• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.119-121
• /
• 2004

Video event detection has become an essential application in multimedia computing. For sports video, salient events are usually detected by analyzing video sequence by specific decision rules. However in many kinds of sports video (e.g. soccer), the game contains continuous actions, in which the boundaries of shots, scenes are uncertain. So the conventional analyzing methods using crisp decisions are not efficient. Fuzzy logic is a natural approach that can tackle this problem. In this paper, we present a new approach using fuzzy technique for event detection in soccer video. The experiment shows encouraging results for this method

• Journal of Korea Game Society
• /
• v.3 no.1
• /
• pp.18-23
• /
• 2003

Internal organs are in a game paduk[go] to play on a printing, and a poker, Korean playing cards having cards we. And I am with all kinds of electronic amusements to do a computer with a partner and baseball, soccer, golf, tennis, several hundred to enjoy in a stadium. Most games except a computer game are local, and a case to receive a courtship is in a game during this because I need time, personnel (the other party)? and a game tool. But a computer game is single, and a game is possible, and a number for the merit that can easily play a game by an offer of all tools is, and for this reason a lot of games to enjoy in a computer please be, and it has been transplanted. I do I in order to announce that interface of a game studied a problem and an improvement plan to have let there be a few I (to game interface) if a game is ported with a computer in this study by this.

• Journal of Korea Game Society
• /
• v.17 no.6
• /
• pp.129-138
• /
• 2017

In football simulation games, it is very important for the interest of the game to make the stats of the football players close to reality. As the management concept is introduced to the sports simulation game, when the user plays the game for a long time, the existing player character retires. Therefore, the game creates the environment of the game by creating a new player in the game. In this study, we propose a method to create a new player character by using genetic algorithm to have the optimal ability similar to existing players. We compare and evaluate the player character with the existing random generation method, the correction random method and the proposed algorithm, and verify the validity of the proposed method.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.557-564
• /
• 2001

The objective of he study is to record the real conditions along with the soccer ball that is, each player's ball keeping time, the number football keeping, accuracy of passing to other player, direction, etc., on a real-time basis, measure them in numbers and get necessary analyzed output as much as one needs. The study consists of the following stages: (1) Record the data by drawing through Visual Interface on a real-time basis; (2) Graphic windows to display the recorded data item by item in graphic; (3) Form windows to display the individual or team scores anytime when needed; (4) Windows to display the analyzed data in visualized form. The effect of the study is threefold: (1) It inputs all the game-related data on a real-time basis, which was impossible before and shows analyzed contents during the game enabling each tea manager o use; (2) In cse of TV broadcasting or newspaper articles, it explains objectively the situations of he game to the TV viewers or readers; (3) After the game, it provides importance information on each team's playing ability and individual player's technical improvement through data analysis.

• Journal of Korean Orthopaedic Sports Medicine
• /
• v.11 no.2
• /
• pp.92-95
• /
• 2012

Iliacus muscle tears are a rare injury seen after the high-energy trauma or as a result of low-energy injuries in patients with a bleeding diathesis as coagulopathy, receiving anticoagulation therapy and hemophiliac. Femoral nerve palsy due to compression from a hematoma by iliacus muscle rupture are rarely reported. Routine evaluation includes MRI to confirm and define the pathologic abnormality supplemented by EMG and nerve conduction studies to evaluate patterns and extent of femoral nerve injury. Hematologic evaluation for bleeding diathesis may preceded, if suspicion of coagulopathy is present. We report the case of a healthy 32-year-old male with iliacus rupture and concomitant femoral nerve palsy sustained by kicking motion during soccer game. After 6 months of observation with non-operative treatment regimen, satisfactory results were obtained, so we report it with a review of the literatures.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.59-64
• /
• 2001

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 chose 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 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 it 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 effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Journal of KIISE:Software and Applications
• /
• v.27 no.7
• /
• pp.712-722
• /
• 2000

In this paper, we suggest and test a classification technique of offence pattern from group formation to automatically index highlights of soccer games. A BP (Back-propagation) neural nets technique was applied to the information of the position of both the player and the ball on a ground, and the distance between the player and the ball to identify the group formation in space and time. The real soccer game scenes including '98 France World Cup were used to extract 297 video clips of various types of offence patterns; Left Running 60, Right Running 74, Center Running 72, Corner-kick 39 and Free-kick 52. The results are as follows: Left Running comes to 91.7%, Right Running 100%. Center Running 87.5%, Corner-kick 97.4% and Free-kick 75%, and these showed quite a satisfactory rate of recognition.

• Journal of Digital Contents Society
• /
• v.15 no.5
• /
• pp.631-642
• /
• 2014

The main memory DBMS is operated which the contents of the table that resides on a disk at the same time as the drive is in the memory. However, because the main memory DBMS stores the data and transaction log file using the disk file system, there are a limit to the speed at which the CPU accesses the memory. In this paper, I evaluated the performance through analysis of the application side difference the technology that has been implemented in Altibase system of main memory DBMS and Sybase of disk-based DBMS. When the application performance of main memory DBMS is in comparison with the disk-based DBMS, the performance of main memory DBMS was outperformed 1.24~3.36 times in the single soccer game, and was outperformed 1.29~7.9 times in the soccer game / special soccer. The result of sale transaction response time showed a fast response time of 1.78 ~ 6.09 times.

• 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 Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.837-844
• /
• 2009

This study used data of soccer match 5170 games from 1950 to 2008 in five European football professional leagues. We compared average of SGPG (scored goal per game) in each two and three points of win. And we compared average of SGPG in each leagues. In order to predict PtsG (points per game), we executed regression analysis using SGPG and LGPG (lossed goal per game). Finally, We applied regression analysis to a K-league.