• Journal of Biomedical Engineering Research
• /
• v.43 no.2
• /
• pp.102-108
• /
• 2022

Purpose: To propose a deep learning-based clinical decision support technique for laryngeal disease on epiglottis, tongue and vocal cords. Materials and Methods: A total of 873 laryngeal endoscopic images were acquired from the PACS database of Pusan N ational University Yangsan Hospital. and VGG16 model was applied with transfer learning and fine-tuning. Results: The values of precision, recall, accuracy and F1-score for test dataset were 0.94, 0.97, 0.95 and 0.95 for epiglottis images, 0.91, 1.00, 0.95 and 0.95 for tongue images, and 0.90, 0.64, 0.73 and 0.75 for vocal cord images, respectively. Conclusion: Experimental results demonstrated that the proposed model have a potential as a tool for decision-supporting of otolaryngologist during manual inspection of laryngeal endoscopic images.

• IE interfaces
• /
• v.11 no.2
• /
• pp.159-176
• /
• 1998

In the motor manufacturing system with the properties of short delivery and order based production, the process plan is performed individually for each order by the expert of process plan after the completion of the detail design process to satisfy the specification to be required by customer. Also it is hard to establish the standard process plan in reality because part routings and operation times are varied for each order. Hence, the production planner has the problem that is hard to establish the production schedule releasing the job to the factory because there occurs the big difference between the real time to be completed the process plan and the time to be required by the production planner. In this paper, we study the decision supporting system for the process plan based on knowledge base concept. First, we represent the knowledge of process planner as a database model through the modified POI-Feature graph. Then we design and implement the decision supporting system imbedded in the heuristic algorithm in the client/server environment using the ORACLE relational database management system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3196-3203
• /
• 2010

The regional strategic industry support has been increasingly developed due to the change of environmental and political conditions for the last 10 years. As the paradigm changed from the central government-sponsored system to regional government-sponsored system, the policy has been diversified into various support systems such as regional strategic industry, specialized industry, supporting technology, supporting business, etc. It is crucial to establish the overall development plans and project strategies for the regional industry in terms of effectiveness and efficiency which will generate an integrated strategic frame to adjust overlapped supporting policies and offer a consumer-oriented service. Not only does the study focus on performance-based outcome regarding to a regional business (supporting policy) portfolio, but it also analyzes and proves an empirical decision-making model to draw out the priority and relative importance according to the regional strategic industry and support cases by analyzing the case of Chungnam area's strategic industry support in 2009. Following a priority list of 20 support cases selected from this research model by the Analytic Hierarchy Process (AHP), the result shows that the diverse support plans are needed according to the different strategic industries or the size of enterprise due to the fact that priority of project type varies upon the characteristics of strategic industry. Thus, the support project needs to generate various strategic industries and develop differentiated support policy to consolidate competitiveness of regional enterprises and revitalize the regional economy.

• Journal of Digital Convergence
• /
• v.8 no.3
• /
• pp.63-77
• /
• 2010

The purpose of this study is to determine potential effects of region marketing activities on attraction of domestic or overseas business. In order to meet the goal, this study set a research model and hypotheses on the basis of preceding reference literatures and case studies. This study identifies management environment, life environment, marketability, investment supporting environment as the variables of investment decision and urban attitude. As a result, it was found that marketability and investment supporting environment had positive effects on urban attitudes and investment decision, and urban attitudes had positive effects on investment decision as well.

• Journal of Distribution Science
• /
• v.15 no.6
• /
• pp.37-46
• /
• 2017

Purpose - The paper aims to propose an optimization model for supporting the buyer-seller negotiations. We consider the price, quality, and delivery as evaluation criteria, also recognized as objectives for negotiation. Research design, data, and methodology - The methodology used in this paper involves the input-oriented DEA with the inverse optimization. Under the existence of several potential suppliers, the price would be considered to be the decision variable to conclude the negotiation so as to meet the desired level of the quality and delivery. The data set for six suppliers with three criteria is examined by the proposed approach. Results - We present the decision aid model by displaying the price spectrum as the changes of desired output levels. It overcomes the shortcomings from previous researches mainly based on the discrete types of scenario generations. This approach shows that the obtained results help the buyer understand the trade-offs between price and performance when he/she considers the negotiation. Conclusions - The paper contributes to the numerical models for buyer-supplier negotiation in that the model for the supplier evaluation and selection is closely linked with the model for negotiation. In addition, it eliminates the unrealistic negotiation strategy, and provides the negotiation strategies that the buyer would not shift the burden on suppliers by maintaining the current efficiency.

• Korean Journal of Hydrosciences
• /
• v.8
• /
• pp.31-40
• /
• 1997

Flow carrying capacity of water distribution systems is getting reduced by deterioration of pipes in the systems. The objective of this paper is to present a managerial decision-making model for the rehabilitation of water distribution systems with a mininum cost. The decisions made by the model also satisfy the requirements for discharge and pressure at demanding nodes in the systems. Replacement cost, pipe break repair cost, and pumping cost are considered in the economic evaluation of the decision along with the break rate and the interest rate to determine the optimal replacement time for each pipe. Then, the hydraulic integrity of the water distribution system is checked for the decision by a pipe network simulator, KYPIPE, if discharge and pressure requirements are satisfied. In case the system does not satisfy the hydraulic requirements, the decision made for the optimal replacement time is revised until the requirments are satisfied. The model is well applied to an existing water distribution system, the Seoul Metropolitan Water Supply System (1st Phase). The results show that the decisions for the replacement time determined by the economic analysis are accepted as optimal and hydraulic integrity of the system is in good condition.

• Journal of the Korea Society for Simulation
• /
• v.8 no.1
• /
• pp.89-99
• /
• 1999

The major objective of this research is to propose a design architecture for autonomous defense systems for supporting highly intelligent behavior by combining decision, perception, and action components. Systems with such high levels of autonomy are critical for advanced battlefield missions. By integrating a plenty of advanced modeling concepts such as system entity structure, endomorphic modeling, engine-based modeling, and hierarchical encapsulation & abstraction principle, we have proposed four layered design methodology for autonomous defense systems that can support an intelligent behavior under the complicated and unstable warfare. Proposed methodology has been successfully applied to a design of autonomous tank systems capable of supporting the autonomous planning, sensing, control, and diagnosis.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.111-120
• /
• 1999

Although the concept of viewing knowledge as a critical resource has been widely accepted in prior studies, it is not fully understood how to acquire available knowledge in order to improve organizational effectiveness. However, it si sure that organizational knowledge management should pursuit the achievement of the business goal by delivering relevant and useful information to the right person at the right time. Group Support System (GSS) can play an important role to transfer scatter information into meaningful business knowledge for supporting strategic corporate decision-making. This study proposes a fuzzy GSS framework for acquiring workgroup knowledge from individual memory and aggregating workgroup knowledge to organizational knowledge. This study also proposes an architecture to support the fuzzy GSS framework. The architecture consists of user agents, information management agents, and a fuzzy model manager. To illustrate how the fuzzy GSS framework can be used to support the whole process of organization knowledge acquisition, an Internet-based GSS was developed and applied in a marketing decision process. It showed that the framework was effective for acquiring organizational knowledge.

• Journal of Information Management
• /
• v.33 no.4
• /
• pp.107-128
• /
• 2002

The purpose of this study is developing a information support system for R&D decision making to maximize economic results of the R&D. This system is composed of studying the model of work flow for R&D decision making, analyzing a technology information, connecting with the databases from KISTI and others, and valuing R&D technology on line. Especially in the case of technology valuation, this system is combined with the valuation model which supports knowledge information for helping more objective estimation.

• Journal of Korean Academy of Nursing
• /
• v.48 no.5
• /
• pp.578-587
• /
• 2018

Purpose: This study aimed to understand the mechanisms of decision regret and stress of family surrogates' end-of-life decision making using an exploratory path model. In particular, the research identified the direct effects of perceptions of uncertainty and effective decisions on decision regret and stress, and examined the indirect effects of being informed, having clear values, and being supported for decision regret and the stress of end-of-life decision making through the mediating variables of perceptions of uncertainty and effective decisions. Methods: Data were collected from 102 family surrogates who had participated in end-of-life decision making for patients with terminal cancer in a tertiary hospital. Results: Perception of effective decisions was a significant direct predictor of decision regret, and uncertainty was a significant predictor of stress among the participants. Being informed, having clear values, and being supported had a significant indirect influence on decision regret through the perception of effective decisions among family surrogates. However, only having clear values had a significant indirect influence on stress through the perception of uncertainty. The model explained 63.0% of decision regret and 20.0% of stress among the participants and showed a good fit with the data, ${\chi}^2=12.40$ (df=8, p=.134), TLI=.97, and RMSEA=.07. Conclusion: Nurses can support family surrogates in end-of-life decision-making processes to decrease their decision regret by providing information about end-of-life care choices, clarifying personal values, and supporting the decision-making process, and to relieve their stress by facilitating the clarification of personal values.