• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.21-27
• /
• 2019

Selection of feature pattern gathered from the observation of the RNA sequencing data (RNA-seq) are not all equally informative for identification of differential expressions: some of them may be noisy, correlated or irrelevant because of redundancy in Big-Data sets. Variable selection of feature pattern aims at differential expressed gene set that is significantly relevant for a special task. This issues are complex and important in many domains, for example. In terms of a computational research field of machine learning, selection of feature pattern has been studied such as Random Forest, K-Nearest and Support Vector Machine (SVM). One of most the well-known machine learning algorithms is SVM, which is classical as well as original. The one of a member of SVM-criterion is Support Vector Machine-Recursive Feature Elimination (SVM-RFE), which have been utilized in our research work. We propose a novel algorithm of the SVM-RFE with Q-learning in reinforcement learning for better variable selection of feature pattern. By comparing our proposed algorithm with the well-known SVM-RFE combining Welch' T in published data, our result can show that the criterion from weight vector of SVM-RFE enhanced by Q-learning has been improved by an off-policy by a more exploratory scheme of Q-learning.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.06a
• /
• pp.224.2-224.2
• /
• 2010

연료개질기는 연료전지 시스템의 핵심 구성요소 중의 하나로 도시가스로부터 수소를 생산하는 역할을 담당한다. 연료개질기는 주로 탈황, 수증기 개질, 수성가스 전이, 선택적 산화 반응의 4단계로 구성되어 있으며 이 중 상온 탈황부분을 제외한 나머지 부분은 일체화 설계를 통해 제작된다. 탈황의 경우 도시가스에 포함된 부취제인 황화합물를 제거하여 후단에 위치한 촉매층이 황에 의해 피독되는 것을 막는 역할을 하며 주로 상온흡착식 탈황제를 사용한다. 황이 제거된 도시가스는 물과 함께 연료개질기로 도입되어 수증기 개질반응을 통하여 수소, 일산화탄소, 이산화탄소 및 소량의 메탄과 미반응 수증기로 구성된 개질가스로 전환된다. 이후의 수성가스 전이반응에서는 일산화탄소가 물과 반응하여 수소 생산량을 늘리며 동시에 일산화탄소의 농도를 낮추게 된다. 또한 고분자 전해질 연료전지에 공급되는 개질가스는 선택적 산화반응을 통하여 일산화탄소의 농도를 10ppm이하로 유지하게 된다. 이러한 기능의 연료개질기 개발의 주요 이슈로는 컴팩트화 및 고효율화이며 이 두가지 요소를 고려하여 연료개질기를 설계하여야 한다. 연료전지 시스템의 전체부피를 줄이기 위한 노력의 일환으로 연료개질기의 컴팩트화가 요구되는데 가정용 연료전지 기술 선진국인 일본 제품의 경우 $1Nm^3/h$급 연료개질기의 부피는 20L정도로 알려져 있다. 또한 연료전지 시스템의 효율은 연료개질기의 개질효율과 연료전지 스택의 발전효율의 곱으로 계산되기 때문에 연료개질기의 연료개질 효율은 전체 시스템의 효율에 직접적으로 영향을 미치게 된다. 한국에너지기술연구원에서는 수소생산량 기준 $1Nm^3/h$급 연료개질기의 개발을 완료하였으며 크기 및 효율면에서 선진국 제품과 비교하여 동등 또는 우위의 수준을 달성하였다. 연료개질기 내부의 혼합 및 분배 구조를 개선하고 각 촉매층의 최적 배치를 통해 연료개질기의 부피를 최소화 하였으며 연료개질기 내부에서 고온부위와 저온부위 사이의 최적 열교환을 통해 열효율을 극대화 시켰다. 현재 개발된 $1Nm^3/h$급 개질기의 단열 후 부피는 13.5L 그리고 단독운전 시 열효율은 80%(LHV)로 측정되었다. 또한 $1Nm^3/h$급의 연료개질기의 스케일-업 설계를 통하여 수소생산량 3, $5Nm^3/h$ 규모의 연료개질기를 개발하였으며 성능평가가 진행 중이다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.4
• /
• pp.21-26
• /
• 2011

Feature ranking is useful to gain knowledge of data and identify relevant features. In this study, we proposed a use of feature ranking for classification of neuro-degeneration and vascular dementia in micro-Raman spectra of platelet. The entire region of the spectrum is divided into local region including several peaks, followed by Gaussian curve fitting method in the region to be modeled. Local minima select from the subregion and then remove the background based on the position by using interpolation method. After preprocessing steps, significant features were selected by feature ranking method to improve the classification accuracy and the computational complexity of classification system. PCA (principal component analysis) transform the selected features and the overall features that is used classification with the number of principal components. These were classified as MAP (maximum a posteriori) and it compared with classification result using overall features. In all experiments, the computational complexity of the classification system was remarkably reduced and the classification accuracy was partially increased. Particularly, the proposed method increased the classification accuracy in the experiment classifying the Parkinson's disease and normal with the average 1.7 %. From the result, it confirmed that proposed method could be efficiently used in the classification system of the neuro-degenerative disease and vascular dementia of platelet.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.141-149
• /
• 2008

Recently we frequently analyze multivariate data with quite large number of variables. In such data sets, virtually duplicated variables may exist simultaneously even though they are conceptually distinguishable. Duplicate variables may cause problems such as the distortion of principal axes in principal component analysis and factor analysis and the distortion of the distances between observations, i.e. the input for cluster analysis. Also in supervised learning or regression analysis, duplicated explanatory variables often cause the instability of fitted models. Since real data analyses are aimed often at multiple purposes, it is necessary to reduce the number of variables to a parsimonious level. The aim of this paper is to propose a practical algorithm for selection of a subset of variables from a given set of p input variables, by the criterion of minimum trace of partial variances of unselected variables unexplained by selected variables. The usefulness of proposed method is demonstrated in visualizing the relationship between selected and unselected variables, in building a predictive model with very large number of independent variables, and in reducing the number of variables and purging/merging categories in categorical data.

• Journal of Soil and Groundwater Environment
• /
• v.13 no.6
• /
• pp.23-30
• /
• 2008

Air sparging technique has been used for remediation of VOC(volatile organic compound)-contaminated aquifer. The aim of this study was to develop an innovative air sparging technique that enhances the efficiency of air intrusion into a specific horizontal layer of aquifer where the contaminants exist with the help of water-soluble surfactant. A twodimensional physical box model, packed with homogeneous sand, was used for simulating the aquifer in this study. Aqueous solution of anionic surfactant (100 mg/L, sodium dodecylbenzene sulfonate) was used to suppress the surface tension of groundwater. Three sets of experiments were conducted: air sparging experiment without surfactant application, air sparging experiments for box model where the surfactant solution was applied right above the air injection point, and air sparging experiments with surfactant solution layer formed in the middle of the box. It was found that the sparging influence zone was expanded up to five times of that formed by sparging without surfactant application. The size of sparging influence zone was more sensitive to the air flow (injection) rate with surfactant application than that without surfactant. More importantly, injection of air into the target aquifer layer was successful with surfactant application. Findings in this study are expected to provide more options for designing remediation processes using air sparging.

• Journal of the Korean Ceramic Society
• /
• v.42 no.1
• /
• pp.56-61
• /
• 2005

Highly durable photocatalytic paper containing anatase $TiO_{2}$, active carbon and ceramic fiber, which can adsorb VOCs and decompose them by photo oxidation simultaneously, was manufactured and characterized. Optimum concentration of PDADMAC to let $TiO_{2}$ adhere on the surfaces of active carbon and ceramic fiber selectively was $10\~15$ ppm in a slurry mixture for making photocatalytic paper. The thickness and basis weight of the produced catalytic paper by paper-making method were 0.4 mm and 380 $g/m^{2}$, respectively. Adsorption reaction by active carbon and photocatalytic decomposition reaction by $TiO_{2}$ were proceeded simultaneously, by which the abatement rate was found to be greatly enhanced compared to the similar environment with single adsorption reaction or single photocatalytic reaction only. The selective attachment of $TiO_{2}$ on ceramic fiber and active carbon was found to be very effective in preventing decomposition of substrate by the $TiO_{2}$ attack during exposure to UV light.

• Resources Recycling
• /
• v.10 no.5
• /
• pp.29-35
• /
• 2001

This study was carried out to recover gold, silver and valuable metals from the printed circuit boards (PCBs) of waste computers. PCBs samples were crushed under 1 mm by a shredder and separated into 30% conducting and loft nonconducting materials by an electrostatic separator. The conducting materials contained valuable metals which were then used as feed materials for magnetic separation. 42% of magnetic materials from the conducting materials was removed by magnetic separation as nonvaluable materials and the others, 58% of non magnetic materials, was used as leaching samples containing 0.227 mg/g Au and 0.697 mg/g Ag. Using the materials of leaching from magnetic separation, more than 95% of copper, iron, zinc, nickel and aluminium was dissolved in 2.0M sulfuric acid solution, added with 0.2M hydrogen peroxide at $85^{\circ}C$. Au and Ag were not extracted in this solution. On the other hand, more than 95% of gold and 100% of silver were leached by the selective leaching with a mixed solvent (0.2M($NH_4$)$_2$$S_2$$O_3$,0.02M $CuSO_4$,0.4M $NH_4$OH). Finally, the residues were reacted with a NaCl solution to leach Pb whereas sulfuric acid was used to leach Sn. Recoveries reached 95% and 98% in solution, respectively.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.23 no.3
• /
• pp.33-41
• /
• 2015

An alternative was investigated to maximize the treatment efficiency of wastewater treatment plant without large scale expansion. 79% of detention time was required for enough nitrogen control. As aeration time was extended, nitrification was processed, but opposite trend was seen in phosphorus. High concentration of $NO_3-N$ interrupted PAOs activity not to absorb phosphorus. An alternative was devised for selective use of anaerobic or anoxic zone. Trisection was suggested for alternative use of center room. The result was relatively successful. The concentration of phosphorus was reduced with reduction of nitrogen. Extended anaerobic condition seemed to stimulate denitrification. Valve connection of internal return from aeration tank will make it possible to use middle room alternatively. This method will be a good alternative for seasonal variation of water temperature.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.121-130
• /
• 2004

In these days, multiple-path generation method is highly demanded in practice and research areas, which can represents realistically travelers behavior in choosing possible alternative paths. The multiple-path generation algorithm is one of the key components for policy analysis related to ATIS, DRGS and ATMS in ITS. This study suggested a method to generate multiple Possible paths from an origin to a destination. The approach of the suggested method is different from an other existing methods(K-shortest path algorithm) such as link elimination approach, link penalty approach and simulation approach. The result of the multi-label vine-building shortest path algorithm(MVA) by Kim (1998) and Kim(2001) was used to generate multiple reasonable possible paths with the concept of the rational upper boundary. Because the MVA algorithm records the cost, back-node and back-back node of the minimum path from the origin to the concerned node(intersection) for each direction to the node, many potential possible paths can be generated by tracing back. Among such large number of the potential possible paths, the algorithm distinguishes reasonable alternative paths from the unrealistic potential possible paths by using the concept of the rational upper boundary. The study also shows the very simple network examples to help the concept of the suggested path generation algorithm.

• Journal of Korean Society of Environmental Engineers
• /
• v.38 no.7
• /
• pp.343-352
• /
• 2016

Effects of grinding time and chemicals dosage in arsenic removal from contaminated paddy soil in China were investigated using lab scale attrition and froth flotation combining process. Arsenic concentration in the field soil was 76.51 mg/kg, exceeding Korean and Chinese standards, and predominant arsenic compounds fraction in sequential extraction was "residual" (over 80%). After wet sieving, soil with >2 mm and < 0.038 mm showed concentration lower than 'Warning Level' in Korea. Soil with 0.038-0.075 mm, showing the highest concentration, was discarded since it occupied minor weight fraction (10.1%). Thus soil between 0.075 and 2 mm was only used in the combining process. The highest Arsenic concentration in progeny fragments smaller than 0.038 mm reached up to 981.66 mg/kg after 5 min of attrition. Optimal dosage of collector ($C_5H_{11}OCS_2K$) and modifier ($Na_2S$ and $CuSO_4$) in froth flotation process for the selective separation of the chipped progeny particles from the parent fragments were determined both as 200 g/ton. Arsenic removal efficiency in froth flotation process was 38.47% and it was increased to 72.74% in additional flotation process, scavenging. Average arsenic concentration after overall process - wet sieving, attrition and froth flotation - was estimated to 16.45 mg/kg.