• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.262-267
• /
• 2007

퍼지 ART 알고리즘에서 경계 변수는 패턴들을 클러스터링하는데 있어서 반지름 값이 되며 임의의 패턴과 저장된 패턴과의 불일치(mismatch) 허용도를 결정한다. 이 경계 변수가 크면 입력 벡터와 기대 벡터 사이에 약간의 차이가 있어도 새로운 카테고리(category)로 분류하게 된다. 반대로 경계 변수가 작으면 입력 벡터와 기대 벡터 사이에 많은 차이가 있더라도 유사성이 인정되어 입력 벡터들을 대략적으로 분류한다. 따라서 영상 인식에 적용하기 위해서는 경험적으로 경계 변수를 설정해야 단점이 있다. 그리고 연결 가중치를 조정하는 과정에서 학습률의 설정에 따라 저장된 패턴들의 정보들이 손실되는 경우가 발생하여 인식율을 저하시킨다. 본 논문에서는 퍼지 ART 알고리즘의 문제점을 개선하기 위하여 퍼지 논리 접속 연산자를 이용하여 경계 변수를 동적으로 조정하고 저장 패턴들과 학습 패턴간의 실제적인 왜곡 정도를 충분히 고려하여 승자 노드로 선택된 빈도수를 학습률로 설정하여 가중치 조정에 적용한 개선된 퍼지 ART 알고리즘을 제안하였다. 제안된 방법의 성능을 확인하기 위해서 실제 영문 명함에서 추출한 영문자들을 대상으로 실험한 결과, 기존의 ART1과 ART2 알고리즘이나 퍼지 ART 알고리즘보다 클러스터의 수가 적게 생성되었고 인식 성능도 기존의 방법들보다 우수한 성능이 있음을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.15 no.1
• /
• pp.475-481
• /
• 2015

We use polynomial regression instead of linear regression if there is a nonlinear relation between a dependent variable and independent variables in a regression analysis. The performance of polynomial regression, however, may deteriorate because of the correlation caused by the power terms of independent variables. We present a polynomial regression model for the numerical inversion of PGF and show that polynomial regression results in the deterioration of the estimation of the coefficients. We apply principal components regression to the polynomial regression model and show that principal components regression dramatically improves the performance of the parameter estimation.

• Database Research
• /
• v.34 no.3
• /
• pp.159-169
• /
• 2018

Discretization of continuous variables intended to improve the performance of various algorithms such as data mining by transforming quantitative variables into qualitative variables. If we use appropriate discretization techniques for data, we can expect not only better performance of classification algorithms, but also accurate and concise interpretation of results and speed improvements. Various discretization techniques have been studied up to now, and however there is still demand of research on discretization studies. In this paper, we propose a new discretization technique to set the cut-point using Wasserstein distance with considering the distribution of continuous variable values with classes of data. We show the superiority of the proposed method through the performance comparison between the proposed method and the existing proven methods.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.7
• /
• pp.791-798
• /
• 2011

All mechanical-system parameters have uncertainty, and this uncertainty directly affects system performances and results in a decrease in the manufacturing outputs. In particular, since the size of a MEMS system is extremely small, the manufacturing tolerances of a MEMS system are relatively large when compared to the tolerances of a macro-scale system. High manufacturing tolerances result from an increase in the uncertainty of the system parameters, thereby affecting the performances and manufacturing yields. In this paper, the performance uncertainty of a MEMS accelerometer due to system parameter uncertainty is analyzed by using several uncertainty analysis methods. Finally, the performance distributions and manufacturing yields of the MEMS accelerometer are predicted.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.10 no.3
• /
• pp.82-89
• /
• 2006

Recently operation and maintenance cost of gas turbine engines has been issued as a major parameter in terms of designing and manufacturing. Accordingly, the conception that the maintenance and repair of an engine has to be conducted in assembled condition has been spreaded out. However, it is possible only if the prediction of the engine performance is clearly identified. In this study, therefore, a diagnostic code of the engine performance has been developed by using GPA(Gas Path Analysis) and Fuzzy Logic which can analyze the engine performance and estimate the health parameters. The prediction of the quantitative performance deterioration of the established model of the turbo-shaft engine for SUAV has been achieved in a satisfied level compared to that obtained by GSP code.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.04a
• /
• pp.287-291
• /
• 1995

다구찌 방법을 이용하여 안정거울 시스템의 민감도 해석, 강건설계 및 공차설계를 행하였다. 민감도 해석을 통해 안정거울 시스템의 안정화 성능에 크게 영향을 미치는 7개의 중요한 설계변수를 도출하였다. $m_{M}$이 안정화 성능에 가장 크게 영향을 주므로 공차범위를 줄여야 한다. $m_{M}$, $m_{B}$, $K_{MB}$ , $p_{3}$, $b_{3}$는 공차범위가 크게 안정화 성능에 영향을 미치지 못함을 알 수 있다. 기타의 변수들은 각각 하한공차 및 상한공차로 주어진다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.36 no.6
• /
• pp.583-591
• /
• 2012

Plate heat exchangers have been widely used in many industrial applications because of their compactness and high efficiency. Even though plate heat exchangers have been investigated extensively, studies on the effects of geometric parameters other than the chevron angle are very limited in the open literature. In this study, the effects of the chevron angle, corrugation length, corrugation depth, and the number of plates on the heat transfer and pressure drop characteristics of plate heat exchangers were investigated experimentally. Based on the experimental results, empirical correlations were proposed. More than 95% of the predictions made based on the correlations had relative deviations of less than ${\pm}10%$ when compared with the measured data.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.4
• /
• pp.60-68
• /
• 2003

In this study, a steady state performance analysis program was developed for a turbofan engine, and its performance was analyzed at installed conditions. For the purpose of evaluation, the developed program was compared with the performance data provided by the engine manufacturer. It was confirmed that the developed program was reliable because the results by the developed program were well agreed with those by the engine manufacturer within 3.5%. The non-linear GPA(Gas Path Analysis) program for performance diagnostics were developed, and selection of optimal measurement variables was studied. Furthermore, in order to investigate effects of the number and the kind of measurement variables, the non-linear GPA was analyzed with various measurement sets. Finally, the measurement parameters selected in the previous step were applied to the fault detection analysis of the 2-spool separate flow type turbofan engine.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.2
• /
• pp.114-123
• /
• 2018

Wind power tower (WPT) has been used to augment the performance of vertical axis wind turbine (VAWT). However, the performance of the WPT depends on several design parameters, such as inner and outer radius, or number of guide walls. Therefore, an experimental study was conducted to investigate efficient design parameters on the WPT. A wind tunnel was utilized and its test section dimension was 2m height and 2.2m width. One story model of the WPT was manufactured with seven guide walls and a VAWT was installed within the WPT. Three different sizes of guide walls were applied to test with various design parameters. The power coefficients were measured along the azimuthal direction in a state of equal inlet velocity in order to compare its performance relatively. The experimental results showed that the gap between the inner radius of the WPT and the rotating radius of the VAWT was a major parameter to improve the performance of VAWT within the WPT.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.30 no.1
• /
• pp.105-113
• /
• 2002

In this study, the steady state performance analysis program was developed for a turboprop engine, and its performance was analyzed at uninstalled and installed conditions. For the purpose of evaluation the developed program was compared with the performance data provided by the engine manufacturer and analysis results of GASTURB8.0 program. It was confirmed that the developed program was reliable because the results by the developed program were well agreed with those by GASTURB8.0 within %%. The linear and non-linear GPA(Gas Path Analysis) programs for performance diagnotics were developed, and selection of optimal measurement variables was studied. Furthermore, in order to investigate effects of the number and the kind of measurement variables, the linear and non-linear GPAs were analyzed with various measurement set. If the measurement parameters were properly selected, the reliable and economic faults detection might be possible even thought the small number of measuring parameters were used.