• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.99-120
• /
• 2010

Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

• Korean Journal of Remote Sensing
• /
• v.25 no.5
• /
• pp.435-444
• /
• 2009

In the case of oil spill accident at sea, information concerning the movement of spilled oil is important in making response strategies. Aircrafts and the satellites have been utilized for monitoring of spilled oil. In these days, numerical models are using to predict the movement of the spilled oil. In the future a coupling method of modeling and remote sensing data should be needed to predict more correctly the spilled oil. The purpose of this paper is to present an application of satellite image data to an oil spill prediction model as an initial condition. Environmental Fluid Dynamics Computer Code (EFDC) was used to predict the movement of the oil spilled from Hebei Spirit incident occurred in Taean coastal area on December 7,2007. In order to make the model initial condition and to compare the model results, two satellite images, KOMPSAT-2 MSC and ENVISAT ASAR obtained on December 8 and 11, were used during the period of the oil spill incident. The model results showed an improvement for the prediction of the spilled oil by using the initial condition deduced from satellite image data than the initial condition specified at the oil spill incident site in the respects of the distributed spilled area.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4D
• /
• pp.351-360
• /
• 2010

In 2010, the number of registered vehicles reached almost at 17.48 millions in Korea. This dramatic increase of vehicles influenced to increase the number of traffic accidents which is one of the serious social problems and also to soar the personal and economic losses in Korea. Through this research, an enhanced intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network will be developed in order to obtain the important data for developing the countermeasures of traffic accidents and eventually to reduce the traffic accidents in Korea. Firstly, this research has investigated the influencing factors of road geometric features on the traffic volume of each approaching for the intersections where traffic accidents and congestions frequently take place and, a linear regression model of traffic accidents and traffic conflicts were developed by examining the relationship between traffic accidents and traffic conflicts through the statistical significance tests. Secondly, this research also developed an intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network through applying the intersection traffic volume, the road geometric features and the specific variables of traffic conflicts. Lastly, this research found out that the developed model is better than the existed forecasting models in terms of the reliability and accuracy by comparing the actual number of traffic accidents and the predicted number of accidents from the developed model. In conclusion, it is expect that the cost/effectiveness of any traffic safety improvement projects can be maximized if this developed intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network use practically at field in the future.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.19 no.1
• /
• pp.52-61
• /
• 2016

To inject huge amount of $CO_2$ for CCS application, high pressure pipeline transport is accompanied. Rapid depressurization of $CO_2$ pipeline is required in case of transient processes such as accident and maintenance. In this study, numerical analysis on the depressurization of high pressure $CO_2$ pipeline was carried out. The prediction capability of the numerical model was evaluated by comparing the benchmark experiments. The numerical models well predicted the liquid-vapor two-phase depressurization. On the other hands, there were some limitations in predicting the temperature behavior during the supercritical, liquid phase and gaseous phase expansions.

• Journal of the Ergonomics Society of Korea
• /
• v.24 no.1
• /
• pp.9-17
• /
• 2005

81.1% of traffic accidents is attributed to the drivers. In this regard, D/E model is a practical and effective method in terms of the cost and time in evaluating the road hazardousness. To examine the validity of the threshold values by the levels of demand We selected 10 subjects and collected their physiological signals while they were driving on Honam Highway (Jeonju ${\leftrighttarro}$ Hoideog section). Based on the collected data, the hazardous road condition was evaluated using the new threshold values of the effort level determined by cluster analysis. In applying the D/E model, a decision method based on the demand level was suggested, using a traffic accident prediction model. Additionally, the limit value of the effort level was determined using the drivers' physiological signal data collected at the highway. A comparison analysis of the two D/E models revealed no significant difference: The existing method and the clustering method determined 9 and 7 hazardous road zones, respectively, while actual traffic accidents were reported in 6 and 4 zones, respectively among the predicted road hazardous zones. However, the latter method suggested a more scientific and rational basis in determining the limit value of the Effort level. In conclusion, although D/E model has a great merit as a pioneering method to reflect human factors in evaluating the road hazardousness, it is believed that this method could be improved by a more dynamic method that considers the traffic conditions and the individual physiological signal of the drivers simultaneously in determining a better limit.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.64-75
• /
• 2017

Previous count models using fixed parameter can not consider the unobserved heterogeneity, as the standard error of the count value is underestimated, excessive t-values are derived thereby reducing the reliability of the model. Also, the study of unsignalized intersections are inadequate because of the difficulty of collecting data and statistical limits for accurate analytical processes compared to the signalized intersections. The purpose of this study is to analyze the factors affecting traffic accidents by constructing the count model using random parameters, and it aimed to distinguish between existing studies based on the rural unsignalized intersections. As a result of the analysis, 7 variables were presented as significant variables, and 2 variables(presence of crosswalk, speed limit) were presented as random parameter.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3B
• /
• pp.221-230
• /
• 2009

In Korea, many water intake plants are easily affected by effluents of sewage treatment plants because sewage treatment plants are usually located upstream or nearby the plants of the same riverine area. Furthermore, the inflow of harmful contaminants owing to pollutant spills or transportation accidents of vehicles using the roads and bridges intersecting the river causes significant impact on the management of water intake plants. Paldang lake, the main water intake plants in Korea, is especially exposed to various water pollution accidents, because the drainage basin area is significantly large compared to the water surface area of the lake. Therefore it is necessary to predict the possible pollutant spill in advance and consider measurements in case of water pollution. In this study, water quality prediction was performed in Paldang Lake in Korea durig the dry season using two-dimensional numerical models. In order to represent the cases of pollutant accidents, the difference of pollutant transport patterns with varying injection points was analyzed. Numerical simulations for hydrodynamics of water flow and water quality predictions were performed using RMA-2 and RAM4 respectively. As a result of simulation, the difference of pollutant transport with the injection points was analyzed. As a countermeasure against the pollutant accident, the augmentation of the flow rate is proposed. In comparison with the present state, the rapid dilution and flushing effects on the pollutant cloud could be expected with increase of flow rate. Thus, increase of flow rate can be used for operation of water intake plants in case of pollutant spill accidents.

• Journal of Radiation Protection and Research
• /
• v.38 no.2
• /
• pp.60-67
• /
• 2013

A diffusion coefficient is an important parameter in the prediction of atmospheric dispersion using a Gaussian plume model, and its modelling approach varies. In this study, dispersion coefficients recommended by the U. S. Nuclear Regulatory Commission's (U. S. NRC's) regulatory guide and the Canadian Nuclear Safety Commission's (CNSC's) regulatory guide, and used in probabilistic accident consequence analysis codes MACCS and MACCS2 have been investigated. Based on the atmospheric dispersion model for a hypothetical accidental release recommended by the U. S. NRC, its influence to atmospheric dispersion factor was discussed. It was found that diffusion coefficients are basically predicted from a Pasquill- Gifford curve, but various curve fitting equations are recommended or used. A lateral dispersion coefficient is corrected with consideration for the additional spread due to plume meandering in all models, however its modelling approach showed a distinctive difference. Moreover, a vertical dispersion coefficient is corrected with consideration for the additional plume spread due to surface roughness in all models, except for the U. S. NRC's recommendation. For a specified surface roughness, the atmospheric dispersion factors showed differences up to approximately 4 times depending on the modelling approach of a dispersion coefficient. For the same model, the atmospheric dispersion factors showed differences by 2 to 3 times depending on surface roughness.

• Journal of Korea Water Resources Association
• /
• v.39 no.5 s.166
• /
• pp.395-403
• /
• 2006

This study suggests the use of a simple method, called the unit concentration response function(UCRF) for predicting travel time and dispersion of pollutants with the minimum information of study area instead of numerical models which are widely used In the Previous studies. However, the numerical models require time-consuming, tedious effort, and many data sets. So we derive the UCRF using some components such as travel time, peak concentration, and passage time of pollutant etc. We use the regression equation for the estimations of components which were developed from the investigations of many river basins in USA. This study used the regression equaiton for the UCRF to the accident of Dichloromethane leak into the Nakdong River occurred on June 30, 1994 and applied the UCRF for the predictions of travel time and dispersion. The predictions were compared with the results by QUAL2E model. The results by the regression equaiton and QUAL2E model had a good agreement between observed and simulated concentrations. Therefore, the regression equation for the UCRF which can simply estimate travel time and concentration of pollutants showed its applicability for the ungaged basin.

• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.105-126
• /
• 2023

The domestic used car market continues to grow along with the used car online platform service. The used car online platform service discloses vehicle specifications, accident history, inspection history, and detailed options to service consumers. Most of the preceding studies were predictions of used car prices using vehicle specifications and some options for vehicles. As a result of the study, it was confirmed that there was a nonlinear relationship between used car prices and some specification variables. Accordingly, the researchers tried to solve the nonlinear problem by executing a Machine Learning model. In common, the Regression based Machine Learning model had the advantage of knowing the actual influence and direction of variables, but there was a disadvantage of low Cost Function figures compared to the Decision Tree based Machine Learning model. This study attempted to predict used car prices of six domestic brands by utilizing both vehicle specifications and vehicle options. Through this, we tried to collect the advantages of the two types of Machine Learning models. To this end, we sequentially conducted a regression based Machine Learning model and a decision tree based Machine Learning model. As a result of the analysis, the practical influence and direction of each brand variable, and the best tree based Machine Learning model were selected. The implications of this study are as follows. It will help buyers and sellers who use used car online platform services to predict approximate used car prices. And it is hoped that it will help solve the problem caused by information inequality among users of the used car online platform service.