• Journal of the Korea Society of Computer and Information
• /
• v.26 no.8
• /
• pp.31-37
• /
• 2021

In this paper, we propose a method to effectively search by automatically classifying scenes in which specific images such as pitching or swing appear in baseball game images using a CNN(Convolution Neural Network) model. In addition, we propose a video scene search system that links the classification results of specific motions and game records. In order to test the efficiency of the proposed system, an experiment was conducted to classify the Korean professional baseball game videos from 2018 to 2019 by specific scenes. In an experiment to classify pitching scenes in baseball game images, the accuracy was about 90% for each game. And in the video scene search experiment linking the game record by extracting the scoreboard included in the game video, the accuracy was about 80% for each game. It is expected that the results of this study can be used effectively to establish strategies for improving performance by systematically analyzing past game images in Korean professional baseball games.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.49-61
• /
• 2022

In sports, the proportion of data analysis in team management such as team strategy planning and marketing is increasing. In KBO(Korea Baseball Organization) league, in particular, plans such as recruiting players and fostering players are established to devise team strategies for the next year, such as FA and trade, at the end of a season. For these reasons, it is very important to predict players' performance for the next year. In this study, the target was limited to only the batter and tried to find out how to predict whether the performance of the next year will improve. As a standard record for rising and falling, OPS(On-Base Plus Slugging), which is easy to calculate and has a high relationship with team score, was used. In this study, 40 years of regular season data from 1982 to 2021 were used as data, and 11 machine learning classification models were used as experimental methods. Predicting the rise and fall of OPS, RBF SVM, Neural Net, Gaussian Process, and AdaBoost were more accurate than other classification models, and age did not significantly affect accuracy.

• Proceedings of the Korean Fiber Society Conference
• /
• 2003.10a
• /
• pp.113-113
• /
• 2003

Four main factors, cling force, wicking force, water retention and water transport, affecting the clinginess of the sportswear fabric have been identified and measured by combining a new equipment and a statistical analysis. A classification model based on those factors has been developed in order to evaluate and standardize fabric wear comforts during heavy physical acting. Ten sportswear fabrics assumed different in their wear characteristics have been employed to investigate the relationship between the measurements and actual performance. It has been shown that the subjective evaluation ratings were well agreed with the measurement.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.35-36
• /
• 2016

본 논문에서는 기존 Bag-of-Visual words (BoW) 접근법에서 반영하지 못한 이미지의 공간 정보를 활용하기 위해서 Spatial Pyramid Matching (SPM) 기법을 Latent Dirichlet Allocation (LDA) 모델에 결합하여 이미지를 분류하는 모델을 제안한다. BoW 접근법은 이미지 패치를 시각적 단어로 변환하여 시각적 단어의 분포로 이미지를 표현하는 기법이며, 기존의 방식이 이미지 패치의 위치정보를 활용하지 못하는 점을 극복하기 위하여 SPM 기법을 도입하는 연구가 진행되어 왔다. 또한 이미지 패치를 정확하게 표현하기 위해서 벡터 양자화 대신 희소 부호화 기법을 이용하여 이미지 패치를 시각적 단어로 변환하였다. 제안하는 모델은 BoW 접근법을 기반으로 위치정보를 활용하는 SPM 을 LDA 모델에 적용하여 시각적 단어의 토픽을 추론함과 동시에 multi-class SVM 분류기를 이용하여 이미지를 분류한다. UIUC 스포츠 데이터를 이용하여 제안하는 모델의 분류 성능을 검증하였다.

• Journal of applied mathematics & informatics
• /
• v.9 no.2
• /
• pp.771-785
• /
• 2002

Many industries like energy, utilities, ice cream and leisure sports are closely related to the weather. In order to hedge weather related risks, they invest their assets with portfolios like option, coupons, future, and other weather derivatives. Among weather related derivatives, CDD and HDD index options are mainly transacted between companies. In this paper, the autocorrelation system of temperature will be checked for several cities in Korea and the parameter estimation will be carried based on the maximum likelihood estimation. Since the log likelihood increase as the number of parameters increases, we adopt the Schwarz information criterion .

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1851-1863
• /
• 2015

– In the paper, to handle the problem of traditional bag-of-features model ignoring the spatial relationship of local features in human action recognition, we proposed a Multiscale Spatial Position Coding under Locality Constraint method. Specifically, to describe this spatial relationship, we proposed a mixed feature combining motion feature and multi-spatial-scale configuration. To utilize temporal information between features, sub spatial-temporal-volumes are built. Next, the pooled features of sub-STVs are obtained via max-pooling method. In classification stage, the Locality-Constrained Group Sparse Representation is adopted to utilize the intrinsic group information of the sub-STV features. The experimental results on the KTH, Weizmann, and UCF sports datasets show that our action recognition system outperforms the classical local ST feature-based recognition systems published recently.

• Korean Journal of Oriental Medicine
• /
• v.10 no.1
• /
• pp.97-105
• /
• 2004

1. To define 'Korean medicine industry' through study on existing medicine related industries, Korean medicine industry means all industrial activities related to Korean medicine. It covers material resources such as herbs and products made with herbs, medical instruments, Korean medical service and related information service based on Korean medicine theories. 2. According to Korea National Statistical Office standard industrial branch, Korean medicine industry was classified as a large branch. There were industries such as agriculture, food and beverage manufacture, publishing, copy of prints and record media, manufacture of compound and chemical products, medical service, manufacture of precise optical instruments, wholesale trade and product mediation, retail trade, restaurant, research and development, education service, health preservation service, entertainment, culture and sports industry related to the Korean medicine industry. 3. If we classify this according to the industry branch of English economists Clark, Colin Grant, herb cultivating industry will be classified as primary industry, manufacture of foot and beverage related to Korean medicine, secondary industry and wholesale and retail sales of herb, research and development, education, health preservation, social welfare, tertiary industries.

• Journal of Korean Foot and Ankle Society
• /
• v.20 no.3
• /
• pp.100-105
• /
• 2016

Syndesmotic injury can either be isolated or associated with bony or ligamentous ankle injury. When it is not associated with an ankle fracture, it may not be easy to diagnose, especially when there is no franck diastasis on a plain radiograph. Without proper treatment, syndesmotic injury can lead to chronic pain due to impingement of scar tissues and instability. It may further lead to ankle arthritis. Early diagnosis with appropriate management is a prerequisite to avoid these problems. Herein, we review and discuss the mechanism of injury, classification, diagnosis, and treatment of isolated syndesmotic injury.

• Proceedings of the IEEK Conference
• /
• 2003.07c
• /
• pp.2693-2696
• /
• 2003

The national standard physique research of Korea is being conducted every 5-6 year term after its first research was started in 1979, the fourth research was conducted in 1997. The result of the national physique research was reflected in manufactured goods design of allied industries such as clothing, shoes, furniture. In this thesis, we measured anthropometry value for every bodily figurative classification after dividing users according to gender, age, bodily figure using the result of the national standard physique research. We constructed 3D character through the process of analyzing interrelation of measured anthropometry and measuring representative category. For the process for organization, we measured anthropometry which can express sports action of golf, tennis and etc effectively. We made it by Presenting measurement which is able to form each type of 3D character after the category was decided. Quantitative and objective valuation for posture and action became possible by developing visible information offer and posture action analysis protocol in theoretical approach for analysis of posture and action in sports.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.631-634
• /
• 2006

The national standard physique research of Korea is being conducted every 5$\sim$6 year term after its first research was started in 1979. The result of the national physique research was reflected in manufactured goods design of allied industries such as clothing, shoes, furniture. In this thesis, we measured anthropometry value for every bodily figurative classification after dividing users according to gender, age, bodily figure using the result of the national standard physique research. We constructed 3D character through the process of analyzing interrelation of measured anthropometry and measuring representative category. For the process for organization, we measured anthropometry which can express sports action of golf, tennis and etc effectively. We made it by presenting measurement which is able to form each type of 3D character after the category was decided. Quantitative and objective valuation for posture and action became possible by developing visible information offer and posture action analysis protocol in theoretical approach for analysis of posture and action in sports.