• 한국빅데이터학회지
• /
• 제4권2호
• /
• pp.61-71
• /
• 2019

반도체 웨이퍼의 표면을 연마하여 평탄화하는 Chemical Mechanical Planarization(CMP) 공정은 다양한 화학물질과 물리적인 기계장치에 의한 작용을 받기 때문에 공정을 안정적으로 관리하기 힘들다. CMP 공정에서 품질 지표로는 Material Removal Rate(MRR)를 많이 사용하고, CMP 공정의 안정적 관리를 위해서는 MRR을 예측하는 것이 중요하다. 본 연구에서는 머신러닝 기법들을 이용하여 CMP 공정에서 수집된 시계열 센서 데이터를 분석하여 MRR을 예측하는 모형과 공정 품질을 해석하기 위한 분류 모형을 개발한다. 나아가 분류 결과를 분석하여, CMP 공정 품질에 영향을 미치는 유의미한 변수를 파악하고 고품질을 유지하기 위한 공정 조건을 설명한다.

• 한국가스학회지
• /
• 제24권1호
• /
• pp.56-65
• /
• 2020

일반적으로 화재는 다양한 원인으로 발생하며 무작위로 보이기에 화재의 발생을 예측한다는 것은 매우 도전적인 문제이다. 하지만 모든 화재가 아닌 큰 피해를 주는 초대형 화재사고의 예측이 가능하다면, 선제적 대응을 통한 손실 최소화를 기대할 수 있다. 본 연구에서는 국가 전체를 대상으로 초대형 화재사고를 예측하기 위해 기계학습 기법인 k-평균 클러스터링을 이용하여 화재사고를 분류하고, 이를 인위적인 설정이 강한 비전문가 기준, 전문가 기준 분류 결과와 비교하여 예측에 적절한 분류 기준을 제안하였다. 비교 결과 기계학습을 이용한 분류가 일정한 피해규모와 비율로 분류되어, 예측에 적절한 분류 기준이라 판단하였다. 또한 초대형 화재사고의 주기성을 분석한 결과 일정한 패턴을 보였지만 높은 편차를 보였다. 따라서 단순 예측기법이 아닌 고급 예측기법을 사용하였을 때 초대형 화재사고의 발생 예측이 가능하다고 판단되었다.

• Advances in nano research
• /
• 제12권5호
• /
• pp.489-499
• /
• 2022

Nanofluids have recently triggered a substantial scientific interest as cooling media. However, their stability is challenging for successful engagement in industrial applications. Different factors, including temperature, nanoparticles and base fluids characteristics, pH, ultrasonic power and frequency, agitation time, and surfactant type and concentration, determine the nanofluid stability regime. Indeed, it is often too complicated and even impossible to accurately find the conditions resulting in a stabilized nanofluid. Furthermore, there are no empirical, semi-empirical, and even intelligent scenarios for anticipating the stability of nanofluids. Therefore, this study introduces a straightforward and reliable intelligent classifier for discriminating among the stability regimes of alumina-water nanofluids based on the Zeta potential margins. In this regard, various intelligent classifiers (i.e., deep learning and multilayer perceptron neural network, decision tree, GoogleNet, and multi-output least squares support vector regression) have been designed, and their classification accuracy was compared. This comparison approved that the multilayer perceptron neural network (MLPNN) with the SoftMax activation function trained by the Bayesian regularization algorithm is the best classifier for the considered task. This intelligent classifier accurately detects the stability regimes of more than 90% of 345 different nanofluid samples. The overall classification accuracy and misclassification percent of 90.1% and 9.9% have been achieved by this model. This research is the first try toward anticipting the stability of water-alumin nanofluids from some easily measured independent variables.

• 한국환경농학회지
• /
• 제19권3호
• /
• pp.259-269
• /
• 2000

식품원료인 농수축산물은 생산측면과 소비측면에서 각각 관행적으로 분류되어 사용되어 왔다. 한편 식품원료 중 잔류농약, 가축의약품, 환경오염물질과 같은 화학잔류물의 기준설정 및 규제를 위해서는 잔류가능성을 감안한 분류방식이 요구되고 있으나 식품원료의 분류방식이 통일되지 못하여 많은 혼란을 가져왔다. 본 연구에서는 농산물 중 농약잔류 허용기준을 적용하는데 있어서 국내외적으로 나타난 문제들을 지적하였으며 국제식품규격위원회의 Codex 기준을 무난히 수용할 수 있는 농수축산물 분류방식을 제시하였다. 이와 아울러 여기에서 제시한 분류법을 이용하여 잔류농약을 비롯한 다른 화학물질의 오염기준을 설치할 경우의 고려할 점을 제시하였다.

• 한국산업보건학회지
• /
• 제23권2호
• /
• pp.156-163
• /
• 2013

Objectives: Numerous poisonous substances are used in paint manufacture, but there are differences in the results of GHS classification between the Ministry of Labor(MOL) and the Ministry of Environment(MOE). Therefore, paint manufacturers suffer confusion as to how to classify a given chemical's risk and hazard level. This paper was designed to compare the classification results of chemicals by the MOL and the MOE and suggest a harmonization measure. Methods: After selecting 25 poisonous substances from among the organic solvents, pigments, and additives used in paint manufacturer, the GHS classification results by MOL and MOE were compared. Further the logic and classification of the GHS proposed by each Ministry was analyzed. Based on the derived results, a harmonization plan was proposed. Results: Based on the GHS classification of the poisonous substances, the concordance is 10.0-66.6 %, excluded flammable liquid. The GHS classifications differed based on the suggested building blocks, the sub-classification method used, the references(data sources), and subjective judgment of the experts from each Ministry. In order to pursue the harmonization plan, cooperation is demanded from the MOL and MOE.

• 한국한의학연구원논문집
• /
• 제3권1호
• /
• pp.153-167
• /
• 1997

Conventionally, identification and classification methods of natural products include the morphological survey and assay of chemical disposition, sing these methods, however, is not satisfying for the precise identification of natural products because they are often valiable in the compositions and morphology To standardize the natural products identification and classification, genomic DNA analysis such as RAPD, RFLP and Amp-FLP can be adopted for this purpose. In this study, various ginsengs and bear gall bladder were tested for the development of genetic identification and classification method. Varieties of ginsengs such as, P. ginseng, P. quinquefolium, P. japonicus and P. notoginseng, were genetically analyzed by RAPD. Also, DNA isolated from Bear blood and gall bladder, Ursus thibetanus, Ursus americanus and Ursus arctos, were analyzed by the same method. The results demonstrated that the identification and classification of bear gall bladder and various ginsengs were possible by RAPD analysis. Therefore, this method was thought to be used as a additional method for the identification and classification of other natural products.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제15권6호
• /
• pp.122-127
• /
• 2010

Constructing the national inventory that can be used as a tool to identify and assess existing or potential contamination is necessary for efficiently managing the soil and groundwater contamination. In order to start this construction, the first step is how we define and classify potential contamination sources of soil and groundwater. After selecting the basic classification model of contamination sources from developed countries, we suggested the classification and list of the potential contamination sources of soil and groundwater which are appropriate for specific conditions of South Korea. In addition, we investigated several databases to confirm the existence of available data sources and then examined established attribute data through chemical accident response information system (CARIS) and water information system (WIS) in National Institute of Environmental Research and mine geographic information system (MGIS) in Mine Reclamation Corporation. All sorts of attribute data in the existing databases can be utilized as significant assessment factors for determining the management priority of potential contamination sources in the future. Therefore, it is required the expanded investigation of additional database sources and the continual modification so that the classification system of potential contamination sources can be improved.

• 대한안전경영과학회지
• /
• 제12권3호
• /
• pp.107-119
• /
• 2010

The aim of this study was to compare the carcinogen classification systems of developed countries or global organizations with domestic system under Industrial Safety and Health Act (ISHA). We selected the representative institutions which had carcinogen classification system such as International Agency for Research on Cancer (IARC), National Toxicological Program (NTP), Environmental Protection Agency (US-EPA), American Conference of Governmental Industrial Hygienists (ACGIH), and European Union (EU). We collected the carcinogen lists issued by 5 institutions, and merged by CAS number of each chemical with Microsoft Access 7.0. We found that confirmed human carcinogens, probable human carcinogens and possible human carcinogens were 34, 179, and 252, respectively. All of the institutions classified chemicals as 2 (NTP), 3 (EU) or 5 (IARC, ACGIH, US-EPA) categories based on the weight of scientific evidences for carcinogenicity and periodically updated the carcinogen list by regular procedure. However, a total of 90 chemicals could be classified as carcinogen under ISHA in Korea. There was no procedure or system which periodically update the carcinogen lists. In addition, the status of carcinogen classification according to regulation was confused. In conclusion, these findings suggest that the carcinogen classification and management system should be amended by consideration of systems of advanced institutions and the domestic regulation system.

• Bulletin of the Korean Chemical Society
• /
• 제30권11호
• /
• pp.2717-2722
• /
• 2009

The use of the classification and regression tree (CART) methodology was studied in a quantitative structure-activity relationship (QSAR) context on a data set consisting of the binding affinities of 39 imidazobenzodiazepines for the α1 benzodiazepine receptor. The 3-D structures of these compounds were optimized using HyperChem software with semiempirical AM1 optimization method. After optimization a set of 1481 zero-to three-dimentional descriptors was calculated for each molecule in the data set. The response (dependent variable) in the tree model consisted of the binding affinities of drugs. Three descriptors (two topological and one 3D-Morse descriptors) were applied in the final tree structure to describe the binding affinities. The mean relative error percent for the data set is 3.20%, compared with a previous model with mean relative error percent of 6.63%. To evaluate the predictive power of CART cross validation method was also performed.

• 대한화학회지
• /
• 제63권2호
• /
• pp.78-84
• /
• 2019

High-resolution $^1H$ NMR spectroscopic technique has been widely used as one of the most powerful analytical tools in food chemistry as well as to define molecular structure. The $^1H$ NMR spectra-based metabolomics has focused on classification and chemometric analysis of complex mixtures. The principal component analysis (PCA), an unsupervised clustering method and used to reduce the dimensionality of multivariate data, facilitates direct peak quantitation and pattern recognition. Using a combination of these techniques, the various green teas and black teas brewed were investigated via metabolite profiling. These teas were characterized based on the leaf size and country of cultivation, respectively.