• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1171-1180
• /
• 2019

Emotion is a psycho-physiological process that plays an important role in human interactions. Affective computing is centered on the development of human-aware artificial intelligence that can understand and regulate emotions. This field of study is also critical as mental diseases such as depression, autism, attention deficit hyperactivity disorder, and game addiction are associated with emotion. Despite the efforts in emotions recognition and emotion detection from nonstationary, detecting emotions from abnormal EEG signals requires sophisticated learning algorithms because they require a high level of abstraction. In this paper, we investigated LSTM hyperparameters for an optimal emotion EEG classification. Results of several experiments are hereby presented. From the results, optimal LSTM hyperparameter configuration was achieved.

• Korean Journal of Human Ecology
• /
• v.18 no.1
• /
• pp.29-39
• /
• 2009

The purpose of this study is to investigate children's emotional regulation and social competence in relation with peer friendliness. Specifically, it examined the hypotheses that children's emotion regulation strategies would be different depending on age, gender, and peer friendliness, and that children's emotion regulation strategies would affect their social competences. The subjects were 197 of the second, fourth, and sixth graders in an elementary school located in Gangdong-gu, Seoul. The findings are as follows: first, children's emotion regulation strategies are different according to gender and age. Girls use more 'external response strategy' than boys do. Elder children use more 'internal response strategy' than younger children, and younger children use more 'problem solving strategy' than elder children. Second, children's emotion regulation strategies are different depending on the degree of peer friendliness. Children employ more 'problem solving' and 'internal response' strategies to close friends rather than to just friends. Children used more the strategies as 'request for social support', 'evasion', and 'external response' to just friends rather than to close friends. Finally, children's social competencies are influenced by the strategies of 'problem solving' and 'evasion'.

• Korean Journal of Human Ecology
• /
• v.17 no.6
• /
• pp.1051-1063
• /
• 2008

This study was to investigate the relationships between stress coping strategies, emotion regulation ability and behavior problems with children from low-income families and middle-income families. Subjects were 171 children from low-income families and 228 children from middle-income families, 4th - 6th grade in elementary school. The major findings are followings: (1) The level of emotion regulation ability in children from low-income families was lower and active stress coping strategies were less than children from middle-income families. In the behavior problem, children from low-income families were higher than children from middle-income families. (2) The stress coping strategies(active/ social support) in children from low-income families were related with internal behavior problem(anxiety /withdrawal). And the emotion regulation ability was related to the children's behavior problem. (3) Regression analysis model showed that emotion-regulation ability was the most influential factor to the children's behavior problem, and children from low-income families with aggressive coping strategy showed hyperactive behavior problem. So, the education/therapy programs for children from low-income families have to be developed and practiced in schools, local children centers and so on.

• Korean Journal of Human Ecology
• /
• v.24 no.6
• /
• pp.783-793
• /
• 2015

The purpose of this study was to investigate the effect of Parenting Attitude, Self-esteem, and Peer Attachment on Emotion Problem. The study is based on data from first wave of 'Korean Child Youth Panel Survey 2010(KCYPS)' and the subjects of this survey were 2,098 1st grade junior middle school students. To measure the variables, this study used such scales as the parenting attitude scale, self-esteem scale, and peer attachment scale and emotional problem scale. The data were analyzed using descriptive statistics, Pearson's correlation and structural equation modeling analysis. Results of structural equation modeling with data indicated that hypothesized structural equation model produced a good fit but, no direct effect between negative parenting attitude and peer attachment. The self-esteem have mediating effect between parenting attitude and peer attachment, emotion problem. The peer attachment have mediating effect between positive parenting attitude and emotion problem but, did not have mediating effect between negative parenting attitude and emotion problem. The implications for counseling and suggestions for future research are discussed.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• Journal of the Korean Home Economics Association
• /
• v.48 no.5
• /
• pp.61-72
• /
• 2010

This study examined the effects of maternal parenting, children's self-esteem and emotion regulation strategy on emotion regulation. Data were collected from 493 5th and 6th graders. The results were as follows: Firstly, maternal authoritarian and permissive parenting directly affected children's maladaptive emotion regulation, while maternal affectionate and permissive parenting directly affected children's adaptive emotion regulation. Secondly, children's selfesteem directly affected both their maladaptive and adaptive emotion regulation, while also acting as a mediator between maternal parenting and children's maladaptive and adaptive emotion regulation. Children's cognitive reappraiser strategy positively affected adaptive emotion regulation, but emotion suppressive strategy negatively affected adaptive emotion regulation. These emotion regulation strategies played a mediating role between maternal parenting or children's self-esteem and adaptive emotion regulation.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.1
• /
• pp.179-186
• /
• 2011

Objective: This study is to review three representative psychological perspectives that explain scientific construct of emotion, that are the discrete emotion model, appraisal model, and dimensional model. Background: To develop emotion sensitive interface is the fusion area of emotion and scientific technology, it is necessary to have a balanced mixture of both the scientific theory of emotion and practical engineering technology. Extensional theories of the emotional structure can provide engineers with relevant knowledge in functional application of the systems. Method: To achieve this purpose, firstly, literature review on the basic emotion model and the circuit model of discrete emotion model as well as representative theories was done. Secondly, review on the classical and modern theories of the appraisal model emphasizing cognitive appraisal in emotion provoking events was conducted. Lastly, a review on dimensional theories describing emotion by dimensions and representative theories was conducted. Results: The paper compared the three models based on the prime points of the each model. In addition, this paper also made a comment on a need for a comprehensive model an alternative to each model, which is componential model by Scherer(2001) describing numerous emotional aspects. Conclusion: However, this review suggests a need for an evolved comprehensive model taking consideration of social context effect and discrete neural circuit while pinpointing the limitation of componential model. Application: Insight obtained by extensive scientific research in human emotion can be valuable in development of emotion sensitive interface and emotion recognition technology.

• Journal of the Ergonomics Society of Korea
• /
• v.15 no.2
• /
• pp.185-192
• /
• 1996

EEG(electroencephalogram) is characterized with auditory emotion in this study. Twenty university students participated in this study. The auditory stimulus was the natural sounds such as creek sound, clash, machining noise, and etc. They can cause the positive and negative emotion. EEG characteristics according to positive and negative auditory stimuli is tried to observe statistic difference. The significant difference is shown depending on the localized area. The auditory paraameters of EEG variation is examined for defining human emotion qualitatively. The results shows that the alpha and the beta at temproal area may be thd determinat of human auditory emotion.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.426-430
• /
• 2000

This study is about the human sensibility measurement method. Researches on human sensibility measurement have been performed in many aspects. However, due to the subtlety and intricacy of human sensibility, it has been difficult to exactly measure human sensibility.At present, Semantic Differential(SD) method is most widely used to quantify human sensibility. In SD method, complicate human sensibility is represented on a scale with equal interval or equal ratio. However, this method has a critical problem in that human sensibility cannot be expressed with equal interval or equal ratio.In order to complement SD method and represent human sensibilities appropriately, we proposed an alternative method using the chroma-scale with saturation that had not equal interval or ratio. In experiment, proposed method shown that subjects understood a new scale easily and they could express their sensibilities on a new scale without any limitation. As a result, the chroma-scale can be used not only for measuring consumer's preference but also for evaluating or selecting sensibility words.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.231-234
• /
• 2011

Audiovisual-based human emotion recognition can be considered a good approach for multimodal humancomputer interaction. However, the optimal multimodal information fusion remains challenges. In order to overcome the limitations and bring robustness to the interface, we propose a framework of automatic human emotion recognition system from speech and face display. In this paper, we develop a new approach for fusing information in model-level based on the relationship between speech and face expression to detect automatic temporal segments and perform multimodal information fusion.