• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.71-85
• /
• 2021

The purpose of this study is to find out which artificial intelligence methodology is most suitable for creating a foreign exchange rate prediction model using the indicators of bond market and interest rate market. KTBs and MSBs, which are representative products of the Korea bond market, are sold on a large scale when a risk aversion occurs, and in such cases, the USD/KRW exchange rate often rises. When USD liquidity problems occur in the onshore Korean market, the KRW Cross-Currency Swap price in the interest rate market falls, then it plays as a signal to buy USD/KRW in the foreign exchange market. Considering that the price and movement of products traded in the bond market and interest rate market directly or indirectly affect the foreign exchange market, it may be regarded that there is a close and complementary relationship among the three markets. There have been studies that reveal the relationship and correlation between the bond market, interest rate market, and foreign exchange market, but many exchange rate prediction studies in the past have mainly focused on studies based on macroeconomic indicators such as GDP, current account surplus/deficit, and inflation while active research to predict the exchange rate of the foreign exchange market using artificial intelligence based on the bond market and interest rate market indicators has not been conducted yet. This study uses the bond market and interest rate market indicator, runs artificial neural network suitable for nonlinear data analysis, logistic regression suitable for linear data analysis, and decision tree suitable for nonlinear & linear data analysis, and proves that the artificial neural network is the most suitable methodology for predicting the foreign exchange rates which are nonlinear and times series data. Beyond revealing the simple correlation between the bond market, interest rate market, and foreign exchange market, capturing the trading signals between the three markets to reveal the active correlation and prove the mutual organic movement is not only to provide foreign exchange market traders with a new trading model but also to be expected to contribute to increasing the efficiency and the knowledge management of the entire financial market.

• Korean Chemical Engineering Research
• /
• v.55 no.3
• /
• pp.322-331
• /
• 2017

District heating was first introduced in Korea in 1985. As the service life of the underground thermal piping network has increased for more than 30 years, the maintenance of the underground thermal pipe has become an important issue. A variety of complex technologies are required for periodic inspection and operation management for the maintenance of the aged thermal piping network. Especially, it is required to develop a model that can be used for decision making in order to derive optimal maintenance and replacement point from the economic viewpoint in the field. In this study, the analysis was carried out based on the repair history and accident data at the operation of the thermal pipe network of five districts in the Korea District Heating Corporation. A failure probability model was developed by introducing statistical techniques of qualitative analysis and binomial logistic regression analysis. As a result of qualitative analysis of maintenance history and accident data, the most important cause of pipeline damage was construction erosion, corrosion of pipe and bad material accounted for about 82%. In the statistical model analysis, by setting the separation point of the classification to 0.25, the accuracy of the thermal pipe breakage and non-breakage classification improved to 73.5%. In order to establish the failure probability model, the fitness of the model was verified through the Hosmer and Lemeshow test, the independent test of the independent variables, and the Chi-Square test of the model. According to the results of analysis of the risk of thermal pipe network damage, the highest probability of failure was analyzed as the thermal pipeline constructed by the F construction company in the reducer pipe of less than 250mm, which is more than 10 years on the Seoul area motorway in winter. The results of this study can be used to prioritize maintenance, preventive inspection, and replacement of thermal piping systems. In addition, it will be possible to reduce the frequency of thermal pipeline damage and to use it more aggressively to manage thermal piping network by establishing and coping with accident prevention plan in advance such as inspection and maintenance.

• Journal of dental hygiene science
• /
• v.12 no.2
• /
• pp.85-91
• /
• 2012

The purpose of this study was to examine the factors influencing the decision to get implant treatment at dental clinic. The subjects in this study were 321 patients at dental hospitals and clinics. Andersen model in which predisposing variables, enabling variables and need variables were suggested as independent variables was used. The implant decision making was selected as a dependent variable in the model. Using logistic regression analysis, we found statistically significant effects of three independent variables: 1) class, 2) satisfaction with the facility; 3) familiarity with others received implant treatment. Those with the middle or high class background were more likely to take implant treatment. Those who were satisfied with clinic facility were more likely to take implant treatment. Those who were familiar with others received implant treatment were more likely to take implant treatment. This result implies the importance of opinion of others were received the same treatment. Hence viral marketing effort is required even in dental care field.

• The Journal of the Korea Contents Association
• /
• v.20 no.4
• /
• pp.508-517
• /
• 2020

Servitization presents an innovative model to create business value in the automotive industries. This study set out to introduce a servitization model based on the rental business of the tire industry and identify determinants to affect the renewal of contracts around the service types of servitization and the characteristics of customers. Independent variables include the service types, demographics and regions, and inflow channels in 163,742 contracts by case companies in the nation in 2016~2019 with the renewal of contracts as a dependent variable. Correlations between variables were analyzed through cross-tabulation and binary logistic regression analysis. The findings show that the contract renewal rate had positive(+) relations with customized service and negative(-) ones with vehicle maintenance service. There were differences in the contract renewal rate according to such customer characteristics as gender and region, but no clear correlations were found in the age group and vehicle type(domestic/foreign). Of the inflow channels, offline channels tended to have a higher renewal rate than online channels. At open malls, contract renewal increased by 8.4 times due to contract switches at offline channels. Based on these findings, the study discussed directions for practical strategies with regard to the development of new service, implementation of customer-centric servitization, and management of sales channels according to the servitization of manufacturers.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.2
• /
• pp.139-148
• /
• 2020

The most important factor affecting the berthing energy generated when a ship berths is the berthing velocity. Thus, an accident may occur if the berthing velocity is extremely high. Several ship features influence the determination of the berthing velocity. However, previous studies have mostly focused on the size of the vessel. Therefore, the aim of this study is to analyze various features that influence berthing velocity and determine their respective importance. The data used in the analysis was based on the berthing velocity of a ship on a jetty in Korea. Using the collected data, machine learning classification algorithms were compared and analyzed, such as decision tree, random forest, logistic regression, and perceptron. As an algorithm evaluation method, indexes according to the confusion matrix were used. Consequently, perceptron demonstrated the best performance, and the feature importance was in the following order: DWT, jetty number, and state. Hence, when berthing a ship, the berthing velocity should be determined in consideration of various features, such as the size of the ship, position of the jetty, and loading condition of the cargo.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.4
• /
• pp.1759-1768
• /
• 2012

The present study was intended to measure the level of fatigue symptoms among nurses working for a university hospital and to reveal its related factors. The self-administered questionnaires were given to 450 nurses during the period from October 1st to 31st, 2010. As a results, the level of fatigue symptoms were 75.1% in normal group, and the high-risk group 24.9%. The level of fatigue symptoms reflected in job stress contents were higher as job demand was higher, and the autonomy of job and the supervisor support was lower. In correlations, fatigue symptoms were found to be in a positive correlation with job demand, whereas in negative correlation with autonomy of job and supervisor support. The adjusted odds ratio of fatigue symptoms on job demand were significantly increased in the high risk group than in low group, but autonomy of job. were significantly decreased in the high risk group than in low group. In conclusion, the study results indicated that the level of fatigue symptoms is independently influenced by job stress contents.

• Management & Information Systems Review
• /
• v.32 no.2
• /
• pp.21-46
• /
• 2013

The purpose of this paper is to find impacts of financial activities-financing and investment of Venture Firms during pre-listing periods on the firms' Venture Firm's listing(delisting). The several ratios financial variables relevant to the financing and investment were examined whether there are difference or not between two venture firms groups. The results of study can be summarized as follows. First, the firms of successful group have fewer numbers of equity financing and higher times of premium in issuing stocks than those of failed firms but there is no significant difference in the required time from startup to listing the KOSDAQ. Second, there is no significant difference in the ratio of capital increase in IPO between two groups but additional survey reveals that the successful firms financed equity in IPO by higher numbers of premium than failed firms, which can makes the major shareholder of the successful firms maintain high rayios share of stock. Third, the ratio of working capital investment of the successful firms is significantly higher than that of failed firms, on the other hand the failed firms' ratios of equipment and repayment investment are higher than those of successful firms. Finally, the ratio of R&D investment has no difference between two groups, this result is against the expectation, which is to be further analyzed.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.145-154
• /
• 2012

Recently, the cardiovascular disease has increased by causes such as westernization dietary life, smoking, and obesity. In particular, the acute myocardial infarction (AMI) occupies 50% death rate in cardiovascular disease. Following this trend, the AMI has been carried out a research for discovery of risk factors based on national data. However, there is a lack of diagnosis minor suitable for Korean. The objective of this paper is to develop a classifier for short-term relapse mortality prediction of cardiovascular disease patient based on prognosis data which is supported by KAMIR(Korea Acute Myocardial Infarction). Through this study, we came to a conclusion that ANN is the most suitable method for predicting the short-term relapse mortality of patients who have ST-segment elevation myocardial infarction. Also, data set obtained by logistic regression analysis performed highly efficient performance than existing data set. So, it is expect to contribute to prognosis estimation through proper classification of high-risk patients.

• Journal of Hospice and Palliative Care
• /
• v.19 no.3
• /
• pp.233-239
• /
• 2016

Purpose: Little is known regarding the factors associated with the willingness of family caregivers of terminal cancer patients to participate in a bereaved survey. This study aimed to ascertain the pre-loss factors that predict actual participation in a bereaved survey. Methods: We conducted a prospective observational study using data from two multi-center surveys at the end-of-life and after loss. In order to identify the pre-loss factors associated with participating in the bereaved survey, we used a step-wise multivariate logistic regression analysis. Results: Among 185 bereaved individuals, 30 responded to the survey (response rate: 16.2%). There were differences between the participation group and the non-participation group regarding religion, economic status, and perceived quality of care as assessed by the Quality Care Questionnaire-End of Life. A final multivariate model revealed that bereaved individuals who professed a religion (adjusted odds ratio [aOR]=5.01; P=0.008), had a high income (aOR=4.86, P=0.003), and satisfied with the care for familial relationship (aOR=4.49, P=0.003) were more likely to engage in the bereaved survey. Conclusion: Our finding suggests that improving the quality of end-of-life care may promote actual participation in a bereaved survey through easing post-loss distress. More attention should also be paid to those bereaved individuals who are hesitant to participate in a bereaved survey.