• 가정과삶의질연구
• /
• 제27권1호
• /
• pp.221-234
• /
• 2009

This study focused on the relationship between ego- resilience and stress coping styles of male and female adolescents. The study also tried to identify differences in stress coping styles based on sexual differences and the level of ego- resilience in adolescents. Ego-resilience showed a positive correlation to problem-focused and social support seeking coping styles and a negative correlation to emotion-focused coping style for both male and female adolescents. Canonical Correlation analysis revealed that self-confidence among four sub-domains of ego-resilience made the most outstanding contributions in predicting stress coping styles of female adolescents. The self-confident female adolescents tended to use the problem-focused coping style. For male adolescents, the optimistic attitude among four sub-domains of ego-resilience was the most significant factor in predicting emotion-focused coping style. Female adolescents tended to use more varied coping strategies than male adolescents in stressful situations. The group of adolescents who had a higher level of ego-resilience reported more problem-focused and social support- seeking coping styles in stressful situations. Conversely the group of adolescents with lower level of ego-resilience tended to use emotion-focused coping strategy. The results of this study have important implications for theory, research, and practice. Development of ego-resilience in adolescents based on sexual differences was an important task for their effective coping strategies.

• 대한가정학회지
• /
• 제49권3호
• /
• pp.11-21
• /
• 2011

The purposes of this study were to explore the gender differences in children's behavior problems, emotional regulation and social support, and to investigate differences between boys and girls in the interrelationships between these kinds of variables. The participants were 189 children in 4 to 6 grades and their teachers from one elementary school in Seoul. The data were analyzed using descriptive statistics, t-test, Pearson's correlation, and multiple regression. The results were as follows: (1) There were statistically significant gender differences in the children's behavior problems, emotional regulation and social support. (2) Children's negative emotion explained boys and girls acting out problems and learning problems. Children's positive emotion regulation explained boys' and girls' shy-anxious and learning problems. Boys, who perceived less support from parents, displayed more acting out behavior, boys who perceived less supports from friends showed more shy-anxious behavior, and boys who perceived less supports from teachers exhibited more learning problems.

• 한국콘텐츠학회논문지
• /
• 제17권5호
• /
• pp.45-55
• /
• 2017

본 연구의 목적은 시설에 거주하는 치매노인의 활동 참여, 정서, 문제행동을 파악하는 것이다. 본 연구는 관찰조사연구이며, 치매노인 81명을 대상으로 활동참여 여부와 정서, 문제행동을 각 대상자 당 20분 간격으로 1일 12회 4시간 관찰 측정하여 총 7일간 6,804회 자료를 분석하였다. 연구 결과 대상자들의 인지기능은 중증이 90.1%이었다. 정서는 7점 만점 중 4.0점이었다. 활동 참여는 주로 앉아있거나 누워있는 등의 목적 없는 활동을 대부분 하고 있었으며, 사회적 활동을 할 때 대상자의 정서는 가장 긍정적으로 나타났다. 문제행동은 반복적인 행동과 소음발생 행동의 빈도가 가장 높았고, 시간대별 문제행동 유형의 발생빈도는 다소 달랐다. 대상자의 인지기능과 정서, 문제행동의 상관관계는 유의하였다. 따라서 시설 거주 치매노인의 활동참여를 높이고, 긍정적인 정서를 보이는 활동에 참여할 수 있도록 유도하고, 시간대별로 가장 두드러지게 나타나는 문제행동을 낮추기 위한 효과적인 방법이 모색되어야 한다.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.146-154
• /
• 2020

Negative emotion causes stress and lack of attention concentration. The classification of negative emotion is important to recognize risk factors. To classify emotion status, various methods such as questionnaires and interview are used and it could be changed by personal thinking. To solve the problem, we acquire multi modal bio-signals such as electrocardiogram (ECG), skin temperature (ST), galvanic skin response (GSR) and extract features. The neural network (NN), the deep neural network (DNN), and the deep belief network (DBN) is designed using the multi modal bio-signals to analyze emotion status. As a result, the DBN based on features extracted from ECG, ST and GSR shows the highest accuracy (93.8%). It is 5.7% higher than compared to the NN and 1.4% higher than compared to the DNN. It shows 12.2% higher accuracy than using only single bio-signal (GSR). The multi modal bio-signal acquisition and the deep learning classifier play an important role to classify emotion.

• 재활간호학회지
• /
• 제6권1호
• /
• pp.26-39
• /
• 2003

The elderly can experience a lot of stressful events and the stress acts as a various fluent that affects a well-being level, the self-contentment of lives, and the achievements by themselves. Also, the elderly are different from the young in many unexpressed stress and have diverse copings for perceived stress. Moreover, they mainly seem to use a problem-focused coping and an emotion-focused coping. To use whatever copings is to improve the quality of life in the old period and very important fact to achieve their ends. The purpose of this study was to investigate the relationship between Perceived Stress and the Ways of Coping in the Elderly and to gain the baseline data for development of nursing intervention program for improve to the quality of life in the elderly. The design of this study was a correlational study. The subjects of this study consisted of 230 of the elderly living in Pusan. The data was collected from 1st July. to 1st September, 2002. The instruments used for this study were 'Perceived Stress Scale(20items, 5point. scale)' developed by Kang In(1990) and translated by Lee young-ja(1999), and its reliability is Cronbach's ${\alpha}=.89$. 'Coping Scale(30items, 4point. scale, 14 items about a problem-focused coping, 16 items about an emotion-focused coping, 4 points scale) developed by Lazarus & Folkman(1984) and translated by Yang Young-hee(1998). The reliability of this study is Cronbach's ${\alpha}=.90$. The data was analyzed by the SPSS WIN 10.0 program using frequency, percentage, mean, standard deviation, t-test, ANOVA & Scheffe test and Pearson's correlation coefficient. The results of this study were as follows; 1. The mean score of perceived stress was $31.75{\pm}10.23$(Min 20, Max 100), which the item mean score was $1.59{\pm}.51$(Min 1, Max 5). 2. The number of subjects in a problem-focused coping was 72(31.3%), the number of subjects in an emotion-focused coping was 158(68.7%) 3. There were statistically significant positive correlation between perceived stress and problem-focused coping method and the more emotion-focoused coping method.(r=.180, r= .209, P< .05). It means the more stress, the more problem-focused coping method and the more emotion-focused coping method. 4. There was significant difference the score of perceived stress according to sex (F=-5.057, P=.000)marital status, (F=-2.909, P=.004), economic level, (F=10.243, P=.000), paticipated meeting, (F=9.346, P=.000), perceived health status(F=5.117, P=.007). 5. There was significant difference the score of problem-focused coping method according to age(F=14.200, P=.000), marital status (F=2.432, P=.0160), economic level (F=14.410, P=.000), monthly income, (F=8.300. P=.000), income resource (F=10.235, P=.000), educational level (F=15.222, P=.000), occupation (F=1.544, P=.041), paticipated meeting (F=4.936, P=.008), perceived health status(F=5.655, P=.004). And there was significant difference the score of emotion-focused coping method according to monthly income(F=4.781, P=.009), income resource(F=2.930, P=.035), educational level(F=6.101, P=.003), religionF=2.698, P=.032), paticipated meetings(F=7.285, P=.001). As a result of the study, the elderly had a bit less stress and the two-thirds of the elderly used the emotion-focused coping. Thus, the more perceived stress, the more problem-focused coping method and the more emotion-focused coping method. Accordingly, to improve the quality of life of the elderly, there needs and applies a nursing intervention program that relieves the stress and use effective coping method.

• 로봇학회논문지
• /
• 제8권4호
• /
• pp.266-272
• /
• 2013

Facial feature extraction and tracking are essential steps in human-robot-interaction (HRI) field such as face recognition, gaze estimation, and emotion recognition. Active shape model (ASM) is one of the successful generative models that extract the facial features. However, applying only ASM is not adequate for modeling a face in actual applications, because positions of facial features are unstably extracted due to limitation of the number of iterations in the ASM fitting algorithm. The unaccurate positions of facial features decrease the performance of the emotion recognition. In this paper, we propose real-time facial feature extraction and tracking framework using ASM and LK optical flow for emotion recognition. LK optical flow is desirable to estimate time-varying geometric parameters in sequential face images. In addition, we introduce a straightforward method to avoid tracking failure caused by partial occlusions that can be a serious problem for tracking based algorithm. Emotion recognition experiments with k-NN and SVM classifier shows over 95% classification accuracy for three emotions: "joy", "anger", and "disgust".

• 한국음향학회지
• /
• 제38권5호
• /
• pp.614-620
• /
• 2019

본 논문은 전역 스타일 토큰(Global Style Token, GST)을 사용하는 종단 간(end-to-end) 감정 음성 합성 시스템의 성능을 높이기 위해 각 감정의 스타일 벡터를 효과적으로 결정하는 방법을 제안한다. 기존 방법은 각 감정을 표현하기 위해 한 개의 대푯값만을 사용하므로 감정 표현의 풍부함 측면에서 크게 제한된다. 이를 해결하기 위해 본 논문에서는 k-평균 알고리즘을 사용하여 다수의 대표 스타일을 추출하는 방법을 제안한다. 청취 평가를 통해 제안 방법을 이용해 추출한 각 감정의 대표 스타일이 기존 방법에 비해 감정 표현 정도가 뛰어나며, 감정 간의 차이를 명확히 구별할 수 있음을 보였다.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• 대한가정학회지
• /
• 제50권1호
• /
• pp.103-119
• /
• 2012

The purpose of this study was to explore the mediating effects of preschooler's effortful control on the relationship between maternal emotional availability and preschooler's social skills and problem behaviors. One hundred-thirty six 5-year-old preschoolers and their mothers participated in this study. Instruments for this study were the Emotional Availability Scale for maternal emotional availability, the Delay task, and the Child Behavior Questionnaire for preschooler's effortful control, and the Social Skill Rating Scale, K-CBCL 1.5-5 and K-TRF for preschooler's social skills and problem behaviors. The resulting data were analyzed using descriptive statistics, partial correlation, and structural equation modeling analysis. As predicted, the preschooler's effortful control mediated the effects of maternal emotional availability on preschooler's social skills and problem behaviors. In conclusion, the preschooler's effortful control mediates the effects of emotion related socialization behavior on the preschooler's socio-emotional adjustment.

• 감성과학
• /
• 제15권1호
• /
• pp.97-104
• /
• 2012

최근에 사용자에 의한 대량의 텍스트 데이터가 발생하면서 사용자의 정보, 의견 등을 분석하는 오피니언 마이닝이 중요하게 부각되고 있다. 오피니언 마이닝 중 특히 정서 분석은 제품, 사회적 이슈, 정치인에 대한 호감 등에 대한 개인적 의견이나 정서를 분석하여 긍정, 부정이나 행복, 슬픔 등의 정서를 분석하는 연구 분야이다. 정서 분석을 위해서 정서 차원 이론의 정서가와 각성 차원의 2차원 공간을 사용하고, 이 공간에서 정서가 분포하는 영역을 설정하여 매핑하는 방법을 사용한다. 그러나 기존에는 정서의 분포 영역을 임의로 설정하는 문제가 있었다. 본 논문에서는 이 문제를 해결하기 위해, 한국어 정서 단어 목록을 사용해 사용자 설문을 실시하여 2차원 상에 12개 정서의 분포를 구성하였다. 또한 2차원 상의 특정 정서 상태가 여러 개의 정서에 중첩되는 경우, 정서에 소속될 확률을 사용한 룰렛휠 방법을 사용하여 하나의 정서를 선택하는 방법을 제안하였다. 제안한 방법을 사용하여 텍스트에서 정서 단어를 추출하여 텍스트를 정서로 분류할 수 있다.