• Journal of Marine Bioscience and Biotechnology
• /
• 제6권1호
• /
• pp.31-40
• /
• 2014

The production of astaxanthin in the microalga Haematococcus pluvialis has been investigated using a sequential methodology based on the application of two types of statistical designs. The employed preliminary experiment was a fractional factorial design $2^6$ in which the factors studied were: excessive irradiance and nitrate starvation, phosphate deficiency, acetate supplementation, salt stress, and elevated temperature. The experimental results indicate that the amount of astaxanthin accumulation in the cells can be enhanced by excessive irradiance and nitrate starvation whereas the other factors tested did not yield any enhancement. In the subsequent experiment, a central composite design was applied with four variables, light intensity, nitrate, phosphate, and acetate, at five levels each. The optimal conditions for the highest astaxanthin production were found to be $1040{\mu}E/(m^2{\cdot}s)$ light intensity, 0.04 g/L nitrate, 0.31 g/L phosphate, 0.05 g/L acetate concentration.

• Korean System Dynamics Review
• /
• 제13권2호
• /
• pp.47-71
• /
• 2012

The purpose of this research is the examination of validity of data as well as simulation model, i.e. to simulate the real data in the SD model with the least error using the adjustments for the faithful reflection of real data to the simulation. In general, SD programs (e.g. VENSIM) utilize the Euler or Runge-Kutta method as an algorithm. It is possible to reflect the trend of real data via these two estimation methods however can cause the validity problem in case of the simulation requiring the accuracy as they have endogenous errors. In this article, the future population estimated by the Korea National Statistical Office (KNSO) to 2050 is simulated by the aging chain model, dividing the population into three cohorts, 0-14, 15-64, 65 and over cohorts by age and offering the adjustments to them. Adjustments are calculated by optimization with three different methods, optimization in EXCEL, manual optimization with iterative calculation, and optimization in VENSIM DSS, the results are compared, and at last the optimal adjustment set with the least error are found among them. The simulation results with the pre-determined optimal adjustment set are validated by methods proposed by Barlas (1996) and other alternative methods. It is concluded that the result of simulation model in this research has no significant difference from the real data and reflects the real trend faithfully.

• Journal of Korean Society for Quality Management
• /
• 제34권4호
• /
• pp.33-39
• /
• 2006

These days manufacture technology and manufacture environment are changing rapidly. By development of computer and enlargement of technique, most of manufacture field are computerized. In order to win international competition, it is important for companies how fast get the useful information from vast data. Statistical process control(SPC) techniques have been used as a problem solution tool at manufacturing process until present. However, these statistical methods are not applied more extensively because it has much restrictions in realistic problems. These statistical techniques have lots of problems when much data and factors are analyzed. In this paper, we proposed more practical and efficient a new statistical design technique which integrated data mining (DM) and statistical methods as alternative of problems. First step is selecting significant factor using DM feature selection algorithm from data of manufacturing process including many factors. Second step is finding optimum of process after estimating response function through response surface methodology(RSM) that is a statistical techniques

• Proceedings of the Korean Statistical Society Conference
• /
• 한국통계학회 2003년도 춘계 학술발표회 논문집
• /
• pp.203-206
• /
• 2003

This paper studies constrained optimization of an M/G/1 queue with a server that can be switched on and off. One criterion is an average number of customers in the system and another criterion is an average operating cost per unit time, where operating costs consist of switching and running costs. With the help of queueing theory, we solve the problems of optimization of one of these criteria under a constraint for another one.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• 제35권2호
• /
• pp.163-168
• /
• 2011

Robust optimization or reliability-based design optimization are some of the methodologies that are employed to take into account the uncertainties of a system at the design stage. For applying such methodologies to solve industrial problems, accurate and efficient methods for estimating statistical moments and failure probability are required, and further, the results of sensitivity analysis, which is needed for searching direction during the optimization process, should also be accurate. The aim of this study is to employ the function approximation moment method into the sensitivity analysis formulation, which is expressed as an integral form, to verify the accuracy of the sensitivity results, and to solve a typical problem of reliability-based design optimization. These results are compared with those of other moment methods, and the feasibility of the function approximation moment method is verified. The sensitivity analysis formula with integral form is the efficient formulation for evaluating sensitivity because any additional function calculation is not needed provided the failure probability or statistical moments are calculated.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 한국품질경영학회 2006년도 추계 학술대회
• /
• pp.205-210
• /
• 2006

Nowaday manufacture technology and manufacture environment are changing rapidly. By development of computer and enlargement of technique, most of manufacture field are computerized. It is measured automatically do much quality characteristics thereby and great many data happen in a day. corporations is important if have gotten fast information that are useful from wide data to go first in international competition according to these change. Statistical process control(SPC) techniques are used as a problem solution tool at manufacturing process until present. However, this statistical methods is not applied more extensively because have much restrictions in realistic problem. In this paper, wish to develop more realistic and scientific new statistical design techniques doing to integrate data mining(DM) and statistical methods by the alternative to cope these problem. First step selects significant factor using DM techniques from datas of manufacturing process including much factors and second step wish to find optimum of process after get the estimated response function through response surf ace methodology(RSM) that is statistical techniques.

• Journal of the Korean Statistical Society
• /
• 제33권1호
• /
• pp.25-34
• /
• 2004

In this paper we propose a prediction method on the regression model with randomly censored observations of the training data set. The least squares support vector machine regression is applied for the regression function prediction by incorporating the weights assessed upon each observation in the optimization problem. Numerical examples are given to show the performance of the proposed prediction method.

• Communications for Statistical Applications and Methods
• /
• 제10권1호
• /
• pp.153-166
• /
• 2003

This study presents the time-divided forecasting model to integrate evolutionary optimization algorithm and change point detection based on artificial neural networks (ANN) for the prediction of (Korea) stock price index. The genetic algorithm(GA) is introduced as an evolutionary optimization method in this study. The basic concept of the proposed model is to obtain intervals divided by change points, to identify them as optimal or near-optimal change point groups, and to use them in the forecasting of the stock price index. The proposed model consists of three phases. The first phase detects successive change points. The second phase detects the change-point groups with the GA. Finally, the third phase forecasts the output with ANN using the GA. This study examines the predictability of the proposed model for the prediction of stock price index.

• Journal of Microbiology and Biotechnology
• /
• 제19권4호
• /
• pp.378-386
• /
• 2009

A sequential optimization strategy, based on statistical experimental designs, is employed to enhance the production of alkaline protease by a Bacillus pseudofirmus local isolate. To screen the bioprocess parameters significantly influencing the alkaline protease activity, a 2-level Plackett-Burman design was applied. Among 15 variables tested, the pH, peptone, and incubation time were selected based on their high positive significant effect on the protease activity. A near-optimum medium formulation was then obtained that increased the protease yield by more than 5-fold. Thereafter, the response surface methodology(RSM) was adopted to acquire the best process conditions among the selected variables, where a 3-level Box-Behnken design was utilized to create a polynomial quadratic model correlating the relationship between the three variables and the protease activity. The optimal combination of the major medium constituents for alkaline protease production, evaluated using the nonlinear optimization algorithm of EXCEL-Solver, was as follows: pH of 9.5, 2% peptone, and incubation time of 60 h. The predicted optimum alkaline protease activity was 3,213 U/ml/min, which was 6.4 times the activity with the basal medium.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제17권5호
• /
• pp.645-652
• /
• 2016

The statistical modeling of input random variables is necessary in reliability analysis, reliability-based design optimization, and statistical validation and calibration of analysis models of mechanical systems. In statistical modeling methods, there are the Akaike Information Criterion (AIC), AIC correction (AICc), Bayesian Information Criterion, Maximum Likelihood Estimation (MLE), and Bayesian method. Those methods basically select the best fitted distribution among candidate models by calculating their likelihood function values from a given data set. The number of data or parameters in some methods are considered to identify the distribution types. On the other hand, the engineers in a real field have difficulties in selecting the statistical modeling method to obtain a statistical model of the experimental data because of a lack of knowledge of those methods. In this study, commonly used statistical modeling methods were compared using statistical simulation tests. Their advantages and disadvantages were then analyzed. In the simulation tests, various types of distribution were assumed as populations and the samples were generated randomly from them with different sample sizes. Real engineering data were used to verify each statistical modeling method.