• 대한화학회지
• /
• 제58권6호
• /
• pp.543-552
• /
• 2014

A quantitative structure activity relationship (QSAR) study is performed for modeling and prediction of oral bioavailabilities of 216 diverse set of drugs. After calculation and screening of molecular descriptors, linear and nonlinear models were developed by using multiple linear regression (MLR), artificial neural network (ANN), support vector machine (SVM) and random forest (RF) techniques. Comparison between statistical parameters of these models indicates the suitability of SVM over other models. The root mean square errors of SVM model were 5.933 and 4.934 for training and test sets, respectively. Robustness and reliability of the developed SVM model was evaluated by performing of leave many out cross validation test, which produces the statistic of $Q^2_{SVM}=0.603$ and SPRESS = 7.902. Moreover, the chemical applicability domains of model were determined via leverage approach. The results of this study revealed the applicability of QSAR approach by using SVM in prediction of oral bioavailability of drugs.

• Journal of Welding and Joining
• /
• 제19권3호
• /
• pp.334-341
• /
• 2001

The chemical and geometric effects of weld on flow-accelerated corrosion (FAC) of SA106 Gr.C low alloy steel pipe in 3.5wt% NaCl and simulated feedwater of nuclear power plant have been investigated by using rotating cylinder electrode. Polarization test and weight loss test were conducted and compared at rotating speed of 2000rpm (3.14m/s) with the variables of chemical and geometric parameters. The results showed that the chemical effects were relatively larger than the geometric effects, and the welded parts were the local anode and preferentially corroded, which could be explained by the differences between microstructural and compositional parameters. On the other hand, under active corrosion conditions, the heat affected zone were severely corroded and microstructural effects became the important role in the whole process.

• 펄프종이기술
• /
• 제37권1호
• /
• pp.67-72
• /
• 2005

In the grade change operations inputs and outputs are highly correlated and application of conventional linear feedback control methods such as PID schemes might lead to poor control performance. In this study the neural networks model for the grade change operation is trained by using bilinear terms which can represent non-linear characteristics of grade change operations. The inverse model of the grade change operation is obtained from training and the optimal input variables are computed from the trained neural networks as well. The proposed bilinear inverse model predictive control scheme was found out to showlittle discrepancy between simulated outputs and setpoints.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2009년도 제38회 동계학술대회 초록집
• /
• pp.137-137
• /
• 2010

Copper electroplating is a very popular and important technology for depositing high-quality conductor interconnections, especially in through silicon via (TSV). As this advanced packaging technique developing, a mass of copper and chemical solution are used, so attention to these chemical materials into the utilization and costs can not be ignored. An economical and practical real-time chemical solution monitoring has not been achieved yet. Either Red-green-blue (RGB) or optical emission spectroscopy (OES) color sensor can successfully monitor the color condition of solution during the process. The reaction rate, uniformity and quality can map onto the color changing. Hidden Semi Markov model (HSMM) can establish mapping from the color change to upper indicators, and artificial neural network (ANN) can be integrated to comprehensively determine its targets, whether the solution inside the container can continue to use.

• 한국표면공학회지
• /
• 제36권6호
• /
• pp.466-474
• /
• 2003

To develop a method of detecting dross in coating layer on hot-dip galvanizing steel, chemical etching behavior of the artificial coating layers with top and bottom dross were investigated. After chemical etching with the mixture of picric acid and sodium thiosulfate, each of the top and bottom dross take its distinct color, and alloy layer in coating is also observed. Defects in the coating layers of HGI(hot rolled galvanized iron), CGI(continuous galvanized steel sheet) and GA(galvannealed steel) were analysed, and methods of dross detection which can be applied to inspection process in manufacture were suggested.

• Elastomers and Composites
• /
• 제56권3호
• /
• pp.117-123
• /
• 2021

Electronic skin (or E-skin) is an artificial smart skin composed of one or more than two sensors. E-skins detect external stimuli and convert them into electrical signals. Various types of E-skin sensors exist, including mechanical, physical, and chemical, depending on the detection signals involved. For wearable E-skins with superior sensitivity and reliability, developing conductors that possess both good elasticity and sensitivity is essential. Typical electrical conductors used in these sensors show very high sensitivity, but they have drawbacks such as non-linearity, irreversibility, and a narrow sensing range. To address these issues, stretchable and lightweight ionic conductors have been actively used in E-skin applications. This study summarizes the recent progress on various types of ionic conductors and ionic-conductor-based E-skin sensors.

• Membrane and Water Treatment
• /
• 제9권5호
• /
• pp.363-371
• /
• 2018

In this work, it was investigated the usability of artificial bee colony (ABC) and genetic algorithm (GA) in modeling adsorption of Co(II) onto drinking water treatment sludge (DWTS). DWTS, obtained as inevitable byproduct at the end of drinking water treatment stages, was used as an adsorbent without any physical or chemical pre-treatment in the adsorption experiments. Firstly, DWTS was characterized employing various analytical procedures such as elemental, FT-IR, SEM-EDS, XRD, XRF and TGA/DTA analysis. Then, adsorption experiments were carried out in a batch system and DWTS's Co(II) removal potential was modelled via ABC and GA methods considering the effects of certain experimental parameters (initial pH, contact time, initial Co(II) concentration, DWTS dosage) called as the input parameters. The accuracy of ABC and GA method was determined and these methods were applied to four different functions: quadratic, exponential, linear and power. Some statistical indices (sum square error, root mean square error, mean absolute error, average relative error, and determination coefficient) were used to evaluate the performance of these models. The ABC and GA method with quadratic forms obtained better prediction. As a result, it was shown ABC and GA can be used optimization of the regression function coefficients in modeling adsorption experiments.

• 보존과학연구
• /
• 통권29호
• /
• pp.149-162
• /
• 2008

Because stone cultural heritages in Korea are mostly situated outdoors without any notable protection, there are severe damages from physical, chemical and biological weathering. And this in turn causes deformation and structural damage. To counteract this problem and increase durability, various kinds of conservation materials are used in the conservation and restoration treatment. However, there are not many practical and technological experiments on this subject. Accordingly this research is for analysis of effect for treatment to make use a resin of the ethyl silicate for the granite in Mt. Nam of Gyeongju. It takes a long time to confirm the test result regarding durability and side effects of the conservatives after treatment. So we built up an artificial environment through freezing and melting test, and evaluated the conservation materials. As a result of this experiment, porosity and absorptivity was increased in accordance with processing of freezing and melting test. But other things such as elastic wave speed, elastic modulus, uniaxial compressive strength and tensile strength was decreased. It will make a plan to form a method of research systematically for mechanism and element of weathering and to elicit a correlation among experiment of artificial weathering and practical natural weathering from next research.

• 상하수도학회지
• /
• 제18권3호
• /
• pp.357-365
• /
• 2004

Effect of artificial circulation on amelioration of water quality in Yeoncho Lake was analyzed using summer data between 1991-2002. Two sites, intake tower area where aeration systems are concentrated in and near the inlet of reservoir were selected for comparison in this study. Summer averages between may and september Showed that aeration system might be beneficial in the improvement of water quality of BOD5, COD, and TN while Chl-a concentration and transparency did show opposite pattems. Wilcoxon's singed rank test for matched pair indicated slight increase of BOD5 and COD concentrations in the vicinity of intake tower while other variables did not show any significant differences from data of inlet of reservoir. During the study, it was found that the following subjects need to be investigated for more detailed analysis. 1) Dynamic pollutant loading from outside and inside the lake, 2) Biological, Chemical and Physical lake data when aeration systems are in and not in operation and 3) Radius of influence of aeration system.

• 보존과학연구
• /
• 통권30호
• /
• pp.93-102
• /
• 2009

This study was carried out to investigate the effect of artificial accelerated ageing treatment on the permanence of lining papers produced from Korea and Japan. As time gone by, organic cultural properties are affected by chemical and physical deterioration because of various factors including the conditions of preservation environment and their material properties. In the public historical storage or owned as private collections, are vulnerable to sever amages caused by poor preservation environment as well as by other natural factors. In this study, the deterioration behaviors of lining paper in optical & mechanical properties were discussed. Overall, lining papers produced from Korea showed lower reduction in mechanical strength properties compared to the lining papers produced from Japan.