• 대한토목학회논문집
• /
• 제38권6호
• /
• pp.801-808
• /
• 2018

선형회귀모형의 학습은 일반적으로 자료의 개수가 설명변수의 개수보다 충분히 크고, 설명변수들 사이에 심각한 다중공선성이 없다는 가정 하에서 안정적으로 이루어진다. 본 연구에서는 이러한 가정이 위배되었을 경우 모형 학습의 어려움을 실제 호우피해자료를 분석함으로써 조명하였고, 이를 해결하기 위해 자료를 통합한 다음 주성분회귀모형 또는 능형회귀모형을 사용할 것을 검토하였다. 모형의 학습에 사용된 자료와 별도의 독립된 자료에서 제안된 모형들의 예측력을 평가하였고, 제안된 방법이 선형회귀모형보다 더 나은 예측력을 보이는 것을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.664-667
• /
• 1997

For higher component density per chip, it is necessary to identify and control the semiconductor manufacturing process more stringently. Recently, neural networks have been identified as one of the most promising techniques for modeling and control of complicated processes such as plasma etching process. Since wafer states after each run using identical recipe may differ from each other, conventional neural network models utilizing input factors only cannot represent the actual state of process and equipment. In this paper, in addition to the input factors of the recipe, real-time tool data are utilized for modeling of 64M DRAM s-poly plasma etching process to reflect the actual state of process and equipment. For real-time tool data, we collect optical emission spectroscopy (OES) data. Through principal component analysis (PCA), we extract principal components from entire OES data. And then these principal components are included to input parameters of neural network model. Finally neural network model is trained using feed forward error back propagation (FFEBP) algorithm. As a results, simulation results exhibit good wafer state prediction capability after plasma etching process.

• 천문학회보
• /
• 제36권2호
• /
• pp.100.1-100.1
• /
• 2011

Everybody wants to see the future, but nobody does for sure. Reliably forecasting the solar activity in the near future looks like an easy task, but in fact still remains one of difficult problems in the solar-terrestrial research. We have sought for good univariate methods that can predict future smoothed sunspot numbers reasonably well based on past smoothed sunspot number data only. Here we consider a specific method we call principal component-and-autoregression (PCAR) method. The variation of sunspot number during a period of finite duration (past) before an epoch (present) is modeled by a linear combination of a small number of dominant principal components, and this model is extended to the period (future) beyond the epoch using the autoregressive model of finite order. From the application of this method, we find that the $24^{th}$ solar maximum is likely to occur near the end of the year 2013 (and there is a possibility that it occurs earlier near the start of 2013), and to have a peak sunspot number of about 86, indicating that the activity of the $24^{th}$ cycle will be weaker than the average. We will discuss how much this estimate is reliable.

• 응용통계연구
• /
• 제19권3호
• /
• pp.431-445
• /
• 2006

본 연구는 함수적 데이터 분석의 몇 가지 이론에 대해 소개하고 분석 기법을 실제 자료에 적용하는 내용을 다루었다. 함수적 데이터 분석의 이론적 내용으로 기저를 이용해 자료를 함수적 데이터로 표현하는 방법, 그리고 함수적 데이터의 변동성을 조사하는 주성분분석, 선형모형 등에 대해 살펴보았다. 그리고 우리나라 기온 데이터와 강수량 데이터를 대상으로 각각 함수적 데이터 분석 기법을 적용해 보았다. 또한, 기온과 강수량 데이터에 대해 함수적 회귀모형을 적합시켜 두 변수간의 함수관계를 살펴보았다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 춘계 학술발표회
• /
• pp.1358-1365
• /
• 2010

Estimating condition of slope is difficult because of nonlinear time dependency and seasonal effects, which affect the displacements. Displacements and displacement patterns of landslides are highly variable in time and space, and a unique approach cannot be defined to model landslide movements. Characteristics of movements are obtained by using a statistical method called Principal Component Analysis(PCA). The PCA is a non-parametric method to separate unknown, statistically uncorrelated source processes from observed mixed processes. In the non-parametric approaches, no physical assumptions of target systems are required. Instead, since the "best" mathematical relationship is estimated for given data sets of the input and output measured from target systems. As a consequence, non-parametric approaches are advantageous in modeling systems whose geomechanical properties are unknown or difficult to be measured. Non-parametric approaches are consequently more flexible in modeling than parametric approaches. This method is expected to be a useful tool for the slope management of and alarm systems.

• 상하수도학회지
• /
• 제27권3호
• /
• pp.351-361
• /
• 2013

In this study the Principal Component Analysis (PCA) was applied to flow data in a water distribution pipe system to analyze the relevance between the flow observation dates, which have the outliers of observed night flows, and the maintenance records. The data was obtained from four small size water distribution blocks to which 13 maintenance records such as pipe leak and water meter leak belong. The flow data during four months were used for the analysis. The analysis was carried out to identify an appropriate analysis period for a PCA model for a water distribution block. To facilitate the analyses a computational algorithm was developed. MATLAB was utilized to realize the algorithm as a computer program. As a result, an appropriate PCA period for each of the case study small size water distribution blocks was identified.

• International Journal of Concrete Structures and Materials
• /
• 제7권4호
• /
• pp.303-317
• /
• 2013

This study evaluates the shear strength of steel fiber reinforced concrete (SFRC) beams from a database, which consists of extensive experimental results of 222 SFRC beams having no stirrups. In order to predict the analytical shear strength of the SFRC beams more precisely, the selected beams were sorted into six different groups based on their ultimate concrete strength (low strength with $f_c^{\prime}$ <50 MPa and high strength with $f_c^{\prime}$ <50 MPa), span-depth ratio (shallow beam with $a/d{\geq}2.5 $and deep beam with a/d<2.5) and steel fiber shape (plain, crimped and hooked). Principal component and multiple regression analyses were performed to determine the most feasible model in predicting the shear strength of SFRC beams. A variety of statistical analyses were conducted, and compared with those of the existing equations in estimating the shear strength of SFRC beams. The results showed that the recommended empirical equations were best suited to assess the shear strength of SFRC beams more accurately as compared to those obtained by the previously developed models.

• Environmental Engineering Research
• /
• 제22권3호
• /
• pp.302-311
• /
• 2017

Nowadays, with the burgeoning development of economy, $CO_2$ emissions increase rapidly in China. It has become a common concern to seek effective methods to forecast $CO_2$ emissions and put forward the targeted reduction measures. This paper proposes a novel hybrid model combined principal component analysis (PCA) with regularized extreme learning machine (RELM) to make $CO_2$ emissions prediction based on the data from 1978 to 2014 in China. First eleven variables are selected on the basis of Pearson coefficient test. Partial autocorrelation function (PACF) is utilized to determine the lag phases of historical $CO_2$ emissions so as to improve the rationality of input selection. Then PCA is employed to reduce the dimensionality of the influential factors. Finally RELM is applied to forecast $CO_2$ emissions. According to the modeling results, the proposed model outperforms a single RELM model, extreme learning machine (ELM), back propagation neural network (BPNN), GM(1,1) and Logistic model in terms of errors. Moreover, it can be clearly seen that ELM-based approaches save more computing time than BPNN. Therefore the developed model is a promising technique in terms of forecasting accuracy and computing efficiency for $CO_2$ emission prediction.

• 한국식품과학회지
• /
• 제44권5호
• /
• pp.648-652
• /
• 2012

시중에 판매되고 있는 증류식 소주 9종에 대해 묘사분석법을 적용하여 18가지의 관능특성을 도출하였다. 전반적으로 시료의 향, 맛, 입안감촉 관련 관능특성은 알코올 수준을 반영하여 시료간의 차이를 보였다. 재래 증류식 소주와는 달리 현대 증류식 소주는 균일화된 원재료의 사용과 생산 조건의 영향으로 복합적인 향을 나타내지 않는 것으로 보이며, 관능특성 분석과 더불어 이를 나타내는 주요한 향기성분에 대한 규명도 향후 필요하리라 여겨진다. 이를 통해 향후 국내시장에서 다양한 증류식 소주의 품질 향상과 대중화에 기여하리라 여겨진다.

• Geomechanics and Engineering
• /
• 제27권6호
• /
• pp.551-560
• /
• 2021

Due to the low strength and high compressibility characteristics, the loess deposits tunnels are prone to large deformations and collapse. An accurate stability evaluation for loess deposits is of considerable significance in deformation control and safety work during tunnel construction. 37 groups of representative data based on real loess deposits cases were adopted to establish the stability evaluation model for the tunnel project in Yan'an, China. Physical and mechanical indices, including water content, cohesion, internal friction angle, elastic modulus, and poisson ratio are selected as index system on the stability level of loess. The data set is randomly divided into 80% as the training set and 20% as the test set. Firstly, principal component analysis (PCA) is used to convert the five index system to three linearly independent principal components X1, X2 and X3. Then, the principal components were used as input vectors for probabilistic neural network (PNN) to map the nonlinear relationship between the index system and stability level of loess. Furthermore, Leave-One-Out cross validation was applied for the training set to find the suitable smoothing factor. At last, the established model with the target smoothing factor 0.04 was applied for the test set, and a 100% prediction accuracy rate was obtained. This intelligent classification method for loess deposits can be easily conducted, which has wide potential applications in evaluating loess deposits.