• 한국컴퓨터정보학회논문지
• /
• 제23권8호
• /
• pp.37-43
• /
• 2018

In this paper, we propose a framework that automatically suggests emotion using emotion analysis method based on facial expression change. We use Microsoft's Emotion API to calculate and analyze emotion values in facial expressions to recognize emotions that change over time. In this step, we use standard deviations based on peak analysis to measure and classify emotional changes. The difference between the classified emotion and the normal emotion is calculated, and the difference is used to recognize the emotion abnormality. We match user's emotions to relatively relaxed emotions using histograms and emotional meshes. As a result, we provide relaxed emotions to users through images. The proposed framework helps users to recognize emotional changes easily and to train their emotions through emotional relaxation.

• 한국실내디자인학회논문집
• /
• 제18권5호
• /
• pp.31-39
• /
• 2009

Today, 'Emotion' has come to stay as a powerful culture code. Though there has been not a few research results based on the recognition of the importance of emotion, the concept of 'Emotion' still differs according not only to researchers but also to the fields. There firstly lies the aim of this study to research the moaning and feature of 'Emotion' through John Dewey's Theory of Experience. Secondly, this study tries to categorize the strata of emotion in space, and further tries to present the methodology for the study of emotion shown in the space. Emotion is the impulse corresponding to the root force drawing out indefinite situations into the context of the problem, and is also the force which integrates all the elements in the process of reflective correlation. Emotion can be referred to as the activating and combining force which makes it possible for the separate elements to be related to the whole as one, and as the feature forming the completion of the transaction between organisms and environment.

• 대한산업공학회지
• /
• 제23권3호
• /
• pp.609-619
• /
• 1997

The concept of human emotion is recently demanded to be imbedded in industrial product and environment for enhancing quality of life. Human emotion is attempted to be qualified and quantified by physiological measurements. EEG variation, one of the physiological measurement, is observed to characterize psychological response in this study. This study is to find function and process of brain according to emotion. Twenty university students participated in this study and experienced positive and negative emotion by auditory stimulus. Delta, theta, alpha and beta waves showed characteristic variation in normalized sense according to positive and negative emotion. Local area showing significant difference between positive and negative emotion decreases with stimulus duration. Delta, theta and beta waves increase with negative emotion while alpha wave does with positive emotion.

• Journal of Computing Science and Engineering
• /
• 제10권4호
• /
• pp.103-110
• /
• 2016

Emotion recognition is an important component of affective computing, and is significant in the implementation of natural and friendly human-computer interaction. An effective approach to recognizing emotion from text is based on a machine learning technique, which deals with emotion recognition as a classification problem. However, in emotion recognition, the texts involved are usually very short, leaving a very large, sparse feature space, which decreases the performance of emotion classification. This paper proposes to resolve the problem of feature sparseness, and largely improve the emotion recognition performance from short texts by doing the following: representing short texts with word cluster features, offering a novel word clustering algorithm, and using a new feature weighting scheme. Emotion classification experiments were performed with different features and weighting schemes on a publicly available dataset. The experimental results suggest that the word cluster features and the proposed weighting scheme can partly resolve problems with feature sparseness and emotion recognition performance.

• 통합자연과학논문집
• /
• 제13권3호
• /
• pp.97-104
• /
• 2020

This study suggests the emotion space modeling and emotion inference methods suitable for personalized services based on psychological and emotional models. For personalized emotion space modeling taking into account the subjective disposition based on the empirical assessment of the personal emotions felt by the personalization process of emotion space was used as a decision support tool, the Analytic Hierarchy Process. This confirmed that the special learning to perform personalized emotion space modeling without considering the subjective tendencies. In particular to check the possible reasoning based on fuzzy emotion space modeling and sensitivity for the quantification and vague human emotion to it based on the inherent human sensitivity.

• 아동학회지
• /
• 제21권4호
• /
• pp.21-34
• /
• 2000

This investigation of developmental trends in children's emotional intelligence used the Emotional Intelligence Rating Scale for Preschool Children(Kim, 1998) to study 973 children. Significant age differences were found in 5 factors: 'utilization of emotion', 'regulation of emotion', 'handling of relationship between child and teacher' and 'handling of relationship with peers'. Children's emotional intelligence scores increased with age in 3 factors: 'utilization of emotion', 'empathy', and 'regulation of emotion'. Sex differences were found in 5 factors: 'utilization of emotion', 'empathy', 'appraisal and expression of self emotion', 'regulation of emotion', and 'handling of relationship between child and teacher'. In all factors, the scores of girls were higher than those the scores of boys.

• 반도체디스플레이기술학회지
• /
• 제12권3호
• /
• pp.53-57
• /
• 2013

Human emotions are expressed in various ways. It can be expressed through language, facial expression and gestures. In particular, the facial expression contains many information about human emotion. These vague human emotion appear not in single emotion, but in combination of various emotion. This paper proposes a emotional expression algorithm using Active Appearance Model(AAM) and Fuzz k- Nearest Neighbor which give facial expression in similar with vague human emotion. Applying Mahalanobis distance on the center class, determine inclusion level between center class and each class. Also following inclusion level, appear intensity of emotion. Our emotion recognition system can recognize a complex emotion using Fuzzy k-NN classifier.

• 한국의류학회지
• /
• 제23권2호
• /
• pp.314-325
• /
• 1999

The purposes of this study were to classify the types of consumers' emotion experienced in-store by shopping motivation and to examined the effects of store environmental factors on emotion and on shopping behavior. The questionnaires were administered to 330 women shopped in department store. Data from 299 women were analyzed by using frequency t-test and regression analysis by SPSS for windows PC program The results of this study were as follows : 1. The consumers' emotion experienced in -store were composed of five factors. But it could be divided by positive negative factors. 2. There was not significant difference in positive emotion between he Product Pu-rchasing Motive Group and the Window Shopping Motive Group. But there was significant difference n negative emotion between two groups. 3. It was found that the effect of environmental factors of apparel store on emotion was significant in both groups. Especially salespeoples' pressure significantly influenced negative emotion in both groups. 4. The emotion experienced in -store significantly influenced clothing shopping behavior.

• 한국의류학회지
• /
• 제31권9_10
• /
• pp.1373-1383
• /
• 2007

The purpose of this study is to find out the dimensions of kidult fashion emotion and identify the influence of socio-psychological characteristics(nostalgic orientation, change inclination, and self-esteem) on kidult fashion emotion. 'Kidult', composite of kid and adult is indicating a group of people who feel nostalgic for and feel attachment to the products that they have been used in their childhood. A questionnaire was prepared in the survey and a total of 474 women in their twenties and thirties who had purchased the kidult fashion products were selected. The research findings are as follows: 1. Kidult fashion emotion can be classified as 5 factors: pursuits of fashion emotion, seeking girlish image emotion, preference for character emotion, seeking fun emotion, and past oriented emotion. 2. Socio-psychological variable that affected kidult fashion emotion is turned out change inclination. 3. The higher the seeking girlish image and pursuit of fashion emotion tendencies, the more they purchase the kidult fashion products. Based on these results, kidult fashion emotions are not the attachment to the past but positive expression of self and individuality.

• 지역사회간호학회지
• /
• 제30권4호
• /
• pp.571-580
• /
• 2019

Purpose: The purpose of this study is to examine the mediating effects of emotional venting via instant messaging (IM) and positive emotion in the relationship between negative emotion and depression. Methods: Online survey was conducted in Korea between 2 April and 7 April 2019. To obtain samples with representativeness, data were gathered by the professional research firm. A total of 250 Koreans were participated in this study. The collected data were analyzed using descriptive statistics, Pearson's correlation coefficients, and SPSS PROCESS macro to test the mediating effects. Results: This study analyzed the direct/indirect effects of negative emotion on emotional venting via IM, in the relationship between positive emotion and depression. Negative emotion had indirect effects on depression through emotional venting via IM and positive emotion. Both emotional venting via IM and positive emotion had dual mediating effects in the influence of negative emotion on depression. Conclusion: These results suggest that it is important to manage negative emotion to prevent depression. Also, this study confirmed that emotional venting via IM is a powerful factor influencing emotional recovery.