• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.139-146
• /
• 2014

This paper proposes an efficient method for automatically distinguishing various facial expressions. To recognize the emotions from facial expressions, the facial images are obtained by digital cameras, and a number of feature points were extracted. The extracted feature points are then transformed to 49-dimensional feature vectors which are robust to scale and translational variations, and the facial emotions are recognized by statistical pattern classifiers such Naive Bayes, MLP (multi-layer perceptron), and SVM (support vector machine). Based on the experimental results with 5-fold cross validation, SVM was the best among the classifiers, whose performance was obtained by 50.8% for 6 emotion classification, and 78.0% for 3 emotions.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1567-1577
• /
• 2020

Urban land cover classification is role in urban planning and management. So, it's important to improve classification accuracy on urban location. In this paper, machine learning model, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are proposed for urban land cover classification based on high resolution satellite imagery (KOMPSAT-3A). Satellite image was trained based on 25 m rectangle grid to create training data, and training models used for classifying test area. During the validation process, we presented confusion matrix for each result with 250 Ground Truth Points (GTP). Of the four SVM kernels and the two activation functions ANN, the SVM Polynomial kernel model had the highest accuracy of 86%. In the process of comparing the SVM and ANN using GTP, the SVM model was more effective than the ANN model for KOMPSAT-3A classification. Among the four classes (building, road, vegetation, and bare-soil), building class showed the lowest classification accuracy due to the shadow caused by the high rise building.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.293-304
• /
• 2022

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALS-SVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

• Korean Journal of Adult Nursing
• /
• v.12 no.2
• /
• pp.184-195
• /
• 2000

It has been believed that cancer is an omnious factor threatening the future and life itself. Patients having the disease experience anxiety, fear, feeling of weakness, depression and feelings of uncertainty and hopelessness. Most cancer patients, however, have expectations of possible recovery and a better future, very different from the patients who feel hopeless. Therefore. hope allows people to respond effectively to the fatal disease they have and prevents them from detoriorating physically and spiritually, positively influencing their survival, response to treatment and sense of security. Studies previously performed showed that hope is positively correlated with social and family supports, self-esteem, spiritual well-being, responsive action, health promotion behavior and quality of life. Thus, the study attempted to provide basic information on nursing cancer patients by investigating their levels of hope and determining predictive factors which influence hope. For the study 200 cancer patients in two university hospitals located in Pusan were sampled as subjects. Data were collected for twenty nine days from Feburary 1, 1999 to March 1. Instrumets for the study included 10 items from the self-esteem scale by Rosenberg (1965), 39 hope measurements by Kim and Lee(1965), 16 of the social support scale by Tae(1986) and 16 of the general characteristics scale, all of which totaled 81 items. The data were analyzed using the SPSS program. General characteristics of the investigated based on numbers and percentage. Hope, self-esteem and social support were analyzed using means, minimum, maximum and standard deviation. Relations among the foregoing three factors were analyzed using Pearson' correlation coefficient. Levels of hope in cancer patients were determined using t-test, ANOVA and Scheffe test. Predictive factors influencing hope were investigated using multiple stepwise regression analysis. Results of the study are summarized as follows: 1. An average level of hope was $185.55{\pm}23.39$ points(96 min. and 234 max.) 2. Levels of hope showed a significant difference among them according to sex (t=-3.69, P=.000), age(F=4.714, P=.000), job(F=3.247, P=.008), monthly income (F=6.113, P=.003), treatment charge (F=3.796, P=.011), supportive resources (F=10.554, P=.000), diagnosis(F=2.287, P=.029), perceived health status(F=22.184, P=.000), level of pain(F=3.334, P=.021), religion (F=4.911, P=.001) and religion's effect in life (F=11.706, P=.000), 3. For the subjects, self-esteem and social support were $38.32{\pm}7.21$(13 min, and 50 max.) and $52.97{\pm}8.49$points(28 min, 80 max.). Concerning social support, average levels of family support and medical support were found $35.95{\pm}6.05$(18 min, and 40 max) and $27.02{\pm}4.99$ points(20 min and 40 max). The hope the cancer patients showed significant correlations with self-esteem (r=.588, P=.000), family support(r=.224, p=.001) and medical support(r=.221, P=.002). 4. The five variables related to hope (self-esteem, religion's effect in life, perceived health status, social support and age) accounted for 54.2 percent of the hope level; especially, self-esteem was the highest at 34.6%. As shown in the above results, predictive factors which most influence hope in cancer patients were self-esteem and religion's effect of life. Therefore, nursing interventions to increase self-esteem should be developed. Regarding religion's effects, studies on spiritual aspects should be carried out in a way that contributes to promotion of hope.

• Journal of Digital Convergence
• /
• v.15 no.9
• /
• pp.397-406
• /
• 2017

This study was conducted to identify moderating effects of interpersonal relation and social support on the relationship between depression and health promoting behaviors in the elderly. The participants were 286 elderly using two elderly welfare centers and one cultural center in D city. Data were collected from October 12th to 20th December, 2016, and were analyzed by t-test, ANOVA, multiple regression using SPSS 20.0. The result were as follows; The result were as follows; 1) Mean score of variables was Depression: 20.47, interpersonal relationship: 21.27 points, social support: 20.92 points, and health promotion behaviors: 111.69. 2) Depression had negative relationship with interpersonal relationship(r=-.283, p<.000), social network (r=-.391, p<.000), health promotion behaviors(r=-.611, p<.000), and interpersonal relationship had positive relationship with social support(r=.353, p<.000) and health promotion behaviors(r=.372, p<.000) significantly. 3) Social support had a moderating effect in the relationship between depression and health promoting behaviors(${\beta}=.448$, p=.011), while interpersonal relationship did not show moderation effect(${\beta}=.380$, p=.135). Based on these results, health program for elderly including social support is recommended to promote health behavior of the elderly in the community.

• Research in Community and Public Health Nursing
• /
• v.9 no.2
• /
• pp.550-563
• /
• 1998

This study was designed to provide the basic data of effective nursing intervention for alleviation of psychosocial adjustment of patients in mastectomy after identifying the correlation between the spouse support, self esteem and psychosocial adjustment. The study subjects were 83 postmastectomy patients who visited the outpatient clinic at 3 university hospitals in Taegu city from September 10, 1997 to October 16 1997. Data was collected by researcher and face to-face interview was conducted. Nam's spouse support scale(1987), Rosenberg's self esteem instrument (1965), Derogatis' Psychosocial Adjustment to Illness Scale were used. The data were analyzed by using descriptive statistics, Pearson correlation coefficient, t -test and ANOVA with the SAS program. The results of this study were as follows: 1. The mean score for the spouse support of the subjects was 3.73, self esteem was 3.69 and psychosocial adjustment was 3.61points. 2. According to the patient's hope of breast reconstruction(t=2.04, p=0.0445), there was significant difference of self esteem. According to the patient's family number( t = 2.31, p = 0.0237), there was significant difference of the psychosocial adjustment. 3. Perceived spouse support and self esteem had statistically significant positive correlations(r= 0.5120, p=0.0001). Perceived spouse support and psychosocial adjustment had statistically significant positive correlations(r=0.4187, p=0.0001). Perceived self esteem and psychosocial adjustment had statistically significant positive correlations(r = 0.6296, p=0.0001). Therefore, to increase the level of psychosocial adjustment of patients in mastectomy, it will be effective to supportive nursing intervention by improving spouse support and enhancing self esteem.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.622-631
• /
• 2016

This study examined 316 soldiers in the South Korean Army and the mediation effects of social support on bullying and frustration. Bullying, social support, and frustration showed average scores of 2.23, 3.60, and 2.75 points, respectively. There was a positive correlation between bullying, social support, and frustration. All of the subordinate variables of bullying showed significant impacts on frustration (p<.05), with psychological harassment showing the greatest impact (${\beta}=.340$), followed by bullying in interpersonal relationships (${\beta}=.149$) and bullying at work (${\beta}=.130$). In all the interaction items of the subordinate variable bullying ${\times}$ social support, bullying had a significant impact on frustration at p<.01, while the highest impact was shown in the interaction item of bullying ${\times}$ member support (${\beta}=.456$). The results imply that intangible combat power and solidarity among soldiers can be guaranteed only when superiors and peers provide full support for soldiers who are victims of bullying.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.63-70
• /
• 2014

Process of recognizing objects in binary images consists of image segmentation and pattern matching. If binary objects in the image are assumed to be separated, global features such as area, length of perimeter, or the ratio of the two can be used to recognize the objects in the image. However, if such an assumption is not valid, the global features can not be used but local features such as points or line segments should be used to recognize the objects. In this paper points with large curvature along the perimeter are chosen to be the feature points, and pairs of points selected from them are used as local features. Similarity of two local features are defined using elastic deformation energy for making the lengths and angles between gradient vectors at the end points same. Neighbour support value is defined and used for robust recognition of partially occluded binary objects. An experiment on Kimia-25 data showed that the proposed algorithm runs 4.5 times faster than the maximum clique algorithm with same recognition rate.

• Journal of Korean Association for Spatial Structures
• /
• v.14 no.4
• /
• pp.89-96
• /
• 2014

Spatial structures as like dome structure have the different dynamic characteristics from general rahmen structures. Therefore, it is necessary to accurately analyze dynamic characteristics and effectively control of seismic response of spatial structure subjected to multi-supported excitation. In this study, star dome structure that is subjected to multi-supported excitation was used as an example spatial structure. The response of the star dome structure under multiple support excitation are analyzed by means of the pseudo excitation method. Pseudo excitation method shows that the structural response is divided into two parts, ground displacement and structural dynamic response due to ground motion excitation. And the application of passive tuned mass damper(TMD) to seismic response control of star dome structures has been investigated. From this numerical analysis, it is shown that the seismic response of spatial structure under multiple support seismic excitation are different from those of spatial structure under unique excitation. And it is reasonable to install TMD to the dominant points of each mode. And it is found that the passive TMD could effectively reduce the seismic responses of dome structure subjected to multi-supported excitation.

• Journal of Home Health Care Nursing
• /
• v.12 no.1
• /
• pp.136-154
• /
• 2005

Purpose : This study purposed to conduct a comprehensive survey of home care nursing clients' quality of life based on the PRECEDE model. Method : This study selected 74 home care nursing clients registered at a university hospital in Incheon and performed face-to-face interviews by structured questionnaire. The research period was two months from the $2^{nd}$ of February to the $30^{th}$ of March in 2004. Result : According to the result of assessment at each stage of the PRECEDE model, home care nursing clients' quality of life was 13.88 out of 25 points, health level 15.22 out of 21, abilities to perform activities of daily living 29.26 out of 100, cognitive abilities 16.00 out of 30, social support 13.68 out of 20, and satisfaction with home care nursing service 33.26 out of 40. According to the result of stepwise regression in order to identify factors influencing home care nursing clients' quality of life, social support and abilities of daily living were found to be significant variables among the characteristics of each assessment stage. Conclusion : It is necessary to develop nursing intervention strategies for strengthening social support and enhancing abilities to perform activities of daily living in order to improve home nursing clients' quality of life.