• Title/Summary/Keyword: 분류나무 분석

Search Result 595, Processing Time 0.022 seconds

Vegetation Structure of Urban Forests on Mt. Goehwa, Sejong-Si (세종시 괴화산 도시숲의 식생구조)

  • Hyeon-Hwa Kim;Jeong-Eun Lee;Sung-Yeon Lee;Da-Eun Park;Chung-Weon Yun
    • Journal of Korean Society of Forest Science
    • /
    • v.113 no.1
    • /
    • pp.51-65
    • /
    • 2024
  • Phyto-sociological methods were used in this study to assess the vegetation structure of a forest stand at Mt. Goehwa in Sejong-Si with the aim of providing vegetation information for urban forest utilization and management plans. The actual forest vegetation was classified into two types of community groups (Quercus serrata-Lindera obtusiloba and Coreopsis lanceolata community groups) at the highest hierarchical level. The Q. serrata-L. obtusiloba community group was classified into six units, which included artificial forest and natural forest vegetation. Artificial forests were classified into three communities (Pinus rigida, Castanea crenata, and Robinia pseudoacacia), whereas natural forests were classified into three communities (Quercus variabilis, Quercus acutissimaa, and Pinus densiflora). The Coreopsis lanceolata community group, which exhibited vegetative characteristics of urban forest edge areas, was categorized into four units. The urban forest edges were classified into four communities (Indigofera bungeana, Lespedeza bicolor, Amorpha fruticosa, and Lespedeza cuneata). Accordingly, the vegetation structure of Mt. Goehwa was categorized into 10 vegetation unit systems. An importance value analysis showed the highest importance value for C. crenata at 6.7%, followed by P. rigida at 6.4%, and R. pseudoacacia at 6.3%, indicating that the ecological impact of plantation species can be significant on Mt. Goehwa. A community coefficient of similarity analysis revealed that the artificial and natural forests had similar species compositions; however, both forests differed from the urban forest edge. This variation was further confirmed by Detrended correspondence analysis(DCA), with similar results. Canonical correspondence analysis(CCA) showed that the artificial forest and natural forest community types were positively correlated with altitude, bare rock, and the present species. By contrast, the urban forest edge community types were negatively correlated with these factors.

Developing a Binary Classification Method for Bankruptcy Prediction (기업도산예측을 위한 이진분류기법의 개발)

  • Min, Jae-Hyeong;Jeong, Cheol-U
    • 한국경영정보학회:학술대회논문집
    • /
    • 2007.06a
    • /
    • pp.619-624
    • /
    • 2007
  • 본 연구는 유전 알고리듬에 기반한 새로운 도산예측기법을 개발하고 그 기법의 타당성 및 예측 우수성을 검증하는데 목적이 있다. 본 연구에서 제안하는 이진분류기법은 도산기업과 비도산기업을 대표할 수 있는 가상기업(virtual company)을 설정하고, 그 가상기업과 분류대상 기업 간의 유사도를 측정하여 도산여부를 분류하는 방법론으로, 가상기업의 변수 값과 각 변수의 가중치는 훈련용 자료의 분류정확도를 극대화할 수 있도록 유전 알고리듬을 이용하여 구하게 된다. 본 연구에서 제안하는 기법의 타당성을 검증하기 위해 기존의 도산예측기법과 예측성과를 실험을 통해 비교한 결과, 본 연구에서 개발한 기법의 예측력이 기존의 다변량판별분석, 로지스틱 회귀모형, 의사결정나무, 인공신경망 모형보다 높은 수준을 보이는 것을 확인하였다.

  • PDF

A Study on the Fraud Detection of Industrial Accident Compensation Insurance (산재보험 부정수급 식별모형에 관한 연구)

  • Ham, Seung-O;Hong, Jeong-Sik
    • Proceedings of the Korean Operations and Management Science Society Conference
    • /
    • 2008.10a
    • /
    • pp.342-345
    • /
    • 2008
  • 산재 발생 시 산재근로자는 근로복지공단을 통해서 각종 급여를 받게 된다. 본 논문은 심사 과정과 급여지급 후에 부정수급으로 판명된 산재 청구 건을 데이터 마이닝을 통해서 분석하여 부정수급의 유형을 발견하고자 한다. 이 연구에서는 서울관내 4개 지사에서 8년 동안(2000년$\sim$2007년)의 총 61,536명의 최초요양 신청을 한 산재근로자 자료를 대상으로 하였고, 종속변수에 영향을 미치는 8개의 독립변수를 선택해서 사용한다. 데이터 마이닝을 적용함에 있어서 가장 효율적인 허위 부정 탐지 모델을 만들기 위해 의사결정나무분석(Decision Tree)과 로지스틱 회귀분석(Logistic Regresion)등의 다양한 기법을 적용하여 결과를 비교분석 하고, 오분류 비용을 적용하여, 최적의 분류결정 값을 가지는 모델을 도출한다. 분석결과, 로지스틱 회귀분석이 산재보험 부정수급 유형 발견에 보다 효과적인 모델로 판명되었다. 또한 판별점(Cut-Off) 0.01로 했을 때 4개변수(요양기간, 업종형태, 의료기관, 재해발생형태)가 부정수급에 탐지하는데 영향력이 큰 변수로 선정되었다.

  • PDF

The Research on the Phytosociological Characteristics of Abies nephrolepis Maxim. Community in Mt. Seorak, Korea (설악산 분비나무군락의 식물사회학적 특성)

  • Lee, Ho-Young;Chung, Bo-Kwang;Chun, Young-Moon;Oh, Choong-Hyeon
    • Korean Journal of Environment and Ecology
    • /
    • v.35 no.1
    • /
    • pp.37-47
    • /
    • 2021
  • This study carried out the plant sociological survey of Abies nephrolepis forest in Mt. Seorak, which is in danger of deterioration due to the accelerated climate change. We examined seventy quadrats obtained from the survey and used the TWINSPAN technique to classify communities. We then performed the DCA method for the sequence analysis and analyzed the characteristics of each community. A. nephrolepis forest of Mt. Seorak is composed of four communities (A. nephrolepis-Lonicera caerulea var. edulis community, A. nephrolepis-Acer komarovii community, A. nephrolepis-Ac. pseudosieboldianum community, and A. nephrolepis-Betula costata community). Each community showed a different distribution according to location because different microenvironments are formed depending on location such as altitude and slope direction, resulting in different species composition. Each community showed differences in environmental characteristics such as altitude, rock ratio, soil characteristics, and litter layer thickness. As a result, there were significant differences between communities in the number of species and individuals, coverage, tree size, and species diversity, as well as differences in species composition. The A. nephrolepis-L. caerulea var. edulis and A. nephrolepis-Ac. komarovii communities were located in high altitude with high rock ratios and had little development of tree layer. On the other hand, the A. nephrolepis-Ac. pseudosieboldianum and A. nephrolepis-B. costata communities were relatively in low altitude with high soil ratio and had the development of tree layer with high species diversity.

Exploring Sport Consumption Style of Generation Z that the 4th Industrial revolution paid attention to: Applying Decision Tree Analysis based on Data Mining (4차 산업혁명이 주목한 Z세대의 스포츠 소비 스타일 탐색: 데이터마이닝 기반 의사결정 나무 분석 적용)

  • Shin, Jin-Ho;Lim, Young-Sam;Kim, Ji-Sun
    • Journal of the Korean Applied Science and Technology
    • /
    • v.37 no.5
    • /
    • pp.1208-1221
    • /
    • 2020
  • The purpose of this study was to provide basic data for predicting the sports consumption market that Generation Z will lead by applying data mining based decision tree analysis to explore Generation Z sports consumption style. Therefore, the survey was conducted by selecting males and females aged 19 or older as a sample among Generation Z, and data of 429 people were used for the final analysis. For data processing, frequency analysis, exploratory factor analysis, retest and reliability analysis, and decision tree analysis were performed using the SPSS statistics (ver. 21.0) program. The main results of this study are as follows. First, if the rational efficiency index is high and the aesthetic consumption index is low, the probability of being classified as a group of female was 96.8%. On the other hand, if the rational efficiency and perception of price index were low, the probability of being classified as a male group was 100%. Second, if the brand orientation, perception of price, and rational efficiency index were high, the probability of being classified as a capital area group was 97.3%. Contrary to the results presented above, the probability of being classified as a other area group was 82.1% when the brand orientation, commemoration rites, and status symbol index were low. Third, the status symbol and trend oriented index were high, and if the functionality index was low, the probability of being classified into daily life and fashion groups was 77.6%. On the contrary, if the status symbol index is low, the retention of membership and enjoy consumption index is high, the probability of being classified into exercise and competition groups was 81.0%.

A Study on the Forest Vegetation Classification and Analysis of Interspecific Association in Mt. Munsu and Mt. Okseok (문수산.옥석산 일대의 산림식생유형 분류와 종간연관 분석)

  • Kim, Hye-Jin;Yun, Chung-Weon
    • Journal of Korean Society of Forest Science
    • /
    • v.98 no.4
    • /
    • pp.379-391
    • /
    • 2009
  • This study was carried out to classify forest vegetation structure of Mt. Munsu and Mt. Okseok from May to September in 2008 using phytosociological analysis methodology of Z-M school under the purpose of furnishing basic materials for rational and scientific forest management. Total of one hundred five study sites (quadrats) was investigated in the area. Quercus mongolica community group was divided into 5 communities such as Pinus densiflora for. erecta community, Hydrangea serrata for. acuminata community, Salix gracilistyla community, Pinus koraiensis community and Larix kaempferi community. Pinus densiflora for. erecta community was subdivided into Rhododendron micranthum group, Quercus variabilis group and Pinus densiflora for. erecta typical group. Hydrangea serrata for. acuminata community also into Ligularia fischeri group, Deutzia glabrata group (into Juglans mandshurica subgroup, Prunus maackii subgroup and Callicarpa japonica subgroup). Accordingly, the vegetation of the study areas could be described as 1 community group, 5 communities, 5 groups, and 3 subgroups and as 10 units in total. Classified vegetation units were highly correlated with altitude and topography. According the analysis of interspecific association, it was shown as three types which were coincident with differential species and character species on the constancy table.

A Synecological Study of the Riverside Vegetation of the Upper Stream of Nakdong River, Korea1a - I. Forest and Shrub Vegetation - (낙동강 상류의 하천변 식생의 군락생태학적 연구 - I. 삼림 및 관목성 식생 -)

  • Song, Jong-Suk
    • Korean Journal of Environment and Ecology
    • /
    • v.22 no.4
    • /
    • pp.443-452
    • /
    • 2008
  • This study conducted a survey on forest and shrub vegetation in the riverside of the main stream of the Nakdong River on the southeastern part of Korea based on the method of ZM school of phytosociology. As a result, this study identified the vegetation units as ten associations and communities belonging to three classes, and four communities unclear to the upper units. The identified vegetation units were as follows: A-1 Acero-Fagetea class group, Fraxino-Ulmetaria, undecided alliance: 1) Fraxinus mandshurica community; Zelkovetalia(prov.), Zelkovion(prov.): 2) Zelkova serrata community, A-2 Salicetea sachalinensis, Salicetalia koreensis, Salicion koreensis: 3) Salicetum koreensio-chaenomeloides, 4) Salicetum koreensis, 5) Hemipteletum davidii, 6) Salicetum gracilistylae, 7) Salicetum graciliglandis, 8) Salicetum subfragilis, A-3 Rosetea multiflorae, Dioscoreo-Puerarietalia lobatae, Actinidio-Vition coignetiae: 9) Stephanandra incisa community, 10) Lycium chinense community, A-4 unclear upper units: 11) Clerodendron trichotomum community, 12) Ailanthus altissima community, 13) Robinia pseudo-acacia community. 14) Amorpha fruticosa community. The community units identified by the study corresponded with the result of cluster analysis quite nicely while the result of PCA analysis in multivariate analyses showed less correspondence with cluster analysis result, but it was interpreted as a degree of aggregation according to anthropogenic influence. The vegetation unit of forests and shrubs, unlike the herbal community in highly common with those of Japan, included five vegetation units unique to Korea at a collective level. On the basis of the above synecological study, this research discussed the relation between each community and environment, and natural environment, etc.

Vascular Plants Distributed in Baekdudaegan Mountains (Gitdaebaegibong~Mt. Cheonghwasan) (백두대간(깃대배기봉~청화산)에 분포하는 관속식물상)

  • Oh, Hyun-Kyung;You, Ju-Han
    • Korean Journal of Environment and Ecology
    • /
    • v.32 no.1
    • /
    • pp.1-22
    • /
    • 2018
  • The purpose of this study is to provide the baseline data for conservation and management of Korean forest ecosystem by surveying and analyzing the vascular plants distributed from Gitdaebaegibong to Cheonghwasan in Baekdudaegan Mountains. The results are as follows. The numbers of vascular plants in the whole survey section were summarized as 771 taxa including 103 families, 379 genera, 623 species, 4 subspecies, 121 varieties and 23 forms. There were 377 taxa in A-section, 395 taxa in B-section, 278 taxa in C-section, 325 taxa in D-section, 534 taxa in E-section, and 406 taxa in F-section. The rare plants were 32 taxa including Megaleranthis saniculifolia, Rodgersia podophylla, Iris ensata var. spontanea, and Gastrodia elata. In IUCN Red List categories, there were 1 taxon of CR, EN, and DD each, 11 taxa of the VU, and 18 taxa of the LC. The Korean endemic plants were 26 taxa including Asarum versicolor, Clematis fusca var. coreana, Vicia chosenensis, Stewartia pseudocamellia, Carex okamotoi, and Luzula sudetica var. nipponica. The specific plants by floristic region were 143 taxa including 3 taxa of grade V, 12 taxa of grade IV, 41 taxa of grade III, 42 taxa of grade II, and 45 taxa of grade I. The naturalized plants were 41 taxa including Rumex crispus, Ailanthus altissima, Erechtites hieracifolia, Erigeron annuus, and Poa pratensis. The invasive alien plants were 4 taxa including Rumex acetocella, Sicyos angulatus, Ambrosia artemisiifolia, and Aster pilosus. The plants adaptable to climate change were 43 taxa including 14 taxa of endemic plants, 2 taxa of southern plants, and 27 taxa of northern plants.

A Systematic Study of the Theaceae 6 Species in Korea (한국산(韓國產) 차나무과(科) 6종(種)의 계통(系統) 분류학적(分類學的) 연구(硏究))

  • Kim, Sam Sik;Lee, Jeong Hwan
    • Journal of Korean Society of Forest Science
    • /
    • v.82 no.4
    • /
    • pp.431-440
    • /
    • 1993
  • This study was carried out to clarify a taxonomical relationships of the Korean Theaceae using characters from morphological, anatomical, electrophoretic and numerical methods. The results are summarized as follows ; Morphological data were cluster analysis by Euclidean distance, the complete and average linkage cluster were most distinctly classified into subfamily level. At the principal components analysis(PCA), the commutative contribution rate of three principal components showed to 91.1% total variance. By the leaf venation were classified semicraspedromous type of Theoideae and brochidodromous type of Ternstroemioideae. The stomatal types were classified Paracytic of Theoideae and Anomocytic type of Ternstroemioideae ; the former has founded subsideary cell the latter has not found. All taxa possessed common isozyme bands did not found out of Theaceae banding patterns. But, the activity of Theoideae were existed in below No.5(Rf. 4.0-4.4), in contrast to Ternstroemioideae were existed in more than No.7(Rf. 5.7-6.2). The cluster analysis of leaf characters and peroxidase isozymes were similarity between two methods.

  • PDF

A Study on the Node Split in Decision Tree with Multivariate Target Variables (다변량 목표변수를 갖는 의사결정나무의 노드분리에 관한 연구)

  • Kim, Seong-Jun
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.13 no.4
    • /
    • pp.386-390
    • /
    • 2003
  • Data mining is a process of discovering useful patterns for decision making from an amount of data. It has recently received much attention in a wide range of business and engineering fields. Classifying a group into subgroups is one of the most important subjects in data mining. Tree-based methods, known as decision trees, provide an efficient way to finding the classification model. The primary concern in tree learning is to minimize a node impurity, which is evaluated using a target variable in the data set. However, there are situations where multiple target variable should be taken into account, for example, such as manufacturing process monitoring, marketing science, and clinical and health analysis. The purpose of this article is to present some methods for measuring the node impurity, which are applicable to data sets with multivariate target variables. For illustration, a numerical cxample is given with discussion.