• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.159-166
• /
• 2009

So far, many researches have been done to retrieve music information using static classification descriptors such as genre and mood. Since static classification descriptors are based on diverse content-based musical features, they are effective in retrieving similar music in terms of such features. However, human emotion or mood transition triggered by music enables more effective and sophisticated query in music retrieval. So far, few works have been done to evaluate the effect of human mood transition by music. Using formal representation of such mood transitions, we can provide personalized service more effectively in the new applications such as music recommendation. In this paper, we first propose our Emotion State Transition Model (ESTM) for describing human mood transition by music and then describe a music classification and recommendation scheme based on the ESTM. In the experiment, diverse content-based features were extracted from music clips, dimensionally reduced by NMF (Non-negative Matrix Factorization, and classified by SVM (Support Vector Machine). In the performance analysis, we achieved average accuracy 67.54% and maximum accuracy 87.78%.

• Journal of the Korean Society of School Health
• /
• v.29 no.2
• /
• pp.90-97
• /
• 2016

Purpose: The purpose of this study was to investigate the relationship between sleep timing and depressive mood in Korean adolescents. Methods: The study analyzed the data from the 2007~2015 Korea Youth Risk Behavior Web-based Survey. A total of 541,693 students in grades 7~12 were included in the final analysis. Multivariable logistic regression was used to examine their sleep timing and depressive mood, adjusted for sex, grade, region, socioeconomic status, academic performance, alcohol, smoking and physical activity. Sleep duration and sleep quality were also included in our model to identify whether or not the effect of sleep timing on depression is mediated by sleep duration or sleep quality. Results: The prevalence of depressive mood was 32.7% and the mean sleep timing was 12:13 AM. After adjustment for eligible covariates, the association between sleep timing and depressive mood showed a J-shaped curve. Adolescents who slept at 8 pm~10 pm were 39% more likely to be depressive (OR = 1.39, 95% CI 1.30~1.40) and at 3 am~ 4 am were 67% more likely to be depressive (OR=1.67, 95% CI 1.64~1.70) than adolescents who slept at 11 pm~12 am. These associations persisted after being adjusted for sleep duration and sleep quality. Conclusion: Sleep timing was related to depression in adolescents, independent of sleep duration and sleep quality. It appears that there is a certain sleep timing beneficial to mental health of adolescents.

• Korean Journal of Adult Nursing
• /
• v.26 no.6
• /
• pp.693-702
• /
• 2014

Purpose: The purpose of this study was to examine the relationships between treatment belief, personal control, depressive mood, and health-related quality of life in patients with hemodialysis based on self-regulation theory. Methods: Data were collected from 220 patients at 27 local hemodialysis clinics in Seoul during 2013 and 2014. The Revised Illness Perception Questionnaire, the Hospital Anxiety and Depression Scale, and Medical Outcomes Study Short Form-12 were used to measure outcome variables. Data were analyzed using descriptive statistics, t-tests, ANOVA, Pearson correlation, and multiple regression using the 'enter' method. Results: Treatment belief and personal control scored 3.58 and 3.54 out of 5 points respectively, on average. Treatment belief and personal control of kidney disease were negatively correlated with depressive mood and positively correlated with health-related quality of life. According to the regression analysis, treatment belief, monthly income, and personal control were discovered to account for 21.8% of the variance in depressive mood, where as depressive mood, monthly income, treatment belief, and age were found out to account for 40.6% of the variance in health-related quality of life. Conclusion: Our study demonstrated significant positive relationships between treatment belief and illness outcome in hemodialysis patients. Interventions aimed to provide the necessary information and trust to maximize the effectiveness of treatment need be developed to improve patients outcomes.

• Journal of the Korea Convergence Society
• /
• v.11 no.2
• /
• pp.375-384
• /
• 2020

The purpose of this study was to assess the relationship between drinking patterns and depressive mood, and to understand the factors associated with depressive mood among problem drinkers. Data of 19,878 adults over 19 years of age and older from the third Korea National Health and Nutrition Examination Survey were evaluated by multivariate logistic regression analysis. The risk of depressive mood was greater with higher level of problem drinking in both genders. For male problem drinkers, the factors associated with depressive mood include older age, lower education level, unemployment, high perceived stress, bad subjective health status, and non-married status. For female, higher risk was found in groups with the age of 40-49, lower education level, unemployment, high perceived stress, and bad subjective health status. By early screening of the identified risk factors, progression to mental health problem can be avoided. For preventative measures, differential approach depending on gender is suggested.

• Biomolecules & Therapeutics
• /
• v.21 no.6
• /
• pp.476-480
• /
• 2013

Obesity is one of the most serious health problems in developed countries. It negatively affects diverse aspects of human wellbeing. Of these, a relationship between obesity and depression is widely recognized but biomarkers for assessment of obesity-associated mood changes in animal obesity models are rarely known. Here we explored the link between obesity and the plasma levels of monoamine neurotransmitters involved in mood control using a sensitive UPLC/MSMS technique in high fat diet (HFD)-induced obesity model in male C57BL/6 mice to explore the potential utility of plasma tests for obesity-associated mood change. HFD (60% of total calories, 8 weeks) induced significantly higher weight gains in body (+37.8%) and fat tissue (+306%) in male C57BL/6 mice. Bioanalysis of serotonin, dopamine and norepinephrine in plasma at 8 weeks of HFD revealed that serotonin decreased significantly in the obese mice when compared to normal diet-fed mice ($2.7{\pm}0.6$ vs $4.3{\pm}2.0ng/ml$, N=8). Notably, a negative correlation was found between the levels of serotonin and body weight gains. Furthermore, principal component analysis (PCA) with the individual levels of neurotransmitters revealed that plasma levels of dopamine and serotonin could apparently differentiate the obese mice from lean ones. Our study demonstrated that blood plasma levels of neurotransmitters can be employed to evaluate the mood changes associated with obesity and more importantly, provided an important clue for understanding of the relationship between obesity and mood disorders.

• Women's Health Nursing
• /
• v.27 no.3
• /
• pp.196-208
• /
• 2021

Purpose: This study aimed to test the efficacy of a nurse-led postpartum self-care (NLPPSC) intervention at reducing postpartum fatigue (PPF) and depressive mood and promoting maternal functioning among first-time mothers in Bangladesh. Methods: A non-synchronized quasi-experimental design was used. First-time mothers were recruited during postpartum and assigned to the experimental or control group (34 each). The experimental group received the NLPPSC in the hospital, a 1-day intervention that focused on increasing self-efficacy. The control group received usual care. Data on PPF, depressive mood, maternal functioning, self-care behaviors, postpartum self-efficacy, and self-care knowledge were collected at postpartum 2 weeks (attrition 23.5%) and 6 weeks (attrition 16.1%). Data were analyzed using descriptive statistics, bivariate statistics, and linear mixed model analysis. Results: One-third (33.3%) of new mothers experienced depressive mood (Edinburgh Postnatal Depression Scale scores of ≥13 points). The NLPPSC intervention was statistically significant in decreasing PPF (β=-6.17, SE=1.81, t=-3.39, p<.01) and increased maternal functioning at postpartum 6 weeks in the experimental group (β=13.72, t=3.73, p<.01) compared to the control. Knowledge was also statistically significant for increased maternal functioning over time (β=.37, SE=.18, t=2.03, p<.05). However, there were no statistically significant differences in depressive mood over time. Conclusion: The NLPPSC intervention was feasible and effective in improving fatigue and maternal functioning in Bangladeshi mothers by postpartum 6 weeks and thus supports implementing the NLPPSC intervention for new mothers after childbirth.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.13 no.1
• /
• pp.153-162
• /
• 2002

Summary：This study was designed to examine the effect of mother's depressive mood and parenting related attitude on parenting behavior, focusing on the cases having an ADHD child. Method：A total of 82 parents, 31 parents having children with ADHD and 51 normal, were involved in this study. The children of ADHD and normal group were 6-11 years old. ADHD group were diagnosed as attention-deficit hyperactivity disorder by psychiatric doctor and psychological evaluations using DSMIV criteria and the normal group were excluded by using Diagnostic Rating Scale-Parent, Teacher Form. The mothers of both group completed a series of questionnaire about mother's depressive mood and parenting-related attitude. To investigate the relationships between each variables, Student's t-test, correlation, stepwise regression, and hierarchical regression analysis were performed. Result：In correlation analysis, Mothers with an ADHD child were likely to report more coercive parenting behavior, more negative parenting-related attitudes, and depressive mood than normal group. In regression analysis, mother's parenting stress, dysfunctional thoughts, parenting competence, and depressive mood predicted coercive parenting behavior significantly, total explaining 50% of its variance, and especially depressive mood explained 29% of their coercive parenting behavior. These Results indicated that mother's depressive mood accounted for a substantial portion of coercive parenting behavior. Conclusion：These findings suggested that it is significantly important to reduce Mother's depressive mood through dealing with parenting sense of competence and dysfunctional thoughts, so, both parent education program and cognitive-behavioral therapeutic approach are needed to change parent's coercive parenting behavior. Finally, limitation of the present study and suggestions were discussed for further studies.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.53-64
• /
• 2013

Folksonomies have potential problems caused by synonyms, tagging level, neologisms and so forth when retrieving music by tags. These problems can be tackled by introducing the mood intensity (Arousal and Valence value) of music as its internal tag. That is, if moods of music pieces and their mood tags are all represented internally by numeric values, A (Arousal) value and V (Valence) value, and they are retrieved by these values, then music pieces having similar mood with the mood tag of a query can be retrieved based on the similarity of their AV values though their tags are not exactly matched with the query. As a prerequisite study, in this paper, we propose the mapping table defining the relation between AV values and folksonomy tags. For analysis of the association between AV values and tags, ANOVA tests are performed on the test data collected from the well known music retrieval site last.fm. The results show that the P values for A values and V values are 0.0, which means the null hypotheses could be rejected and the alternative hypotheses could be adopted. Consequently, it is verified that the distribution of AV values depends on folksonomy tags.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.363-372
• /
• 2013

When retrieving music with folksonomy tags, internal use of numeric tags (AV tags: tags consisting of Arousal and Valence values ) instead of word tags can partially solve the problem posed by synonyms. However, the two predecessor tasks should be done correctly; the first task is to map word tags to their numeric tags; the second is to get numeric tags of the music pieces to be retrieved. The first task is verified through our prior study and thus, in this paper, its significance is seen for the second task. To this end, we propose the music mapping table defining the relation between AV values and music and ANOVA tests are performed for analysis. The result shows that the arousal values and valence values of music have different distributions for 12 mood tags with or without synonymy and that their type I error values are P<0.001. Consequently, it is checked that the distribution of AV values is different according to music mood.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• 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.