• Journal of Intelligence and Information Systems
• /
• v.11 no.3
• /
• pp.83-101
• /
• 2005

Customer retention is one of the major issues in life insurance industry, in which competition is increasingly fierce. There are many things for the life insurers to do many things to retain the customers. One of those things is to make sure to keep in touch with all customers. When an insurance-planner resigned, his/her customers must be taken care of by some planner-assistants. This article outlines the design of Contact Scheduling System (CSS) that supports planner-assistants for contacting the customers. Planner-assistants are unable to share the resigned insurance-planner's experience and knowledge regarding the customer relationship management. The CSS developed by employing both Classification And Regression Tree (CART) technique and Sequential Pattern Mining (SPM) technique has a two-stage process. In the first stage, it segments the customers into eight groups by CART model. Then it generates contact scheduling information consisting of contact-purpose, contact-interval and contact-channel, according to the segment's typical contact pattern. Contact-purpose is derived by schedule-driven, event-driven, or business-rule-driven. Schedule-driven contact is determined by SPM model. In the operation of CSS in a realistic situation, it shows a practicality in supporting planner-assistants to keep in touch with the customers efficiently and effectively.

• Journal of Korean Society on Water Environment
• /
• v.31 no.1
• /
• pp.12-18
• /
• 2015

In this research, the hydrologic effects between a pre-existing urban landuse and low impact development (LID) applied conditions were compared and evaluated. The infiltration trench and tree box filter that were utilized in LID represent only 1% of the catchment area that they drain. Storm event monitoring were conducted from July 2010 to July 2014 on a total of 22 storm events in both LID sites. After LID, hydrological improvement was observed as the sites exhibited a delay (lag time) or reduction in the magnitude, frequency and duration of runoff and flow peaks as the rainfall progress. In addition, the maximum irreducible peak flow reduction for infiltration trench was found to be 61% and 33% for the tree box filter when rainfall was 40 mm and 30 mm, respectively. In designing LID, it is recommended to consider the storage capacity and catchment area, as well as the amount of rainfall and runoff on the site.

• The Journal of Engineering Geology
• /
• v.21 no.4
• /
• pp.281-293
• /
• 2011

We investigated the causes and characteristics of a landslide at Hwangryeong Mountain, Busan, based on aerial photos, annual precipitation data, rock fracture patterns, and geomorphic features using GIS Software, and a statistical analysis of tilted trees. The analyzed slope shows evidence of a previous slope failure event and the possibility of future failures. Although the NW-SE trending slope was relatively stable until 1975, a large-scale slope failure occurred between 1975 and 1985 due to complex factors, including favorably oriented geologic structures, human activity, and heavy rain. This indicates that a detailed study of geologic structures, slope stability, and rainfall characteristics is important for slope cuttings that could be a major factor and cause of urban landsliding events. The statistic analysis of tilted trees shows a slow progressive creeping type of mass wasting with rock falls oblique to the dip of the slope, with the slope having moved towards the west since 1985. A concentration of tree tilting has developed on the northwestern part of the slope, which could reach critical levels in the future. The analysis of deformed trees is a useful tool for understanding landslides and for predicting and preventing future landslide events.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.1
• /
• pp.229-249
• /
• 2022

This paper investigates machine learning models for predicting the designation of administrative issues in the KOSDAQ market through various techniques. When a company in the Korean stock market is designated as administrative issue, the market recognizes the event itself as negative information, causing losses to the company and investors. The purpose of this study is to evaluate alternative methods for developing a artificial intelligence service to examine a possibility to the designation of administrative issues early through the financial ratio of companies and to help investors manage portfolio risks. In this study, the independent variables used 21 financial ratios representing profitability, stability, activity, and growth. From 2011 to 2020, when K-IFRS was applied, financial data of companies in administrative issues and non-administrative issues stocks are sampled. Logistic regression analysis, decision tree, support vector machine, random forest, and LightGBM are used to predict the designation of administrative issues. According to the results of analysis, LightGBM with 82.73% classification accuracy is the best prediction model, and the prediction model with the lowest classification accuracy is a decision tree with 71.94% accuracy. As a result of checking the top three variables of the importance of variables in the decision tree-based learning model, the financial variables common in each model are ROE(Net profit) and Capital stock turnover ratio, which are relatively important variables in designating administrative issues. In general, it is confirmed that the learning model using the ensemble had higher predictive performance than the single learning model.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1133-1148
• /
• 2019

Tree growth and vitality in forest shows seasonal changes. So, in order to detect forest damage accurately, we have to use satellite images before and after damages taken at the same season. However, temporal resolution of high or medium resolution images is very low,so it is not easy to acquire satellite images of the same seasons. Therefore, in this study, we estimated spectral information of the same DOY using time-series Landsat images and used the estimates as reference values to assess forest damages. The study site is Hwasun, Jeollanam-do, where forest damage occurred due to hail and drought in 2017. Time-series vegetation index (NDVI, EVI, NDMI) maps were produced using all Landsat 8 images taken in the past 3 years. Daily normal vegetation index maps were produced through cloud removal and data interpolation processes. We analyzed the difference of daily normal vegetation index value before damage event and vegetation index value after event at the same DOY, and applied the criteria of forest damage. Finally, forest damage map based on daily normal vegetation index was produced. Forest damage map based on Landsat images could detect better subtle changes of vegetation vitality than the existing map based on UAV images. In the extreme damage areas, forest damage map based on NDMI using the SWIR band showed similar results to the existing forest damage map. The daily normal vegetation index map can used to detect forest damage more rapidly and accurately.

• Fire Science and Engineering
• /
• v.33 no.5
• /
• pp.149-154
• /
• 2019

The stability of firefighting pipes is crucial in the event of an earthquake. In Korea, specification-based designs are used in accordance with NFSC. However, engineering performance-based designs are used for buildings that have special requirements. For firefighting pipes, tree type pipe networks are usually utilized in buildings; however, they are characterized by several limitations. Hence, grid type and loop type networks are being utilized lately. Earthquake-resistant designs for firefighting pipes in Korea utilize NFPA 13 as the cookbook. Nevertheless, an engineering analysis is required to verify its reliability. The NFPA 13 standard used in Korea is a design method for engineers who lack earthquake engineering analysis knowledge of pipes and adapt ASCE and ASME guidelines. Earthquake resistant designs in Korea review braces only. Hence, various analyses under load conditions, such as the internal pressure of a pipe, force exerted by a continuous load, and an earthquake, are required to ensure reliability. An engineering earthquake-resistance analysis showed that tree type pipe networks are less stable than grid and loop type pipe networks. A comparison of earthquake-resistance analysis based on stress and strain revealed that strain analysis exhibited a conservative result value in the range of over-stress. Therefore, for the earthquake-resistance analysis of pipes, it is rational that engineers perform analysis to achieve the required standards through engineering analysis rather than uniform calculations, which should also be analyzed considering various analysis conditions.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.323-338
• /
• 2024

This study analyzes the Korean professional volleyball league and predict match outcomes using popular machine learning classification methods. Match data from the 2012/2013 to 2022/2023 seasons for both male and female leagues were collected, including match details. Two different data structures were applied to the models: Separating matches results into two teams and performance differentials between the home and away teams. These two data structures were applied to construct a total of four predictive models, encompassing both male and female leagues. As specific variable values used in the models are unavailable before the end of matches, the results of the most recent 3 to 4 matches, up until just before today's match, were preprocessed and utilized as variables. Logistc Regrssion, Decision Tree, Bagging, Random Forest, Xgboost, Adaboost, and Light GBM, were employed for classification, and the model employing Random Forest showed the highest predictive performance. The results indicated that while significant variables varied by gender and data structure, set success rate, blocking points scored, and the number of faults were consistently crucial. Notably, our win-loss prediction model's distinctiveness lies in its ability to provide pre-match forecasts rather than post-event predictions.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.19 no.2
• /
• pp.145-154
• /
• 2013

HNS, including crude oil and products, shipments have increased. The risk analysis of HNS has assumed the importance, especially in maritime transportation area. There are various forms and kinds of HNS and the consequences of an accident are serious. In order to provide practical measures for preventing accidents, this study analyses the potential risks of HNS on maritime transportation accidents at domestic sea by using Event Tree Analysis. This study carries out risk assessment with F-N curve and risk matrix focusing on liquid cargo carriers (Oil and Products Tanker, Chemical Tanker, LPG/LNG Tanker, etc.). Explosion and sinking, suffocation indicate high consequence when on collision represent high probability. Improving human errors should be the main factor to mitigate risk on human lives.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.1
• /
• pp.33-40
• /
• 2012

This paper proposes a method to implement biological early warning systems(BEWS). This system generates periodically data event using a monitoring daemon and it extracts the feature parameters from this data sets. The feature parameters are derived with 6 variables, x/y coordinates, distance, absolute distance, angle, and fractal dimension. Specially by using the fractal dimension theory, the proposed algorithm define the input features represent the organism characteristics in non-toxic or toxic environment. And to find a moderate algorithm for learning the extracted feature data, the system uses an extended learning algorithm(UChoo) popularly used in machine learning. And this algorithm includes a learning method with the extended data expression to overcome the BEWS environment which the feature sets added periodically by a monitoring daemon. In this algorithm, decision tree classifier define class distribution information using the weight parameter in the extended data expression. Experimental results show that the proposed BEWS is available for environmental toxicity detection.

• Tuberculosis and Respiratory Diseases
• /
• v.44 no.5
• /
• pp.1166-1171
• /
• 1997

Aspiration of foreign bodies into tracheobronchial tree is more common in children than in adults. Foreign bodies in airway commonly occur by accident, and in most cases they get removed without delay. Small foreign bodies that lodge in the peripheral airway are often asymptomatic initially and can result in respiratory symptoms several years later. Although foreign body aspiration is frequently suspected in children with acute or recurrent pulmonary symptoms, it is rarely considered in adults, unless a clear history of an aspiration event can be obtained. We have experienced and studied a case of occult aspiration of a shrimp which had been lodged for a long period.