• The Korean Journal of Applied Statistics
• /
• v.18 no.3
• /
• pp.617-625
• /
• 2005

We usually use orthogonal designs-orthogonal array of strength 2 as orthogonal arrays. It was shown that fractional factorial plaits represented by orthogonal arrays of strength 3 are universally optimal under the additive motels that includes the mean, all main effects and all two-factor interactions. Therefore, we need the measure for evaluating the orthogonal array of strength 3. We can extend this measure as the measure for evaluating the orthogonal array of strength t($\ge$ 2).

• Journal of Ginseng Research
• /
• v.18 no.1
• /
• pp.53-59
• /
• 1994

To develop the methodology of the quantitative analysis of saponin in ginseng milk, conditions of the saponin extraction were optimized using the fractional factorial design with 3 variables and 3 levels by a RSM computer program. The extraction of saponin increased with an increase in extraction temperature up to $90^{\circ}C$ and then decreased significantly at $100^{\circ}C$. Extraction time affected the saponin yield in a similar trend. On the other hand, decreasing cooling temperature increased the amount of the saponin extracted. Recovery yield of the saponin from ginseng milk varied from 70.0% to 92.9%. The optimum extraction temperature, time and cooling temperature determined by partial differentiation of the model equation were $86^{\circ}C$, 2.83 hrs and $4^{\circ}C$, respectively. Key words Ginseng milk, saponin, response surface methodology.

• International Journal of Contents
• /
• v.16 no.4
• /
• pp.26-38
• /
• 2020

Determining the optimal levels of the technical attributes (TAs) of a product to achieve a high level of customer satisfaction is the main activity in the planning process for quality function deployment (QFD). In real applications, the number of customer requirements for developing a single product is quite large, and the number of converted TAs is also high so the size of the house of quality (HoQ) becomes huge. Furthermore, the TA levels are often discrete instead of continuous and the product market can be divided into several market segments corresponding to the number of HoQ, which also unacceptably increases the size of the QFD optimization problem and the time spent on making decisions. This paper proposed a genetic algorithm (GA) solution approach to finding the optimum set of TAs in QFD in the above situation. A numerical example is provided for illustrating the proposed approach. To assess the computational performance of the GA, tests were performed on problems of various sizes using a fractional factorial design.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.4
• /
• pp.592-603
• /
• 2014

We developed various recipes of turmeric powder (Curcuma longa L.) added to milk bread and assessed the individual effects of seven ingredients [milk ($X_1$), turmeric powder ($X_2$), bread improver ($X_3$), fresh yeast ($X_4$), butter ($X_5$), sugar ($X_6$), and salt ($X_7$)] as well as the 2-way interaction effects of the ingredients on the sensory characteristics of breads using fractional factorial design method. The center and end points of each component were determined via literature review and multiple test baking. Seven trained sensory test panels evaluated the outside appearance (OA), inside appearance (IA), and flavor & texture (FT) of 38 breads using 46 items of sensory evaluation. Findings are as follows: for the OA, $X_1$ (P<0.05) and $X_4$ (P<0.0001) exhibited significant individual effects, whereas $X_1*X_7$, $X_2*X_5$, $X_3*X_6$, and $X_4*X_6$ indicated significant interaction effects (P<0.05). For the IA, $X_1$ (P<0.0001), $X_4$ (P<0.0001), $X_6$ (P<0.05), $X_2*X_4$ (P<0.05), and $X_3*X_6$ (P<0.01) showed individual and interaction effects, respectively. For the FT, $X_1$ and $X_2$ showed the most significant individual effect (P<0.0001), followed by $X_4$, $X_5$ and $X_6$ (P<0.05) in descending order. $X_4*X_7$ indicated the only significant interaction effect. We computed the magnitudes of the 2-way interaction effects of the ingredients with a distinct emphasis. Model equations predicting the levels of the ingredient effects on the breads were also provided via regression analyses. In summation, $X_4$ appeared to be the most significant component affecting the sensory characteristics based on its individual and 2-way interaction effects. Further, $X_6$, $X_1$, $X_2$, and $X_5$ indicated both individual and interaction effects. $X_3$ and X7 showed only interaction effects. The center point effect appeared to be unequivocal for whole sensory characteristics. Findings of the present study may provide insights into the selection of ingredients to derive an optimal model for turmeric powder-added bread using the response surface method hereafter.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1730-1738
• /
• 2011

Personal Rapid Transit (PRT) has emerged as a promising alternative transportation mode for transit-oriented sustainable communities by creating compact and walkable environments with competitive construction and operational costs. This study seeks to capture the changes in travel mode choice behavior in response to the introduction of PRT to travelers who have no previous experience of using it. A critical issue in modeling the PRT mode choice is how to capture travelers' perception and evaluation of the unexperienced travel mode. The data used come from questionnaire surveys, in which RP (Revealed Preference) and SP (Stated Preference) data were collected in relation to travel mode choices with and without PRT systems. The questionnaire was designed especially for mitigating the potential bias in favor of or against choosing PRT. In addition, an efficient approach was proposed to reduce the number of SP questions by avoiding the complex fractional factorial design which tends to make it difficult for respondents to keep their attention throughout the survey. The analysis results show that the proposed approach is able to realistically capture the effects of explanatory variables on the travel mode choice. Discrete choice models are developed to predict travelers' mode choices under different choice scenarios by varying PRT system specifications and operational characteristics. PRT patronages are projected for two different test sites using the developed PRT mode choice models.

• Korean Journal of Food Science and Technology
• /
• v.23 no.4
• /
• pp.510-516
• /
• 1991

To improve the stability of frozen yeast raised dough for doughnuts, amounts of sugar, sodium steroyl lactylate(SSL) and $KBrO_{3}$ to be added to the premix were optimized, using the fractional factorial design with 3 variables and 3 levels, by a RSM computer program. The optimum sugar, SSL and$KBrO_{3}$ levels to be added to the premix were 2%, 0.3% and 25 ppm for a desired doughnut volume, and 2%, 0.4% and 10 ppm for a desired doughnut texture, and 2%, 0.4% and 20 ppm, respectively, for an overall optimum quality of doughnuts. The frozen stored yeast raised dough prepared without floor time resulted in better doughnut volume and texture than that with floor time. The yeast raised dough prepared with the formula for overall optimum quality, was formed to ‘plain ring’ type doughnuts and stored at $-18^{\circ}C$ for 5 weeks. Volume and texture of fried doughnuts were comparable to those of control for 2 weeks of storage, and then deteriorated noticeablly from 3 weeks of storage.

• Journal of Applied Biological Chemistry
• /
• v.53 no.3
• /
• pp.126-131
• /
• 2010

In order to maximize the growth of Bifidobacterium lactis BL 740 and soy isoflavone agycones production, we investigated the optimization of a culture medium containing soy hypocotyls, which are the byproducts of the soy manufacturing process, and soy proteins. The ingredients of the medium containing soy materials (S-medium) were selected by fractional factorial design (FFD) and central composite design (CCD) within a desirable range. The FFD was applied by six factors: glucose, cellobiose, fructooligosaccharide, soy peptone, soy protein, and soy hypocotyl. Soy protein, soy peptone, and soy hypocotyl were found to be significant factors from the result of FFD for both the growth of B. lactis BL 740 and aglycone production. The CCD was then applied with three variables found from FFD at five levels each and the optimum values were determined for the three variables: soy peptone, soy protein, and soy hypocotyl. In the case of the growth of B. lactics BL740, the proposed optimal media contained 12.73 g/L of soy protein, 29.55 g/L of soy peptone, and 130.67 g/L of soy hypocotyl. To produce isoflavone aglycones, optimized media was composed of 2.06 g/L, soy protein, 1.25 g/L of soy peptone, and 60.02 g/L of soy hypocotyl.

• Environmental and Resource Economics Review
• /
• v.14 no.2
• /
• pp.337-379
• /
• 2005

This choice experiments study values the non-market benefits of water quality improvements in Paldang Reservoir and Han River, located in Korea. A fractional factorial orthogonal design was used to produce four different choice sets per respondent, before employing choice examples to screen out irrational responses. The panel mixed logit model (with normal distributions for the attributes) fit the data best, indicating that allowing for both heterogeneous preferences across households and correlation between repeated choices may represent actual choice behaviors best of all the estimated models. The significant standard deviations of the random attributes suggest that the taste for each attribute may vary considerably in the population. The annual benefits to the Seoul Metropolitan area for a small (large) enhancement of the clarity of water, a gradual removal of unpleasant waters, and a gradual improvement in biodiversity, were estimated to be some 1.5 trillion (1.7 trillion) Won, 2 trillion Won, and 1.7 trillion Won, respectively, with 1.8~2.6 trillion Won for at least two of them occurring together. The study also discusses potential biases germane to choice experiments studies of this type.

• Journal of Ginseng Research
• /
• v.33 no.2
• /
• pp.143-148
• /
• 2009

This study was carried out to detennine the optimal submerged culture conditions for the growth increase of ginseng adventitious roots containing germanium by means of a fractional factorial design with four factors and three levels, using the response surface methodology (RSM). The ginseng (Panax ginseng CA. Meyer) adventitious roots were induced by plant growth regulators and cultured in a liquid SH medium. The effects of various $GeO_2$ and phosphoric acid ($H_3P0_4$) concentrations in the medium, $GeO_2$ addition time and the pH of the medium on the fresh weight of the ginseng adventitious roots were investigated. The optimum pH of the medium and the phosphoric acid concentration detennined by the partial differentiation of the model equation were 4.7 and 6.0 roM, respectively. The predicted optimal $GeO_2$ concentration was 10 ppm and the $GeO_2$ addition time did not affect the growth of ginseng adventitious roots. Under these conditions, the growth of the ginseng adventitious root containing germanium was predicted to be 2.47 g.

• Journal of the Korea Concrete Institute
• /
• v.20 no.2
• /
• pp.147-156
• /
• 2008

In an uniaxial compressive test of a concrete standard specimen (150$\times$300 mm) the crack initiation and extension with the stress increase are the major reason of the failure, which is similar to the breakage of the particle bonding in the simulation by using particle bonded model, especially particle flow code in 3 dimensions (PFC3D) developed by Itasca Consulting Group Inc. That is the main motive to study the possibility of an uniaxial compressive strength test simulation. It is important to investigate the relationship between the micro-parameters and the macro-properties because the 3-dimensional particle bonded model uses the spherical particles to analyze the physical phenomena. Contact bonded model used herein has eight micro-parameters and there are five macro-properties; Young's modulus, Poisson's ratio, uniaxial compressive strength and the crack initiation stress and the ratio concerning the crack propagation with the stress. To simulate the compressive test we made quantitative relationships between the micro-parameters and the macro-properties by using the fractional factorial design and various sensitivity analyses including regression analysis, which result in the good agreement with the previous studies. Also, the stress-stain curve and the crack distribution over the specimen given by PFC3D showed the mechanical behavior of the concrete standard specimen under the uniaxial compression. It is concluded that the particle bonded model can be a good tool for the analyzing the mechanical behavior of concrete under the uniaxial compressive load.