• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1391-1392
• /
• 2015

최근 컴퓨터 기술이 발전하고, 컴퓨터의 형태가 다양해지면서 여러 wearable device들이 생겨났다. 이에 따라 휴먼 인터페이스 기술에서 사람의 감정정보가 중요해졌고, 감정인식에 대한 연구들이 많이 진행 되어 왔다. 본 논문에서는 감정분석에 적합한 특징벡터를 제시하고자 한다. 이를 위해 사람의 감정을 보통, 기쁨, 슬픔, 화남 4가지로 분류하고 방송매체를 통하여 잡음 없이 녹음하였다. 특징벡터는 MFCC, LPC, LPCC 3가지를 추출하였고 Bhattacharyya거리 측정을 통하여 분리도를 비교하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.115-118
• /
• 2008

본 논문에서는 음성으로부터 감정을 인식하고 감성적인 운율로 음성 출력을 산출해 내는 시스템을 제안 한다. 음성적인 운율로부터 감정을 인식하기 위해서 퍼지룰(rule)을 이용한다. 본 논문에서 감정 인식 시스템은 음성 샘플들로 학습 데이터를 구축하고 이를 기반으로 하여 추출된 20개의 특징 집합으로부터 가장 중요한 특징들을 자동적으로 선택한다. 화남, 놀람, 행복, 슬픔, 보통의 5가지 감정 상태를 구분하기 위하여 접근법에 기반한 퍼지를 이용하였다.

• Korean Journal of Child Studies
• /
• v.9 no.2
• /
• pp.95-117
• /
• 1988

The present research was designed to study the effect of gender differences and focus of attention (on sadness and on joy) in altruistic behavior. The subjects were 74 boys and 76 girls from a junior high school in Seoul. Emotion arousing and focus of attention identifying methods were used. Statistical analyses were with two-way ANOVA and $Scheff\acute{e}$ test. There were significant differences in altruisic behavior between the sadness self-oriented group and the sadness other-oriented group. The results were explained in terms of the accessibility of cognitive contents.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2001.08a
• /
• pp.29-34
• /
• 2001

영상자료 및 소리자료의 색인과 검색을 위해서는 감정동사 및 감정형용사 등의 감정 어휘를 필요로 한다. 그러나 감정어휘는 그 뉘앙스가 미묘하여 분명한 분류체계가 없이는 체계적인 정리가 불가능하다. 이에 따라 본 연구에서는 국어학과 분류사전의 분류체계를 고찰하고 새로운 감정어휘의 분류방안을 연구하였으며, 감정에 따른 기쁨, 슬픔, 놀람, 공포, 혐오, 분노의 6가지 기본유형을 제시하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.817-819
• /
• 2004

본 논문에서는 사람의 얼굴표정을 구분하기 위해서 무표정 영상으로부터 18개의 특징점을 찾고, 그 특징점 간의 거리를 템플릿으로 이용하는 방법을 연구하였다. 얼굴표정인식을 위해 정의된 기본 템플릿과 입력 표정 영상에서의 특징정 간의 상대적인 거리의 차이와 특징점의 좌표변위 차이를 이용하여 표정을 구분하도록 하였다. 각 테스트 표정영상의 특징점은 주요 얼굴요소로부터 아이겐포인트(eigen-point)를 자동으로 추출하였다. 표정 인식은 신경망 학습을 통해서 기쁨, 경멸, 놀람, 공포 슬픔 등 5가지로 나누어 실험하였고, 신경망의 인식 결과와 사람의 인식 결과를 통해서 비교한 결과, 72%의 인식성능을 보여주었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.603-610
• /
• 2020

This study examined the mental health-related factors of Korean adolescents, especially focusing on the influence of internet use. This study analyzed the raw data from the 14th Korea Youth Risk Behavior Survey, 2018. The study population was 60,040, with 50.7% male students and 49.3% female students, and 49.7% high school students and 50.3% middle school students. The dependent variables were stress, sadness and despair, suicidal ideation, suicidal plan, and suicidal attempt. The independent variables were gender and age, health behaviors, and time using the internet. Logistic regression analysis was applied to derive the related factors. For all dependent variables, the main contributing variables were gender, grade, economic status, and academic performance. The mental health of adolescents was related to various factors. In particular, the time using the internet was linearly related to the degree of stress, and a higher student group of time using the internet had a more significant effect on sadness, despair, suicidal thoughts, and suicidal plans. In conclusion, the time using the internet has harmful effects on the mental health of Korean adolescents.

• Journal of Korean Academy of Nursing
• /
• v.30 no.6
• /
• pp.1569-1579
• /
• 2000

The purpose of this study was to identify the level of grief experience, family hardiness and family resource for management after bereavement of a family member. The subjects of this study were 100 family members who had lost a family member from cancer within the past two years. The data was analyzed using the SPSS program for descriptive statistics, t-test, ANOVA, Duncan test, and Pearson correlation. The results were as follows. 1. The mean score for the level of grief was 2.84 $\pm$ 0.66. The mean score for the a family hardiness was 3.08 $\pm$ 0.39. The mean score for the level of family resource management was 2.70 $\pm$ 0.35. 2. The level of grief experience differed respondent's age was F=2.95, p=.02, and type of bereavement was t=2.01, p=.04. 3. The level of family hardiness was not significantly different according to respondent's and familial characteristics. 4. The level of family resource management differed according to monthly income of the family (F=3.98, p=.01). 5. There were negative correlations between grief experience and family hardiness (r= -.551, p<.001), grief experience and family resource for management (r=-.351, p<.001). Family hardiness was positively related with family resource for management (r=.709, p<.001). In conclusion, family hardiness and family resource management were identified as important variables that contributed to reduce the grief experience. Therefore, it is important to develop nursing intervention that enhances family hardiness and family resource for management for bereaved family.

• Journal of Korean Academy of Nursing
• /
• v.48 no.1
• /
• pp.59-69
• /
• 2018

Purpose: The purpose of this study was to investigate variables and construct paths that affect complicated grief. Methods: Participants in this cross-sectional, descriptive study were 164 bereaved spouses of cancer patients at least 12 months before the death. Data were collected from October 2016 to February 2017 using self-report structured questionnaires and were analyzed using IBM SPSS 21.0 and AMOS 20.0. Results: The variables affecting complicated grief of bereaved spouses of cancer patients were the quality of end-of-life care (${\gamma}=.15$, p<.001), preparedness for death (${\beta}=-.06$, p=.005), and coping with bereavement (${\beta}=-.24$, p<.001), whereas the quality of death and dying did not show any effects. Preparedness for death had multiple mediating effects in the relationship between the quality of end-of-life care and complicated grief (z=-2.20, p=.028), and in the relationship between the quality of end-of-life care and coping with bereavement (z=2.11, p=.035). Coping with bereavement had a mediating effect on the relationship between preparedness for death and complicated grief (z=-2.39, p=.017). Conclusion: This study revealed that preparedness for death and coping with bereavement play a prominent role in complicated grief. Therefore, it is important to help in preparing for death and enhancing coping with bereavement of spouses providing end-of-life care to cancer patients. In addition, investigating cultural differences in the relationship between the quality of end-of-life care and complicated grief is recommended.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.547-552
• /
• 2008

Human and robot will have closer relation in the future, and we can expect that the interaction between human and robot will be more intense. To take the advantage of people's innate ability of communication, researchers concentrated on the facial expression so far. But for the robot to express emotional intensity, other modalities such as gesture, movement, sound, color are also needed. This paper suggests that the intensity of emotion can be expressed with color and blinking so that it is possible to apply the result to LED. Color and emotion definitely have relation, however, the previous results are difficult to implement due to the lack of quantitative data. In this paper, we determined color and blinking period to express the 6 basic emotions (anger, sadness, disgust, surprise, happiness, fear). It is implemented on avatar and the intensities of emotions are evaluated through survey. We figured out that the color and blinking helped to express the intensity of emotion for sadness, disgust, anger. For fear, happiness, surprise, the color and blinking didn't play an important role; however, we may improve them by adjusting the color or blinking.

• Science of Emotion and Sensibility
• /
• v.12 no.4
• /
• pp.381-392
• /
• 2009

The aim of this study was to develop a research protocol that provides standardized conditioning stimuli in effectively evoking emotion-specific responses in children. The protocol targets five specific emotions(i.e., happiness, sadness, anger, distress, and boredom) by introducing study participants to a combination of music, color, stories, and dolls. This research protocol also includes a self-report emotion assessment scale specially developed for this study to verify the types of emotion induced. Evaluation of the method entailed triangulation of the results from the subjects' self-reported emotional state corresponding to each conditioned stimulus as well as behavioral observations conducted by researchers. Findings suggest that this new protocol effectively evokes five emotions in correspondence to the way it was intended for appropriate emotion induction. Additionally, results showed that female children than male children are more likely to feel boredom; and school-aged children were more likely to react to sadness than pre-school children.