• 한국도로학회논문집
• /
• 제10권3호
• /
• pp.129-138
• /
• 2008

기존 콘크리트 포장의 단면 설계 시 발생하는 문제점을 해결하기 위해 유한 요소법(FEM)을 이용하여 것이 하나의 방법론으로 부각되었으며 현재 한국형 포장 설계법 개발 연구에서도 적용 중에 있다. 본 연구에서는 ABAQUS와 포트란 해석 프로그램을 이용하여 콘크리트 포장의 한계 응력을 계산하였고, 그 결과를 뉴럴 네트워크와 선형 회귀식을 이용하여 비교 분석하였다. 입력 변수가 많지만 다양한 해석을 하지 못하는 경우(입력변수 6개에 대해 81 경우 수 해석)에 대해 구조해석 결과를 뉴럴 네트워크(이하 NN: Neural Networks)와 선형 회귀식으로 비교한 결과, 구조해석 결과와 다소 차이가 있음을 확인하였다. 반면 입력 변수를 줄이되 다양한 경우에 해석한 경우(입력 변수 3개에 대해 343 경우의 수)의 분석 결과, NN과 선형 회귀식이 구조해석 결과와 매우 유사한 결과가 나타나는 것을 알 수 있었다. 하지만 그래프의 (0,0), (1,1) 부분에서 NN이 선형 회귀식에 비해 더 정확한 것을 확인하였다. 이와 같은 연구 결과를 통해서 한국형 포장 설계법의 핵심인 응력 계산 모듈을 선형 회귀식보다 좀 더 정확한 NN으로 해석하는 것을 제안하였다.

• 한국환경과학회지
• /
• 제9권1호
• /
• pp.13-18
• /
• 2000

The purpose of this study is to estimate the low-flow statistics at the mountainous watershed. The formulation for the estimation of the design low-flow statistics was obtained by means of a hydraulic approach applied to a simple conceptual model for a mountainous watershed. Three of the independent variables associated with the low-flow statistics is watershed area(A), average basin slope(S) and the base flow recession constant(K); Watershed area was measured from topographic maps and average basin slope is approximated in this study using Strahler's slope determining method. And base flow recession constant computed using Vogel and Kroll's method. Unfortunately, this method is usually unavailable at ungaged sites. In this study, recession constant at ungaged sites is estimated using graphical regression method used by Giese and Mason. The model for estimating low-flow statistics were applied to all 61 catchments in the Sumjin, Mankyung basin.

• 한국농공학회논문집
• /
• 제59권4호
• /
• pp.97-107
• /
• 2017

This study is to determine the coefficients of regression equations and to select the optimal regression equation in the LOADEST model after classifying the whole study period into 5 flow conditions for 16 watersheds located in the Nakdonggang waterbody. The optimized coefficients of regression equations were derived using the gradient descent method as a learning method in Tensorflow which is the engine of machine-learning method. In South Korea, the variability of streamflow is relatively high, and rainfall is concentrated in summer that can significantly affect the characteristic analysis of pollutant loads. Thus, unlike the previous application of the LOADEST model (adjusting whole study period), the study period was classified into 5 flow conditions to estimate the optimized coefficients and regression equations in the LOADEST model. As shown in the results, the equation #9 which has 7 coefficients related to flow and seasonal characteristics was selected for each flow condition in the study watersheds. When compared the simulated load (SS) to observed load, the simulation showed a similar pattern to the observation for the high flow condition due to the flow parameters related to precipitation directly. On the other hand, although the simulated load showed a similar pattern to observation in several watersheds, most of study watersheds showed large differences for the low flow conditions. This is because the pollutant load during low flow conditions might be significantly affected by baseflow or point-source pollutant load. Thus, based on the results of this study, it can be found that to estimate the continuous pollutant load properly the regression equations need to be determined with proper coefficients based on various flow conditions in watersheds. Furthermore, the machine-learning method can be useful to estimate the coefficients of regression equations in the LOADEST model.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.394-394
• /
• 2000

This Paper proposes a new nonlinear partial least square method that extends the linear PLS. Proposed nonlinear PLS uses self-organizing feature map as PLS outer relation and multilayer neural network as PLS inner regression method.

• 한국소음진동공학회논문집
• /
• 제15권8호
• /
• pp.945-953
• /
• 2005

The purpose of this paper is to develop a linear regression model for the sound quality index of vehicle Interior noise. For this, objective measurement data of the vehicles driving in acceleration was measured. On the basis of analysis, psychoacoustic parameters were extracted and subjective evaluation was performed by noise and vibration expert evaluators. For the subjective evaluation, the paired comparisons and the semantic differential methods were used to evaluate sound quality of vehicle interior noise. By the paired comparison which evaluate two pairs of vehicle interior noise, the preference was estimated. With the semantic differential and the factor analysis, it was evaluated words of two pairs which expressed appropriately the sense of evaluator about noise source. Therefore the characteristics of the sound qualify for the vehicle were differentiated. From the results of both the correlation analysis and the multiple factor regression analysis, the sound quality evaluation model for the sense of human hearing was derived and indexed.

• 약학회지
• /
• 제40권1호
• /
• pp.1-9
• /
• 1996

The purpose of this investigation was to determine pharmacokinetic parameters of gentamicin using nonlinear least square regression(NLSR) and Bayesian analysis in Korean normal volunteers and gastrointestinal surgical patients. Nonparametric expected maximum(NPEM) method for population pharmacokinetic parameters was used. Gentamicin was administered every 8 hours for 3 days by infusion over 30 minutes. The volume of distribution(V) and elimination rate constant(K) of gentamicin were $0.226{\pm}0.032,\;0.231{\pm}0.063L/Kg\;and\;0.357{\pm}0.024,\;0.337{\pm}0.041hr^{-1}$ for normal volunteers and gastrointestinal surgical patients using NLSR analysis. Population pharmacokinetic parameters, KS and VS were $0.00344{\pm}0.00049(hr{\cdot}ml/min/1.73m^2)^{-1}\;and\;0.214{\pm}0.0502L/Kg$ for gastrointestinal surgical patients using NPEM method. The V and K were $0.216{\pm}0.048L/Kg\;and\;0.336{\pm}0.043hr^{-1}$ for gastrointestinal surgical patients using Bayesian analysis. There were no differences in gentamicin pharmacokinetics between NLSR and Bayesian analysis in gastrointestinal surgical patient.

• 한국어업기술학회:학술대회논문집
• /
• 한국어업기술학회 1994년도 학술발표회
• /
• pp.69-69
• /
• 1994

• 한국항공우주학회지
• /
• 제32권4호
• /
• pp.80-87
• /
• 2004

KSR-III 비행용 액체추진제 로켓엔진의 각 성능 변수 간 상관관계를 파악하기 위하여, 엔 진 지상연소시험의 결과에 대한 분석이 수행되었다. 내열재 연소실의 삭마에 따른 변화를 고려하였으며, 산화제/연료비에 의한 변화를 무시한 선형 회귀분석과 이를 포함한 이변수 이차 회귀분석이 수행되었다. 선형 회귀분석은 간단하면서도 분석영역 내에서 1% 이내의 오차율을 가지는 매우 실용적인 방법임을 보여주었다. 또한 이변수 이차 회귀분석 결과는 분석영역 내에서 매우 높은 정확도의 예측이 가능하였으며, KSR-III 엔진의 추력 (혹은 비추력) 및 연소실 압력 (혹은 특성속도)에 대한 최적 산화제/연료비가 각각 2.22 와 2.17 인 것으로 분석되었다.

• Journal of information and communication convergence engineering
• /
• 제17권1호
• /
• pp.41-48
• /
• 2019

In recent years, sentiment analysis research has become popular. The research results of sentiment analysis have achieved remarkable results in practical applications, such as in Amazon's book recommendation system and the North American movie box office evaluation system. Analyzing big data based on user preferences and evaluations and recommending hot-selling books and hot-rated movies to users in a targeted manner greatly improve book sales and attendance rate in movies [1, 2]. However, traditional machine learning-based sentiment analysis methods such as the Classification and Regression Tree (CART), Support Vector Machine (SVM), and k-nearest neighbor classification (kNN) had performed poorly in accuracy. In this paper, an improved kNN classification method is proposed. Through the improved method and normalizing of data, the purpose of improving accuracy is achieved. Subsequently, the three classification algorithms and the improved algorithm were compared based on experimental data. Experiments show that the improved method performs best in the kNN classification method, with an accuracy rate of 11.5% and a precision rate of 20.3%.

• Communications for Statistical Applications and Methods
• /
• 제28권2호
• /
• pp.135-150
• /
• 2021

We propose principal differential analysis based classification methods. Computations of squared multiple correlation function (RSQ) and principal differential analysis (PDA) scores are reviewed; in addition, we combine principal differential analysis results with the logistic regression for binary classification. In the numerical study, we compare the principal differential analysis based classification methods with functional principal component analysis based classification. Various scenarios are considered in a simulation study, and principal differential analysis based classification methods classify the functional data well. Gene expression data is considered for real data analysis. We observe that the PDA score based method also performs well.