• 대한안전경영과학회지
• /
• 제7권5호
• /
• pp.1-8
• /
• 2005

The consequences of rapid industrial advancement, diversified types of business and unexpected industrial accidents have caused a lot of damage to many unspecified persons both in a human way and a material way Although various previous studies have been analyzed to prevent industrial accidents, these studies only provide managerial and educational policies using frequency analysis and comparative analysis based on data from past industrial accidents. The main objective of this study is to find an optimal algorithm for data analysis of industrial accidents and this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. Enterprise Miner of SAS and AnswerTree of SPSS will be used to evaluate the validity of the results of the four algorithms. The sample for this work chosen from 19,574 data related to construction industries during three years ($2002\sim2004$) in Korea.

• 아동학회지
• /
• 제31권2호
• /
• pp.183-195
• /
• 2010

This study sought to investigate the environmental predictors of atopic dermatitis in children. The participants were 1050 (age 3-5) children taken from data data from the Ministry for Health, Welfare and Family Affairs. A data mining decision tree model revealed that the factors of medical neglect, breakfast, attachment to mother, and mother's depression influenced atopic dermatitis in children. Our results revealed that in the factors considered above, medical neglect had the greatest influence upon atopic dermatitis in children.

• 대한한의진단학회지
• /
• 제11권1호
• /
• pp.130-145
• /
• 2007

Background and purpose: The purpose of this study is to search recognition patients in Eight constitution Oriental Medical Clinic. And we compare Eight constitution acupuncture methods with the another acupuncture methods. Methods: The subjects were comprised of 200 volunteers. In 3 Eight constitution Oriental Medical Clinic participants were chosen through questionnaire. Finishing answer participants put in their lacked name questionnaire to gathering box. DecisionTree (AnswerTree 3.0 Ver.) statistical software was used for statistical analysis. Results and Conclusion: As a result of the analysis of cognition to Eight constitution acupuncture methods was influenced to patients health, dietetic therapy is best influenced. Next influenced acupuncture reflex degree, age, job, constitution, cure periods, sex distinction, cure degree, diagnosed participant's Constitution by pulse diagnosis in 8 Constitution Medicine.

• 한국정보통신학회논문지
• /
• 제18권3호
• /
• pp.595-601
• /
• 2014

스마트 정보통신시대에 데이터의 수는 기하급수적으로 증가하고 있다. 이에 데이터 발생지역과 발생상황을 실시간으로 파악하고 분석하는 것이 신속한 조치를 취하는 중요한 요소로 떠오르고 있다. 본논문에서는 분석자가 원하는 특성 데이터 발생지역의 국소적 판단을 하기 위하여 데이터 발생에 대한 값을 최하위 모듈에서부터 최상위 모듈까지 이어지는 루트를 역순으로 진행하면 데이터 발생과 동시에 분석이 가능하다. 먼저 군집분석에 대해 알아보고 군집원들의 합에 의한 분석법을 트리 구조에 병합하여 최하위 모듈부터 최상위 모듈까지 발생 특성값에 대해 수치로 치환하고 그 합을 도출하도록 설계하였다. 또한 특성값에 대한 가중치를 부여하여 원하는 값의 발생상황을 실시간으로 도출되도록 설계하였다.

• 한국응급구조학회지
• /
• 제15권3호
• /
• pp.57-70
• /
• 2011

Purpose : The purpose of this study was to reveal some factors of ROSC & survival for cardiac arrests from sport & leisure activities(CASLs). Methods : A retrospective study of the 1,341 out of hospital cardiac arrests(OHCAs) treated by EMS in Gyeonggi Provincial Fire and Disaster Headquarters from January to December in 2008 was conducted. The primary end-point was admission to emergency room. To clarify the factors through comparison of CASLs(n=58) with ROSCs & survivals(n=58), Answer Tree analysis for data mining with the CHAID algorithm was performed and alpha was set at .05. Mean, median, and percentile of time intervals, distances, and age on the 58 CASLs, 75 ROSCs, and 27 survivals(patients admitted to emergency room) were analysed. Results : Fourteen CASLs(24.1%), 41 ROSCs(54.7%), 16 survivals(59.3%) were treated with CPR within 5 min., and only 2 CASLs(3.4%), 11 ROSCs(14.7%), 10 survivals(37.0%) were treated with defilbrillation within 10 min. from arrest. If time recording from arrest to defilbrillation, the patients were classified 81.0%($X^2=9.83$, p=.005) into ROSCs & survivals. And the patients with no history, 100.0%($X^2=5.44$, p=.020). The other patients with no intention, 87.5%($X^2=7.00$, p=.024). Whereas the other patients with intention, treated with CPR after 4 min. from arrest were classified 67.2%($X^2=3.99$, p=.046) into CASLs. Conclusion : CPR within 4 minutes was the most important factor that discriminates between CASLs and ROSCs & survivals to record cardiac arrests-defilbrillation time. CPR within 4 min. from arrest, no history, and no intention were factors for improved ROSC & survival.

• 대한안전경영과학회지
• /
• 제7권5호
• /
• pp.59-67
• /
• 2005

The main objective of the statistical analysis about industrial accidents is to find out what is the dangerous factor in its own industrial field so that it is possible to prevent or decrease the number of the possible accidents by educating those who work in the fields for safety tools. However, so far, there is no technique of quantitative evaluation on danger. Almost all previous researches as to industrial accidents have only relied on the frequency analysis such as the analysis of the constituent ratio on accidents. As an application of data mining technique, this paper presents analysis on the efficiency of the CHAID algorithm to classify types of industrial accidents data and thereby identifies potential weak points in accident risk grouping.

• 대한안전경영과학회지
• /
• 제8권1호
• /
• pp.53-64
• /
• 2006

Many researches and analyses have been focused on industrial accidents in order to predict and reduce them. As a similar endeavor, this paper is to develop an expert system for prevention of industrial accidents. Although various previous studies have been performed to prevent industrial accidents, these studies only provide managerial and educational policies using frequency analysis and comparative analysis based on data from past industrial accidents. As an initial step for the purpose of this study, this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. Enterprise Miner of SAS and Answer Tree of SPSS will be used to evaluate the validity of the results of the four algorithms. The sample for this work was chosen from 10,536 data related to manufacturing industries during three years$(2002\sim2004)$ in korea. The initial sample includes a range of different businesses including the construction and manufacturing industries, which are typically vulnerable to industrial accidents.

• 산업공학
• /
• 제22권3호
• /
• pp.278-286
• /
• 2009

The anti-collision algorithms to identify a number of tags in real-time in RFID systems are divided into the anti-collision algorithms based on the Framed slotted ALOHA that randomly select multiple slots to identify the tags, and the anti-collision algorithms based on the Tree-based algorithm that repeat the questions and answer process to identify the tags. In the hybrid algorithm which is combined the advantages of these algorithms, tags are distributed over the frames by selecting one frame among them and then identified by using the Query tree frame by frame. In this hybrid algorithm, however, the time of identifying all tags may increase if many tags are concentrated in a few frames. In this study, to improve the performance of the hybrid algorithm, we suggest an improved algorithm that the tags select a specific group of frames based on the earlier bits of the tag ID so that the tags are distribute equally over the frames. By using the simulation and mathematical analysis, we show that the suggested algorithm outperforms traditional hybrid algorithm from the viewpoint of the number of queries per frame and the time of identifying all tags.

• 대한안전경영과학회지
• /
• 제7권4호
• /
• pp.61-71
• /
• 2005

Many researches have been focused on the analysis of industry disasters in order to reduce them. As a similar endeavor, this paper provides a propensity analysis of injured people from various industries using classification and regression tree(CART), a data mining algorithm. The sample for this work was chosen from 25,157data related to various industries during one year ( $2003.2\sim2004.1$ ) at Kangwon-Do in Korea. For the purpose of this paper, eight independent variables (injured date, injured time, injured month, type of Injured person, continuous service period, sex, company size, age)are taken from injured person group. According to the analysis result, it is found that five out of the eight factors that are predicted as significant have salient effects. Factors of season, time/hour, day of the week, or month which disasters happened do not show any significant effect. This paper provides common features of injured people. The provided analysis result will be helpful as a starting point for root cause analysis and reduction of industry disasters and also for development of a guideline of safety management.

• Journal of the Korean Data and Information Science Society
• /
• 제23권5호
• /
• pp.993-1003
• /
• 2012

한국남자프로농구 경기기록을 이용하여 승패결정요인을 분석하였다. 2010년 10월부터 2011년 3월까지, 2011년 10월부터 2012년 3월까지 치러진 정규리그 (540경기)의 기록을 분석하여 승패결정요인을 추정하였다. 한국농구연맹은 7개 공격변인과 7개 수비변인에 대한 자료를 제공하고 있다. 이들 자료 중에 공헌도와 공격력에 적용되는 6개 공격변인 (2점슛 성공률, 3점슛 성공률, 자유투 성공률, 공격리바운드, 어시스트, 턴오버)과 4개 수비변인 (수비리바운드, 스틸, 굿디펜스, 블록슛)이 승패에 미치는 영향을 통계적으로 분석하기 위해 로지스틱회귀분석과 의사결정나무분석을 적용하였다. 두 분석은 PASW와 Answer Tree 통계프로그램을 사용하였으며 모든 유의수준은 .05로 설정하였다. 로지스틱회귀분석 결과, 6개 공격변인 중 2점슛 성공률, 3점슛 성공률, 턴오버가 통계적으로 승패에 유의미한 영향을 미치고 4개 수비변인 중 굿디펜스를 제외한 수비리바운드, 스틸, 블록슛이 통계적으로 승패에 유의미한 영향을 미치는 것으로 나타났다. 그리고 공격변인 의사결정나무분석 결과에서는 2점슛 성공률이 51%-58%이며, 3P%가 31%를 초과하고 TO가 11개 이하일때 승리할 수 있는 확률이 80.85%로 가장 높게 나타났다. 이에 반해 수비변인 의사결정나무분석 결과, 수비리바운드가 24개를 초과하고 스틸이 6개를 초과하며, 블록슛이 2개를 초과할 때 승리할 수 있는 확률이 94.12%로 가장 높게 나타났다.