• 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 Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.20-26
• /
• 2008

As they have more and more intelligence robots or computers these days, so the interaction between intelligence robot(computer) - human is getting more and more important also the emotion recognition and expression are indispensable for interaction between intelligence robot(computer) - human. In this paper, firstly we extract emotional features at speech signal and facial image. Secondly we apply both BL(Bayesian Learning) and PCA(Principal Component Analysis), lastly we classify five emotions patterns(normal, happy, anger, surprise and sad) also, we experiment with decision fusion and feature fusion to enhance emotion recognition rate. The decision fusion method experiment on emotion recognition that result values of each recognition system apply Fuzzy membership function and the feature fusion method selects superior features through SFS(Sequential Forward Selection) method and superior features are applied to Neural Networks based on MLP(Multi Layer Perceptron) for classifying five emotions patterns. and recognized result apply to 2D facial shape for express emotion.

• Korean Journal of Childcare and Education
• /
• v.3 no.1
• /
• pp.17-37
• /
• 2007

An abundant emotional experience in childhood can be a basis of success of their life. In this research, I set up a hypothesis as follows to see if a group plastic activities are effective for the improvement of children's emotional intelligence and self-emotion awareness ability, self-emotion management ability, self-motivation ability, other's emotion awareness ability and personal relationship skill ability. The research subjects were 40 children of 5 years old(experimental Group: 20, controlled group: 20) in Y kindergarten located in Ulsan. In pretest, we confirmed homogeneity between experiment and control group using child emotional checklist and then applied small group plastic artistic activities to the experiment group. Data analysis was performed with population, percentage, t-test and Cronbach a. The findings of this study were: First, the group plastic artistic activities was effective for the emotional intelligence of children. Second, the small group plastic activities was effective for the self-emotion awareness, self-emotion control and self motivation ability of children. Third, the small group plastic activities was effective for the awareness ability about other's emotion and personal relationship skill ability. The result of this study implies that the small group plastic artistic activities are effective children's emotion and we need to develop the various activity program and practice for children's emotion development.

• Journal of Gifted/Talented Education
• /
• v.20 no.3
• /
• pp.985-1004
• /
• 2010

The purpose of this study was to examine the gender differences in children's emotional intelligence or their giftedness, and to investigate the relationship between children's emotional intelligence and their giftedness. Subjects were 268 5-year-old kindergarten children who were composed of 131 male children and 137 female children. The collected data were analyzed by using t-test, Pearson's correlation, and multiple regression. The major results of this study were as follows: First, female children showed higher emotional intelligence than male children. Second, there was no signifiant difference between male children and female children in their giftedness. Third, controlling for children's IQ, utilization of emotion, appraisal and expression of self-emotion, and relationship with peers were predictable variables of children's giftedness. Among the subareas of emotional intellignece, utilization of emotion was the most important predictor in explaining children's giftedness. The results showed that there was significant relationship between children's emotional intelligence and their giftedness.

• Journal of Families and Better Life
• /
• v.31 no.3
• /
• pp.49-62
• /
• 2013

The purpose of this study was to investigate the emotional ability between abused children and general children by comparing their emotional intelligence and emotional control. Participants were 17 abused children who had been separated from their abusers and 17 general children, all elementary school students. The answers to the questionnaire items on emotional intelligence and situations of emotional motivation were analyzed by Mann-Whitney U as a study tool. The results of this study were as follows: First, the difference of emotional intelligence between abused children and general children was statistically significant. Abused children received lower scores than general children when it came to their emotional recognition, emotional expression, empathy, and emotional regulation as a subordinate scope of emotional intelligence. Second, the difference of emotional regulation strategy between abused children and general children was statistically significant. Abused children presented negative responses and less frequently used positive strategy, inhibitory avoidance strategy and alternative strategy than general children. Third, the difference of emotional regulation motivation between abused children and general children was statistically significant. Abused children presented less prosocial motivation, motivation of self-preservation and normative motivation than general children.

• The Journal of the Korea Contents Association
• /
• v.15 no.12
• /
• pp.387-406
• /
• 2015

Recently emotional labor is an essential situation for hospital employees in relation to surface and deep acting as the core of emotional labor strategies. This study empirically examines the relation between hospital employees' emotional intelligence and emotional labor strategies in the context of emotional labor. For empirical experiments, we conducted a questionnaire survey targeting hospital employees, and we employed the method of Partial Least Squares (PLS) for data analysis. Major findings are as follows. Hospital employees' emotional intelligence including self emotion appraisal, others' emotion appraisal, regulation of emotion, and use of emotion, have a significantly positive effect on hospital employees' deep acting. And hospital employees' deep acting has a significantly positive effect on hospital employees' organizational attachment, knowledge sharing intentions, and innovative activities.

• Lingua Humanitatis
• /
• v.1 no.1
• /
• pp.13-31
• /
• 2001

This essay seeks new possibilities in experimental thinking and to find ways in which philosophy can aid humanistic imagination. In emphasizing logical precision, philosophy has so far ignored the role of imagination in philosophical logic and limited itself to deductive logic. Despite the obvious fact that no degree of logical precision can fully account for, nor provide complete expression for, the vast range of human thought, other modes of thinking have suffered in the shadow of deductive logic. But these non-deductive models of thinking can in many cases better explain the emotive, aesthetic logic of the humanities. The kinds of models (deductive and non-deductive) in humanistic thinking include dialectic, abductive, analogic, pragmatic, inductive, and deductive logic. Each mode of logical thinking may be assigned a color that represents its emotive characteristics: red for dialectics (opposition): blue for abduction (transcendence); yellow for analogy (flexibility); green for pragmatics (peace); violet/purple for induction (fantasy); and finally orange for deduction (trust). And each mode can also be keyed to major areas in humanistic thought, making up the following connections: dialectic-red-history; abduction-blue-literature; analogy-yellow-philosophy ; pragmatics-green-religion ; induction-violet/purple-arts; and deduction-orange-science. These connections serve to illustrate the interrelationship between emotion and intelligence, leading us toward considerations of emotional intelligence and intelligent emotion. The former is increasingly gaining attention, as the effect of 'mood space' on intelligence is being scrutinized. That the rate of suicide among mathematicians is very high points to the need for careful study of the reverse relationship between emotion and intelligence, intelligent emotion. The need for the latter is all the more pressing, as the emergence of new technology is allowing, even forcing, us more and more to experience the world intellectually (i.e., sans emotive experience) through a new virtual space called cyberspace.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.503-508
• /
• 2023

The purpose of this study was to examine the impact of emotional intelligence and cognitive emotion regulation strategies on career maturity among university students during this period of increasing employment challenges. The study participants consisted of 348 students who attended general education courses at a 4-year N University located in Chungnam. The analysis was conducted using SPSS 26.0, and descriptive statistics, correlation analysis, and regression analysis were applied. The research findings indicated a significant correlation between emotional intelligence and cognitive emotion regulation strategies with career maturity among university students. The results suggested that positive thinking and motivation related to their emotions and feelings could enhance career maturity. Based on these findings, it is expected that various research and programs aiming to enhance career maturity will be promoted in the future. Additionally, the study aspires to serve as foundational data in devising concrete and achievable strategies for career and employment fields.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.359-367
• /
• 2020

This study is a descriptive research to identify the factors affecting the mental health of nursing aides. The subjects were 227 nursing aides working in the metropolitan area of South Korea, and the survey was conducted in October 2019 using the structured questionnaires. The results showed that the factors affecting mental health of nursing aides were emotion stability, emotional intelligence, occupational stress, and subjective perception of physical health, and their explanatory power for mental health was 64.6%. As a result, it is necessary to develop an intervention program to improve emotion stability, emotional intelligence, occupational stress, and subjective perception of physical health in order to improve mental health of nursing aides.

• Science of Emotion and Sensibility
• /
• v.24 no.2
• /
• pp.75-80
• /
• 2021

Do happy applicants achieve more? Although it is well established that happiness predicts desirable work-related outcomes, previous findings were primarily obtained in social settings. In this study, we extended the scope of the "happiness premium" effect to the artificial intelligence (AI) context. Specifically, we examined whether an applicant's happiness signal captured using an AI system effectively predicts his/her objective performance. Data from 3,609 job applicants showed that verbally expressed happiness (frequency of positive words) during an AI interview predicts cognitive task scores, and this tendency was more pronounced among women than men. However, facially expressed happiness (frequency of smiling) recorded using AI could not predict the performance. Thus, when AI is involved in a hiring process, verbal rather than the facial cues of happiness provide a more valid marker for applicants' hiring chances.