• Journal of the Korean Data and Information Science Society
• /
• v.12 no.1
• /
• pp.61-69
• /
• 2001

We present a probabilistic reasoning method for inferring knowledge about mathematical truth before an automated theorem prover completes a proof. We use a Bayesian analysis to update beleif in truth, given theorem-proving progress, and show how decision-theoretic methods can be used to determine the value of continuing to deliberate versus taking immediate action in time-critical situations.

• Journal of Construction Engineering and Project Management
• /
• v.3 no.2
• /
• pp.49-57
• /
• 2013

A sea dike construction has been increased in Korea because of the actively deployed reclamation project in basis of efficient application in land. The degree of completion in sea dike construction is affected by final closing construction, which has a lot of uncertainty that often results in higher accidents rate. Therefore, this research identified risk factors of final closing construction and classified them. This research examines the likelihood and its impact for each risk factor and calculates the risk degree as to the risk matrix. Based on this, the impact and the environmental conditions that affect to risk factors are investigated and further responsive methods are established for each risk factor. Ultimately, this research attempts to provide the risk retrenchment method for inspectors by proposing risk estimation model, responsive action list, and risk management process.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.3
• /
• pp.170-177
• /
• 2010

Poker is a game of imperfect information where competing players must deal with multiple risk factors stemming from unknown information while making the best decision to win, and this makes it an interesting test-bed for artificial intelligence research. This paper introduces a new learning AI algorithm with embedded opponent modeling that can be used for these types of situations and we use this AI and apply it to a poker program. The new AI will be based on several graphs with each of its nodes representing inputs, and the algorithm will learn the optimal decision to make by updating the weight of the edges connecting these nodes and returning a probability for each action the graphs represent.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.423-428
• /
• 2004

Flooding is one of the main causes of loss of lives and properties among various natural disasters in Korea. Flood risk maps are currently being produced in Korea but the progress is slow considering the necessity to map at nationwide scale. In this study, GIS-based multi-criteria decision making process which is normally used for resource management and site analysis was applied to locate flood vulnerable areas. Past records of flooding maps were analysed to extract topographic characteristics of flooded areas. The extracted characteristics were then set as criteria for flooding analysis using the Fuzzy and Analytic Hierarchy Process(AHP) methodology. Results from this study showed that an improved phased action plan was possible, because the flood vulnerable areas are shown in varying degrees of uncertainty unlike the conventional Boolean type GIS layer superimposition analysis.

• Journal of the Korea Safety Management & Science
• /
• v.5 no.2
• /
• pp.225-238
• /
• 2003

This study shows that the SWOT is efficient to select a factor which is valuable as worth consideration when a decision making is necessary. Such processing of information is able to present the policy for the development of bio-industry in northern area of Kyonggi province, and create the pragmatic value and effect in carrying out the policy. The object of this study is to survey present conditions, to analyze the development of bio-industry in northern area of Kyonggi province by the decision making method of the SWOT model, to suggest a plan for the prospect of continued development field and the location of industry, and to extract fundamental data for establishment of annual action and investment plan which can develop bio-industry.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.312-319
• /
• 2002

A recommendation system tracks past action of a group of users to make a recommendation to individual members of the group. The computer-mediated marking and commerce have grown rapidly nowadays so the concerns about various recommendation procedure are increasing. We introduce a recommendation methodology by which Korean department store suggests products and services to their customers. The suggested methodology is based on decision tree, product taxonomy, and association rule mining. Decision tree is to select target customers, who have high purchase possibility of recommended products. Product taxonomy and association rule mining are used to select proper products. The validity of our recommendation methodology is discussed with the analysis of a real Korean department store.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.305-308
• /
• 2003

요즘 사람들이 많이 즐기는 전략 게임은 전략 시뮬레이션이라는 말이 무색할 정도로 장르가 가지는 특성 을 이행하지 못하고 있다. 그래서 게이머들은 별다른 전략 없이 쉽게 컴퓨터를 상대로 쉽게 게임을 승리 할 수 있게 됐다. 이것은 게임의 재미를 크게 반감시키는 한 요인이 된다. 전략 게임의 컴퓨터 플레이어에게 상황 판단과 학습 능력을 갖게 하면, 게이머가 보다 재미있게 컴퓨터와 대전을 할 수 있다. 본 논문에서는 인공지능을 가지는 컴퓨터 플레이어에 사용될 Default 추론 엔진과 컴퓨터 플레이어의 작전과 행동을 결정하기 위한 action & strategy generator 시스템을 연구한다. Default 추론 엔진은 귀납적 학습방법을 통 해서 컴퓨터 플레이어가 추론 및 학습을 할 수 있는 정보를 생성하게 된다. 이렇게 생성된 정보를 바탕으로 컴퓨터 캐릭터의 행동과 전략을 결정한다. 이에 본 논문에서는 전략 게임에 인공 지능으로 machine leaning 기법 중의 하나인 decision Tree 틀 사용하였다. decision Tree를 적용하여 기존 컴퓨터 플레이어의 행위와 어떻게 다른지 차별성을 밝혀내고, 컴퓨터 플레이어가 향상된 전략을 구사할 수 있게 하는 것이 주된 목표다.

• The Journal of Korea Robotics Society
• /
• v.14 no.3
• /
• pp.157-162
• /
• 2019

The video game Tetris is one of most popular game and it is well known that its game rule can be modelled as MDP (Markov Decision Process). This paper presents a DQN (Deep Q-Network) based game agent for Tetris game. To this end, the state is defined as the captured image of the Tetris game board and the reward is designed as a function of cleared lines by the game agent. The action is defined as left, right, rotate, drop, and their finite number of combinations. In addition to this, PER (Prioritized Experience Replay) is employed in order to enhance learning performance. To train the network more than 500000 episodes are used. The game agent employs the trained network to make a decision. The performance of the developed algorithm is validated via not only simulation but also real Tetris robot agent which is made of a camera, two Arduinos, 4 servo motors, and artificial fingers by 3D printing.

• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.27-32
• /
• 2017

The several wearable devices are not able to communicate through cable due to its portability. The wireless communication method is used because of its good communication quality and group action features when the several wearable devices communicate with each other. In this paper, we proposed the group decision algorithm for grouping display of the several wearable devices. It means that recognize as a group member after measuring distance in the wireless communication environment. The result of experience showed that the group-type display of several wearable devices method overcome the limit of the display of single wearable device.

• Child Health Nursing Research
• /
• v.23 no.2
• /
• pp.168-178
• /
• 2017

Purpose: The purpose of this study was to explore and describe the experiences of career decision making by Korean nursing students. Methods: The participants were 18 nursing students from one nursing college. Data were collected through in-depth individual interviews, and the main question was, "Could you describe your experience of making a career decision?" Data from the field and transcribed notes were analyzed using Strauss and Corbin's grounded theory methodology. Results: Core category of nursing students' experiences in making career decisions was 'trying to find the way of being a nurse'. Action/interaction strategies were 'becoming one's own self', 'actively exploring the way of being a nurse', and 'experiencing one's own achievement as a future nurse'. Consequences were 'deciding on the career on one's own' and 'career indecision on one's own'. Conclusion: The findings indicate that nursing students tried to know themselves, explore careers and experience their achievements, and that their efforts were influenced by real situations and support systems. Therefore, nurse educators should develop systems and programs to help students in nursing make career decisions.