• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.27 no.2
• /
• pp.16-25
• /
• 2019

While various efforts are being made to ensure aviation safety, air accident rate induced by pilot human factors is still high worldwide. In particular, among pilot human factors, it would be the most important issue for pilots to anticipate and recognize flight environmental factors beyond their control and to make a positive decision making(ADM). In the Republic of Korea Air Force(ROKAF), there were many dizzying experiences induced by bird strike incidents and developed into dangerous moments such as damage to the aircraft and pilots' increased mental stress. It is a matter of serious concern in terms of safety management and human factors to dismiss bird strike incidents as inevitable misfortune due to environmental factors. In 2018, the ROKAF Aviation Safety Agency(ASA) conducted an experimental study to enhance pilots' ADM competence that can anticipate and avoid a bird strike. As the way of the study, 'Bird Strike Preventing Information' had been written and distributed every week by the ASA to flight units in the ROKAF during the period of the study. Through enhanced pilots' perceptual ADM competence, there was a noticeable number of reduction in bird strike incident compared to previous years of the experimental study.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.679-682
• /
• 1996

The level of informaiton provided by most current EIS systems is not above presentation and reporting. To maximize the effect of EIS, we must increase executives' use-rate. To do so, it is important to provide information really required by the user. In a addition, the decision support funcitons should be provided for strategic decision making. In this paper we propose the methodology for adding the analysis and prediciton functions to the EIS that is, for supporting the decision making with the system. Finally, we present a pilot system based on the proposed methodology.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.18 no.2
• /
• pp.45-55
• /
• 1993

In multiattribute decision making a decision maker (DM) can choose the best alternative if his/her multiattribute utility function and the joint probability distribution of outcomes are exactly known. This paper develops multiattribute stochastic-statistical dominance rules which can be applied to the situation when neither of them is known exactly, that is, when the DM cannot calculate the expected utility for each alternative. First, the notion of relative risk aversion is used dominance rules are developed to screen out dominated alternatives so that hi/she choose the best one among the remaining nondominated alternatives.

• Asia pacific journal of information systems
• /
• v.15 no.3
• /
• pp.41-64
• /
• 2005

The effects of information quality and the importance of information have been reported in the information Systems(IS) literature. However, little has been learned about the impact of data quality(DQ) on decision performance. Recognizing with this problem, this study explores the effects of contextual DQ on decision performance. To examine them, a laboratory experiment was conducted. Based on two levels of contextual DQ and two levels of task complexity, this study had a $2{\times}2$ factorial design. The dependent variables used to measure the outcomes of decision performance were problem-solving accuracy and time. The results demonstrated that the effects of contextual DQ on decision performance were significant. The findings suggest that decision makers can expect to improve their decision performance by enhancing contextual DQ. This research not only extends a body of research examining the effects of factors that can be tied to human decision-making performance, but also provides empirical evidence to validate and extend DeLone and McLean's IS success model.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.133-136
• /
• 2010

A lot of GIS DB in Korea is distributed and integration for decision making is difficult. Therefore, the SDW is needed to improve the problems and enhance efficiency. The SDW is used for making decisions about various problems by integrating scattered spatial information. This study analyzes business activity of a local government and plan the data cube to implement spatial OLAP for an efficient decision making.

• Spatial Information Research
• /
• v.7 no.2
• /
• pp.191-207
• /
• 1999

Data and information necessary for solving the spatial decision making problems are imperfect or inaccurate and most are described by natural language. In order to process these arts of information by the computer, the obscure linguistic value need to be described quantitatively to let and computer understand natural language used by humans. For this , the fuzzy set theory and the fuzzy logic are used representative methodology. So this paper describes the construction of the language model by the natural language that user easily can understand and the logical concepts and construction process for building the fuzzy inference mechanism. It makes possible to solve the space related decision making problems intellectually through structuring and inference used by the computer, in case of the evaluation concern or decision making problems are described inaccurate, based on the inaccurate or indistinct data and information.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.1
• /
• pp.167-179
• /
• 2016

The safety of SOC facilities is constantly under threat by the globally increasing abnormal climate. Responding to disasters requires prompt decision-making such as suggesting evacuation paths. For doing so, spatio-temporal information with convergence of disaster information and SOC facility information must be utilized. Such information is being collected separately by the government or related organizations, but not collectively. The collective control of the separately collected disaster information and the generation of SOC facility safety and damage information are required for prompt disaster response. Also, as disaster information requires spatio-temporal convergence in its nature, the construction of an inventory that integrates related information and assists disaster response decision-making is required. A plan to construct a facility importance, risk, and damage estimation inventory for assisting prompt disaster response decision-making is suggested in this study. Through this study, the disaster and SOC facility-related data, which are being managed separately, can be collected and standardized. The integrated information required for the estimation of facility importance, risk, and damage can be provided. The suggested system is expected to be used as a decision-making tool for proactive disaster response.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.115-128
• /
• 2002

One of the well-studied problems in data mining is the search for association rules. In this paper we consider the statistical decision making of association threshold in association rule. A chi-squared statistic is used to find minimum association threshold. We calculate the range of the value that two item sets are occurred simultaneously, and find the minimum confidence threshold values.

• Journal of Information Management
• /
• v.19 no.1
• /
• pp.1-29
• /
• 1988

The purpose of this study is to investigate a decision making support system for the effective information management. Decision making theory is reviewed and problems are discussed. A model is suggested through the computing of expected monetary value in decision tree technique. The expected monetary value is computed by 1 inking the probability theory with chance node. The selection of right expected monetary value and expected value of perfect information will make great advance the present system. It is concluded that expected monetary value and expected value of perfect information in decision tree techniques will make great aids to advance information management system.