• Geomechanics and Engineering
• /
• v.30 no.3
• /
• pp.259-272
• /
• 2022

Rockburst is a dynamic, multivariate, and non-linear phenomenon that occurs in underground mining and civil engineering structures. Predicting rockburst is challenging since conventional models are not standardized. Hence, machine learning techniques would improve the prediction accuracies. This study describes decision based uncertainty models to predict rockburst in underground engineering structures using gradient boosting algorithms (GBM). The model input variables were uniaxial compressive strength (UCS), uniaxial tensile strength (UTS), maximum tangential stress (MTS), excavation depth (D), stress ratio (SR), and brittleness coefficient (BC). Several models were trained using different combinations of the input variables and a 3-fold cross-validation resampling procedure. The hyperparameters comprising learning rate, number of boosting iterations, tree depth, and number of minimum observations were tuned to attain the optimum models. The performance of the models was tested using classification accuracy, Cohen's kappa coefficient (k), sensitivity and specificity. The best-performing model showed a classification accuracy, k, sensitivity and specificity values of 98%, 93%, 1.00 and 0.957 respectively by optimizing model ROC metrics. The most and least influential input variables were MTS and BC, respectively. The partial dependence plots revealed the relationship between the changes in the input variables and model predictions. The findings reveal that GBM can be used to anticipate rockburst and guide decisions about support requirements before mining development.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.489-503
• /
• 2000

Data mining means data analysis and model selection using various types of data in order to explore useful information and knowledge for making decisions. Examples of data mining include scoring for credit analysis of a new customer and scoring for churn management, where the customers with high scores are given special attention. In this paper, scoring is interpreted as a modeling process of the conditional probability and polyclass scoring method is described. German credit data, a PC communication company data and a mobile communication company data are used to compare the performance of polyclass scoring method with that of the scoring method based on a tree model.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.352-357
• /
• 2001

This study presents an analysis of healthcare quality indicators using data mining for developing quality improvement strategies. Specifically, important factors influencing the inpatient mortality were identified using a decision tree method for data mining based on 8,405 patients who were discharged from the study hospital during the period of December 1, 2000 and January 31, 2001. Important factors for the inpatient mortality were length of stay, disease classes, discharge departments, and age groups. The optimum range of target group in inpatient healthcare quality indicators were identified from the gains chart. In addition, a decision support system was developed to analyze and monitor trends of quality indicators using Visual Basic 6.0. Guidelines and tutorial for quality improvement activities were also included in the system. In the future, other quality indicators should be analyze to effectively support a hospital-wide continuous quality improvement (CQI) activity and the decision support system should be well integrated with the hospital OCS (Order Communication System) to support concurrent review.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.279-300
• /
• 2001

Data mining plays an important role in knowledge discovery process and usually various existing algorithms are selected for the specific purpose of the mining. Currently, data mining techniques are actively to the statistics, business, electronic commerce, biology, and medical area and currently numerous algorithms are being researched and developed for these applications. However, in a long run, only a few algorithms, which are well-suited to specific applications with excellent performance in large database, will survive. So it is reasonable to focus our effort on those selected algorithms in the future. This paper classifies about 30 existing algorithms into 7 categories - association rule, clustering, neural network, decision tree, genetic algorithm, memory-based reasoning, and bayesian network. First of all, this work analyzes systematic hierarchy and characteristics of algorithms and we present 14 criteria for classifying the algorithms and the results based on this criteria. Finally, we propose the best algorithms among some comparable algorithms with different features and performances. The result of this paper can be used as a guideline for data mining researches as well as field applications of data mining.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.5
• /
• pp.1100-1108
• /
• 2009

The Objectives: The purpose of this study is to identify the factors related to management of DM in Korea. Methods: The subjects selected by using data of National Health and Nutrition Survey(NHANS) in 2005 were 415 adults, aged 20 and older, and diagnosed with DM. This study used data mining algorithms. This study validated the predictive power of data mining algorithms by comparing the performance of logistic regression, decision tree, and Neural Network on the basic of validation, it was found that the model performance of decision tree was the best among the above three techniques. Result: First, awareness of DM was positively associated with age, residential area, and job. The most important factor of DM awareness is age. Awareness rate of DM with 52 age over is 76.1%. Among the ${\geq}52$ age group, an important factor is family history. Among patients who are 52 years or over with family history of DM, an important factor is job. The awareness rate of patients who are 52 age over, family, history of DM, and professionals is 95.0%. Second, treatment of DM was also positively associated with awareness, region, and job. The most important factor of DM treatment is DM awareness. Treatment rate of patients who are aware of DM is 84.8%. Among patients who have awareness of DM, an important factor is region. The awareness rate of patients who are aware of DM in rural area is 10.4%. Conclusion: Finally, the result of analysis suggest that DM management programs should consider group characteristic of DM patients.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.6
• /
• pp.9-19
• /
• 2016

In finance literature, stock liquidity showing how stocks can be cashed out in the market has received rich attentions from both academicians and practitioners. The reasons are plenty. First, it is known that stock liquidity affects significantly asset pricing. Second, macroeconomic announcements influence liquidity in the stock market. Therefore, stock liquidity itself affects investors' decision and managers' decision as well. Though there exist a great deal of literature about stock liquidity in finance literature, it is quite clear that there are no studies attempting to investigate the stock liquidity issue as one of decision making problems. In finance literature, most of stock liquidity studies had dealt with limited views such as how much it influences stock price, which variables are associated with describing the stock liquidity significantly, etc. However, this paper posits that stock liquidity issue may become a serious decision-making problem, and then be handled by using data mining techniques to estimate its future extent with statistical validity. In this sense, we collected financial data set from a number of manufacturing companies listed in KRX (Korea Exchange) during the period of 2010 to 2013. The reason why we selected dataset from 2010 was to avoid the after-shocks of financial crisis that occurred in 2008. We used Fn-GuidPro system to gather total 5,700 financial data set. Stock liquidity measure was computed by the procedures proposed by Amihud (2002) which is known to show best metrics for showing relationship with daily return. We applied five data mining techniques (or classifiers) such as Bayesian network, support vector machine (SVM), decision tree, neural network, and ensemble method. Bayesian networks include GBN (General Bayesian Network), NBN (Naive BN), TAN (Tree Augmented NBN). Decision tree uses CART and C4.5. Regression result was used as a benchmarking performance. Ensemble method uses two types-integration of two classifiers, and three classifiers. Ensemble method is based on voting for the sake of integrating classifiers. Among the single classifiers, CART showed best performance with 48.2%, compared with 37.18% by regression. Among the ensemble methods, the result from integrating TAN, CART, and SVM was best with 49.25%. Through the additional analysis in individual industries, those relatively stabilized industries like electronic appliances, wholesale & retailing, woods, leather-bags-shoes showed better performance over 50%.

• Journal of Information Technology Services
• /
• v.10 no.3
• /
• pp.113-126
• /
• 2011

The smelting and the continuous casting of steel are important processes that determine the quality of steel products. Especially most of quality defects occur during solidification of the steel continuous casting process. Although quality control techniques such as six sigma, SQC, and TQM can be applied to the continuous casting process for improving quality of steel products, these techniques don't provide real-time analysis to identify the causes of defect occurrence. To solve problems, we have developed a detection model using decision tree which identified abnormal transactions to have a coarse grain structure. And we have compared the proposed model with models using neural network and logistic regression. Experiments on steel data showed that the performance of the proposed model was higher than those of neural network model and logistic regression model. Thus, we expect that the suggested model will be helpful to control the quality of steel products in real-time in the continuous casting process.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.211-218
• /
• 2005

This study presents an integrated data mining model for the credit evaluation of the customers of a capital company. Based on customer information and financing processes in capital market, we derived individual models from multi-layered perceptrons(MLP), multivariate discrimination analysis(MDA), and decision tree. Further, the results from the existing models were compared with the results from the integrated model using genetic algorithm. The integrated model presented by this study turned out to be superior to the existing models. This study contributes not only to verifying the existing individual models but also to overcoming the limitations of the existing approaches.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.917-926
• /
• 2010

It is known that bagging and boosting techniques improve the performance in classification problem. A number of researchers have proved the high performance of bagging and boosting through experiments for categorical response but not for continuous response. We study whether bagging and boosting improve data mining methods for continuous responses such as linear regression, decision tree, neural network through bagging and boosting. The analysis of eight real data sets prove the high performance of bagging and boosting empirically.

• Journal of the Korea Safety Management & Science
• /
• v.6 no.3
• /
• pp.237-247
• /
• 2004

The condition of the manufacturing process in a factory should be diagnosed and maintained efficiently because any unexpected disorder in the process will be reason to decrease the efficiency of the overall system. However, if an expert experienced in this system leaves, there will be a problem for the efficient process diagnosis and maintenance, because disorder diagnosis within the process is normally dependent on the expert's experience. This paper suggests a process diagnosis using data mining based on the collected data from the coil-spring manufacturing process. The rules are generated for the relations between the attributes of the process and the output class of the product using a decision tree after selecting the effective attributes. Using the generated rules from decision tree, the condition of the current process is diagnosed and the possible maintenance actions are identified to correct any abnormal condition. Then, the appropriate maintenance action is recommended using the decision network.