• Journal of Korean Society for Quality Management
• /
• v.38 no.3
• /
• pp.413-424
• /
• 2010

Mixture experiments involve combining ingredients or components of a mixture and the response is a function of the proportions of ingredients which is independent of the total amount of a mixture. The purpose of the mixture experiments is to find the optimum blending at which responses such as the flavor and acceptability are maximized. We assume the quadratic or special cubic canonical polynomial model over the experimental region for a mixture since the current mixture is assumed to be located in the neighborhood of the optimal mixture. The cost of the mixture is proportional to the cost of the ingredients of the mixture and is the linear function of the proportions of the ingredients. In this paper, we propose mixture response surface methods to develop a mixture such that the cost is down more than ten percent as well as mean responses are as good as those from the current mixture. The proposed methods are illustrated with the well known the flare experimental data described by McLean and Anderson(1966).

• Applied Chemistry for Engineering
• /
• v.32 no.5
• /
• pp.574-580
• /
• 2021

The main goal of this study was to find an optimal surfactant mixture composition for the development of the best performing cleansing products. Three different surfactants including sodium cocoyl alaninate (SCoA), cocamidopropyl betaine (CPB), and decyl glucoside (DG) were selected, which showed excellent properties in detergency, foaming height, and contamination rate through preliminary experiments. The experiments by simplex centroid design matrix for surfactant mixtures were performed, and the regression analysis was conducted with the experimental data. Surface response model equations, which is statistically significant (p < 0.05), were obtained. The optimal composition of the surfactant mixture was also determined as SCoA (0.22), CPB (0.78), and DG(0.00) from simultaneous optimization of three response variables.

• Journal of the Korean Applied Science and Technology
• /
• v.41 no.2
• /
• pp.318-328
• /
• 2024

In this study, we enhanced the emulsifying power and solubilization of sucrose stearate (SS) by creating mixtures with sodium deoxycholate (SDOC) and PEG-40 hydrogenated castor oil (HCO). We employed the design of mixture experiments (DOME) methodology to identify the optimal composition of the mixture, and the impact of varying the mixture composition on its characteristics was examined through regression analysis of the experimental data. It was revealed that the emulsifying power for coconut oil was most improved when only SDOC was added to SS, and solubilization was most improved when only HCO was added, while the emulsifying power for cetyl ethylhexanoate (CEH) was most significantly improved when SDOC and HCO were added together. As a result of simultaneous optimization of three characteristics, emulsifying power for each of coconut oil and CEH, and solubilization, the optimal surfactant mixture composition was determined as SS 0.7939, SDOC 0.0586, and HCO 0.1475.

• Korean Journal of Food Science and Technology
• /
• v.35 no.4
• /
• pp.617-622
• /
• 2003

Experimental designs were applied to optimize the mixture ratio for the extrudate made by soymilk residue and corn grits. Nine candidate points were examined for their significance on extrudate using the modified distance design. Bending force, expansion ratio, bulk density, water solubility index (WSI), water absorption index (WAI) and color $(L^*,\;a^*,\;b^*)$ were the significant factors improving the extruded cereal production, and these values were applied to the mathematical models. Results showed that bending force, expansion ratio WSI, WAI and color $(L^*,\;b^*)$ increased with increasing the corn grits, whereas bulk density tended to decrease. The statistical study showed that the fitted models were adequate to describe the contour plot and all responses. Optimum mixture ratio allowing to maximize the two responses (expansion ratio and $b^*$) and minimize the response (WAI) were examined with a numerical optimization methods. The numerical optimization method was obtained as 53.18% : 46.19% (corn grits : soymilk residue).

• Korean journal of food and cookery science
• /
• v.23 no.4 s.100
• /
• pp.551-560
• /
• 2007

This study was performed to determine the optimum ratio of ingredients in the Sulgidduk with barley(Hordeum vulgare L.) sprout powder. A mathematical analytical tool was employed for optimization of the typical ingredients. The canonical form and trace plot showed the affect of each ingredient in the mixture against the final product. Mixture design showed 14 experimental points, including 4 replicates for three independent variables. The three independent variables selected for the experiment were: water($15{\sim}22%$), barley sprout powder($1{\sim}4%$), and sugar($12{\sim}19%$). The optimum responses variables such as color values(L, a, and b), instrumental texture parameters(hardness, gumminess, and chewiness), and sensory characteristics(appearance, color, smell, taste, softness, moistness, and overall acceptability) were evaluated. The Hunter colorimetric L- and a-values of the Sulgidduk decreased with an increasing amount of barley sprout powder. As more barley sprout powder was added, a higher b-value resulted. Textural hardness, gumminess, and chewiness were lowered by the addition of barley sprout powder. The optimum formulation obtained by both numerical and graphical methods showed similar results. The representative optimal ingredient ratio commonly obtained by both methods were: 18.2% water, 2.0% barley sprout powder, and 14.8% sugar.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.795-800
• /
• 2010

Embedding a large vocabulary speech recognition system in mobile devices requires a reduced acoustic model obtained by eliminating redundant model parameters. In conventional optimization methods based on the minimum description length (MDL) criterion, a binary Gaussian tree is built at each state of a hidden Markov model by iteratively finding and merging similar mixture components. An optimal subset of the tree nodes is then selected to generate a downsized acoustic model. To obtain a better binary Gaussian tree by improving the process of finding the most similar Gaussian components, this paper proposes a new distance measure that exploits the difference in likelihood values for cases before and after two components are combined. The mixture weight of Gaussian components is also introduced in the component merging step. Experimental results show that the proposed method outperforms MDL-based optimization using either a Kullback-Leibler (KL) divergence or weighted KL divergence measure. The proposed method could also reduce the acoustic model size by 50% with less than a 1.5% increase in error rate compared to a baseline system.

• International Journal of Safety
• /
• v.9 no.2
• /
• pp.6-10
• /
• 2010

The flash point of liquid solution is one of the most important flammability properties that used in hazard and risk assessments. Minimum flash point behaviour (MFPB) is showed when the flash point of a liquid mixture is below the flash points of the individual components. In this paper, the lower flash points for the flammable binary system, n-decane+n-octanol, were measured by Pensky-Martens closed cup tester. This binary mixture exhibited MFPB. The measured flash points were compared with the values calculated by the Raoult's law and the optimization method using van Laar and UNIQUAC equations. The optimization method were found to be better than those based on the Raoult's law, and successfully estimated MFPB. The opimization method based on the van Laar equation described the experimentally-derived data more effectively than was the case when the prediction model was based upon the UNIQUAC.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• Clean Technology
• /
• v.20 no.3
• /
• pp.314-320
• /
• 2014

The purpose of this work is to optimize composition of mixture refrigerants used in the C3MR (Propane & Mixed Refrigerants) process by a statistical optimization technique. C3MR studied in this work is one of widely used commercial natural gas liquefaction processes with high efficiency. Process simulation was performed in a commercial process simulator and methane ($C_1$), ethane ($C_2$), propane ($C_3$), and nitrogen ($N_2$) were selected as mixed refrigerants. Using the process model, optimum composition of refrigerants mixture was determined via mixture design and central composite design to produce minimum energy consumption. As a result, it was confirmed that energy consumption is reduced down to 11.3% comparing to existing design. It was also compared with heat effectiveness through temperature profile of MCHE (main cryogenic heat exchanger).

• The Korean Journal of Food And Nutrition
• /
• v.26 no.1
• /
• pp.29-34
• /
• 2013

The objective of this study was to manufacture three kinds of domestic sweet potato Makgeolli using a mixture design and an optimization technique. The effects of four different manufacture methods, such as simultaneous saccharification and fermentation (SSF) with or without malt and separate hydrolysis and fermentation (SHF) with or without malt were determined. The SSF methods of Makgeolli produced higher alcohol content than that of SHF methods. The sensory score was not influenced by different making methods. Fourteen experimental points were selected, and rice (10~50%), sweet potato (10~50%) and water (40~60%) were chosen as independent variables. The measured responses were sensory preference, total polyphenol content, and DPPH radical scavenging activities. The ratio of the optimum sweet potato Makgeolli mixture formulation was developed as 15.11 (rice): 44.89 (sweet potato): 40 (water) using the optimization technique. The desirability of the optimum mixture formulation was 0.839. Yellow sweet potato Makgeolli using the optimum mixture formulation produced higher soluble sugar content compared to others. Regular sweet potato Makgeolli produced higher pH. The purple sweet potato Makgeolli's total polyphenol content and DPPH radical scavenging activity were measured to be the highest at $771.91{\pm}1.42mg\;GAE/{\ell}$, $131.55{\pm}4.03%$.