• 한국정보처리학회논문지
• /
• 제7권11호
• /
• pp.3408-3416
• /
• 2000

본 논문에서는 독립변수들의 특징을 추출하여 패턴층 뉴런의 중앙값을 이용함으로써 일반회귀 신경망의 성능을 개선하는 방법을 제안하였다. 제안된 방법에서는 적응적 학습 알고리즘의 주요성분분석 기법을 이용하여 회귀분석에 이용되는 데이터의 각 독립변수들의 집합으로 변환시키는 특징을 살려 일반회귀 신경망의 성능을 더 개선하기 위함이다. 제안된 기법의 일반회귀 신경망을 2개의 독립변수 집합을 가진 Solow의 경제문제와 4개의 독립변수 집합을 가진 국내 유선전화문제에 각각 적용하여 시뮬레이션한 결과, 중심값을 각 독립변수들의 평균이나 가중평균을 이용하는 일반회귀 신경망에 의한 결과와 비교할 때 더욱 우수한 회귀성능이 있음을 확인할 수 있었다. 그리고 신경망의 뉴런 수나 평활요소의 설정 면에서도 우수한 특성이 있음을 확인할 수 있었다.

• 소음진동
• /
• 제3권1호
• /
• pp.77-82
• /
• 1993

In general, the dynamic analysis with FEM(Finite Element Method) of large structures requires large computer memory space and long computational time. For the purpose of economical dynamic analysis of large structures, most of engineers want to use an efficient solution algorithm. This paper reports the modified CMS(Component Mode Synthesis) method which uses more efficient algorithm than the classical CMS method. In this paper, it is shown that Ritz vector sets can play the role of normal mode vector sets of substurctures in the CMS algorithm. The modified CMS method has good convergence performance compared with that of the classical CMS method.

• Asian-Australasian Journal of Animal Sciences
• /
• 제4권3호
• /
• pp.245-250
• /
• 1991

Analysis of the characteristics and the grouping of the species of sown and weeds in artificial pastures was studied applying the principal component analysis method. Presency and coverage of six sown species and fifteen weed species which occurred in pastures of under-grazing and optimumgrazing were subject to analysis. From field survey, species were divided into three groups: the group A included five species such as Festuca arundinacea, Lolium perenne and Dactylis glomerata, etc., the group B included eleven species such as Polygonum longisetum, Agrostis alba and Rumex obtusifolius, etc., and the group C included five species such as Miscanthus sinensis, Rubus palmatus and Artemisia princeps, etc. The group A species corresponded to good pasture conditions and management. On the contrary, the group C species occurred in poor pasture conditions with inadequate management. The group B species corresponded to intermediate pasture conditions and management. Interrelated pair species co-existing and species non-co-existing were discovered. Factor loading as negative for the group A species. positive for the group C species and positive but lower than the group C species for the group B species. From these results it is concluded that the principal component analysis seems to one of the useful tools for the analysis of characteristics of species and the diagnosis of sown pasture vegetation, although further studies are required to get more general information about species characteristics.

• 대한기계학회논문집A
• /
• 제26권6호
• /
• pp.1085-1091
• /
• 2002

General vehicle is evaluated by its acceleration, fuel economy, NVH (Noise, Vibration and Harshness) and subjective (such as launching feel) performance. The first step to enhance its performance is to know how much each component affects on the vehicle performance. It is very important to know what is the key factor of the component among many specifications. Hydraulic torque converter can be expressed by means of its performance curve (torque ratio and capacity factor). In this paper, the key factor of torque converter, which affect vehicle performance, are explored by using Taguchi method. Moreover, general sensitivity analysis method is compared with Taguchi's experiment.

• 한국정밀공학회지
• /
• 제11권6호
• /
• pp.65-74
• /
• 1994

Various substructure synthesis methods, such as component mode synthesis, building block analysis and reduced impedance method, are studied for the determination of vibration characteristics of plate problems. Comparisons are made for each methods in terms of accuracy and computational efficiency. Following conclusions are made from the results of computer simulations and experiments. i) The computation time of component mode synthesis is much shorter than that of whole structure analysis. The natural frequencies of lower modes obtained from component mode synthesis are almost same as those obtained from whole structure analysis, but in higher modes the differences between those two methods are increases. ii) The transfer function obtained from building block analysis is same as that obtained from the finite element method. iii) Same transfer functions can be obtained by the reduced impedance method. The computation time of reduced impedance mathod is shorter that that of general finite element method, but for the solutions in broad frequency band it requires long calculation time.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권6호
• /
• pp.2289-2295
• /
• 2015

The paper presents the incidence rates of malignant tumors of the central nervous system assessed by the component analysis. The data on primary registered cases of malignant tumors of the central nervous system in the country were used as the material of the study for the period from 2004 to 2011. A general trend of increase in the number of patients with malignant tumors of the central nervous system in Kazakhstan was determined and the potential of their increase was evaluated, which can be due to changes in the morbidity risk and age specifics, as well as the increase in population.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권3호
• /
• pp.1945-1949
• /
• 2013

Esophageal cancer (EC) incidence rates in Kazakhstan were assessed by component analysis based on primary registered cases in 2001-2010. It was found that despite an apparent general decrease in the number of EC patients in Kazakhstan, a potential increase should be evaluated, due to changes in aging as well as the increase in population. Some problems of EC patients' registration were broached with an emphasis on the importance of the expected absolute number and reasons for undercounting in the country. Based on these, ways of improving the recording and registration of such patients in the country were suggested.

• Journal of the Optical Society of Korea
• /
• 제12권3호
• /
• pp.121-125
• /
• 2008

We address the problem of Blind Source Separation(BSS) of superimposed signals in situations where one signal has constant or slowly varying intensities at some consecutive locations and at the corresponding locations the other signal has highly varying intensities. Independent Component Analysis(ICA) is a major technique for Blind Source Separation and the existing ICA algorithms fail to estimate the original intensities in the stated situation. We combine the advantages of existing sparse methods and Kernel ICA in our technique, by proposing wavelet packet based sparse decomposition of signals prior to the application of Kernel ICA. Simulations and experimental results illustrate the effectiveness and accuracy of the proposed approach. The approach is general in the way that it can be tailored and applied to a wide range of BSS problems concerning one-dimensional signals and images(two-dimensional signals).

• 산업경영시스템학회지
• /
• 제38권1호
• /
• pp.143-151
• /
• 2015

In this paper, we investigate how the power consumption of a heat pump dryer depends on various factors in the drying process by analyzing variables that affect the power consumption. Since there are in general many variables that affect the power consumption, for a feasible analysis, we utilize the principal component analysis to reduce the number of variables (or dimensionality) to two or three. We find that the first component is correlated positively to the entrance temperature of various devices such as compressor, expander, evaporator, and the second, negatively to condenser. We then model the power consumption as a multiple regression with two and/or three transformed variables of the selected principal components. We find that fitted value from the multiple regression explains 80~90% of the observed value of the power consumption. This results can be applied to a more elaborate control of the power consumption in the heat pump dryer.

• 농촌계획
• /
• 제14권1호
• /
• pp.33-41
• /
• 2008

The main entrance is even disappeared nowadays when the component type is changed, because it loses the actual function. On the other hand, the type of main entrance is changed variously depended on the materials for house and method of construction. Eleven points in the Chungyang-Gun where the environment of rural villages is well maintained was choosed researched to make data. These data of visual component elements were analysed by using the SPSS 12.0 Windows. Cluster Analysis and Factor Analysis was performed to analyze the different types of main entrance in the rural villages. From the above research, we could conclude below results. Research result, The whole quality of the farming village gate with fine feeling and constant temperature characteristic order appeared with the fact that preference quality is highest, in afterwords was analyzed. Also the research which sees led and the result which appears from the landscape quality analysis which the residential gates are general and type by landscape quality analysis the result which appears with the comparative analysis overcomes the limit which the residential gates are general and type by landscape quality analysis the result which appears with the comparative analysis overcomes the limit which the abstractive landscape image has. Like this research result judges currently the research which is meaning which provides a planning standards and the guideline which the governmental department and the rural village improvement enterprising public opinion rural village residential enterprise which is propelling from oneself are detailed. Specially about landscape quality of the residential gate that presents a type classification and preference quality from the actual condition where the research is insufficient the hereafter rural village improvement enterprise specially, sees with the fact that will be the possibility of affecting is meaning to residential section the succeeding researches actively, there being could be advanced, wishes.