• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.574-576
• /
• 2007

판례 자동분류 시스템은 일반적인 문서 자동분류 시스템과 기본적인 동작방법은 동일하다. 본 논문에서는 노동법에 관련된 판례를 대상으로 지지벡터기계(SVM), 단일 의사결정나무, 복수 의사결정나무, 신경망 기법 등을 사용하여 문서의 자동 분류 실험을 수행하고, 판례분류에 가장 적합한 기계학습기법이 무엇인지를 실험해 보았다. 실험 결과 복수 의사결정나무가 93%로 가장 높은 정확도를 나타내었다.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2017.11a
• /
• pp.1523-1529
• /
• 2017

신정부의 탈원전 정책에 의해 급속하게 원자력계를 둘러싼 환경이 변하고 있다. 지금까지의 정부가 추진해온 원자력 중심의 전원계획이 신재생에너지 확대를 위한 계획으로 변화되어 가고 있다. 그리고 이러한 정부 정책 추진의 중심에는 매우 높은 대통령 지지율이 기반이 되고 있다. 하지만 여러 여론 조사 결과를 살펴보면 대통령은 약 65% 내외의 지지를 기록함에도 불구하고 원자력 활용에 대해서는 찬반 의견이 매우 팽팽하다. 즉, 원자력에 대한 이슈가 최근 에너지, 경제 문제가 아닌 정치 이슈가 된 상황에서도 원자력에 대해 지지를 보여주는 집단이 존재한다는 것을 뜻한다. 하지만 원자력을 지지하는 일반인들이 정치권과 탈핵 시민단체에서 원자력 분야를 소위 '적폐'로 규정하고 '원자력 마피아'로 명명한 상태에서 원자력에 대해 드러내놓고 지지하는 것은 쉽지 않다. 따라서 본 연구는 우리나라의 어떠한 계층에서 원자력을 지지하는지, 즉 'Shy Nuclear'를 찾고 이 지지층들의 특징에 대해서 분석하였다. 지지층 분류를 위해서 머신러닝의 분류분석 기법인 Decision Tree Analysis(의사결정나무) 방법론을 활용하였다. 분석 결과 Shy Nuclear를 결정하는 주 요인은 거주지역으로 나타났다. 아울러 수도권에 거주하고 있는 사무/관리/전문직/퇴직자 집단이 가장 원자력에 높은 호감도(긍정 76.1%)를 보여주었다.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.552-560
• /
• 2021

This study attempted to explore the experience of patients' having hypertension and diabetes participation in health care. 11 chronic patients who regularly visited community health centers for more than a year participated in this study. The data was collected through individual interviews and analyzed by thematic analysis method. As a result, 6 sub-themes and 3 themes derived from the data. The themes were 'Trying to utilize short consultation time efficiently', 'Answering within narrow limits to healthcare provider', 'Being lack of continuous motivation for health care'. The result showed the need for nurses to provide accurate and sufficient health information and motivate patients in supportive manner to encourage chronic patients' participation in health care.

• 대한공업교육학회지
• /
• v.34 no.2
• /
• pp.304-320
• /
• 2009

This study was performed to grasp relations between different sub-factors of youths' leadership living skills and between the sub-factors of youths' leadership living skills and personal features (support by parents, support by peers, sense of self-respect, sense of self-effectiveness) in order to generally understand the characteristics of youths. The result and conclusion of this study are as follows. First, the sub-factors of youths' leadership living skills showed various kinds of correlations and especially, measures to improve learning ability skill, self-understanding skill and group activity skill are necessary for healthy and general growth in adolescence. Second, the sense of self-respect showed positive correlations with decision making skill and self-understanding skill and programs are to improve leadership living skill gradually and positively through the enhancement of the sense of self-respect. Third, the degree of support by peers showed relations with decision making skill and group activity skill meaning the importance of peer groups in adolescence and diverse measures to form peer groups are necessary.

• Journal of radiological science and technology
• /
• v.38 no.3
• /
• pp.295-304
• /
• 2015

This study intended to examine the correlation of career self-regulation (plan and check-up, positive thinking, career feedback, environment formation for career) and career identity (career decision, indecisiveness, career indecision) caused by parental career support (informative, emotional, financial, and empirical) among freshmen, sophomores, and juniors in the radiotechnology department. For assessment, a survey was conducted and according to the results, there existed correlation as follows. Regarding parental career support, emotional support is plan and check-up (r=.25, p<.001), Career feedback (r=.54, p<.001), and positive thinking (r=.46, p<.001) showed high positive correlation while informative support showed correlation in all factors showing high correlation with environment formation for career (r=.22, p<.001), plan and check-up (r=.20, p<.001), career feedback (r=.24, p<.001), and positive thinking (r=.26, p<.001). Financial support career feedback (r=.33, p<.001) and positive thinking (r=.34, p<.001) showed somewhat higher correlation. All factors of environment formation for career (r=.18, p<.001), plan and check-up (r=.25, p<.001), career feedback (r=.37, p<.001), and positive thinking (r=.30, p<.001) showed high correlation. Informative support showed high correlation only with career decision (r=.27, p<.001) and financial support also showed high correlation only with career decision (r=.18, p<.001). Also, empirical support was somewhat highly correlated only with career decision (r=.23, p<.001). Regarding school-year difference depending on parental career support, there was significant difference between emotional support (F=8.52, p<.001), financial support (F=8.97, p<.001), and empirical support (F=5.36, p<.05) while informative support was dismissed. Regarding school-year difference depending on career self-regulation, there was significant difference between career feedback (F=8.48, p<.001) and positive thinking (F=16.29, p<.001) while environment formation for career and plan and check-up were dismissed. Regarding school-year difference depending on career identity, there was significant difference between career indecision (F=4.01, p<.05) and career decision (F=11.72, p<.001) while indecisiveness was dismissed. According to the analysis results, parents' active support to their child like respecting and listening to their opinion on career, provision of career related experience or information, and provision of necessary financial aid for their study or academic preparation made the students plan and exploring their career, examine accomplishment progress, have positive idea to realize their objectives. In addition, the students were able to establish the objective of their career by forming the environment that helped them realize their objectives by seeking advices and encouragement from surroundings. Meanwhile, the parents' attitude to respect and listen to their child's career related opinion affected their career decision and indecision. Although informative support helped the students' career decision, financial and empirical support caused effect only to career decision.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.263-270
• /
• 2010

Data mining is the process of sorting through large amounts of data and picking out useful information. An important goal of data mining is to discover, define and determine the relationship between several variables. Association rule mining is an important research topic in data mining. An association rule technique finds the relation among each items in massive volume database. Association rule technique consists of two steps: finding frequent itemsets and then extracting interesting rules from the frequent itemsets. Some interestingness measures have been developed in association rule mining. Interestingness measures are useful in that it shows the causes for pruning uninteresting rules statistically or logically. This paper explores some problems for two interestingness measures, confidence and net confidence, and then propose a decision process for right association rule generation using these interestingness measures.

• Journal of Technology Innovation
• /
• v.24 no.4
• /
• pp.159-191
• /
• 2016

In order to deal with uncertainty and conflicting interests in technological risk policy-making, various participatory decision-making models have been practiced. This participatory approach is an alterative to the traditional process of science and technology policy-making where scientific experts provide evidence and government officials make decisions. However, there still remain different opinions on who should play what kind of role in decision-making process. Therefore this paper examines the division of labour in the public deliberations for radioactive waste management policy carried out in the UK and Korea. It discusses the ways in which various actors are defined, and the rationales are employed for allocating actors to certain roles and participatory methods. In so doing, this paper unfolds the ways in which the participatory decision-making process for risk governance is delivered in real policy context. Similarities and differences revealed in the division of labour of two cases contribute to development of radioactive waste management policy and the policy instruments for risk governance.

• The Korean Society of Law and Medicine
• /
• v.20 no.2
• /
• pp.43-82
• /
• 2019

In Korea surrogate medical decision makings happen without legal grounds. The purpose of this article is to research the issues in preparing policies for decision-making on behalf of unrepresented patients. As aspects of comparative law, there are two approaches. One of them is to regulate default surrogate list. If no agent or guardian has been appointed, some legislatures provide that members of patient's family who is reasonably available, in descending order of priority of not, may act as surrogate: (1) the spouse, unless legally separated; (2) an adult child; (3) a parent; or (4) an adult brother or sister. If none of them is eligible to act as surrogate, some legislatures allow close friends to make health-care decisions for adult individuals who lack capacity. On the other hand there are other legislatures which provide no surrogate decision maker list but oblige the responsible authority to determine with advice of family members or friends of the patient. In the end the first approach can not guarantee that the surrogate decision maker like family members or friends will determine in the best interest of the patient.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.285-290
• /
• 2018

논지가 높은 설득력을 갖기 위해서는 충분한 지지 근거가 필요하다. 논지 내의 주장을 논리적으로 지지할 수 있는 근거 자료 추출의 자동화는 자동 토론 시스템, 정책 투표에 대한 의사 결정 보조 등 여러 어플리케이션의 개발 및 상용화를 위해 필수적으로 해결되어야 한다. 하지만 웹문서로부터 지지 근거를 추출하는 시스템을 위해서는 다음과 같은 두 가지 연구가 선행되어야 하고, 이는 높은 성능의 시스템 구현을 어렵게 한다: 1) 논지의 주제와 직접적인 관련성은 낮지만 지지 근거로 사용될 수 있는 정보를 확보하기 위한 넓은 검색 범위, 2) 수집한 정보 내에서 논지의 주장을 명확하게 지지할 수 있는 근거를 식별할 수 있는 인지 능력. 본 연구는 높은 정밀도와 확장 가능성을 가진 지지 근거 추출을 위해 다음과 같은 단계적 지지 근거 추출 시스템을 제안한다: 1) TF-IDF 유사도 기반 관련 문서 선별, 2) 의미적 유사도를 통한 지지 근거 1차 추출, 3) 신경망 분류기를 통한 지지 근거 2차 추출. 제안하는 시스템의 유효성을 검증하기 위해 사설 4008개 내의 주장에 대해 웹 상에 있는 845675개의 뉴스에서 지지 근거를 추출하는 실험을 수행하였다. 주장과 지지 근거를 주석한 정보에 대하여 성능 평가를 진행한 결과 본 연구에서 제안한 단계적 시스템은 1,2차 추출 과정에서 각각 0.41, 0.70의 정밀도를 보였다. 이후 시스템이 추출한 지지 근거를 분석하여, 논지에 대한 적절한 이해를 바탕으로 한 지지 근거 추출이 가능하다는 것을 확인하였다.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1341-1348
• /
• 2013

To solve the classification problems, various data mining techniques have been applied to database marketing, credit scoring and market forecasting. In this paper, we compare various techniques such as bagging, boosting, LASSO, random forest and support vector machine with the daily lens transaction data. The classical techniques-decision tree, logistic regression-are used too. The experiment shows that the random forest has a little smaller misclassification rate and standard error than those of other methods. The performance of the SVM is good in the sense of misclassfication rate and bad in the sense of standard error. Taking the model interpretation and computing time into consideration, we conclude that the LASSO gives the best result.