• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.713-719
• /
• 2009

In this paper, we develope a water demand forecasting algorithm using AR(Auto-regressive) and MLP(Multi-layer perceptron). To show effectiveness of the proposed method, we analyzed characteristics of time-series data collected in "A" purification plant at Jeon-Buk province during 2007-2008, and then performed the proposed method with various input factors selected through various analyses. As noted in experimental results, the performance of three types model such as multi-regressive, AR(Auto-regressive), and AR+MLP(Auto-regressive + Multi-layer perceptron) show 5.1%, 3.8%, and 3.6% with respect to MAPE(Mean Absolute Percentage Error), respectively. Thus, it is noted that the proposed method can be used to predict short-term water demand for the efficient operation of a water purification plant.

• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.533-543
• /
• 2011

The hERG (human ether-a-go-go related gene) ion channel is a main factor for cardiac repolarization, and the blockade of this channel could induce arrhythmia and sudden death. Therefore, potential hERG ion channel inhibitors are now a primary concern in the drug discovery process, and lots of efforts are focused on the minimizing the cardiotoxic side effect. In this study, $IC_{50}$ data of 202 organic compounds in HEK (human embryonic kidney) cell from literatures were used to develop predictive 2D-QSAR model. Multiple linear regression (MLR), Support Vector Machine (SVM), and artificial neural network (ANN) were utilized to predict inhibition concentration of hERG ion channel as machine learning methods. Population based-forward selection method with cross-validation procedure was combined with each learning method and used to select best subset descriptors for each learning algorithm. The best model was ANN model based on 14 descriptors ($R^2_{CV}$=0.617, RMSECV=0.762, MAECV=0.583) and the MLR model could describe the structural characteristics of inhibitors and interaction with hERG receptors. The validation of QSAR models was evaluated through the 5-fold cross-validation and Y-scrambling test.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.334-340
• /
• 2002

This paper proposes a self-organizing fuzzy modeling which can create a new hyperplane-shaped cluster by applying multiple regression to input/output data with relatively large fuzzy entropy, add the new cluster to fuzzy rule base and adjust parameters of the fuzzy model in repetition. Tn the coarse tuning, weighted recursive least squared algorithm and fuzzy C-regression model clustering are used and in the fine tuning, gradient descent algorithm is used to adjust parameters of the fuzzy model precisely And learning rates are optimized by utilizing meiosis-genetic algorithm. To check the effectiveness and feasibility of the suggested algorithm, four representative examples for system identification are examined and the performance of the identified fuzzy model is demonstrated in comparison with that of the conventional fuzzy models.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.19 no.5
• /
• pp.429-435
• /
• 2007

The present study proposed a method fer simulating reflective boundary conditions in Boussinesq wave propagation model by lining lateral boundaries like breakwaters and seawalls with artificial sponge layers. In order to find out the reflective characteristics of sponge layers, 1D numerical experiments were performed varying the relative sponge width (sponge width/wave length). The results showed that the reflection coefficient can be effectively realized from no reflection to full reflection simply by adjusting the relative sponge width. Based on the results, a multiple regression formula was proposed to delineate the relationship among the reflection coefficient and other dimensionless variables. Finally, the reflective sponge layer was applied to a semi-infinite breakwater, demonstrating that it can also be successfully employed in 2D applications.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.792-796
• /
• 2002

관찰적 작업자세 평가기법은 각 관절의 자세를 관찰 기록하여 자세 부하를 평가하는 실용적인 인간공학적 작업평가 기법이다. 본 연구에서는 각 관절의 불편도 지수와 전신의 자세 부하의 관계성을 모형화하고, 전신의 작업자세 부하를 평가하는 방법론을 제시하였다. 자동차 조립공정의 대표적인 작업자세들을 대상으로 하여 정적인 자세의 심물리학적 부하를 전신에 대하여 평가하였다 전신의 불편도는 비중립 자세를 취하고 있는 각 관절의 조합에 의해 영향을 받는다. 특히, 자동차 조립공정에서는 어깨 높이 이상의 작업을 대상으로 하는 경우에 어깨, 목, 허리, 손목 등에서 비중립 자세를 동시에 취하여 전신의 불편도가 큰 것으로 나타났다. 평가된 전신의 불편도와 각 자세의 관절별 불편도 지수의 관계를 다중선형회귀모형으로 모형화하는 것이 타당한 것으로 나타났다. 모형에서 전신 불편도에 가장 큰 영향을 미치는 관절은 어깨이며, 손목의 영향이 가장 적은 것으로 나타났다. 이 모형을 통해 작업자세 부하를 정량적으로 평가하는 것이 가능할 것으로 기대된다.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.59-64
• /
• 2020

In this paper, we found the solution using data based machine learning regression method to check the pore shape, to solve the problem of the experiment quantity occurring when producing scaffold with the 3d printer. Through experiments, we learned secured each print condition and pore shape. We have produced the scaffold from scaffold pore shape defect prediction model using multiple linear regression method. We predicted scaffold pore shapes of unsecured print condition using the manufactured scaffold pore shape defect prediction model. We randomly selected 20 print conditions from various predicted print conditions. We print scaffold five times under same print condition. We measured the pore shape of scaffold. We compared printed average pore shape with predicted pore shape. We have confirmed the prediction model precision is 99 %.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.1
• /
• pp.45-50
• /
• 2012

This paper on analysis of roundness error after boring turning of Al-6061 materials with CNC lathe. Experiment applying turning parameters is based on experimental design method. A design and analysis of experiments is conducted to study the effects of these parameters on the roundness error using the S/N ratio and analysis of ANOVA. Multiple linear regression analysis is applied to compare experimental with predicted data in consideration of roundness error. To fixation pressure and the opening which are a turning parameter, the cutting depth and feed speed respected the objective attainment of dissertation and to be applied the result they investigated.

• Journal of the Korean Society for Railway
• /
• v.13 no.2
• /
• pp.222-228
• /
• 2010

In this paper, we propose a optimization approach for the Electric Locomotive Overhaul Maintenance Facility (ELOMF), which aims at the simulation optimization so as to meet the design specification. In simulation design, we consider the critical path and sensitivity analysis of the critical (dependent) factors and the design (independent) parameters for the parameter selection and reduction of the metamodel. Therefore, we construct the multi-objective non-linear programming. The objective function is normalized for the generalization of design parameter while the constraints are composed of the simulation-based regression metamodel for the critical factors and design factor's domain. Then the effective solution procedure based on the pareto optimal solution set is proposed. This approach provides a comprehensive approach for the optimization of Train Overhaul Maintenance Facility(TOMF)'s design parameters using the simulation and metamoels.

• Korean Journal of Soil Science and Fertilizer
• /
• v.32 no.2
• /
• pp.95-108
• /
• 1999

Field experiments were conducted in the 101 tobacco fields(51 fields in 1985 and 50 fields in 1986) of chief tobacco producing counties of Chungbuk province(Jincheon, Eumseong, Goesan, and Joongweon counties), Chungnam province(Cheonweon county), and Kyongbuk province (Cheongdo, Seongju, and Andong counties) for two years from 1985 to 1986 in order to evaluate soil fertility using chemical properties and soil map database. Pot experiments also on the same soils were conducted and the results were compared to those of field experiments. The yield of tobacco in the plots of no fertilization was considered as a basic factor representing the soil fertility and was evaluated by nineteen independent variables, that was 9 chemical properties and 10 soil map databases. These independent variables were classified into two groups, 11 quantitative indexes and 9 qualitative indexes, and were analyzed by multiple linear regression(MLR) of SAS by REG and GLM models. The yield of tobacco in the plot of no fertilization showed high variations, e.g. the difference between minimum and maximum yields was about 5.0-5.5 times in the pot experiment and 8.2-14.9 times in the field experiment. The indexes indicating close link between yield of tobacco and soil chemical indexes, was selected but it was not well matched by the years or between pot and field experiments. Also, the standardized partial regression coefficients of quantitative indexes for the yield of field were less than 1.0, suggesting that it is difficult to develop an available single index for the evaluation of soil fertility. Evaluation for the soil fertility of field by MLR was better than that of single regression and it was gradually improved by adding chemical properties, quantitative indexes, and qualitative indexes of soil map. For example, the coefficient of determination ($R^2$) of MLR for the yield of 1985 was increased to 0.422 with chemical indexes, 0.503 by addition of quantitative indexes, and 0.633 by the additional adding of qualitative indexes of soil map, compared to 0.244 of single index, $NO_3-N$ content of soil. Consequently, it is assumed that this approach by MLR with quantitative and qualitative indexes including chemical properties and soil map databases was available as an evaluation model of soil fertility for tobacco field.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.10
• /
• pp.98-103
• /
• 1997

Given the small bit allocation for motion information in very low bit-rate coding, motion estimation using the block matching algorithm(BMA) fails to maintain an acceptable level of prediction errors. The reson is that the motion model, or spatial transformation, assumed in block matching cannot approximate the motion in the real world precisely with a small number of parameters. In order to overcome the drawback of the conventional block matching algorithm, several triangle-based methods which utilize triangular patches insead of blocks have been proposed. To estimate the motions of image sequences, these methods usually have been based on the combination of optical flow equation, affine transform, and iteration. But the compuataional cost of these methods is expensive. This paper presents a fast motion estimation algorithm using a multiple linear regression model to solve the defects of the BMA and the triange-based methods. After describing the basic 2-D triangle-based method, the details of the proposed multiple linear regression model are presented along with the motion estimation results from one standard video sequence, representative of MPEG-4 class A data. The simulationresuls show that in the proposed method, the average PSNR is improved about 1.24 dB in comparison with the BMA method, and the computational cost is reduced about 25% in comparison with the 2-D triangle-based method.