• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.18 no.1
• /
• pp.62-71
• /
• 2008

The use of chemical products to enhance and improve life is a widespread practice worldwide. But alongside the benefits of these products, there is also the potential for adverse effects to people or the environment. As a result, a number of countries or organizations have developed laws or regulations over the years that require information to be prepared and transmitted to those using chemicals, through labels or Material Safety Data Sheets (MSDS). While these existing laws or regulations are similar in many respects, their differences are significant enough to result in different labels or MSDS for the same product in different countries. Given the reality of the extensive global trade in chemicals, and the need to develop national programs to ensure their safe use, transport, and disposal, it was recognized that a Globally harmonization system of classification and labeling of chemicals(GHS) would provide the foundation for such programs. This study offered complementary details of GHS classification criteria adopted in Korea by analyzing the differences in chemical classification system between UN and Korea Ministry of Labor. Also it is proposed that mutual agreement of information DB used is required by comparing classification results of chemicals in Korea, Japan, and EU. We offered the lists of information sources useful for chemical classification.

• Journal of Korean Society for Quality Management
• /
• v.31 no.1
• /
• pp.11-20
• /
• 2003

In the development of a complex systems, the early prototypes generally have reliability problems, and, consequently these systems are subjected to a reliability growth program to find problems and take corrective action. A variety of models have been proposed to account for the reliability growth phenomena. Clear guidelines need to be established to assist the reliability engineers for model selection. In this paper, some of more well-known growth models are surveyed and classified. These models are classified based upon distinguishing model features. A procedure for model selection is introduced which is based on this classification.

• Journal of Korean Society for Atmospheric Environment
• /
• v.18 no.3
• /
• pp.231-245
• /
• 2002

A better knowledge of emission inventories can serve several important functions such as provision of public information, identification of primary sources, assessment of temporal and spatial trend, and analysis for national modelling studies. The purpose of this paper is to propose the new air emission source categories on the basis of the Korea Standard Industrial Classification. Hence, the paper focuses on reviewing and comparing the air emission sources categories of USEPA, and EU. The new emission source categories compose Tiers 1, 2, and 3. For Tier 1, there are 14 categories; fuel combustion-utilities, industries, and heating and others, chemical and allied product manufacturing, metals processing, and petroleum and related industries, etc. Tier 2 consists of small categories classified minutely in Tier 1. Tier 3 connects the categories of Tier 2 with the Korea Standard Industrial Classification.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.5
• /
• pp.393-402
• /
• 2013

The Mahalanobis-Taguchi System (MTS) is a diagnostic and predictive method for multivariate data. In the MTS, the Mahalanobis space (MS) of reference group is obtained using the standardized variables of normal data. The Mahalanobis space can be used for multi-class classification. Once this MS is established, the useful set of variables is identified to assist in the model analysis or diagnosis using orthogonal arrays and signal-to-noise ratios. And other several techniques have already been used for classification, such as linear discriminant analysis and logistic regression, decision trees, neural networks, etc. The goal of this case study is to compare the ability of the Mahalanobis-Taguchi System and logistic regression using a data set.

• Journal of Fisheries and Marine Sciences Education
• /
• v.20 no.1
• /
• pp.23-35
• /
• 2008

The purposes of this study are to analyze problems in industrial classification of fisheries in Korea and to suggest future directions. Based on a thorough review of relevant literature, the study proposes a five-level scheme for classifying fisheries. The highest level should be the fisheries industry, and the next highest level ought to be fisheries. The medium level should include fishing, aquaculture, and fishery service industries. At the fourth level, fishing is to be further divided into sea fishery and inland fishery, aquaculture into sea-surface aquaculture and inland aquaculture, and fishery service industries into integrated fishery service and fishery distribution service. The lowest level is the most detailed. At this level, sea fishery is split into deep sea fishery, offshore fishery, and coastal fishery; sea-surface aquaculture consists of sea aquaculture, seed production aquaculture, and food organism aquaculture; integrated fishery service is further classified into fishery-related service and fishery information service.

• Korean Management Science Review
• /
• v.24 no.1
• /
• pp.147-160
• /
• 2007

Six Sigma's concept has long been used as an effective way of restructuring the management process of a firm. In literature regarding Six Sigma, a number of successful cases were reported, where Six Sigma based management activities could enhance firm's strategic performance dramatically for year. However, there exist very few researches investigating the effect of Six Sigma on process innovation and quality improvement. Therefore this study propose a research model testing whether Six Sigma innovation could improve process innovation and quality improvement by industrial classification. We collected 332 valid questionnaires from expert in Six Sigma activities, and applied PLS. Empirical results showed that Six Sigma activities could contribute to process innovation and quality improvement.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.2
• /
• pp.135-145
• /
• 2023

Recently, as deep learning technology has developed, various deep learning technologies have been introduced in handwritten recognition, greatly contributing to performance improvement. The recognition accuracy of handwritten Hangeul recognition has also improved significantly, but prior research has focused on recognizing 520 Hangul characters or 2,350 Hangul characters using SERI95 data or PE92 data. In the past, most of the expressions were possible with 2,350 Hangul characters, but as globalization progresses and information and communication technology develops, there are many cases where various foreign words need to be expressed in Hangul. In this paper, we propose a model that recognizes and combines the consonants, medial vowels, and final consonants of a Korean syllable using a multi-label classification model, and achieves a high recognition accuracy of 98.38% as a result of learning with the public data of Korean handwritten characters, PE92. In addition, this model learned only 2,350 Hangul characters, but can recognize the characters which is not included in the 2,350 Hangul characters

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.1
• /
• pp.25-33
• /
• 2015

From the viewpoint of applications to manufacturing, data mining is a useful method to find the meaningful knowledge or information about states of processes. But the data from manufacturing processes usually have two characteristics which are multicollinearity and imbalance distribution of data. Two characteristics are main causes which make bias to classification rules and select wrong variables as important variables. In the paper, we propose a new data mining procedure to solve the problem. First, to determine candidate variables, we propose the multiple hypothesis test. Second, to make unbiased classification rules, we propose the decision tree learning method with different weights for each category of quality variable. The experimental result with a real PDP (Plasma display panel) manufacturing data shows that the proposed procedure can make better information than other data mining procedures.

• Industrial Engineering and Management Systems
• /
• v.10 no.4
• /
• pp.272-278
• /
• 2011

Decision tree as a classification tool is being used successfully in many areas such as medical diagnosis, customer churn prediction, signal detection and so on. The main advantage of decision tree classifiers is their capability to break down a complex structure into a collection of simpler structures, thus providing a solution that is easy to interpret. Since decision tree is a top-down algorithm using a divide and conquer induction process, there is a risk of reaching a local optimal solution. This paper proposes a procedure of optimally determining thresholds of the chosen variables for a decision tree using an adaptive particle swarm optimization (APSO). The proposed algorithm consists of two phases. First, we construct a decision tree and choose the relevant variables. Second, we find the optimum thresholds simultaneously using an APSO for those selected variables. To validate the proposed algorithm, several artificial and real datasets are used. We compare our results with the original CART results and show that the proposed algorithm is promising for improving prediction accuracy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3000-3005
• /
• 2015

Reliable monitoring and diagnosis of industrial processes is quite important for in terms of quality and safety. The goal of fault diagnosis is to find process variables responsible for causing specific abnormalities of the process. This work presents a classification-based diagnostic scheme based on nonlinear representation of process data. The use of a nonlinear kernel technique is able to reduce the size of the data considered and provides efficient and reliable representation of the measurement data. As a filtering stage a preprocessing is performed to eliminate unwanted parts of the data with enhanced performance. The case study of an industrial batch process has shown that the performance of the scheme outperformed other methods. In addition, the use of a nonlinear representation technique and filtering improved the diagnosis performance in the case study.