• Journal of Industrial Convergence
• /
• v.18 no.4
• /
• pp.61-66
• /
• 2020

Recently, attempts have been made to use data to operate games, seasons, and teams in professional baseball. Therefore, in this study, we collected baseball game records and analyzed the relationship between on-base rate and pitching count induction, and this was defined as the third record for non-game factors such as discomfort index, which includes the weather application data. When the discomfort index was over 75, the pitcher's induction of pitching was high, and when the discomfort index was less than 69.9, the on-base rate was high, but when the discomfort index was 70 or more and less than 75, the batter's on-base performance was the lowest. Through the results of the study, it could be inferred that the discomfort index, the batter's on-base rate, and the number of induction pitches are related, and that it is highly likely to be related to the pitcher's performance. Through this study, we could see the possibility of defining a cumulative/ratio record defined as the primary record and a saver metric defined as the secondary record, and a third, tertiary record linking data outside the game.

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.225-230
• /
• 2020

The KBO League is held over a long period of time due to the large number of games. Also, Korea has a diverse and distinct climate. Therefore, this study analyzed the relationship between the daily average temperature and the record of batting power such as home runs, triples, doubles, number of bases, batting percentage, and net batting percentage, and a third baseball record was defined. For this study, the correlation between the daily average temperature data and the batter who entered the standard at-bat in the KBO League in 2019 was analyzed through the SEMMA method. From the results of this study, it was found that the average daily temperature had an effect on a batter's hitting power. In particular, it was found that a batter's hitting power decreased on the day of temperatures recorded between 20.0 degrees and 24.9 degrees, and it was discussed that this may have been related to the physical condition of the pitcher the batter was facing. Therefore, it can be expected that players, coaching staff, and the front desk can use them in the game through conditions outside the game. In addition, it is expected that it will be a more useful analysis model by analyzing the records of pitching, base running, and defense as well as subsequent batting records.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.99-110
• /
• 2016

This study examined the factors affecting the team identification of professional baseball fans. The factors were divided into the fan factor, game factors, and other factors. For the analysis, two investigators visited stadium three times in total and a total number of 297 spectators were sampled using a convenience sampling method from three baseball teams. For the fan factor, a fan who began supporting his/her team from childhood or after childhood was used as a dummy variable. The interaction effects between the fan factor and other variables were investigated to offer a stereoscopic understanding about the role of kids marketing. In addition, three game factors and four non-game factors were analyzed. The results regarding fan variable and interaction effects were obtained. Fans from their childhood have much stronger team identification, and show interaction effects with the players. Regression analysis revealed player, promotion and fan service, price, and regional connection to have positive relations with team identification. This study is especially meaningful in a sense that it has proposed positive results regarding marketing to children, and the results will contribute to both the academic field and the industry.

• Journal of the Korean Arthroscopy Society
• /
• v.17 no.1
• /
• pp.71-75
• /
• 2013

Root tear of the posterior horn of the medial meniscus can occur from trauma or chronic degeneration, leading to meniscus extrusion, articular cartilage loss, osteophyte formation, and medial joint space narrowing. It is common on middle age with or without minor trauma. We experienced a case of medial meniscus posterior horn root tear in 13 years old boy during baseball game. We performed 1 direct suture anchor repair for medial meniscus posterior horn root tear in adolescent and report clinical result.

• ETRI Journal
• /
• v.31 no.1
• /
• pp.10-20
• /
• 2009

In this paper, a video broadcasting system between a home-server-type device and a mobile device is proposed. The home-server-type device can automatically extract semantic information from video contents, such as news, a soccer match, and a baseball game. The indexing results are utilized to convert the original video contents to a digested or arranged format. From the mobile device, a user can make recording requests to the home-server-type devices and can then watch and navigate recorded video contents in a digested form. The novelty of this study is the actual implementation of the proposed system by combining the actual IT environment that is available with indexing algorithms. The implementation of the system is demonstrated along with experimental results of the automatic video indexing algorithms. The overall performance of the developed system is compared with existing state-of-the-art personal video recording products.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.321-322
• /
• 2018

빅데이터 분석은 스포츠에서 다양한 분야에서 사용되고 있다. 야구산업에서도 세이버 메트릭스를 활용하여 전술 훈련, 개인 훈련 등 다양한 방면으로 활용되고 있다. 본 논문에서는 기존의 연구인 빅데이터 분석과 게임이론을 활용한 축구선수 영입 모델을 야구에 적용킨 시뮬레이션을 진행하고 합리적인 의사결정 모델을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.873-876
• /
• 2017

최근 딥러닝(Deep-learning)을 활용한 기상 예측, 심리 예측, 교통상황 예측 등 다양한 분야에 걸쳐 여러 모델의 인공신경망이 활용되고 있다. 본 논문에서는 여러 분야 중 스포츠라는 분야에 접근했으며, 딥러닝 모델을 통해 승부를 예측하는 실험을 진행하였다. 야구의 승부는 선수의 능력치, 기상의 변화, 험/어웨이 여부, 교체 여부 등 가늠할 수 없이 수많은 데이터들에 의존하고 있다. 그러나 본 논문에서는 이러한 수많은 데이터 중 경기 외적인 데이터를 제외한 데이터를 활용하여 그 다음 경기의 승부를 예측할 수 있을 지를 연구한다. 날짜 별 경기들이 훈련데이터가 되고 목표는 이전 경기들의 영향으로 예측된 다음 경기의 승/패를 예측한다. 즉 순차적인 데이터의 활용에 적합한 모델, Recurrent Neural-Network을 이용하였다. 이를 위하여 KBreport에서 데이터를 수집하였고, 수집된 데이터를 훈련 데이터 세트로 만들어 Recurrent Neural Network를 통해 훈련시켜 다음 경기의 승패를 예측하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1175-1181
• /
• 2004

This paper proposes a system to analyze and summarize the video shots of baseball game TV program into fifteen categories. Our System consists of three modules: feature extraction, Hidden Markov Model (HMM) training, and video shot categorization. Video Shots belongs to the same class are not necessarily similar, so we require that the training set is large enough to include video shot with all possible variations to create a robust Hidden Markov Model. In the experiments, we have illustrated that our system can recognize the 15 different shot classes with a success ratio of 84.72%.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.875-879
• /
• 2009

In this paper, we propose the measurement camera system of flight data of golfball for the application of screen golf contents. The existing flight data extraction system that applied on the screen golf content divided plate is dependent on it. in this paper, the camera system install in the ceiling that is able to look at passing golf ball. And left-handed and left-handed bats in the clear of the restrictions. Using high-speed CCD camera is shooting the ball flying. Acquired image is calculated from the coordinates. The location information of the calculated golf ball calculates a speed and a direction by using the physical formula, it applies the golf contents. After this system is useful sports type contents baseball, soccer, tennis.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.663-676
• /
• 2016

In Korean professional baseball the championship team of the year is determined by the four series of games: semi-semi-playoff, semi-playoff, playoff and korean series. To the top 5 teams in a regular season privileges are given to play the games at post season. At semi-semi playoff the winner of two teams which are ranked at 4th and 5th place in the regular season can advance to the game of semi playoff. The winner at semi playoff advances to the playoff to play with the second place team in the regular season. Finally, the championship team is to be determined in the Korean series between the winner of the playoff and the first ranked team in the regular season. We propose methods of how to calculate the winning probabilities of each of high ranked 5 teams advancing to Korean series. From our proposed methods we can estimate the championship probabilities of each of high ranked 5 teams advancing to the Korean series only if we know the winning probabilities between two teams in the regular season or the post season.