• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.201-206
• /
• 2008

본 논문은 한국어 문서 감정분류에 기반이 되는 감정 자질의 가중치 강화를 통해 감정분류의 성능 향상을 얻을 수 있는 기법을 제안한다. 먼저, 어휘 자원인 감정 자질을 확보하고, 확장된 감정 자질이 감정 분류에 얼마나 기여하는지를 평가한다. 그리고 학습 데이터를 이용하여 얻을 수 있는 감정 자질의 카이 제곱 통계량(${\chi}^2$ statics)값을 이용하여 각 문장의 감정 강도를 구한다. 이렇게 구한 문장의 감정 강도의 값을 TF-IDF 가중치 기법에 접목하여 감정 자질의 가중치를 강화시킨다. 마지막으로 긍정 문서에서는 긍정 감정 자질만 강화하고 부정 문서에서는 부정 감정 자질만 강화하여 학습하였다. 본 논문에서는 문서 분류에 뛰어난 성능을 보여주는 지지 벡터 기계(Support Vector Machine)를 사용하여 제안한 방법의 성능을 평가한다. 평가 결과, 일반적인 정보 검색에서 사용하는 내용어(Content Word) 기반의 자질을 사용한 경우 보다 약 2.0%의 성능 향상을 보였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.889-892
• /
• 2013

본 논문에서는 급성 복증을 주소로 야간 응급실 내원 시 영상의학과 전문의 부재 등과 관련된, 급성 충수 돌기염 진단을 위한 복부 초음파 검사의 환자 대기 시간과 충수 돌기 절제술 시행까지 환자 대기 시간을 분석한다. 응급실 내원 환자 41.5%에서 초음파 검사 대기 시간은 10시간 이상으로 나타났고, 외래 내원 환자의 45.2%는 수술 대기 시간이 18시간 이상으로 나왔다. 이는 초음파 검사의 대기 시간이 수술 대기 시간에 영향을 미치는 것으로 카이제곱검증에서 유의하게 나왔다(p<0.05). 따라서 본 논문에서는 환자들의 대기 시간을 감소시키기 위한 방법으로 응급실 의료진의 초음파 검사 시행에 따른 유익성과 급성 충수 돌기염의 특징을 이용한 의료 영상 분석, 연구의 필요성을 제안한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.25-28
• /
• 2011

In this paper, we study some properties of condition for fuzzy data, agrement index by ratio of area and the uniformly most powerful fuzzy test of hypothesis. Also, we suggest a confidence bound for uniformly most powerful fuzzy test. For illustration, we take the most powerful critical fuzzy region from exponential distribution by likelihood ratio and test the hypothesis of ${\chi}^2$-distribution by agreement index.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.2
• /
• pp.483-490
• /
• 1997

The evalution of the cumulative distridution function of the noncentral $X^2$ distribution required in approxi-mate determination of the $X^2$ test. Many approximations to the cumulative distribution function of the noncentral $X^2$ distribution have been suggested. However, in selecting an approximations both simplicity and accuracy should be considered. In this note we compared various approximations in terms of accuracy and efficiency.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.227-234
• /
• 2012

Hamming distances in medical science are used for the diagnosis of diseases. The differences of the distances, however, are often very small, and is not in the general statistical form such as normal or chi-square distribution. In this study, we explore the characteristics and significance of the differences of Hamming distances generated in medical diagnosis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.365-368
• /
• 2012

어의 중의성 해소는 자연어처리에서 중요한 역할을 한다. 감독 중의성 해소 방법은 비감독 중의성 해소 방법보다 높은 성능을 나타내지만, 구축비용이 큰 대규모 의미부착 말뭉치가 필요하다. 본 논문에서는 중국어 어휘의미망(HowNet)과 의미 미부착 말뭉치를 이용한 중국어 비감독 어의 중의성 해소 방법을 제안한다. 의미 미부착 말뭉치에서 통계정보를 추출하고, 중국어 어휘 의미망에서 중의성 어휘의 의미별 형제어를 추출하여 중의성 어휘의 주변 문맥에 나타나는 어휘와 카이제곱검정(${\chi}^2$-test)에 의한 독립성 검정을 통해 어휘 간 연관성을 판단하고 중의성 해소를 한다. 본 논문에서 제안한 중의성 해소방법의 성능을 SemEval-2007 평가데이터에서 측정한 결과 명사와 동사에서 각각 64.7%, 49.4%를 나타냈다. 이는 SemEval-2007 중국어 비감독 중의성 해소에서 가장 높은 성능을 나타낸 시스템보다 13.1%, 13.9% 높은 성능이다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.363-371
• /
• 2019

The purpose of this research is to provide data for the relations between lifestyle, stress and hypertension in a group of construction Temporary employee. The methods taken in this study was to survey the general characteristics and stress in the group, and figure out the relations between lifestyle and hypertension. This study targeted at 301 Temporary employee. in Young-dong for six months (2014~2015). Data analysis used errors and percentages, chi-square tests, one-way ANOVA analysis, independent sample t-test, chi-square test and multivariate logistic regression. The study shows that no relations between age and hypertension, but according to job characteristics, aggravate lifestyle just like smoking(P=0.049), eating habit(P=0.012), physical(p=0.022) & psychological(p=0.011) state there is an effect on hypertension. Based on the results of this study, it is found that temporary workers in small and medium-sized construction companies with high work-related disaster rates need to improve their living habits and physical psychological conditions and manage high blood pressure, as well as research and management of chronic diseases such as obesity, diabetes and dyslipidemia.

• Journal of KIISE:Software and Applications
• /
• v.35 no.6
• /
• pp.374-385
• /
• 2008

Speech act tagging is an important step in various dialogue applications, which recognizes speaker's intentions expressed in natural language utterances. Previous approaches such as rule-based and statistics-based methods utilize the speech acts of previous utterances and sentence features of the current utterance. This paper proposes a method that determines speech acts of the current utterance using the speech acts of the following utterances as well as previous ones. Using the features of following utterances yields the accuracy 95.27%, improving previous methods by 3.65%. Moreover, sentence features of the previous utterances are employed to maximally utilize the information available to the current utterance. By applying the proper probability model for each speech act, final accuracy of 97.97% is achieved.

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.489-495
• /
• 2018

The purpose of this study was to investigate the effect of fouls on performance in field hockey games. A total of 33 matches and 2101 fouls from 10 teams participated in the 2017 World League SEMI-FINAL tournament were analysed by region, race, type, and cause. The total data that is analysed by SportsCode and SPSS(correlation analysis & chi-square test)have showed that the top ranked countries had a higher foul frequency than the lower ranked nations. According to the situation that has showed the result of the analysis, it showed that there was no difference between the results analysed on the foul type and the attacking and defence situation but it has indicated that area, game situation and the cause of fouls showed there was a significant difference. On these results, it is hoped to use fouls as one of the tactical means in women's field hockey games.

• International Journal of Highway Engineering
• /
• v.11 no.2
• /
• pp.17-25
• /
• 2009

The goal of this study is to develop Logistic regression model by accident location(entry section, exit section, inside intersection and pedestrian crossing section). Based on the accident data of Chungbuk Provincial Police Agency(2004$\sim$2005) and the field survey data, the geometric elements, environmental factor and others related to traffic accidents were analyzed. Developed models are all analyzed to be statistically significant(chi-square p=0.000, Nagelkerke $R^2$=0.363$\sim$0.819). The models show that the common factors of accidents are the traffic volume(ADT), distant of crossing and exclusive left turn lane, and the specific factors are the minor traffic volume(inside intersection model) and U-turn of main road(pedestrian crossing model). Hosmer & Loineshow tests are evaluated to be statistically significant(p$\geqq$0.05) except the entry section model. The correct classification rates are also analyzed to be very predictable(more than 73.9% to all models).