result of comparing the predictive power of the models, the Random Forest and XGBoost models showed the best performance in the order of Jeonnam and Gyeongbuk. In future research, we will try not only machine learning models but also forecasting wind power generation based on data mining techniques that have been actively researched recently.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2007.06a
• /
• pp.280-285
• /
• 2007

Since the human civilization, people's livelihood is dependent on natural resources primarily on forest. Human dimensions such as population, poverty, agricultural expansion and infrastructure development are some of the underlying factors and their interrelated associations which could play a vital role in deforestation and forest degradation. This process is not only related to the human population but also connected to the various socioeconomic factors. This paper focuses to link the spatio-temporal extent of population, poverty incidence and forest dependency and their severity on Terai forest of Nepal. Secondary data on censuses were used. ArcGIS and descriptive statistics were also used for data analysis. Based on analysis & literature review we concluded that population, poverty and forest dependency have largely expanded over time in Terai and their interrelated associations substantively influence on deforestation. However, the direct relationship of such factors with deforestation and forest degradation found to be incompatible, complex and hard to perceive with fragmented and inconsistency censuses data. So, deforestation and forest degradation issues intertwined with socioeconomic factors need detailed analysis to comprehend where these linkages are still unravel.