• Journal of Broadcast Engineering
• /
• v.19 no.2
• /
• pp.166-173
• /
• 2014

Recently, human action recognition have been developed for various broadcasting and video process. Since a video can consist of various scenes, keypoint approaches have been more attracted than template based methods for real application. Keypoint approahces tried to find regions having motion in video, and made 3-dimensional patches. Then, descriptors using histograms were computed from the patches, and a classifier based on machine learning method was applied to detect actions in video. However, a single classifier was difficult to handle various human actions. In order to improve this problem, approaches using multi classifiers were used to detect and to recognize objects. Thus, we propose a new human action recognition using decision-level fusion with support vector machine and sparse representation. The proposed method extracted descriptors based on keypoint approach from a video, and acquired results from each classifier for human action recognition. Then, we applied weights which were acquired by training stage to fuse each results from two classifiers. The experiment results in this paper show better result than a previous fusion method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.140-142
• /
• 2000

인간과 기계가 효과적인 상호작용을 하기 위해서는 컴퓨터 시스템이 인간의 행동을 인식할 수 있어야 한다. 본 연구에서는 인공 신경망을 사용하여 컴퓨터 시스템이 인간의 움직임을 관찰한 후 행위자의 성별을 인식하도록 하는 시스템을 구현하였다. 두 가지 감정상태(보통상태, 화난 상태) 하에서 일어난 인간의 세 가지 동작(문 두드리기, 손 흔들기, 물건 들어올리기)을 대상으로 하여 인간 동작 데이터를 통해 만들어진 학습 데이터를 통해 98.0%의 인식률을 보일 때까지 학습시키고 나서, 이전에 사용하지 않았던 새로운 데이터에 대해 얼마나 설별을 잘 구별해 내는지 실험하였다. 동작이 일어나는 동안 행위자의 몸 여섯 군데에서 속도 데이터를 얻어내서 신경망의 입력값으로 사용하였다. 그 결과 최저 62.3%이상 최고 94.3%까지 인간 성별을 구분해 낼 수 있었고 이는 같은 데이터에 대해서 사람을 통해 실험한 것보다 훨씬 나은 것이다.

• Journal of Nutrition and Health
• /
• v.50 no.3
• /
• pp.284-293
• /
• 2017

Purpose: This study was conducted to examine the behavioral intentions of breastfeeding in single women using the theory of planned behavior. Methods: The questionnaires were distributed to 350 single women in her 20~30s, and 316 respondents were analyzed by descriptive statistics, Spearman's correlation, and multiple regression analysis. Results: The subjects showed strong intentions and favorable attitudes toward breastfeeding. The subjects were more favorably influenced by their mothers, siblings, friends, and coworkers who previously experienced breastfeeding than ones with no breastfeeding experiences. There were significant correlations between breastfeeding intention and attitudes (r = 0.321, p < 0.0001), subjective norms (r = 0.434, p < 0.0001), and perceived control (r = 0.307, p < 0.0001). However, regression analysis with two different age groups revealed that subjective norms (p < 0.0001) and perceived control (p < 0.001) contributed to the model of explaining breastfeeding intentions in subjects who were 25 years old or younger, whereas attitudes did not. In addition, subjects who were more than 25 years old showed that attitudes (p < 0.003) and subjective norms (p = 0.002) contributed to the model of explaining breastfeeding intentions while perceived control (p < 0.070) showed less contribution. Conclusion: These results suggest that the theory of planned behavior can be a useful tool to increase the rate of breastfeeding intentions in single women when designing educational materials, which requires consideration of age differences.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.529-531
• /
• 2002

생체인식 시스템은 개인의 물리적/행동적 특성을 측정하여 신원을 확인하기 위한 시스템이다. 이러한 시스템에서 사용되는 특징들은 잡음 등에 의해서 쉽게 영향을 받기 때문에 매우 많은 변형들이 존재하고, 따라서 변형된 특징들을 효과적으로 다루기 위해 다양한 기계학습 방법들이 사용되고 있다. 그런데, 기존의 자료주도적인 방법들을 특정 생체인식 시스템에 적용하기 위해서는 시스템에 등록할 각 사람들로부터 충분히 많은 데이터를 획득해야하는 어려움을 겪게 된다. 또한 시스템에 미등록된 사람의 데이터가 제시될 가능성 등, 무한한 수의 변형이 존재하는 문제점을 갖고 있다. 이러한 문제점들로 인해 데이터의 분포특성을 분석하고 예측하는 것이 어렵다. 생체인식 시스템의 이러한 고유의 문제점을 극복하기 위해서는 새로운 효율적인 식별 및 검증 방법을 필요하다. 따라서, 본 논문에서는 통계적 가설 검증 이론에 기초한 간단한 방법을 제안하고, 실세계 데이터에 대한 실험을 통해 제안한 방법의 가능성을 확인한다.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.13-27
• /
• 2022

This study focused on the role of service robots as employees, and examined how robot services affect customer behavior compared to human employees in service success and failure situations. The three experiments were performed on barista robot, serving robot, and chef robot. The results of this study are as follows. First, in the case of service success, customers showed similar intentions for revisit regardless of employee type. On the other hand, in the case of service failure, the revisit intention was found to be more negative than that of the human employee when the service was received from the robot employee. The reason for this was found to be that customers had lower expectations for the capabilities of service robots compared to humans. Finally, customers perceive that robot services are more stable than human services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1165-1171
• /
• 2022

Human behavior recognition using an accelerometer has been applied to various fields. As smartphones have become used commonly, a method for human behavior recognition using the acceleration sensor built into the smartphone is being studied. In the case of the elderly, falling often leads to serious injuries, and falls are one of the major causes of accidents at construction fields. In this article, we proposed recognition method for human falling direction using built-in acceleration sensor and orientation sensor in the smartphone. In the past, it was a common method to use the magnitude of the acceleration vector to recognize human behavior. These days, deep learning has been actively studied and applied to various areas. In this article, we propose a method for recognizing the direction of human falling by applying the deep learning multilayer technique, which has been widely used recently.

• Journal of Industrial Convergence
• /
• v.20 no.8
• /
• pp.109-118
• /
• 2022

This study aims to examine the extent of lifestyle behavior changes, perceived restrictions in daily life, and their relationship during the COVID-19 pandemic. Using the 2020 Community Health Survey data, this study calculated perceived restrictions in daily life among adults in Korea during the pandemic by sociodemographic characteristics and lifestyle behavior category (physical activity, sleeping duration, drinking, smoking, social contact, public transport use, food delivery, instant food consumption). The generalized linear model examined the relationship between behavior change and perceived restriction on daily life. A total of 227,808 respondents were analyzed. 56.70% of the population perceived their daily lives restricted by 50% and more during the pandemic. The majority of the population decreased physical activity, social contact, and public transport use (52.71%, 89.70%, and 63.74%, respectively). Individuals who decreased physical activity, sleep duration, and social contact frequency, and those who increased drinking frequency, food delivery, and instant food consumption perceived greater restrictions in daily life than those who did not change respective behaviors (p<0.001). In conclusion, decreases in social contact and physical activity and increases in use of food delivery and instant food consumption were associated with greater perceived restrictions of daily life during the pandemic. Efforts to alleviate the negative impact of the pandemic on psychological well-being may need to involve attempts to improve healthy life behaviors.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.09a
• /
• pp.271-272
• /
• 2010

본 연구의 목적은 상황 인식 위치 기반 서비스를 위해 정성적인 개인 공간 행동을 포착하는 새로운 방법을 제안하는 것이다. 단순한 추적이내 사람의 위치 변화에 대해 색인 생성을 넘어서서, 사람과 환경 사이의 관계 변화가 본 연구의 공식 모텔에 대한 기본 소스로 간주된다. 특히 이 연구는 특정 지역의 경계 근처에서의 사람의 움직이는 행위에 중점을 둔다. 그 행위를 포착하기 위해 그 개체의 영향력 범위를 적용하는 새로운 접근 방법이 제안된다. 이러한 개체 시공간적으로 확장된 점는 그 영향력 범위를 그 개체의 위치와 함께 잠재적 사건이내 상호작용 구역으로 간주한다. 이렇게 포착된 정성적 공간 행위는 알려진 지역 근처의 개체 관계의 더 정제된 설명을 제공하여 단순한 공간정보 제공을 넘어선 실시간 공간 의사 결정 지원 시스템 강화에 도움을 줄 수 있다.

• Korean Journal of Culture and Social Issue
• /
• v.28 no.4
• /
• pp.597-625
• /
• 2022

This study aimed to examine the hypothesis that intrapersonal, interpersonal, and environmental self-awareness would alleviate the association between sSchadenfreude and cyberbullying. 300 middle and high school students answered survey questionnaires including sSchadenfreude, cyberbullying behavior, (intrapersonal. interpersonal, and environmental) self-awareness, depression, and anxiety. After controlling depression and anxiety, theThe results reveal that first, Schadenfreude predicts cyberbullying behavior, so those who have a high level of Schadenfreude commit more online cyberbullying behavior. Second, intrapersonal and interpersonal self-awareness moderated the association between schadenfreude and cyberbullying, and those who were above average on intrapersonal and interpersonal self-awareness were more liable to commit cyberbullying, but those below average did not show a significant moderation effect. Third, whereas environmental self-awareness did not show a significant moderation effect. Specifically, those who know well what they think and do and what they look like in interpersonal relationships perpetrate more cyberbullying when their schadenfreude was high. However, knowing well about what was happening around them was not related to the likelihood of schadenfreude that lead to cyberbullying. The results of this study revealed that Schadenfreude, which deals with emotions on expecting the misfortune of others and the possibility of having antisocial characteristics, lead to actual cyberbullying behaviors of adolescents. Also, this study identified that intrapersonal and interpersonal self-awareness are harmful in causing cyberbullying in those with high Schadenfreude. Finally, the implication and the limitation of this study were discussed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.319-320
• /
• 2012

로봇의 동작제어 기술에는 다양한 방법이 있다. 그 중 대부분은 수학적으로 자세를 계산하여 로봇을 제어한다. 본 논문에서는 Kinect를 이용한 휴머노이드의 동작제어 제안한다. Kinect로부터 실시간으로 영상을 입력받아 영상에서 인식된 사람의 각 관절의 좌표값을 추출한다. 추출한 좌표값으로 각 관절의 각도를 계산하고 사람의 행동을 따라하도록 로봇을 제어한다.