• Journal of Digital Convergence
• /
• v.15 no.1
• /
• pp.53-60
• /
• 2017

The time of digital era and the increasing complexity of the management environment have raised uncertainties about the future. Companies have made steady investments in education as a way to prepare for the future. In this study, design and development methodology based on web - based management simulation games (manufacturing, distribution, finance) which author participated in development was presented. The development methodology presented in this study can be roughly divided into business simulation game design methodology and business simulation game development methodology. Since there is no existing research methodology for development methodology, development model is presented based on empirical based on development case. In this paper, we propose an overall content development methodology and propose a detailed methodology of the content.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.769-777
• /
• 2021

Purpose: Earthquake disasters are frequently occur unpredictable situations due to various variables and unexpected situations. As a result, the work process itself is not uniform, making it difficult for public officials in the disaster safety department to familiarize themselves with the earthquake field manual. This paper is specifically and accurately grasp the current work situation conducted by the Disaster and Safety Countermeasures Headquarters of the Gyeongsangbuk-do Office and present a plan for designing serious game scenarios necessary for field manual learning. Method: In this study, scenarios were designed based on the GBS(Goal Based Scenario) model, and in the process of assigning missions and roles based on the Gyeongsangbuk-do earthquake field manual, public officials related to earthquakes were able to acquire knowledge and skills to solve practical tasks. Result: Scenario data of the proposed technique was implemented as a systematic procedure by processing various earthquake-related information into logical data and simplifying and abstracting it for game expression for earthquake situation training. Conclusion: In the event of an earthquake due to learning through serious games, related public officials of Gyeongsangbuk-do provincial are expected to be able to respond quickly to various earthquake disasters.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.17-24
• /
• 2022

Bitcoin is a peer-to-peer cryptocurrency designed for electronic transactions that do not depend on the government or financial institutions. Since Bitcoin was first issued, a huge blockchain financial market has been created, and as a result, research to predict Bitcoin price data using machine learning has been increasing. However, the inefficient Hyper-parameter optimization process of machine learning research is interrupting the progress of the research. In this paper, we analyzes and presents the direction of Hyper-parameter optimization through experiments that compose the entire combination of the Timesteps, the number of LSTM units, and the Dropout ratio among the most representative Hyper-parameter and measure the predictive performance for each combination based on Bitcoin price prediction model using LSTM layer.

• Cartoon and Animation Studies
• /
• s.29
• /
• pp.129-149
• /
• 2012

The purpose of this study was to investigate the clustering and Big Five Personality domains in discriminating groups by level of school-related adjustment, as experienced by Social Sims game users. Social Games are based on web that has simple rules to play in fictional time and space background. This paper is to analyze the relationships between social networks and user behaviors through the social games . In general, characteristics of social games are simple, fun and easy to play, popular to the public, and based on personal connections in reality. These features of social games make themselves different from video games with one player or MMORPG with many unspecific players. Especially Social Game show a noticeable characteristic related to social learning. The object of this research is to provide a possibility that game that its social perspective can be strengthened in social game environment and analyze whether it actually influences on problem solving of real life problems, therefore suggesting its direction of alternative play means and positive simulation game. Data was collected by administering 4 questionnaires (the short version of BFI, Satisfaction with life, Career Decision-.Making Self-.Efficacy, Depression) to the participants who were 20 people in Seoul and Daejeon. For the purposes of the data analysis, both Stepwise Discriminant analysis and Cluster analysis was employed. Neuroticism, Openness, Conscientiousness within the Big Five Personality domains were seen to be significant variables when it came to discriminating the groups. These findings indicated that the short version of the BFI may be useful in understanding for game user behaviors When it comes to cultural research, digital game takes up a significant role. We can see that from the fact that game, which has only been considered as a leisure activity or commercial means, is being actively research for its methodological, social role and function. Among digital game's several meanings, one of the most noticeable ones is the research on its critical, social participating function. According to Jame Paul gee, the most important merit of game is 'projected identity'. This means that experiences from various perspectives is possible.[1] In his recent autobiography , he described gamer as an active problem solver. In addition, Gonzalo Francesca also suggested an alternative game developing method through 'game that conveys critical messages by strengthening critical reasons'. [2] They all provided evidences showing game can be a strong academic tool. Not only does a genre called social game exist in the field of media and Social Network Game, but there are also some efforts to positively evaluate its value Through these kinds of researches, we can study how game can give positive influence along with the change in its general perception, which would eventually lead to spreading healthy game culture and enabling fresh life experience. This would better bring out the educative side of the game and become a social communicative tool. The object of this game is to provide a possibility that the social aspect can be strengthened within the game environment and analyze whether it actually influences the problem solving of real life problems. Therefore suggesting it's direction of alternative play means positive game simulation.

• The Journal of the Korea Contents Association
• /
• v.7 no.9
• /
• pp.248-256
• /
• 2007

The purpose of this study is to design, develope, and deploy of online game content in middle school mathematics. This study analyzed related literature review, case studies, and educational game web sites for seeking better applicable design strategies. After serious discussion with experts based the design ideas, this study established its own educational game design model and it was applied to develop algebraic function lesson for middle school students. The developed content also was deployed in real classroom setting to see how students received the game contents and how. well they processed the design procedures and activities. We found that educational online game content, especially when applied to mathematics subject, can be effective in students interests and their motivations. We also observed that there were a few managerial errors such as need for detailed guidance for game, cumulative game results for later feedback, and so on. This study concluded that educational game contents should be able to widely spread out to get students' learning interests and strong motivation as well. We suggest that related research should be done toward to other subject than mathmatics and various students age groups.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.4
• /
• pp.693-700
• /
• 2023

Sentiment analysis, a branch of natural language processing that classifies and identifies subjective opinions and emotions in text documents as positive or negative, can be used for various promotions and services through customer preference analysis. To this end, recent research has been conducted utilizing various techniques in machine learning and deep learning. In this study, we propose an optimal language model by comparing the accuracy of sentiment analysis for movie, product, and game reviews using existing RNN-based models and recent Transformer-based language models. In our experiments, LMKorBERT and GPT3 showed relatively good accuracy among the models pre-trained on the Korean corpus.

• ETRI Journal
• /
• v.39 no.4
• /
• pp.443-454
• /
• 2017

In this paper, we propose a fine-grained mobile application clustering model using retrofitted document embedding. To automatically determine the clusters and their numbers with no predefined categories, the proposed model initializes the clusters based on title keywords and then merges similar clusters. For improved clustering performance, the proposed model distinguishes between an accurate clustering step with titles and an expansive clustering step with descriptions. During the accurate clustering step, an automatically tagged set is constructed as a result. This set is utilized to learn a high-performance document vector. During the expansive clustering step, more applications are then classified using this document vector. Experimental results showed that the purity of the proposed model increased by 0.19, and the entropy decreased by 1.18, compared with the K-means algorithm. In addition, the mean average precision improved by more than 0.09 in a comparison with a support vector machine classifier.

• Journal of Information Processing Systems
• /
• v.8 no.3
• /
• pp.409-420
• /
• 2012

The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting down the number of policy decisions by agents. Macro-Actions were originally defined as combinations of the same primitive actions. Based on studies that showed the generation of Macro-Actions by learning, Macro-Actions are now thought to consist of diverse kinds of primitive actions. However an enormous amount of learning time and state space are required to generate Macro-Actions. To resolve these issues, we can apply insights from studies on the learning of tasks through Programming by Demonstration (PbD) to generate Macro-Actions that reduce the learning time and state space. In this paper, we propose a method to define and execute Macro-Actions. Macro-Actions are learned from a human subject via PbD and a policy is learned by reinforcement learning. In an experiment, the proposed method was applied to a car simulation to verify the scalability of the proposed method. Data was collected from the driving control of a human subject, and then the Macro-Actions that are required for running a car were generated. Furthermore, the policy that is necessary for driving on a track was learned. The acquisition of Macro-Actions by PbD reduced the driving time by about 16% compared to the case in which Macro-Actions were directly defined by a human subject. In addition, the learning time was also reduced by a faster convergence of the optimum policies.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.159-165
• /
• 2019

Based on deep learning technology, speech recognition method has began to be applied to commercial products, but it is still difficult to be used in the area of VR contents, since there is no easy and efficient way to process the recognized text after the speech recognition module. In this paper, we propose a Korean Language Command System, which can efficiently recognize and respond to Korean speech commands. The system consists of two components. One is a morphological analyzer to analyze sentence morphemes and the other is a retrieval based model which is usually used to develop a chatbot system. Experimental results shows that the proposed system requires only 16% commands to achieve the same level of performance when compared with the conventional string comparison method. Furthermore, when working with Google Cloud Speech module, it revealed 60.1% of success rate. Experimental results show that the proposed system is more efficient than the conventional string comparison method.