• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1042-1044
• /
• 2003

A methodology of the integrating the similar color circle search of the spectral data and segmentation of the height data is developed. The method is then applied to study areas, and the results by IKONOS, LIDAR and data fusion are verified with the ground truth, and examined in terms of the accuracy. Results show that with the data fusion the accuracy are improved by about 15% in most of the study areas. The methodology for the detection of individual tree stands by data fusion is explored, and the utility of combinatorial use of the spectral and the height information is demonstrated.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.467-469
• /
• 2003

This research aimed to develop forest type classification technique for the mixed forest with coniferous and broad-leaved species using the high resolution satellite data. QuickBird data was used as satellite data. The method of this research was to extract satellite data for every single tree crown using image segmentation technique, then to evaluate the accuracy of classification by changing grouping criteria such as tree species, families, coniferous or broad-leaved species, and timber prices. As a result, the classification of tree species and families level was inaccurate, on the other hand, coniferous or broad-leaved species and timber price level was high accurate.

• 한국산림과학회지
• /
• 제108권3호
• /
• pp.372-381
• /
• 2019

조선거수노수명목지는 조선총독부가 조선의 신목을 왜곡하기 위해 만든 자료라는 가설을 세우고 이를 증명하기 위해 연구하였다. 다음과 같은 결론을 얻었다. 첫째 조선거수노수명목지에는 64개 수종 3,170본의 목록이 기록되어 있다. 노거수에 신적 요소 고사 전설이 있으면 신목, 고사적 요소 고사 전설이 있으면 명목으로 분류되어 있다. 본수가 가장 많은 느티나무로부터 8번째로 많은 전나무까지 8수종 2,632본을 분석대상으로 하였다. 8개 수종별 신목과 명목의 평균 직경, 평균 수고, 평균 수령을 산출하였다. 8개 수종 중 7개 수종에서 명목의 직경과 수령이 신목보다 크고, 6개 수종에서 명목의 수고가 신목보다 컸다. 신목이 명목보다 왜소하고 볼품없는 크기의 나무라는 이 상식에 반하는 사실이 조선거수노수명목지에 기록되어 있음이 확인되었다. 본 고의 가설은 위의 사실 확인으로 증명되었다. 둘째 조선총독부는 신목을 중심으로 행해지는 동제를 미신으로 타파하는 시책을 추진하였다. 신목이 작고 볼품없어야 미신이라고 주장하기 좋았을 것이다. 조선 신목의 신성성을 폄하하기 위한 설명자료 또는 증거자료로 조선거수노수명목지를 작성한 것이다. 셋째 조선의 신목이 명목보다 작고 왜소하다는 날조된 내용을 사실인양 쉽게 설명할 수 있도록 조선거수노수명목지를 흉고직경순으로 편찬한 것이다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.753-754
• /
• 2008

LiDAR data are acknowledged as very useful method to represent 3-D geographical information. In this paper aquad tree has been utilized to represent the 3-D spatial information. Compression algorithm is implemented based on a given threshold. The efficiency of compress is very high with large threshold values.

• 대한간호학회지
• /
• 제43권1호
• /
• pp.1-10
• /
• 2013

Purpose: The purpose of this study was to develop a prediction model for the characteristics of older adults with depression using the decision tree method. Methods: A large dataset from the 2008 Korean Elderly Survey was used and data of 14,970 elderly people were analyzed. Target variable was depression and 53 input variables were general characteristics, family & social relationship, economic status, health status, health behavior, functional status, leisure & social activity, quality of life, and living environment. Data were analyzed by decision tree analysis, a data mining technique using SPSS Window 19.0 and Clementine 12.0 programs. Results: The decision trees were classified into five different rules to define the characteristics of older adults with depression. Classification & Regression Tree (C&RT) showed the best prediction with an accuracy of 80.81% among data mining models. Factors in the rules were life satisfaction, nutritional status, daily activity difficulty due to pain, functional limitation for basic or instrumental daily activities, number of chronic diseases and daily activity difficulty due to disease. Conclusion: The different rules classified by the decision tree model in this study should contribute as baseline data for discovering informative knowledge and developing interventions tailored to these individual characteristics.

• Earthquakes and Structures
• /
• 제12권6호
• /
• pp.653-663
• /
• 2017

A seismic margin assessment evaluates how much margin exists for the system under beyond design basis earthquake events. Specifically, the seismic margin for the entire system is evaluated by utilizing a systems analysis based on the sub-system and component seismic fragility data. Each seismic fragility curve is obtained by using empirical, experimental, and/or numerical simulation data. The systems analysis is generally performed by employing a fault tree analysis. However, the current practice has clear limitations in that it cannot deal with the uncertainties of basic components and accommodate the newly observed data. Therefore, in this paper, we present a Bayesian-based seismic margin assessment that is conducted using seismic fragility data and fault tree analysis including Bayesian inference. This proposed approach is first applied to the pooltype nuclear research reactor system for the quantitative evaluation of the seismic margin. The results show that the applied approach can allow updating by considering the newly available data/information at any level of the fault tree, and can identify critical scenarios modified due to new information. Also, given the seismic hazard information, this approach is further extended to the real-time risk evaluation. Thus, the proposed approach can finally be expected to solve the fundamental restrictions of the current method.

• 한국환경과학회지
• /
• 제25권4호
• /
• pp.603-613
• /
• 2016

Fog may have a significant impact on road conditions. In an attempt to improve fog predictability in Jeju, we conducted machine learning with various data mining techniques such as tree models, conditional inference tree, random forest, multinomial logistic regression, neural network and support vector machine. To validate machine learning models, the results from the simulation was compared with the fog data observed over Jeju(184 ASOS site) and Gosan(185 ASOS site). Predictive rates proposed by six data mining methods are all above 92% at two regions. Additionally, we validated the performance of machine learning models with WRF (weather research and forecasting) model meteorological outputs. We found that it is still not good enough for operational fog forecast. According to the model assesment by metrics from confusion matrix, it can be seen that the fog prediction using neural network is the most effective method.

• 서비스연구
• /
• 제2권2호
• /
• pp.35-43
• /
• 2012

데이터 마이닝은 특정분야에서만 관심을 갖는 분야가 아니라 현재 우리주변 여러 분야에서 많이 사용되고 응용되고 있다. 즉, 수많은 데이터 가운데 숨겨져 있는 유용한 상관관계를 발견하여, 미래에 실행 가능한 정보를 예측하여 추출해 내고 추후에 의사 결정에 이용하는 과정을 말한다. 하지만, 일부 데이터 집합에서는 매우 많은 결측치를 포함하는 변수들이 존재한다. 다시 말해서 다수의 레코드에서 측정치가 존재하지 않는 데이터 집합이 존재한다. 그래서 본 논문에서는 Cholesterol 값을 예측하기 위한 결측치 처리에 따른 모델트리 알고리즘을 적용하고, 실험을 통해서 각 처리방식에 대한 성능을 분석한다. 또는 이 결과를 통하여 결측치 대체방법에 대한 효율적인 적용사례를 제시한다.

• Journal of Forest and Environmental Science
• /
• 제29권2호
• /
• pp.131-137
• /
• 2013

This study attempts to classify forest species using hyperspectral data for supporting resources management. The primary dataset used was AISA sensor. The sensor was mounted onboard the NOMAD GAF-27 aircraft at 2,000 m altitude creating a 2 m spatial resolution on the ground. Pre-processing was carried out with CALIGEO software, which automatically corrects for both geometric and radiometric distortions of the raw image data. The radiance data set was then converted to at-sensor reflectance derived from the FODIS sensor. Spectral Angle Mapper (SAM) technique was used for image classification. The spectra libraries for tree species were established after confirming the appropriate match between field spectra and pixel spectra. Results showed that the highest spectral signature in NIR range were Kembang Semangkok (Scaphium macropodum), followed by Meranti Sarang Punai (Shorea parvifolia) and Chengal (Neobalanocarpus hemii). Meanwhile, the lowest spectral response were Kasai (Pometia pinnata), Kelat (Eugenia spp.) and Merawan (Hopea beccariana), respectively. The overall accuracy obtained was 79%. Although the accuracy of SAM techniques is below the expectation level, SAM classifier was able to classify tropical tree species. In future it is believe that the most effective way of ground data collection is to use the ground object that has the strongest response to sensor for more significant tree signatures.

• 한국환경복원기술학회지
• /
• 제25권4호
• /
• pp.49-65
• /
• 2022

Since trees in the city are green assets that create a healthy environment for the city, systematic management of trees improves urban ecosystem services. The sporadic urban tree information centered on the site is vast, and it is difficult to manage the data, so efforts to increase efficiency are needed. This paper summarizes tree data inventory based on data constructed by Seoul Green Trust activists and constructs and discloses online database maps using Tableau Software. In order to verify the utilization of the map, we divided into consumer and supplier aspects to collect various opinions and reflect feedback to implement tree database maps for each area and species of Seoul Forest. As a result, the utilization value of tree database in urban parks was presented. The technical significance of this study is to systematically record the process of constructing and implementing a dashboard directly using the Mapbox platform and Tableau Software in the field of landscaping for the first time in Korea. In addition, the implications and supplements of landscape information were derived by collecting user opinions on the results. This can be used as an exploratory basis in the process of developing online-based services such as web and apps by utilizing landscaping tree information in the future. Although the visualization database currently constructed has limitations that ordinary users cannot interact in both directions because it utilizes business intelligence tools in terms of service provision it has affirmed both the database construction and its usability in web public format. In the future it is essential to investigate the assets of the trees in the city park and to build a database as a public asset of the city. The survey participants positively recognized that information is intuitively presented based on the map and responded that it is necessary to provide information on the overall urban assets such as small parks and roadside trees by using open source maps in the future.