• Journal of Fisheries and Marine Sciences Education
• /
• v.23 no.2
• /
• pp.333-349
• /
• 2011

The purpose of this study was to examine middle school physical education teachers' perceptions of the School Sports Club, Questionnaires were sent to the all 547 middle school physical education teachers in the Busan Metropolitan City, 326 (59.6%) were returned and 322 (58.9%) were analyzed. The results of the study were as follows: Firstly, there were school sports clubs of 24 kinds of sports at middle schools, but overly concentrated in soccer, basketball and badminton. Secondly, physical education teachers responded positively to the importance of school sports club. Thirdly, They thought that school sports club activities had an effect on both the physical and socio-cultural improvement of students. Fourthly, among tough barriers were time restraint, school parents' unfriendly sentiments toward the activities, and financial difficulties. Fifthly, to have better school sports clubs, reducing the barriers is pivotal.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.91-97
• /
• 2004

In this paper, we propose a classification system of TV program scenes based on audio information. The system classifies the video scene into six categories of commercials, basketball games, football games, news reports, weather forecasts and music videos. Two type of audio feature set are extracted from each audio frame-timbral features and coefficient domain features which result in 58-dimensional feature vector. In order to reduce the computational complexity of the system, 58-dimensional feature set is further optimized to yield l0-dimensional features through Sequential Forward Selection (SFS) method. This down-sized feature set is finally used to train and classify the given TV program scenes using κ -NN, Gaussian pattern matching algorithm. The classification result of 91.6% reported here shows the promising performance of the video scene classification based on the audio information. Finally, the system stability problem corresponding to different query length is investigated.

• Journal of the Korean Arthroscopy Society
• /
• v.1 no.1
• /
• pp.26-30
• /
• 1997

Recently, the incidence of anterior cruciate ligament injury is rapidly increasing because many young Korean are actively participating in sports activities including basketball, skiing and soccer. Sometimes acute ACL injuries arc misdiagnosed as sprain because of pain and muscle spasm. An accurate physical examination and careful history taking are very important to diagnose the ACL injuries. Therefore author described the skill of history taking and the technique of physical examination to diagnose ACL injuries. The most sensitive test is the Lachman's test, which is performed with the knee in 200 of flexion, the femur stabilized with full flexed examiner's knee placed behind patient's distal thigh and one hand of examiner, and the proximal tibia grasped with the other. The pivot shift test is a passive motion test that attempts to subluxate the tibia anteriorly, then have it reduce rapidly. The pivot shift test is very sensitive test to diagnose the chronic ACL injuries.

• Proceedings of The KACE
• /
• 2018.01a
• /
• pp.137-140
• /
• 2018

대한민국의 대표적인 구기 종목 중 하나인 농구는 입문 시 기본 동작에 적응하고 기본 규칙을 이해하기 위해 많은 시간이 소비된다. 또한 기존 농구 학습 분야에서 평가 수행 시 평가 대상자의 실력을 정량적으로 도출하는 것이 힘들어 중 고등학교 체육교과의 수행평가에서 객관적인 평가가 이루어지기 힘들었다. 본 연구에서는 이러한 농구 학습의 한계점을 해결하기 위하여 3축 자이로 센서와 스위치가 적용된 웨어러블 시스템을 기반으로 농구 학습을 도와주는 동작인식 기법을 제안한다. 그리고 실험을 통하여 제안하는 동작인식 기법의 성능을 검증하였으며, 생활체육 활성화를 통한 국민 건강증진과 객관적인 수행평가 실현에 기여할 것으로 기대된다.

• Journal of Multimedia Information System
• /
• v.5 no.4
• /
• pp.257-264
• /
• 2018

Over the years application of computer vision techniques in sports videos for analysis have garnered interest among researchers. Videos of sports games like basketball, football are available in plenty due to heavy popularity and coverage. The goal of the researchers is to extract information from sports videos for analytics which requires the tracking of the players. In this paper, we explore use of deep learning networks for player spotting and propose an algorithm for tracking using Kalman filters. We also propose an algorithm for finding distance covered by players. Experiments on sports video datasets have shown promising results when compared with standard techniques like mean shift filters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.475-477
• /
• 2022

최근 강화 학습을 적용한 게임 AI 에 대한 연구가 활발히 진행되고 있다. 하지만 대부분 상용게임은 유한 상태 머신(Finite State Machine, FSM)을 이용한 스크립트 기반 AI 를 사용하기 때문에 복잡한 환경의 게임에서 불안정한 상태로 인해 적절한 강화 학습의 수행이 어렵다. 따라서 본 논문에서는 상용 게임 강화 학습 적용을 위하여 상태 정규화 및 Dense 보상 기반 강화 학습 기법을 제안한다. 제안한 기법을 상용 농구 게임에 적용하고 학습된 모델의 성능을 기존 FSM 기반 AI 와 비교를 통해 성능이 약 80% 증가한 결과를 확인하였다.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.4
• /
• pp.117-129
• /
• 2023

Organizations must seek change in order to adapt to environmental changes and achieve better performance. However, despite this obvious statement, empirical analysis has been almost non-existent due to the difficulty of manipulating organizational performance or change. In this study, we overcame these limitations and analyzed the causes and effects of organizational change by assuming a professional sports team as a venture company, which is relatively easy to objectively measure and evaluate organizational change or performance. We systematically collected and preprocessed traditional and advanced metrics of National Basketball Association (NBA) statistics along with preprocessed trade data from eight years of regular seasons (2014~2015-2021~2022) to analyze our research model. Assessment of process macro model 7 derives the following empirical result. The results of the empirical analysis depict that NBA teams with low organizational performance in the previous season are more likely to make organizational changes through player trades to improve performance. Into the bargain player trades mediate the static relationship between the winning percentage in the previous season and the winning percentage in the current season. However, the indirect effect of a team's previous season's performance on player trades appears to vary depending on the current situations and context of each NBA team. Teams that made the playoffs in the previous season tend to make fewer trades than teams that did not and the previous season's performance is highly correlated with the current season's performance. On the other hand, teams that did not make the playoffs in the previous season tend to make a relatively larger amount of player trades in total, and the mediating effect of trades vanishes in this case. In other words, teams that did not make the playoffs in the previous season experience a larger change in performance due to trades than teams that made the playoffs, even if they achieved the same winning percentage. This empirical analysis of the inverse relationship between organizational change and the performance of professional sports teams has both theoretical and practical implications in the field of sports industry and management by analyzing the fundamentals of organizational change and the performance of professional sports teams.

• Journal of Broadcast Engineering
• /
• v.20 no.1
• /
• pp.26-39
• /
• 2015

UHD (Ultra High Definition) has been developed and standardized over the past few years and considered as a key of the next generation broadcasting. Since major sporting events that attract many viewers have been good opportunities for applying and promoting new broadcasting technology, KBS (Korean Broadcasting System) has carried out live 4K terrestrial broadcasting of three big sports events in 2014, the KBL (Korean Basketball League) finals, the 2014 FIFA World Cup, and the 2014 Incheon Asian Games. Especially, 4K UHD live coverage of the KBL finals was the world's first live 4K terrestrial broadcasting, and people could enjoy the World Cup and the Asian Games with UHDTV at home. In this paper, the overall live production and data transmission of the sporting events is described, including on-location live production, live HEVC (High Efficiency Video Coding) encoding, SFN (Single Frequency Network) transmission, as well as experimental IP transmission of uncompressed 4K video via KREONET, a national R&D network run by KISTI (Korea Institute of Science and Technology Information).

• Journal of Korea Game Society
• /
• v.6 no.2
• /
• pp.3-12
• /
• 2006

Recently, Many 3D augmented reality games that provide strengthened immersive have appeared in the 3D game environment. In this article, we describe a barehanded interaction method based on human hand gestures for augmented reality games. First, feature points are extracted from input video streams. Point features are tracked and motion of moving objects are computed. The shape of the motion trajectories are used to determine whether the motion is intended gestures. A long smooth trajectory toward one of virtual objects or menus is classified as an intended gesture and the corresponding action is invoked. To prove the validity of the proposed method, we implemented two simple augmented reality applications: a gesture-based music player and a virtual basketball game. In the music player, several menu icons are displayed on the top of the screen and an user can activate a menu by hand gestures. In the virtual basketball game, a virtual ball is bouncing in a virtual cube space and the real video stream is shown in the background. An user can hit the virtual ball with his hand gestures. From the experiments for three untrained users, it is shown that the accuracy of menu activation according to the intended gestures is 94% for normal speed gestures and 84% for fast and abrupt gestures.

• Sleep Medicine and Psychophysiology
• /
• v.6 no.2
• /
• pp.116-125
• /
• 1999

Objectives: The purpose of this study is to investigate the effect of exercise load on sleep structure and stress hormone secretion during sleep. Methods: Five male physical education students were included in this study after giving their written, informed consents in the Research Institute for Sports Science at the University of Hanyang. All subjects have performed for at least 3 years in a regular aerobic exercises such as football, basketball, and running. The subjects were divided into three groups ; NOE(non-exercise), MDE(middle duration exercise), LDE(long duration excercise). MDE group maintained a total of 120 min exercise, and LDE group maintained a total of 300 min exercise by football, basketball or badminton. All subjects were acclimatized to the experimental sleep condition by spending one night under expermental conditions, including the placement of an intravenous catheter. During the subsequent night(24:00-08:00), somnopolygraphic sleep recordings were obtained, and blood for measuring growth hormone, cortisol, testosterone, and $\beta$-endorphin was collected every 120 min throughout the night. Blood samples were obtained from prominent forearm veins of subjects. Then, the samples were immediately placed in ice and centrifuged within 10 min at 3000 rpm at $4^{\circ}C$. Statistical analyses were performed using the SPSS/$PC^+$. Data were analyzed by one-way ANOVA with repeated measures. Results: No significant differences among groups were observed in sleep latency, total sleep time, stage 2 sleep, and slow wave sleep. However, daytime exercise produced significant changes in stage 1 sleep, REM sleep, stage 2 sleep latency, REM sleep latency and sleep efficiency. Stage 1 sleep, stage 2 sleep latency, and REM sleep latency significantly increased in LDE compared to those of NOE and MDE groups. But the amount of REM sleep significantly decreased in LDE. Sleep efficiency of MDE was higher than those of NOE and LDE. The blood concentrations of growth hormone, testosterone, and cortisol during night sleep were significantly lower in LDE than in NOE. $\beta$-endorphin concentrations in blood during night sleep were not different among groups. Conclusion: The daytime exercise load was significantly related to sleep structure and stress hormone secretion during night sleep. Long duration exercise showed a harmful effect on sleep structure and hormone secretion. However, middle duration exercise had a beneficial effect on sleep structure and hormone secretion during sleep.