• Title/Summary/Keyword: 희귀분석

Search Result 307, Processing Time 0.025 seconds

A New Learning Algorithm for Rare Class Classification (희귀 목적값 분류를 위한 학습 알고리즘)

  • Lee, Kwang-Ho;Lee, Chang-Hwan
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2006.11a
    • /
    • pp.39-42
    • /
    • 2006
  • 본 논문에서는 데이터 마이닝에서 발생되는 희귀 데이터를 분석하기 위한 희귀 목적값 분석의 새로운 알고리즘을 제시한다. 이를 위하여 속성들이 가지는 속성의 가중치 값과 속성값이 목적 속성에 미치는 가중치값을 정보이론에 입각하여 가중치 계산을 하고, 계산된 가중치값을 사용하여 스코어링 함으로써 희귀 목적값에 속한 데이터 예측/분류에 사용하는 방법을 제시하였다. 실험을 통해 본 알고리즘의 성능을 입증함은 물론 제안된 알고리즘이 희귀 데이터의 분류/학습에 좀 더 효과적이다는 것을 보였다.

  • PDF

Estimating the Intergenerational Income Mobility in Korea (한국의 세대 간 소득이동성 추정)

  • Yang, Jung-Seung
    • Journal of Labour Economics
    • /
    • v.35 no.2
    • /
    • pp.79-115
    • /
    • 2012
  • In the study, we try to get reliable estimates of intergenerational income mobility in Korea. At first, we show that the low estimates of previous studies are mainly due to sample selection problem. The direct estimations using OLS after correcting this problem show higher values than previous estimates. We also compute the attenuation bias by decomposing the variances of earnings into the variances of permanent and transitory components of earnings by the results of the regression. Additionally, we try to estimate the range of intergenerational mobility by comparing the OLS results with the results of the two samples instrumental variable estimation and the three samples instrumental variable estimation. The results of these estimations are a little higher than or similar to OLS results.

  • PDF

Comparison of Bias Correction Methods for the Rare Event Logistic Regression (희귀 사건 로지스틱 회귀분석을 위한 편의 수정 방법 비교 연구)

  • Kim, Hyungwoo;Ko, Taeseok;Park, No-Wook;Lee, Woojoo
    • The Korean Journal of Applied Statistics
    • /
    • v.27 no.2
    • /
    • pp.277-290
    • /
    • 2014
  • We analyzed binary landslide data from the Boeun area with logistic regression. Since the number of landslide occurrences is only 9 out of 5000 observations, this can be regarded as a rare event data. The main issue of logistic regression with the rare event data is a serious bias problem in regression coefficient estimates. Two bias correction methods were proposed before and we quantitatively compared them via simulation. Firth (1993)'s approach outperformed and provided the most stable results for analyzing the rare-event binary data.

Rare and Endangered Plant Conservation in Chinese Botanical Gardens-The Construction and Analysis if Database of Rare and Endangered Plants- (중국 식물원에서 희귀 및 멸종위기 식물의 보전 -희귀 및 멸종위기 식물의 데이터베이스 구축 및 분석)

  • 장덕순
    • Korean Journal of Environment and Ecology
    • /
    • v.15 no.1
    • /
    • pp.1-16
    • /
    • 2001
  • 현재 중국에서는 100개 이상의 식물원이 있으며, 대부분의 식물원은 희귀식물이나 멸종위기 식물의 생식질 자원을 보유하고 있다. 중국의 식물원에서 현지 외 보전과 이와 관련한 일을 수행하기 위하여 1999년 REPC-CBG-DATA라는 데이터베이스를 구축하였다. 본 데이터베이스 구축 결과에 따라 중국내 389종의 희귀 및 멸종위기 식물에 대한 다양한 정보와 보전상태를 분류하였으며, 이를 토태로 관리보전에 활용할 수 있게 되었다. 본 논문에서는 중국 내 희귀 및 멸종위기 식물의 보전을 위하여 각 식물원에 수집된 식물종을 대상으로 REPC-CBG-DATA를 바탕으로 각 해당 식물종의 관리에 대하여 토론하였다.

  • PDF

Estimation of Bituminous Concrete Property Based on Molecular Size Distribution of Asphalt Cement (아스팔트 시멘트의 분자립도 분포특성에 따른 아스팔트의 성질분석)

  • 김광우;연규석
    • Magazine of the Korea Concrete Institute
    • /
    • v.3 no.1
    • /
    • pp.71-78
    • /
    • 1991
  • Moleclar size distribution of three AC-20 asphalt cements were observed using high pressure - gel permeation chromatograph (HP-GPC). Bituminous concrete specimens were made using the asphalt cements and one aggre¬gate in laboratory to measure mechanical properties, tensile strength CIS) and resilient modulusCM,J. in dry and wet conditons. Results of mechanical property tests and profile of molecular size distribution of asphalt cements were analyzed to evaluate the relatonship of mechanical property with chromatogram. Regression analy¬sis showed a strong correlation between a mechanical property and sliced percent areas of chromatogram. Mathematical prediction models were developed based on the regression analysis. It was shown that characteris¬tics of asphalt cement chromatogram could be successfully used for estimation of selected mechanical property of asphalt concrete .

Regression Analysis on the Dispute Cost Property in Apartment Housing Claims (비용항목의 희귀분석을 통한 공동주택 하자분쟁의 비용특성연구)

  • Kang, Yu-Mi;Kim, Beop-Su;Park, Jun-Mo;Choi, Jeong-Hyun;Seo, Deuk-Seok;Kim, Ok-Kyue
    • Proceedings of the Korean Institute of Building Construction Conference
    • /
    • 2010.05a
    • /
    • pp.225-228
    • /
    • 2010
  • It is an social issue that is various claim related on the defect of apartment house. The cost of defect repair is the most important matter that residents dispute constructers with the huge time wasting and cost loss. For resolve the matter of defect claim, it must to be analyze to the cost property that study and find to pending issue about the cost of defect repair. Therefore this study is investigated the cost property of defect repair relation on correlation analysis and regression analysis around the judgement cost. Consequently, cost of the judgment is associated with cost of the accusation and cost of the defect repair, is recognizable as them that is closely connected. Meanwhile, the more time of take effect and time of lawsuit increase, the more cost of the judgment decrease by draw the regression equation. On the contrary, there are same aspects in the case on the cost of the accusation and cost of the defect repair.

  • PDF

Location and Policy Factors Influencing the Move-In Decision of Apartment Factory: Case Study of Middle and Small Sized Companies in Daegu City (아파트형공장의 입지 및 정책요인이 입주의사에 미치는 영향 -대구시 중소기업 사례를 중심으로-)

  • Park, Won-Seok
    • Journal of the Korean association of regional geographers
    • /
    • v.15 no.3
    • /
    • pp.409-420
    • /
    • 2009
  • This study aims at analyzing location and policy factors influencing the move-in decision of apartment factories on the case study of middle and small sized companies in Daegu City. The main results of this study are as follows. Firstly, analyzing the questionnaire survey results, 58.2% of response companies have the intentions to move-in apartment factories. Secondly, through the factor analysis to the location factors, 5 factors such as network, move-in cost, accessibility, factory space and labor are derived. And through the factor analysis to the policy factors, 3 factors such as management support policy, pecuniary support policy and administrative support policy are also derived. Finally, analyzing logistic regression analysis, we can find pecuniary support policies influence the move-in decision of apartment factories.

  • PDF

Estimation Methods for Linear Spatial Model on Lattice (Lattice형 공간정보의 선형모형 추정방법)

  • Gwon, O-Ryong;Yeom, Jun-Geun
    • The Transactions of the Korea Information Processing Society
    • /
    • v.3 no.1
    • /
    • pp.153-159
    • /
    • 1996
  • Linear models for spatial data are proposed by example in the paper. This method was introduced to Korea for the first time in the early part of 1990's. The correlation of spatial patterns is computed by Moran Index., and then correlogram is proposed as the method to identify correlation of spatial patterns. Due to computational difficulties with ML, an alternative estimator has been used as an eigenvalue method.

  • PDF