• The Journal of Korean Association of Computer Education
• /
• v.8 no.6
• /
• pp.113-121
• /
• 2005

Since documents on the Web are naturally partitioned into many document databases, the efficient information retrieval (IR) process requires identifying the document databases that are most likely to provide relevant documents to the query and then querying the identified document databases. We first introduce a neural net agent for such an efficient IR, and then propose the hierarchically organized multi-agent IR system in order to scale our agent with the large number of document databases. In this system, the hierarchical organization of neural net agents reduced the total training cost at an acceptable level without degrading the IR effectiveness in terms of precision and recall. In the experiment, we introduce two neural net IR systems based on single agent approach and multi-agent approach respectively, and evaluate the performance of those systems by comparing their experimental results to those of the conventional statistical systems.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.6-7
• /
• 2011

본 논문에서는 지역적 학습 방법을 활용하는 Average Neighborhood Margin Maximization(ANMM)에 기반하여 피부색과 비피부색 영역을 분리하는 이진 분류의 통계적 접근법을 제안한다. Fisher Linear Discriminant(FLD)와 Average Neighborhood Margin Maximization(ANMM)의 피부색과 비피부색 클래스 내 분산 대비 클래스 간 분산의 비교를 통해 두 클래스 간 분리력 변화를 확인한다. 교사(Supervised) 이진 분류문제에 대하여 Small sample size(SSS) 문제, 가우시안 분포 가정의 문제, 최대 추출 가능 특징 수 제한 문제 등을 해결함과 동시에, 지역적 특성 학습 방법의 도입을 통해 피부색과 비피부색 간 분리력을 향상시킨다.

• The Journal of the Korea Contents Association
• /
• v.5 no.5
• /
• pp.266-272
• /
• 2005

This study is to empirically analyze the effects on job performance of Accounting Information Systems, Analysis methods were used to Cronbach's Alpha analysis, Factor analysis, analysis of variance(ANOVA) and regression in odor by the contingency grouping method. The results of this study are as follows : First, The regression analysis had effects on AIS utility and job performance. Second, The Analysis of variance(ANOVA) had non-effects on systems operating degree and systems satisfaction. Third, The input variables of information accuracy and systems satisfaction had additional effect about IT capability.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.511-520
• /
• 2013

Detection outliers and robust estimators are crucial in regression models with outliers. In such studies the focus is on detecting outliers and estimating the coefficients using leave-one-out. Our study introduces Rice estimator which is an error variance estimator without estimating the coefficients. In particular, we study a comparison of the statistical properties for Rice estimator with and without outliers in simple regression models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.225-228
• /
• 2021

동형암호를 이용한 통계 분석은 기존의 개인정보보호 문제로 수행할 수 없었던 데이터에 대해서 통계분석이 가능하게 만든다. 본 논문에서는 대용량 데이터에 사용되는 대표적 통계 수치인 평균, 분산, 왜도, 첨도를 병렬처리를 사용하여 구하는 방법을 제안한다. 또한, 연산이 비교적 제한적인 동형암호에서도 통계적 수치를 구하기 위하여 동형암호문끼리의 뺄셈, 나눗셈, 제곱근 연산을 제안한다. 이를 통해, 분산된 대용량 데이터에 대해서도 동형암호를 통해 다양한 통계 연산이 가능할 것으로 기대된다.

• Information and Communications Magazine
• /
• v.15 no.2
• /
• pp.61-82
• /
• 1998

무선 ATM의 MAC 프로토콜은 독립적으로 분산되어 있는 이동 단말기들을 대상으로 ATM이 추구하는 진정한 의미의 통계적 다중화 기능을 무선 매체를 통해 확장하는 역할을 한다. 이와 같은 매체 접근 제어 프로토콜을 통해서만 멀티미디어 서비스 특성에 따라 동적으로 변하는 대역 요구 사항과 지연 시간 및 셀 손실 등의 서비스 품질을 동시에 만족시킬 수 있으며, 이동 단말기들이 채널을 공평하면서도 효율적으로 사용할 수 있는 접속 환경을 제공할 수 있다. 따라서, 이와 관련한 유럽의 ACTS 프로젝트 및 제외국에서의 기술 개발 사례와 ATM Forum WATM-WG에서의 표준화 동향을 분석하여 향후 무선 ATM 구현에 필요한 요소 기술로서의 매체 접근 제어 방식의 설계 및 구현 방안에 대해서 고찰함으로써 향후 연구 방향을 제시하고자 한다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1991.10a
• /
• pp.423-439
• /
• 1991

본 연구의 목적은 당제철소에서 생산하는 제품중 전기강판 방향성 제품의 제질(철손) 불량원인을 추적하여 조업 guidance를 제시하는 model개발이다. model개발은 현장조업 data에 대해 상관분석, 회귀분석, 분산분석등의 통계적분석을 통하여 재질에 영향을 미치는 주 관련인자들의 조업기준 재정립과 menu화면에 의한 자동 불량원인 추적 model을 개발하였으며, model개발을 위한 사용 tool은 SAS package를 활용하였다.

• Culinary science and hospitality research
• /
• v.21 no.6
• /
• pp.49-62
• /
• 2015

Give that statistical analysis is an essential component of foodservice-related research, the purpose of this review is to analyse research trends of statistical methods applied to foodservice-related research. To achieve these objective, this study carried out a content analysis on a total of 251 out of 415 research articles published in The Korean Journal of Culinary Research(TKJCR) from January 2010 to December 2013. Of the total 164 research articles focussing on natural science research, qualitative research, articles written in English were excluded from the scope of this study. The results of this study are as follows. First, it turned out that 269 research articles applied quantitative research methods, and only 10 articles applied qualitative research methods among the 279 research articles based on social science research methods. Second, 20 article (8.0%) among the 251 did not specify the statistical methods or computer programs that were used for statistical analysis. Third, it was found that 228 articles (90.8%) used the SPSS program for data analysis. Fourth, in terms of frequency of use, it was revealed frequency analysis was most used, followed in order by reliability analysis, exploratory factor analysis, correlation analysis, regression analysis, structural equation modeling, confirmatory factor analysis, t-test, variance analysis, and cross tabs analysis, However, 3 out of 56 research articles that used a t-test did not suggest a t-value. 10 out of 64 articles that used ANOVA and demonstrated a significant difference in between-group mean did not conducted post-hoc test. Therefore, the researchers with interest in foodservice fields need to keep in mind that choosing and applying the correct statistical technique both determine the value and the success or failure of a study. To enhance the value and success of a study, it is necessary to use the proper statistical technique in an efficient way in order to prevent statistical errors.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.707-716
• /
• 2006

When the regression function is discontinuous at a point, the variance function is usually discontinuous at the point. In this case, we had better propose a test for the existence of a discontinuity point with the regression function rather than the variance function. In this paper we consider that the variance function only has a discontinuity point. We propose a nonparametric test for the existence of a discontinuity point with the second moment function since the variance function and the second moment function have the same location and jump size of the discontinuity point. The proposed method is based on the asymptotic distribution of the estimated jump size.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2A
• /
• pp.119-127
• /
• 2006

In this two-part paper, we consider dynamic resource allocation in orthogonal frequency division multiple access(OFDMA). To reduce the reverse link overhead for channel quality information(CQI) feedback, a set of sub-carriers are tied up to a sub-channel to be used as the unit of CQI feedback, user-multiplexing and the corresponding power/rate allocation. Specifically, we focus on two sub-channel structures, either aggregated or distributed, where the SNR distribution over a sub-channel is modeled as Ricean in general, and the channel quality of a sub-channel is summarized as the mean and variance of channel gain envelop divided by noise standard deviation. Then, we develop a generalized two step channel/resource allocation algorithm, which uses the two statistical measurements, and analyze the spectral efficiency of the OFDMA system in terms of average frequency utilization. An extension to proportional fair algorithm will also be addressed. As confirmed by numerical results, the aggregated structure is preferred especially when intending aggressive link adaptation.