• 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 the Korea Society for Simulation
• /
• v.31 no.1
• /
• pp.11-18
• /
• 2022

Recently, research to classify human activity using imagery has been actively conducted for the purpose of crime prevention and facility safety in public places and facilities. In order to improve the performance of human activity classification, most studies have applied deep learning based-transfer learning. However, despite the increase in the number of backbone network models that are the basis of deep learning as well as the diversification of architectures, research on finding a backbone network model suitable for the purpose of operation is insufficient due to the atmosphere of using a certain model. Thus, this study applies the transfer learning into recently developed deep learning backborn network models to build an intelligent system that classifies human activity using imagery. For this, 12 types of active and high-contact human activities based on sports, not basic human behaviors, were determined and 7,200 images were collected. After 20 epochs of transfer learning were equally applied to five backbone network models, we quantitatively analyzed them to find the best backbone network model for human activity classification in terms of learning process and resultant performance. As a result, XceptionNet model demonstrated 0.99 and 0.91 in training and validation accuracy, 0.96 and 0.91 in Top 2 accuracy and average precision, 1,566 sec in train process time and 260.4MB in model memory size. It was confirmed that the performance of XceptionNet was higher than that of other models.

• Journal of Korean Orthopaedic Sports Medicine
• /
• v.11 no.1
• /
• pp.44-50
• /
• 2012

Purpose: The purpose of this study is to analyze the relationship between acute anterior cruciate ligament (ACL) injury and bone bruise using the survey for location and incidence of bone bruise. Materials and Methods: From Jan. 2006 to Feb. 2010, 87 knees from who had complaint a traumatic knee pain were diagnosed as acute ACL tear using MRI evaluation. Associated injury, location and incidence of bone bruise were analyzed using MRI. The location of bone bruise on the MRI was classified as medial, central and lateral area on anteroposterior and lateral view of femur and tibia. The bone bruise was classified with Costa Paz classification. Results: Bone bruise of injury during daily living activity were located at medial area on coronary view and anterior area on sagittal view of distal femur, at medial area on coronary view and anterior area on sagittal view of proximal tibia (p=0.024, p=0.021, p=0.025 and p=0.029, respectively). Bone bruise of injury during sports activity were located at lateral area on coronary view and central area on sagittal view of distal femur, at lateral area on coronary view and posterior area on sagittal view of proximal tibia (p=0.014, p=0.015, p=0.018 and p=0.017, respectively). Bone bruise patterns due to traffic accident were inconclusive (p=0.264, p=0.254, p=0.229 and p=0.267, respectively). Conclusion: Injury mechanism of acute ACL injury from activities of daily living or sports activities compared to that of traffic accident showed a more consistent bone bruise patterns. Special attention to acute ACL tear must be paid in case of bone bruise at lateral tibial plateau and lateral femoral condyle.

• Journal of Korean Physical Therapy Science
• /
• v.26 no.3
• /
• pp.15-22
• /
• 2019

Background: The purpose of this study is to explore the effect of the functions of GMFM and ICF-CY on the activities and participation of ICF-CY sub-items. Design: Cross-sectional study. Method: This study compared and analyzed 95 children with cerebral palsy [type of CP: spasticity 86 (90.5%), hypotonia 4 (4.2%), mixed 5 (5.3%); type of palsy: quadriplegia 13 (13.7%), diplegia 71 (74.7%), hemiplegia 11 (11.6%)] using sub-items of functions, activities and participation from GMFM and ICF-CY. Result: The results show that the activities and participation of ICF-CY (9 sub-items) have significant effect on the functions of GMFM and ICF-CY (8 sub-items) (p<0.05). Conclusion: It is intended to provide data to establish practical therapeutic goals and interventions for functions, activities and participation, which are sub-categories of ICF-CY in cerebral palsy.

• Journal of Fashion Business
• /
• v.19 no.1
• /
• pp.122-140
• /
• 2015

The research is committed to inquire about the attributes of color schemes and their image, and the results are as follows : One, the preference of ranges of neon colors was explicit, and the frequency of use of neon colors distinctively diverged season by season. Two, it was observed that, with neon colors, an achromatic color scheme was a more preferred arrangement. As for chromatic colors, neutral and mid-tone natural colors were more favored since they did not tarnish the properties of neon colors and, yet, more effective exhibiting images in diversity and variety. Three, the neon color fashion generally displayed a dual image: its original classification embellished with neon colors rendering the image of powerful and futuristic sensation. Having been around since the early 2000's, the frequency and range of use of neon colors have been increasing rapidly mostly by the sports, leisure and related industries. Regardless of the fact, neon colors will be rediscovered with a variety of color schemes and expand their application.

• Korean Journal of Human Ecology
• /
• v.18 no.5
• /
• pp.1115-1122
• /
• 2009

The purpose of this research was to measure the effects of a health management program through a school homepage on Obese Female College Students. The subjects were confined to 70 Obese Female College students from S University, located in C area. They voluntarily participated in this study. The subjects were divided into two groups by the BMI (Body Mass Index) classification: overweight or obesity program group(PG, n=35), and overweight or obesity comparative group(CG, n=35). The results obtained are summarized as follows: First, compared with the CG, there was a significant decrease for waist circumference in PG, and a significant decrease for the variables such as fat mass, weight, %fat, and BMI in PG. Second, in the investigation of blood lipids change of PG, there was a significant decrease for TC, TG and HR-rest. On the other hand, there was a significant increase for HDL-C.

• Journal of the Korean Institute of Educational Facilities
• /
• v.27 no.2
• /
• pp.15-20
• /
• 2020

Due to urbanization and industrialization, the population of rural areas has sharply decreased, and the social phenomena of low fertility and aging have occurred due to many factors such as the spread of individualism and single-person households derived from urbanization and economic growth. In order to cope with the low birth rate and the aged society, the Korean government has invested 152.1 trillion won from 2006 to 2015 and to proceeded total 231 projects in 3 different areas including the low fertility(95 projects), the aged society(78 projects), and the growth momentum(58 projects). Among the social problems caused by the low birth rate and the aged society, there have been not enough studies on the closed schools which will result from the social phenomenon of decreases in the school age population. The purpose of this study is to analyze the current extent of utilizing closed schools in Korea, to derive some types based on the analysis, and to provide basic data on the use of closed schools in Korea in the future. The types of closed schools can be classified into education facilities, social welfare facilities, cultural facilities, public sports facilities, income growing facilities, and others. Based on the classification, the analyses of the characteristics of each type for the facilities are presented.

• Journal of the Korean Institute of Educational Facilities
• /
• v.27 no.3
• /
• pp.25-31
• /
• 2020

The reasons for studying the case of Japan are as follows. First, the increases in the aged population is similar to the case of Korea, and consumers are aging as the population ages. Second, the structure of industry in Japan is very similar to Korea, which describes the fact that the share of the manufacturing industry decreases but the service industry (e.g., medicine, finance, and insurance) increases. Third, Japan is considered as the best predictive model for forecasting the future of closed schools in Korea because the GNI gross income per capita is relatively close to the one of Korea among the several neighboring countries. The purpose of this study is to analyze the current extent of utilizing closed schools in Japan and, based on the analysis, to provide basic data on the use of closed schools in Korea in the future. The types of closed schools can be classified into education facilities, social welfare facilities, cultural facilities, public sports facilities, income growing facilities, and others. Based on the classification, the analyses of the characteristics of each type for the facilities are presented. and When the utilization status of closed schools in Japan is analyzed, 363 schools were utilized (51.4%) in 2003, means the lowest utilization rate of the target year, after that 4198 schools (70.6%) were utilized in 2015. The utilization ratio is steady increased.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.302-304
• /
• 2016

In this paper, we propose the profile processing algorithm based on in-life sports contents. The proposed algorithm is required research for recommending to sport for all contents, and is preceding research to improve reliability of recommendation. So the proposed algorithm processing dynamic profile based on dynamic information for recommendation, and processing weight values that depending on dynamic recommendation classification. The proposed profile processing algorithm is expected to improve satisfaction of contents recommendation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.89-95
• /
• 2023

In recent decades, human action recognition (HAR) has demonstrated potential applications in sports analysis, human-robot interaction, and large-scale signage content. In this paper, spatial temporal attention graph convolutional network (STAGCN)-based HAR system is proposed. Spatioal-temmporal features of skeleton sequences are assigned different weights by STAGCN, enabling the consideration of key joints and viewpoints. From simulation results, it has been shown that the performance of the proposed model can be improved in terms of classification accuracy in the NTU RGB+D dataset.