• The Korean Journal of Applied Statistics
• /
• v.33 no.3
• /
• pp.321-334
• /
• 2020

The US Federal Reserve (Fed) has decided to cut interest rates. When we look at the expression of the FOMC statements at the time of policy change period we can understand that Fed has been communicating with markets through a change of word selection. However, there is a criticism that the method of analyzing the expression of the decision sentence through the context can be subjective and limited in qualitative analysis. In this paper, we evaluate the signaling effect of FOMC statements based on previous research. We analyze decision making characteristics from the viewpoint of text mining and try to predict future policy trend changes by capturing changes in expressions between statements. For this purpose, a decision tree and neural network models are used. As a result of the analysis, it can be judged that the discrepancy indicators between statements could be used to predict the policy change in the future and that the US Federal Reserve has systematically implemented policy signaling through the policy statements.

• Health Policy and Management
• /
• v.12 no.1
• /
• pp.125-143
• /
• 2002

The objectives of this study were analysis of patient\`s characteristics and market segmentation in oriental medical care and western medical care. This study focused on medical utilization using Anderson's health utilization model. The source of data was 1998 National Health and Nutrition Survey which Korean Institute For Health and Social Affairs carried out. A stratified multistage probability sampling design was used in this survey. The analysis was conducted using the statistical software package SPSS version 10.0 and Answer Tree 2.1 which is one of data mining methodology. The results were as follows ; 1) 44.9% of respondents reported visiting oriental medical center within recent two weeks. 3.4% of them used oriental medical care. The group of age, kind of disease and medical expenditure are associated with the difference western and oriental medical utilization rate. 2) There were several factors related to utilization of oriental medical care according to decision tree. Especially, important factors that patient chose his medical center were kinds of disease, kinds of common medical use, and expenditure. 3) in the results of CART analysis, market of oriental medical care were classified by seven categories. The major groups who have a preference for oriental medicine were those musculo-skeletal, cerebra-vascular disease, or chronic headache patients, and they had a preference fur oriental medical care in common use. These results show that oriental and western medical market were divided into various areas by market segmentation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.300-310
• /
• 2018

The purpose of this study is to compare the change of Well-Dying awareness and decision of university student before and after taking the course of death study. A questionnaire survey was conducted for university students 93 before education, 117 after education who participated in the Death Studies related lectures at Daejeon Metropolitan City for 15 weeks from August to December 2016. The general characteristics of survey are gender, age. grade, major, marriage condition, religion, family member living together and health status. Four items on the perception aspect of death, five items on the aspect of acceptance of death, seven items of death decision and twelve items for death education's interest and importance were configured as a reference scale. The statistical method carried out the chi-square test, the independent sample t-test, and the decision tree analysis. Based on the decision tree, At the time of preparation for death(cancer patient, terminal patient, etc.) and the elderly(65 years old or older), the education transition rate was 66.7%. But After education, 65.3% of the respondents were in adult, middle and high school, under elementary school, university, and graduate school, which showed a significant difference. Therefore we are looking for death education's effectiveness and setting directions for education's period and contents. the negative viewpoints and worries about the implementation of death education at elementary, middle and high schools and universities are resolved and the death education will positively affect the change of attitude of students.

• Proceedings of the Korean Society of Toxicology Conference
• /
• 2005.05a
• /
• pp.206-206
• /
• 2005

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.55-75
• /
• 2024

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.1-9
• /
• 2006

For the indoor positioning, wireless fingerprinting is most favorable because fingerprinting is most accurate among the techniques for wireless network based indoor positioning which does not require any special equipments dedicated for positioning. The deployment of a fingerprinting method consists of off-line phase and on-line phase. Off-line phase is not a time critical procedure, but on-line phase is indeed a time-critical procedure. If it is too slow then the user's location can be changed while it is calculating and the positioning method would never be accurate. Even so there is no research of improving efficiency of on-line phase of wireless fingerprinting. This paper proposes a decision-tree method for wireless fingerprinting and performs comparative analysis of the fingerprinting techniques including K-NN, Bayesian and our decision-tree.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.425-433
• /
• 2009

Data mining is the method to find useful information for large amounts of data in database. It is used to find hidden knowledge by massive data, unexpectedly pattern, relation to new rule. We need a data mining tool to explore a lot of information. There are many data mining tools or solutions; E-Miner, Clementine, WEKA, and R. Almost of them are were focused on diversity and general purpose, and they are not useful for laymen. In this paper we design and implement a web-based data mining tool using PHP and WEKA. This system is easy to interpret results and so general users are able to handle. We implement Apriori algorithm of association rule, K-means algorithm of cluster analysis, and J48 algorithm of decision tree.

• Asian Oncology Nursing
• /
• v.5 no.1
• /
• pp.3-10
• /
• 2005

Back ground: Nurses now occupy one third of all hospital human resources. Therefore, efficient management of nursing manpower is getting more important. While it is very clear that nursing workload requirement analysis and patient severity classification should be done first for the efficient allocation of nursing workforce, these processes have been conducted manually with ad hoc rule. Purposes: This study was tried to make a predict model for patient classification according to nursing need. We tried to find the easier and faster method to classify nursing patients that can help efficient management of nursing manpower. Methods: The nursing patient classifications data of the hospitalized cancer patients in one of the biggest cancer center in Korea during 2003.1.1-2003.12.31 were assessed by trained nurses. This study developed a prediction model and analyzing nursing needs by data mining techniques. Patients were classified by three different data mining techniques, (Logistic regression, Decision tree and Neural network) and the results were assessed. Results: The data set was created using 165,073 records of 2,228 patients classification database. Main explaining variables were as follows in 3 different data mining techniques. 1) Logistic regression : age, month and section. 2) Decision tree : section, month, age and tumor. 3) Neural network : section, diagnosis, age, sex, metastasis, hospital days and month. Among these three techniques, neural network showed the best prediction power in ROC curve verification. As the result of the patient classification prediction model developed by neural network based on nurse needs, the prediction accuracy was 84.06%. Conclusion: The patient classification prediction model was developed and tested in this study using real patients data. The result can be employed for more accurate calculation of required nursing staff and effective use of labor force.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.18
• /
• pp.8265-8270
• /
• 2016

Purpose: A cost-utility analysis was performed to assess the cost-utility of neoadjuvant chemotherapy regimens containing doxorubicin and cyclophosphamide (AC) versus paclitaxel and gemcitabine (PG) for locally advanced breast cancer patients in Iran. Materials and Methods: This cross-sectional study in Namazi hospital in Shiraz, in the south of Iran covered 64 breast cancer patients. According to the random numbers, the patients were divided into two groups, 32 receiving AC and 32 PG. Costs were identified and measured from a community perspective. These items included medical and non-medical direct and indirect costs. In this study, a data collection form was used. To assess the utility of the two regimens, the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-Core30 (EORTC QLQ-C30) was applied. Using a decision tree, we calculated the expected costs and quality adjusted life years (QALYs) for both methods; also, the incremental cost-effectiveness ratio was assessed. Results: The results of the decision tree showed that in the AC arm, the expected cost was 39,170 US$ and the expected QALY was 3.39 and in the PG arm, the expected cost was 43,336 dollars and the expected QALY was 2.64. Sensitivity analysis showed the cost effectiveness of the AC and ICER=-5535 US$. Conclusions: Overall, the results showed that AC to be superior to PG in treatment of patients with breast cancer, being less costly and more effective.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.5
• /
• pp.964-968
• /
• 2009

The purpose of this study is to select the major pulse indicators and evaluate their significance in discriminating the subtypes of Pattern Identifications (PI) from stroke patients. Decision tree analysis was carried out using clinical data collected from 835 stroke patients with the same subtypes diagnosed identically by two experts with more than 3 year clinical experiences. Among the 10 pulse indicators, 6 major pulse indicators (slow, rapid, strong, weak, slippery, and fine pulse) were selected by decision tree analysis. The accumulated distributions of six pulse indicators in each PI showed that strong was major pulse indicator in Fire-Heat pattern, slippery in Dampness Phlegm pattern, weak in Qi Deficiency pattern. But there were two major combinations in Yin deficiency pattern, weak or fine with rapid pulse and weak or fine without rapid pulse. Therefore, it is suggested that 6 pulse indicators can be used for discrimination of PI in stroke patients, though the combination studies between these pulse indicators and the other PI indicators are left for further study.