• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Korea Trade Review
• /
• v.42 no.2
• /
• pp.145-174
• /
• 2017

Recently, due to the worsening global economic recession, Korea which is a small, export-oriented economy has decreased exports and the domestic economy also continues to stagnate. Therefore, for continued growth of our economy through export growth, we need to analyze the validity of export support system such as export insurance and prepare ways to expand exports. This study is to investigate the effects of Export Insurance on the exports of SMEs as well as LEs. For this purpose, this study conducted Time Series Analysis using data such as export, export insurance acquisition, export price index, exchange rate, and coincident composite index(CCI). First, as a result of the Granger Causality Test, the exports of LEs has found to have a causal relationship with the CCI, and CCI is to have a causal relationship with the short-term export insurance record. Second, the results of VAR analysis show that the export insurance acquisition result and the export price index have a positive effect on the exports of LEs, while the short - term export insurance has a negative effect on the exports of LEs. Third, as a result of variance decomposition, the export of LEs has much more influenced for mid to long term by the short-term export insurance acquisition compared to SMEs. Fourth, short-term export insurance has a positive effect on exports of SMEs. In order to activate short-term export insurance against SMEs, it is necessary to expand support for SMEs by local governments. This study aims to suggest policy implications for establishing effective export insurance policy by analyzing the effects of export insurance on the export of SMEs as well as LEs. It is necessary to carry out a time series analysis on the export results according to the insurance acquisition results by industry to measure the export support effect of export insurance more precisely.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.441-447
• /
• 2023

Lead(Pb), which is currently mainly used for shielding purposes in the medical radiation, has excellent radiation shielding functions, but is continuously exposed to radiation directly or indirectly due to the harmfulness of lead itself to the human body and the inconvenience caused by its heavy weight. Research on shielding materials that are human-friendly, lightweight, and convenient to use that can block risks and replace lead is continuously being conducted. In this study, based on the commonly used polyethylene terephthalate (PET) film and the fabric material used in actual radiation protective clothing, a multi-layer thin film was realized through sputtering and vacuum deposition of bismuth, tungsten, and tin, which are metal materials that can shield radiation. Thus, a shielding film was produced and its applicability as a radiation shielding material was evaluated. The radiation shielding film was manufactured by establishing the optimized conditions for each shielding material while controlling the applied voltage, roll driving speed, and gas supply amount to manufacture the shielding film. The adhesion between the parent material and the shielding metal thin film was confirmed by Cross-cut 100/100, and the stability of the thin film was confirmed through a hot water test for 1 hour to measure the change of the thin film over time. The shielding performance of the finally realized shielding film was measured by the Korea association for radiation application (KARA), and the test conditions (inverse wide beam, tube voltage 50 kV, half layer 1.828 mmAl) were set to obtain an attenuation ratio of 16.4 (initial value 0.300 mGy/s, measured value 0.018 mGy/s) and damping ratio 4.31 (initial value 0.300 mGy/s, measured value 0.069 mGy/s) were obtained. by securing process efficiency for future commercialization, light and shielding films and fabrics were used to lay the foundation for the application of films to radiation protective clothing or construction materials with shielding functions.

• 한국체육학회지인문사회과학편
• /
• v.54 no.1
• /
• pp.553-566
• /
• 2015

This study was performed to identify the effects of different intensities of regular aerobic exercise on erythropoietin (EPO) and BDNF levels, and cognitive function and working memory in middle-aged women. Women aged 40 to 60 years residing in G-gu, Y-si, Gyeonggi-do were divided into 3 groups: control group, moderate-intensity aerobic exercise group and high-intensity aerobic exercise. All groups were asked to exercise at the given intensities, twice a week for a total of 12 weeks. Blood samples were collected from participants on week 0 (before exercising), week 6 and week 12, and then cognitive function and working memory tests were followed to measure erythropoietin (EPO) and BDNF levels, cognitive function and working memory. Repeated measures ANOVA, univariate analysis and follow-up test were performed on all data to compare the group, period and interaction through a SPSS. As a result, a significant difference over time was observed in EPO, BDNF, cognitive function and working memory; therefore, a follow-up one-way ANOVA analysis was performed on each group. As a result of analysis, a significant increase in erythrocyte, hematocrit, BDNF level and working memory was observed in moderate-intensity aerobic exercise group while erythrocyte and working memory were significantly increased inhigh-intensity aerobic exercise group. When comparing the results between the groups, the level of hematocrit was shown to be significantly higher in both moderate-and high-intensity aerobic group than the control group and also the higher level of hemoglobin was observed in both moderate-and high-intensity aerobic group comparing to control group. Considering the results of this study, therefore, a 12-week long aerobic exercise at moderate to high intensity positively affected EPO and BDNF levels, cognitive function and working memory in middle-aged women.

• Korean Journal of Environment and Ecology
• /
• v.37 no.3
• /
• pp.221-231
• /
• 2023

Great tit (Parus major) is a bioindicator species that can measure environmental changes in urban ecosystems and plays an important role in maintaining health as a representative insectivorous bird. Researchers have utilized artificial nest box surveys to understand the reproductive ecology of the Paridae family of birds, including the Great tits, but it is difficult to conduct a macroscopic study due to spatial and temporal limitations. This study designed and applied a citizen-participatory monitoring of artificial nest boxes project to transcend the limitations of expert-centered monitoring methods. The Suwon Front Yard Bird Monitoring Team installed artificial nest boxes in green spaces in Suwon, Gyeonggi Province and observed the reproductive ecology of the Paridae family through the participation of voluntary citizen surveyors. Participants were recruited through an online survey from February 9 to February 22, 2021, and they directly performed from installation to observation of artificial next boxes from February 23 to August 31, 2021. Online education was provided to the volunteers for the entire monitoring process to lower the entry barrier for non-expert citizen surveyors and collect consistent data, and observation records were collected through a mobile app. A total of 98 citizen surveyors participated in the citizen-participatory monitoring of artificial nest boxes project, and 175 (84.95%) of the 256 distributed artificial nest boxes were installed in green spaces in Suwon City. Among the installed artificial nest boxes, the results of the citizen science project were confirmed for 173 (83.98%), excluding two boxes with position coordinate generation errors. A total of 987 artificial nest box observation records were collected from citizen surveyors, with a minimum of one time, a maximum of 26 times, and an average of 5.71±4.37 times. The number of observations of artificial birdhouses per month was 70 times (7.09%) in February, 444 times (44.98%) in March, 284 times (28.77%) in April, 133 times (13.48%) in May, 46 times (4.66%) in June, 6 times (0.61%) in July, and 4 times (0.41%) in August. Birds using the artificial nest boxes were observed in 57 (32.95%) of the 173 installed artificial nest boxes, and they included Great tit (Parus major) using 12 boxes (21.05%), Varied Tit (Parus varius) using 7 boxes (12.28%), and unidentified birds using 38 boxes (66.67%). This study is the first to consider citizen participation in the monitoring of artificial nest boxes, a survey method for the reproductive ecology of the Paridae family, including Great tits, and it can be utilized as basic data for the design of ecological monitoring combined with citizen science in the future.

• Analytical Science and Technology
• /
• v.20 no.4
• /
• pp.261-267
• /
• 2007

The 20 L small chamber test method is to evaluate pollutants such as TVOC, formaldehyde emitted from building materials. This method was only designed to evaluate the surface emission of sample exposed in the chamber. In this method, building materials cut with a fixed standard size are fixed in a sample sealing box. The sample sealing box is put into the 20 L test chamber. This chamber is ventilated at a standard air change rate with purified air for 7 days then the sample from the chamber is collected and analyzed to measure the emission rate of TVOC and formaldehyde. In this method, however, if the sealing box does not guarantee airtightness, accurate evaluation for the building materials can not be achieved due to the pollutants emitted from edge of the sample so called, edge effect. This edge effect can be much greater when evaluating panels such as plywood, flooring due to their surface treatment. In this study, flooring was tested to check airtightness of the sample sealing box with analytic results between 1L and 20 L test chamber. Furniture materials like LPM coated one side surface treatment and MDF coated both sides surface treatment with LPM were tested to identify whether the improvement of the sample sealing box airtightness is possible with the comparison between existing and improved test method that low VOC emission tape was used to seal the sample edge. After 7 days, MDF TVOC emission rate was different according to the existence and nonexistence of tape. The emission rate of the existing test method was $0.009mg/m^2h$ and that of improved test method was $0.003mg/m^2h$. Relative standard deviation for the existing test method was $0.004mg/m^2h$ and relative standard deviation for the improved test method was $0.002mg/m^2h$ when the same sample was analyzed three times. The improved test method in this study using low VOC emission tape was effective and able to reduce the heterogeneous effect of the edge from the sample sealing box.

• 재활복지
• /
• v.14 no.3
• /
• pp.225-256
• /
• 2010

This study aims to provide the basic data of the rehabilitation program for the schoolchild with intellectual disability by designing new framework of the features of postural control for the schoolchild with intellectual disability. For this, the study investigated what sensations the schoolchild are using to maintain posture by selectively or synthetically applying vision, vestibular sensation and somato-sensation, and how the coordinative sensory system of the schoolchild is responding to any sway referenced sensory stimulus. The study intended to prove the limitation of motor system in estimating the postural stability by providing the cognitive motor task, and provided the features of postural control of the schoolchild with intellectual disability by measuring the onset times and orders of muscle contraction of neuron-muscle when there is a postural control taking place due to the exterior disturbance. Furthermore, by comparatively analyzing the difference between the normal schoolchild and the intellectually disabled schoolchild, this study provided an optimal direction for treatment planning when the rehabilitation program is applied in the postural control ability training program for the schoolchild with intellectual disability. Taking gender and age into consideration, 52 schoolchild including 26 normal schoolchild and 26 intellectually disabled schoolchild were selected. To measure the features of postural control, CTSIB test, and postural control strategy test were conducted. The result of experiment is as followed. First, the schoolchild with intellectual disability showed different feature in using sensory system to control posture. The normal schoolchild tended to depend on somato-sensory or vision, and showed a stable postural control toward a sway referenced stimulus on somato-sensory system. The schoolchild with intellectual disability tended to use somato-sensory or vision, and showed a very instable postural control toward a sway referenced vision or a sway referenced stimulus on somato-sensory system. In sensory analysis, the schoolchild with intellectual disability showed lower level of proficiency in somato-sensation percentile, vision percentile and vestibular sensation percentile compare to the normal schoolchild. Second, as for the onset times and orders of muscle contraction for strategies of postural control when there is an exterior physical stimulus, the schoolchild with intellectual disability showed a relatively delayed onset time of muscle control, and it was specially greater when the perturbation is from backward. As for the onset orders of muscle contraction, it started from muscles near coax then moved to the muscles near ankle joint, and the numbers and kinds of muscles involved were greater than the normal schoolchild. The normal schoolchild showed a fast muscle contracting reaction from every direction after the perturbation stimulus, and the contraction started from the muscles near the ankle joint and expanded to the muscles near coax. From the results of the experiments, the special feature of the postural control of the schoolchild with intellectual disability is that they have a higher dependence on vision in sensory system, and there was no appropriate integration of swayed sensation observed in upper level of central nerve system. In the motor system, the onset time of muscle contraction for postural control was delayed, and it proceeded in reversed order of the normal schoolchild. Therefore, when use the clinical physical therapy to improve the postural control ability, various sensations should be provided and should train the schoolchild to efficiently use the provided sensations and use the sensory experience recorded in upper level of central nerve system to improve postural control ability. At the same time, a treatment program that can improve the processing ability of central nerve system through meaningful activities with organizing and planning adapting reaction should be provided. Also, a proprioceptive motor control training program that can induce faster muscle contraction reaction and more efficient onset orders from muscularskeletal system is need to be provided as well.

• Korean Journal of Health Psychology
• /
• v.14 no.2
• /
• pp.277-292
• /
• 2009

This study investigated the responses of the autonomic nervous system of individuals with Type D personality during an acute stressful situation. Twenty-three female students of Type D personality and 23 female students with non-Type D personality. Stroop Color-Word Task was used to induce a stressful situation, heart rate variability (HRV) was used to measure the responses of the autonomic nervous system during the baseline, acute stress, recovery periods. To analyze the data, the repeated measures analysis of variance was used to compare the autonomic nervous system of the Type D group to that of the non-Type D group. Regression analysis is used to determine if the Type D scale and stress vulnerability predicted the activities of the autonomic nervous system during the baseline period. The results of this study demonstrated that the Type D group's normalized low frequency (LF norm) and ratio of low frequency to high frequency (LF/HF ratio) were higher than those for the non-Type D group, while its normalized high frequency (HF norm) was lower than that for the non-Type D group in all three periods. There were no statistically significant differences among the three periods in terms of LF norm, HF norm, and LF/HF ratio in the Type D group. The study demonstrated that the total scores of the Type DS-14 and scores of social inhibition and negative affect were independent predictors of LF norm and HF norm during the baseline. The Type D group showed increased activation of the sympathetic nervous system and/or decreased activation of the parasympathetic nervous system. These results support the hypothesis that the Type D personality is vulnerable to the stress. Also, the highly activated sympathetic and/or lowly activated parasympathetic nervous systems, which were observed in the Type D group during the baseline, indicated that the Type D individual is susceptible to psychosomatic disorders.

• Korean Journal of School Psychology
• /
• v.9 no.3
• /
• pp.485-503
• /
• 2012

Academic engagement has been known as a strong predictor of students' cognitive and affective outcomes in an educational context. Despite increasing interest and theoretical usefulness of this construct, a few researchers seem to be interested in the validation of instruments to measure academic engagement for Korean students. Thus, this study would like to introduce one of academic scales widely used, UWES-S(Utrecht Work Engagement Scale-Student) (Schaufeli et al., 2002a: 2002b) and to validate the UWES-S for Korean college students. To validate the Korean version of the UWES-S, 651 college students (285 for Field Trial, 366 for Main Study) were used. The procedure is as follows. First, we used an integrated adaptation procedure to produce a Korean version of the UWES-S. Second, EFA(exploratory factor analyses) was applied to explore the factor structure of the UWES-S on the field trial data. Third, the psychometric properties of the UWES-S items were examined by graded response model(GRM). Also CFA(confirmatory factor analysis) was used to examine its internal construct validity for the data from the main study. Finally, the external validity of the UWES-S was scrutinized with the related variables such as academic motivation and satisfaction. As a result, the Korean version of the UWES-S with 13 items was accepted that the four items were excluded from its original version. Second, the internal validity was supported that the 3 factor CFA model(vigor, dedication, absorption) fit the data well. Third, we supported the partial mediation model that academic engagement played as a mediating variable between academic motivation(internal/external) and academic satisfaction. Finally, the differences between a validation of UWES-S for Korean college and high school students, the necessity of construct equivalence testing, and direction for future research of scale validating were discussed.

• Asia Marketing Journal
• /
• v.15 no.3
• /
• pp.117-139
• /
• 2013

Research on purchase intention had showed remarkable progress in contributing to the theory of consumer behavior. Despite the popularity of academic discussions on various issues influencing purchase intention, the mediating role of brand recall and brand attitude on purchase intention, in particular advergames, has not yet been well explored, especially in developing economies such as Malaysia. Furthermore, the influence of self-brand congruity, entertainment and brand placement acceptance as antecedents to brand recall and brand attitude are expected to add value to the brand recall, brand attitude and purchase intention relationships. This paper aims to investigate the impact of the mediating role of brand recall and brand attitude on purchase intention in advergames among Malaysian gamers. The antecedents towards brand recall and brand attitude are also examined to measure their influence on purchase intention. A total of 350 Malaysian gamers were interviewed through online survey in this study. The results showed that brand recall and brand attitude mediate the relationship between self-brand congruity, entertainment and brand placement acceptance with purchase intention. Also, entertainment and brand placement acceptance were found to have a significant relationship with brand recall. As expected, brand recall and brand attitude showed a positive relationship with consumer purchase intention in advergames. It was found that self-brand congruity has a significant influence on brand attitude and purchase intention. When users see the brand which matches with them, they tend to act positively toward the brand exposed in the game. This is consistent with Escalas and Bettman (2005) who suggested that the greater the congruity, the more positive the consumer's attitude toward the brand in question. This leads to game usage and purchase (Davis and Lang, 2013). In the advergaming context, the entertainment value in advergames is very important to determine the level of enjoyment and pleasure experienced by gamers during game-playing. Therefore, the more entertaining the ads, the more it will be remembered and the greater the positive behavior of the consumer towards the advergames - this ultimately stimulates their intention to purchase the brand. This study shows the effect of brand placement on brand recall and brand attitude and also purchase intention. Brand placements might not work in games due to the interactivity involved in game-playing as people could be distracted from noticing the brand placements (Yang et al., 2006). However, the significant influence of brand placements found in this study may provide major promise for advertisers. Game players may or may not explicitly remember the brands they see in the games, but these placements may influence their brand recall and brand attitude and could therefore influence later decisions (Yang et al., 2006). In this study, it was found that self-brand congruity was not significantly related with brand recall. The reason for this could be attributed to the fact that this study examined gamers who are highly involved in the interactive medium of games which force them to focus on game play rather than advertisements; the level of recognition to remember the brand exposed in the game is low and contributes to the "mismatch" between the gamers and the said brand. The present study contributes to the existing literature of the antecedents of brand recall and brand attitude in advergames. This study contributes to the role of brand recall and brand attitude as mediators in purchase behavior theory. Academically, the relationship between brand recall and brand attitude is well known in advergaming research, but their impact as important mediators on purchase intention add new understanding in the interactive communication literature. Their mediating role may provide new insights on how they facilitate the effects of self-brand congruity, entertainment and brand placement on purchase intention. Besides that, the studies on the influence of self-brand congruity on brand recall and brand attitude and also consumer intention to purchase had not well-investigated in advergames. This study contributes to fill those gaps in advergames literature. For practitioners, this study could suggest the use of illustrative or demonstrative placements of new products to help customers remember new brands, and the use of associative placements for existing products to increase consumers' purchase intention (Ho et al., 2011). To advertisers, this study may provide useful information to improve their current advertising strategies in games, for instance, by considering game players' congruity, entertainment value and brand placement factors.