• 한국통신학회논문지
• /
• 제28권12C호
• /
• pp.1200-1208
• /
• 2003

비디오 데이터에 존재하는 감정을 처리하는 것은 지능적인 인간과 컴퓨터와의 상호작용을 위해서 매우 중요한 일이다. 이러한 감정을 추출하기 위해서는 비디오로부터 감정에 관련된 특징들을 검출하기 위한 컴퓨팅 모델을 구축하는 것이 바람직하다. 본 논문에서는 비디오 셧에 존재하는 저급 특징들의 확률적인 분포를 이용하여 감정 이벤트 발생에 관련된 통계학적인 모델을 제안한다. 즉, 비디오 셧의 기본적인 특징을 추출하고 그 특징을 통계적으로 모델화 하여 감정을 유발하는 셧을 찾아낸다. 비디오 셧의 특징으로는 칼라, 카메라 모션 및 셧 길이의 변화를 이용한다. 이러한 특징들을 EM(Expectation Maximization) 알고리즘을 이용하여 GMM(Gaussian Mixture Model) 으로 모델링하고, 감정과 시간과의 관계를 MLE(Maximum Likelihood Estimation)를 이용하여 시간에 따른 확률분포 모델로 구성한다. 이런 두 개의 통계적인 모델들을 융합하여 베이시안 분류법을 적용하여 비디오 데이터로부터 감정에 관련된 셧을 찾아낸다.

• 한국실내디자인학회논문집
• /
• 제21권2호
• /
• pp.101-111
• /
• 2012

The purpose of this study is to draw emotional evaluation model related to LED lighting colors and suggest basic informations that enable planned directions of architectural pacade lighting to simulate beforehand in a laboratory. As experimental methods, extracted PAD emotional evaluation model and then directed a experimental model of 10 LED lighting colors, studied and analyzed survey questions. The results are as follows; First, in the case of P(Pleasure-Unpleasure), Red, Yellow, Green, Cyan, Magenta, White and Combination of $G{\leftrightarrow}B$ Colors are satisfying, vibrant and positive distribution chart has shown. Second, in the case of A(Arousal-Unarousal), Red, Yellow, Green, Cyan, Blue, White and Combinations of $R{\leftrightarrow}G$, $G{\leftrightarrow}B$, $R{\leftrightarrow}B$ Colors, it makes a little difference, they have shown useful distribution chart to induce sight in a aroused state. Third, in the case of D(Dominance-Submissiveness), Red, Cyan, Green and Combinations of $G{\leftrightarrow}B$ Colors are free, controlling and extent of effect was excellent. On the contrary, in the case of Yellow and Magenta and Combinations of $R{\leftrightarrow}B$, they are gentle and arouse the protective instinct or feminine distribution chart has shown. Fourth, it showed difference of preference that difference of select ratios of both men and women in Orange, Blue, Greenish-Yellow (preference of man) and Magenta, Combinations of $R{\leftrightarrow}B$ Colors(preference of woman).

• Child Health Nursing Research
• /
• 제24권3호
• /
• pp.287-297
• /
• 2018

Purpose: This study aimed to identify variables influencing the psychosocial adjustment of North Korean adolescent refugees in order to establish a structural equation model and design an intervention strategy to improve psychosocial adjustment. Methods: The subjects included 290 North Korean adolescent refugees aged 16~24 years who were enrolled in alternative schools or regional adaptation centers. They were surveyed using a structured questionnaire. Results: The goodness of fit measures of the model were as follows: $x^2=131.20$ (p<.001), GFI=.93, CFI=.91, TLI=.86, RMSEA=.08, and SRMR=.07. The results estimated from the structural equation model indicated a good fit of data to the hypothesized model, which proposed that stress and emotional intelligence are associated with psychosocial adjustment. The major variables influencing psychosocial adjustment were stress, emotional intelligence, which was a significant direct effect, whereas attitude of parenting showed an indirect effect on psychosocial adjustment through emotional intelligence. These variables account for 50.0% of psychosocial adjustment. Conclusion: It is necessary to develop a program and intervention plan that can enhance emotional intelligence and thereby relieve the stress of North Korean adolescent refugees. The program should also include parenting education so that parents have positive attitude of parenting.

• 한국경영정보학회:학술대회논문집
• /
• 한국경영정보학회 2007년도 추계학술대회
• /
• pp.245-250
• /
• 2007

Prior research on the user experience assumes that when users acquire good experience through the usage of a certain device or system, the user satisfaction increases, and the user satisfaction can forecast the user loyalty effectively. However, theoretical model based on the user satisfaction does not reflect users' emotional or relationship-based experience factors which are fostered through users' long-term interaction with a device or system. Therefore, this research developed the new theoretical model based on the concept of emotional attachment and integrated the model to the existing user satisfaction model to overcome theoretical and practical limitations of the user satisfaction concept. Also, this integrated model was empirically evaluated to check its validity by surveying users of 4 kinds of electronic products.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.226-229
• /
• 2000

A 2D comic model, a comic-style line drawing model having only eyebrows, eyes, nose and mouth, is much easier to generate facial expressions with small number of points than that of 3D model. In this paper we propose a 3D emotional editor using a 2D comic model, where emotional expressions are represented by using action units(AU) of FACS. Experiments show a possibility that the proposed method could be used efficiently for intelligent sign-language communications between avatars of different languages in the Internet cyberspace.

• 한국보육지원학회지
• /
• 제12권3호
• /
• pp.137-157
• /
• 2016

This study examines the effects of teacher's emotional intelligence on teacher-child interaction through the sequential mediation effects of efficacy belief about play and professional recognition. Participants were 268 teachers working at kindergartens in Gyeonggi area. Data were analyzed by descriptive statistic, Pearson's product-moment correlation, and the structural equation model using the SPSS 21.0 and Mplus 6.12 program. The main findings of this study are as follows: First, in regards to the relationship between emotional intelligence and teacher-child interaction, a single mediation effect of efficacy belief about play is significant. But there is no significant mediation effect of the professional recognition. Second, in regards to the pathway from emotional intelligence to teacher-child interaction, the professional recognition precedent mediation model is statistically significant, but efficacy belief about the play precedent mediation model is not significant. Based on the results, a concluding discussion was made regarding methods toward enhancing interaction between teacher and child.

• 품질경영학회지
• /
• 제48권3호
• /
• pp.361-379
• /
• 2020

Purpose: The purpose of this study was to investigate the relationship between employee authenticity and customer loyalty. This study also examined whether rapport positively mediated the above relationship. In addition this study address the moderating role of customer emotional intelligence in the relationship between employee authenticity and rapport. By developing moderated a mediation model, we addressed indirect conditional effect of customer emotional intelligence on the relationship between employee authenticity and customer loyalty via rapport. Methods: The survey data was collected by customers who used various services in Korea. The main hypotheses were tested using a cross-sectional design, with questionnaires administered to 292 customers. Results: The result of empirical analysis has shown that employee authenticity was significantly positively related to customer loyalty. We have also found that rapport positively mediated the relationship between employee authenticity and customer loyalty. While there was a significant moderating effect of customer emotional intelligence on the relationship between employee authenticity and rapport, the moderated mediating role of customer emotional intelligence was found. Conclusion: The results provide useful theoretical and practical implications to the organizations and managers who want to improve customer loyalty. Future research directions with the limitation of the study were discussed.

• 한국안전학회지
• /
• 제31권6호
• /
• pp.113-120
• /
• 2016

People use social media platforms such as Twitter to leave traces of their personal thoughts and opinions. In other words, social media platforms retain the emotions of the people as it is, and accurately understanding the emotions of the people through social media will be used as a significant index for disaster management. In this research, emotion type modeling method and emotional quotient quantification method will be proposed to understand the emotions present in social media platforms. Emotion types are primarily analyzed based on 3 major emotions of affirmation, caution, and observation. Then, in order to understand the public's emotional progress according to the progress of disaster or accident and government response in detail, negative emotions are broken down into anxiety, seriousness, sadness, and complaint to enhance the analysis. Ultimately, positive emotions are further broken down into 3 more emotions, and Russell emotion model was used as a reference to develop a model of 8 primary emotions in order to acquire an overall understanding of the public's emotions. Then, the emotional quotient of each emotion was quantified. Based on the results, overall emotional status of the public is monitored, and in the event of a disaster, the public's emotional fluctuation rate could be quantitatively observed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권6호
• /
• pp.2056-2069
• /
• 2014

In order to implement interactive and personalized Web services properly, it is necessary to understand the tangible and intangible responses of the users and to recognize their emotional states. Recently, some studies have attempted to build emotional state estimation models based on facial expressions. Most of these studies have applied multiple regression analysis (MRA), artificial neural network (ANN), and support vector regression (SVR) as the prediction algorithm, but the prediction accuracies have been relatively low. In order to improve the prediction performance of the emotion prediction model, we propose a novel SVR model that is optimized using a genetic algorithm (GA). Our proposed algorithm-GASVR-is designed to optimize the kernel parameters and the feature subsets of SVRs in order to predict the levels of two aspects-valence and arousal-of the emotions of the users. In order to validate the usefulness of GASVR, we collected a real-world data set of facial responses and emotional states via a survey. We applied GASVR and other algorithms including MRA, ANN, and conventional SVR to the data set. Finally, we found that GASVR outperformed all of the comparative algorithms in the prediction of the valence and arousal levels.

• Tribology and Lubricants
• /
• 제32권6호
• /
• pp.207-211
• /
• 2016

To interpret the perception that originates from tactile sensibility during people touch and recognize the object surfaces, this study focuses on the development of a friction model that can describe the interaction of a stylus pen sliding over the counter surfaces. In addition, the study includes several other experimental factors such as the pressure, temperature, and topology of surface, which can have an effect on the emotional user experience concerning various surfaces; this research aims to suggest a method to quantitatively evaluate the relation between these experimental parameters and emotional user experience. Accordingly, the objective of research comprises the friction characteristic technology for measurement of fine tribological behavior and a standard to quantify the emotional feedback. Existing panels or input devices that provide interaction feedback about user actions simply operate with a single frequency vibration or sound response. On the contrary, this research investigates various interaction characteristics including friction force, frequency, and surface topology synthetically. Using the developed model, which can explain the relation between the friction parameters and emotional user experience, developers can design their product in order to provide the user with expected emotional sensibility. Consequently, it can contribute to reduce the development cost about sensitivity model.