• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.25-41
• /
• 2011

Recently, support vector machines (SVMs) are being recognized as competitive tools as compared with other data mining techniques for solving pattern recognition or classification decision problems. Furthermore, many researches, in particular, have proved them more powerful than traditional artificial neural networks (ANNs) (Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003).The classification decision, such as a binary or multi-class decision problem, used by any classifier, i.e. data mining techniques is so cost-sensitive particularly in financial classification problems such as the credit ratings that if the credit ratings are misclassified, a terrible economic loss for investors or financial decision makers may happen. Therefore, it is necessary to convert the outputs of the classifier into wellcalibrated posterior probabilities-based multiclass credit ratings according to the bankruptcy probabilities. However, SVMs basically do not provide such probabilities. So it required to use any method to create the probabilities (Platt, 1999; Drish, 2001). This paper applied AdaBoost algorithm-based support vector machines (SVMs) into a bankruptcy prediction as a binary classification problem for the IT companies in Korea and then performed the multi-class credit ratings of the companies by making a normal distribution shape of posterior bankruptcy probabilities from the loss functions extracted from the SVMs. Our proposed approach also showed that their methods can minimize the misclassification problems by adjusting the credit grade interval ranges on condition that each credit grade for credit loan borrowers has its own credit risk, i.e. bankruptcy probability.

• Health Policy and Management
• /
• v.10 no.3
• /
• pp.19-49
• /
• 2000

This study was conducted to help staff members of health centers manage personnel by examining the staff members' recognition level of organization structure of health centers, their motivation, their job satisfaction level and its related factors. Data were collected from 471 staff members of 14 health centers from March 3, 1999 to April 30, 1999. The results of this study are summarized as follows. In recognition levels of organization structure of health centers, the recognition level of necessity of discretion right was highest(3.55 points on the base of 5 points), while the recognition level of the location of decision making right was lowest(2.77 points). The general recognition of organization structure of health centers was 3.06 points, the suitability of division of duties was 3.05 points, and the optimum of manpower and budget was 2.93 points. The staff members' general recognition level of the organization structure appeared significantly higher in case of the groups of small and medium sized cities, above fifties, below high school graduate, above the sixth grade, public service experience of above 20 years, service period of below 2 years at present post, and average monthly salary of one million, eight hundred and ten thousand won. In the recognition level of the location of decision making right, the groups of big cities, male, the married, above the sixth grade, health and administration posts, average monthly salary of one million, three hundred and ten thousand won to one million, and eight hundred thousand won were significantly higher than the other groups. The recognition level of necessity of discretion right was higher in case of the groups of the twenties, the unmarried, above college graduate, nursing post, public service experience of below 5 years, service period of below 2 years at present post, and average monthly salary of below eight hundred thousand won. In the recognition level of suitability of division of duties, the groups of small and medium sized cities, the married, medical technicians, public service experience of above 20 years, and service period of below 4 years at present post were significantly higher than the other groups. In the staff members' recognition levels of organization management, the recognition level of opinion response when making decision was highest(2.92 points). The recognition level of rationality of the target amount establishment method was 2.88 points and the recognition level of personnel management was 2.63 points. The recognition level of personnel management was significantly higher in case of the groups of small and medium sized cities, the forties, above the sixth grade, medical technicians, public service experience of above 20 years, service period of below 2 years at present post, and average monthly salary of above one million, eight hundred and ten thousand won. In the recognition level of opinion response when making decision, the groups of small and medium sized cities, female, the eighth grade, health and administration posts, and service period of below 2 years at present post were higher than the other groups. The recognition level of rationality of the target amount establishment method was significantly higher in case of the groups of above fifties, below high school graduate, above the sixth grade, medical service post, and public service experience of 15 to 20 years. The factors significantly influencing sanitation were sex, education level, the period of public service experience, general recognition of organization structure, recognition of necessity of discretion right, recognition of suitability of division of duties, and recognition of opinion response when making decision. The factors which significantly influenced motivation were marital status, grade, recognition of the location of decision making right, recognition of necessity of discretion right, recognition of division of duties, recognition of opinion response when making decision, and sanitation. Sex, education level, recognition of suitability of division of duties, recognition of the target amount establishment method, and motivation influenced job satisfaction significantly. The factors significantly influencing organization culture were age, the period of public service experience, service period at present post, recognition of optimum of manpower and budget, recognition of suitability of division of duties, recognition of opinion response when making decision, and recognition of rationality of the target amount establishment method. In the coming days, the staff members' job satisfaction level must be increased through motivation and efficient conduct of duty must be accomplished through rational organization structure and management. Moreover, change of the staff members' consciousness and administrative system which are suitable for local autonomy system have to be established with increase of local residents' consciousness level and education level. Forming organization culture by reformative idea which fits the new era, public health service by the Community Health Act and health education service by the Health Promotion Act must be carried out efficiently. In doing so, financial support of central government and active efforts and concerns of local governments have to be devoted in order to get public health service in which peculiarity of the community is considered to be pursued well.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.4
• /
• pp.186-198
• /
• 2016

HPAI(Highly Pathogenic Avian Influenza) is a contagious animal disease that spreads rapidly by diffusion after the first occurrence. The disease has brought tremendous social costs and economic losses. KAHIS (Korea Animal Health Information System) is the integrated system for supporting the task of preventing epidemics. They provide decision-support information, recording vehicle visiting times and facility location, etc., which is possible by enforcing registration of all livestock related facilities and vehicles. KAHIS has accumulated spatial and temporal information that enables effective tracing of potential disease trajectories and diffusion through vehicle movements. The contact network is created utilizing spatial and temporal information in KAHIS to inform facility connection via vehicle visitation. Based on the contact network, it is possible to infer spatial and temporal mechanism of disease spread and diffusion. The study objective is to empirically demonstrate how to utilize primary spatial and temporal information in KAHIS in the form of the contact network. Based on the contact network, facilities with the possibility of infection can be pinpointed within the potential spatial and temporal extent where the disease has spread and diffused. This aids the decision-making process in the task of preventing epidemics. By interpreting our demonstration results, policy implications were presented. Finally, some suggestions were made to comprehensively utilize the contact network to draw enhanced decision-support information.

• Journal of Satellite, Information and Communications
• /
• v.12 no.3
• /
• pp.22-34
• /
• 2017

The K-DRUM(K-water hydrologic & hydraulic Distributed RUnoff Model), a distributed rainfall-runoff model of K-water, calculates predicted runoff and water surface level of a dam using precipitation data. In order to obtain long-term hydrometeorological information, K-DRUM requires long-term weather forecast. In this study, we built a system providing long-term hydrometeorological information using predicted rainfall ensemble of GloSea5(Global Seasonal Forecast System version 5), which is the seasonal meteorological forecasting system of KMA introduced in 2014. This system produces K-DRUM input data by automatic pre-processing and bias-correcting GloSea5 data, then derives long-term inflow predictions via K-DRUM. Web-based UI was developed for users to monitor the hydrometeorological information such as rainfall, runoff, and water surface level of dams. Through this UI, users can also test various dam management scenarios by adjusting discharge amount for decision-making.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.6 no.3
• /
• pp.170-176
• /
• 2004

This study was carried out to establish a spatial decision support system for evaluating climatic aspects of a given geographic location in complex terrains with respect to the quality apple production. Monthly climate data from S6 synoptic stations across South Korea were collected for 1971-2000. A digital elevation model (DEM) with a 10-m cell spacing was used to spatially interpolate daily maximum and minimum temperatures based on relevant topoclimatological models applied to Jangsoo county in Korea. For daily minimum temperature, a spatial interpolation scheme accommodating the potential influences of cold air accumulation and the temperature inversion was used. For daily maximum temperature estimation, a spatial interpolation model loaded with the overheating index was used. Freezing risk in January was estimated under the recurrence intervals of 30 years. Frost risk at bud-burst and blossom was also estimated. Fruit quality was evaluated for soluble solids, anthocyanin content, Hunter L and A values, and LID ratio, which were expressed as empirical functions of temperature based on long-term field observations. AU themes were prepared as ArcGlS Grids with a 10-m cell spacing. Analysis showed that 11 percent of the whole land area of Jangsoo county might be suitable for quality 'Fuji' apple production. A computer program (MAPLE) was written to help utilize the results in decision-making for site-selection of new orchards in this region.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.163-179
• /
• 2010

Recentlythe concept of fast fashion is drawing attention as customer needs are diversified and supply lead time is getting shorter in fashion industry. It is emphasized as one of the critical success factors in the fashion industry how quickly and efficiently to satisfy the customer needs as the competition has intensified. Because the fast fashion is inherently susceptible to trend, it is very important for fashion retailers to make quick decisions regarding items to launch, quantity based on demand prediction, and the time to respond. Also the planning decisions must be executed through the business processes of procurement, production, and logistics in real time. In order to adapt to this trend, the fashion industry urgently needs supports from intelligent quick response(QR) system. However, the traditional functions of QR systems have not been able to completely satisfy such demands of the fast fashion industry. This paper proposes an intelligent quick response system for the fast fashion(IQRS-FF). Presented are models for QR process, QR principles and execution, and QR quantity and timing computation. IQRS-FF models support the decision makers by providing useful information with automated and rule-based algorithms. If the predefined conditions of a rule are satisfied, the actions defined in the rule are automatically taken or informed to the decision makers. In IQRS-FF, QRdecisions are made in two stages: pre-season and in-season. In pre-season, firstly master demand prediction is performed based on the macro level analysis such as local and global economy, fashion trends and competitors. The prediction proceeds to the master production and procurement planning. Checking availability and delivery of materials for production, decision makers must make reservations or request procurements. For the outsourcing materials, they must check the availability and capacity of partners. By the master plans, the performance of the QR during the in-season is greatly enhanced and the decision to select the QR items is made fully considering the availability of materials in warehouse as well as partners' capacity. During in-season, the decision makers must find the right time to QR as the actual sales occur in stores. Then they are to decide items to QRbased not only on the qualitative criteria such as opinions from sales persons but also on the quantitative criteria such as sales volume, the recent sales trend, inventory level, the remaining period, the forecast for the remaining period, and competitors' performance. To calculate QR quantity in IQRS-FF, two calculation methods are designed: QR Index based calculation and attribute similarity based calculation using demographic cluster. In the early period of a new season, the attribute similarity based QR amount calculation is better used because there are not enough historical sales data. By analyzing sales trends of the categories or items that have similar attributes, QR quantity can be computed. On the other hand, in case of having enough information to analyze the sales trends or forecasting, the QR Index based calculation method can be used. Having defined the models for decision making for QR, we design KPIs(Key Performance Indicators) to test the reliability of the models in critical decision makings: the difference of sales volumebetween QR items and non-QR items; the accuracy rate of QR the lead-time spent on QR decision-making. To verify the effectiveness and practicality of the proposed models, a case study has been performed for a representative fashion company which recently developed and launched the IQRS-FF. The case study shows that the average sales rateof QR items increased by 15%, the differences in sales rate between QR items and non-QR items increased by 10%, the QR accuracy was 70%, the lead time for QR dramatically decreased from 120 hours to 8 hours.

• Journal of Korean Society of Transportation
• /
• v.34 no.1
• /
• pp.43-54
• /
• 2016

Although there are continuous demands for activating BSSs(Bicycle Sharing Systems) due to the convenience and positive health effects, it is difficult to make a decision to support the existing systems and build more systems because of the deficit resulting from the operation of BSSs. Consequently, this study estimated the economic effects(WTP; Willingness to Pay) of BSS and analyzed the impact factors of WTP to support the above decision making in Daejeon. For this, we conducted a survey and collected 668 samples from the users and non-users of TASHU that is the BSS operated in Daejeon. Also, we used CVM(Contingent Valuation Method) for the estimation of WTP. The results show that the number of bicycle uses is a determinant factor having a positive relationship with WTP and car ownership and age are also determinant factors having a negative relationship with WTP. On the other hand, income and sex have no significant statistical relationship with WTP. Also, the economic benefit of TASHU was estimated as much as 49.9 billion KRW to 63.6 billion KRW. Considering the operation cost of 2.5 billion KRW, it is quite big benefit. Based on the results, it needs to support TASHU from a user perspective for the efficient operation of the system.

• 재활복지
• /
• v.21 no.2
• /
• pp.29-62
• /
• 2017

The purpose of this study is to find out the main operational scheme of the "financial planning" and "the trust" for people with developmental disabilities as a means of property protecting and managing for them. The results are as follows; Regarding to "Financial planning", it is necessary to establish a measure to meet the financial needs for people with developmental disabilities in future plan; Issues to be taken care of in the point of financial planning include plan for the maintenance and use of property for their independent life; and public and private resources and support for the disabled. Obstacles are lack of national awareness of the financial planning for the disabled. In relation to the contents of the "trust" of people with developmental disabilities, the principles of operation are assuring universality, publicness, stability, self-decision making, and individuality; operating system is a mixture of public and private; subjects of target are people with developmental disabilities with no parents or caring family as well as income. The required support is a supervisory system for the secure management of asset to entrusted institutions; the decision support system for people with developmental disabilities; maintaining the qualification of government receipt of public assistance for those who do not redeem up to a certain amount of personal property utilizing the trust system.

• Journal of Navigation and Port Research
• /
• v.45 no.1
• /
• pp.9-15
• /
• 2021

According to IMO, MASS is defined as a vessel operated at various levels independent of human interference. The safety navigation support service for MASS is designed to improve the safety and efficiency of MASS by developing public services on shore for ship arrivals/departures and for cargo handling. The safety navigation support service consists of a total of six types of services: autonomous operation, berthing/unberthing/mooring, cargo handling and ship arrival/departure service, PSC inspection, condition monitoring, and accident response support services. In order to support accident response service, the relative importance of a bridge navigational equipment was assessed by stratifying the navigation system to provide safe and efficient support services by objective judgment through specific and quantitative methods using AHP, one of decision-making methods used by an expert group. The survey was conducted by dividing the bridge navigational equipment into depth, location, and speed information. As a result of applying the AHP method, the importance of depth, location, and speed information was assessed. The relative importance of each equipment for providing location information was also assessed in order of Radar, DGPS, ECDIS, Gyro compass, Autopilot, and AIS. This was similar to survey results on the utilization of each operator's preference and its impact on marine accidents.

• Journal of Environmental Impact Assessment
• /
• v.17 no.4
• /
• pp.235-242
• /
• 2008

To develop a watershed management plan for protection of the lake water quality, the linkages among land use activities, stream water quality, and lake water quality must be understood. This study conducted to develop a Decision Support System(DSS) for the reservoir water quality managers and a comprehensive watershed management plan. This DSS has three main components; database, interactive decision model, and data delivery interface system. Graphic User Interface(GUI) was developed as the interface medium to deliver the data and modeling results to the end users. Water quality management scenarios in Yongdam reservoir consist of two parts. One is the watershed management, and the other is water quality management in the reservoir. The watershed management scenarios that were evaluated include as follows : a removal of point sources, control of waste water treatment plant, reductions in nonpoint sources, and the management of developed land. Water quality management scenarios in the reservoir include to install a curtain wall and to operate an algae removal system. The results from the scenario analysis indicate that the strategy of the reservoir water quality management can promise the best effectiveness to conserve the quality of reservoir water. It is expected that many local agencies can use this DSS to analyze the impact of landuse changes and activities on the reservoir watershed and can benefit from making watershed management decisions.