• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.7 no.1
• /
• pp.5-28
• /
• 2001

Objectives: The objective of this study was to investigate analysis of bone mineral density according to Women with low back pain women. Methods: The data were collected from women who visited Physical Examination Center of a Catholic university hospital located in Daegu. Questionnaires were completed by 50 women during the period from July 20, 2000 to January 12, 2001. The sample was divided into three groups(the normal group of 16 cases and the osteopenia group of 12cases and the osteoporosis group of 22 cases). Bone mineral density(BMD) of lumbar spine was measured using energy absorptiometry. Results: The bone mineral density of the lumbar spine decreased with aging. The bone mineral density of the lumbar spine decreased with the serum Calcium and Phosphorus and Alkaline phosphatase increased. The mean bone mineral density of the lumbar spine of healthy women in age(50~59) was 0.87g/$cm^2$, the lumbar spine of women with low back pain in age(50~59) was 0.77g/$cm^2$. In the multiple regression of risk factors to bone mineral density(BMD) of lumbar spine were correlated with age, marriage existence, exercise time, the loving food of taste, calcium, bone mineral density standard T scores(p<0.05). The experience for LBP increased as weight increased(Odds ratio=999.000). The experience for LBP increased as number of Exercise decreased(Odds ratio=999.000). The experience for LBP increased as menopause existence increased(Odds ratio=999.000). The experience for LBP increased as serum Calcium and Phosphorus increased (Odds ratio=999.000). however all four variables had significant no relationship. The correlation in variables in relation to low back pain and bone mineral density, age showed contra-correlation with low back pain existence, Alkaline phosphatase(p<0.01). Weight showed contra-correlation with body mass index(BMI)(p<0.01). Exercise time showed correlation with number of exercise(p<0.01). The loving food of taste showed contra-correlation with Alkaline phosphatase(p<0.05). Bone mineral density showed correlation with menopause existence(p<0.05). Conclusions: Results from this study indicated that a statistically significant association between bone mineral density of the lumbar spin and age, marriage existence, exercise time, the loving food of taste, calcium, bone mineral density standard T scores. In logistic regression test, there were no related variables. The combination of bone mineral density measurement and assessment of the bone turnover rate by measuring biochemical would be helpful for the treatment of patients with risks of osteoporosis. The more precise study for risk factors to osteoporosis is essential.

• Journal of agricultural medicine and community health
• /
• v.26 no.1
• /
• pp.81-103
• /
• 2001

This study was conducted to identify the health behavior of middle-aged rural women and the factors that have an effect on them. For the purpose of the study, examinations were made from March 01, 2000 to March 31, 2000 with 468 women aged 40 to 64 out of 2,263 people whom four Primary Health Posts located in Yechon County, Kyongsangbuk-do Province, are in charge of. The results are summarized as follows. 17.5% of the subjects responded that the extent of their own interest in health were high. For the subjects having a chronic disease, a nuclear family, or an open family atmosphere, the extent appeared to be relatively higher, 15.4% responded that the extent of family's interest in their health was high. It was significantly high if the extent of education was high or if the family atmosphere was open. The subjects' average score of self-efficacy was 49.9 out of 68. The score significantly varied depending on religion, education, living together with a spouse or not, and the extent of the subjects' interest in health. The family pattern, family atmosphere, family's interest in the subjects' health were the variables that significantly influenced the self-efficacy. The average score of family function was 5.51 out of 10. The score significantly varies depending on age, education, occupation, financial status, the extent of the subjects' own interest in health, family atmosphere and family's interest in the subjects' health. In the practice of health behavior, the nonsmoking rate was 89.5%, the nondrinking rate 63.0%, the rate of exercising practice 6.6%, the rate of normal sleeping 75.6%, the rate of eating breakfast 91.7%, the rate of not eating between meals 18.2%, and the standard BMI 69.2%. In the frequency of health behavior, the subjects with the Breslow Index of 0-3, 4-5 and 6-7 accounted for 4.5%, 53.2%, and 42.3%, respectively. The average score of health behavior was 5.20 out of 7, in which significant variables were living together with a spouse or not, financial status, absence or presence of a chronic disease, and family atmosphere. In the multiple regression analysis with health behavior as a dependent variable, it was shown that living together with a spouse or not, financial status, and family atmosphere were the significantly substantial variables. The subjects were found to do health behavior well if they had not a spouse, a good financial status, or an open family atmosphere. They were also found to do health behavior well if the extent of self-efficacy was high or if the extent of family function was low, but these were not the significant variables. It is needed to develop a standard measuring tool fit for our environment and perform more studies in the future because the measuring tool used in this study was a tool developed in a foreign county. In promoting community health projects, it is required not to provide all community people with a uniform health program but to identify the health behavior of individuals and other variables such as living together with a spouse or not, financial status and family atmosphere before arranging for a proper health program.

• Journal of agricultural medicine and community health
• /
• v.25 no.1
• /
• pp.65-83
• /
• 2000

To know the relationship of general characteristics with activities of daily living(ADL) and instrumental activities of daily living(IADL), we carried out the study on the elderies living in Chollabuk-Do area during 6 months, from June to December in 1999. Study subjects were 281, women and men were 195(69.6%) and 85(30.4%) respectively. Mean ages of women and men were 71.9 and 70.8 respectively. 81.1% elderies has disease and 18.9% were disease free. Disease prevalences of movement joint disease, others, circulatory disease, digestive disease, dental disease, respiratory disease were 50.1%, 25.0%, 10.5%, 9.4%, 8.5%, and 6.3% respectively. The percentages to the use of medical institution in recent were 40.0% for hospital, 16.8% for oriental hospital, 14.5% for public health center, 10.9% for drug store, 10.0% for others, and 7.8% for dental service. The percentages to the improvement of symptom after the use of medical institution were 62.3% for normal, 19.4% for improvement, and 18.2% for non-improvement. The percentages to the health situation were 37.1% for bad, 35.7% for good, and 27.1% for normal. Activities of daily living were 67.1% for 6 scores, 27.9% for 5 scores, 2.1% for 4 scores and ADL of women was lower than the men's. Instrumental activities of daily living were 50.4% for 5 scores, 19.3% for 3 scores, 12.1% for 4 scores and IADL of women was lower than the men's. Frequencies of disability in ADL were 28.9% for incontinence, 6.1% for bathing, 2.9% for meal, 2.5% for walking around house, 1.8% for toilet use, 1.4% for dressing and disability frequencies of women in 6 items of ADL were higher than the men's. The percentages of high, intermediate, low ADL in activities of daily living were 67.1%, 32.5%, 0.4% respectively and decrease of high ADL, increase of intermediate ADL were found with the increasing of age. Frequencies of disability in IADL were 42.9% for payment in and out, 31.8% for payment of written claim, 21.1% for shopping, 16.4% for preparation of meal, and 11.8% for use of bus. All items of women in IADL was higher than the men's but preparation of meal. The percentages of high, intermediate, low IADL in instrumental activities of daily living were 50.4%, 42.5%, 7.1% and decrease of high IADL, increase of intermediate IADL were found with the increasing of age. Mean of ADL with the general characteristics was 5.56 and 2 variables of level of education, health situation were statistically significant. Mean of IADL with the general characteristics was 3.76 and 8 variables of age, sex, level of education, occupation, presence of spouse, duty of living cost, health situation, category of ADL were statistically significant. With the result of stepwise regression, ADL was statistically related with religion, health situation and ADL was statistically related with level of education, living together with family, duty of living cost, health situation.

• Korean Journal of Agricultural Science
• /
• v.7 no.1
• /
• pp.12-26
• /
• 1980

A new, improved maize varieties are greatly needed to meet the national demand for the maize, and a new germplasm should be investigated to supply necessary breeding materials for the required maize breeding. The Korean local maize lines, which has never been wholly studied for the purpose of breeding should be enough to supply such breeding materials at least in Korea. The objectives of this study were to maintain useful Korean local lines, to investigate good plant characters and to analyze the Korean local maize lines in the respect of genetic make-up. A total of 820 lines and 200 lines were used for the present study. Lines to maintain were planted at experimental farm of the Crop Experiment Station, Office of Rural Development, Suwon and the lines to study genetic make-up were planted in Dae-jon. The summarized results are as follows : 1. A total of 1200 lines from 820 collections were sibbed for future use. 2. Two hundred collection were sibbed, selfed and testcrossed for genetic study in 1980. 3. Ten lines were surely confirmed as resistant lines to virus disease epidemic in most introduced maize varieties. 4. A dozen Lines were having three to four ears per plant. 5. Five lines were showing three to four tillers per plant. 6. One of the most significant and important finding through the study was to obtain the lines with three to four tillers bearing all together eight to nine ears. The lines of multi-ears and multi-tillers must have great breeding potential for the future use. 7. A great variation was observed in the tasselling days, 100 kernel weight and protein content. 8. From the genetic study of local maize lines for plant height and 100 kernel weight, the following findings were obtained. a. On the average six percent of inbreeding depression expressed in percent decrease over sibbed counterpart were found for the plant height. b. Fourty percent of heterosis expressed in percent increase over sibbed counterpart were observed in the plant height. c. The homogeneity or degree of homozygosity calculated from heterosis minus inbreeding depression was on the average 34 percent for plant height. d. The average inbreeding depression expressed in percent decrease over sibbed counterpart was 15 percent for 100 kernel weight. e. The average heterosis expressed in percent increase over sibbed counterpart was 43 percent for 100 kernel weight. f. The degree of homozygosity calculated from the heterosis minus inbreeding depression was 28 percent for 100 kernel weight.

• 한국사회복지학회:학술대회논문집
• /
• 2003.10a
• /
• pp.185-216
• /
• 2003

This study was aimed at investigating important factors influencing career success among regular workers. The current researcher scrutinized the degree to which variables and factors affect the career success and occupational turnover rates of the research participants. At the same tune, two hypothetical path models established by the researcher were examined using linear multiple regression methods and the LISREL. After examining the differences among the factors of career success, a comparison was made between the disabled worker group and the non-disabled worker group. A questionnaire using the 5-point Likert scale was distributed to a group of 374 workers with disabilities and 463 workers without disabilities. For the data analysis purpose, the structural equation model, factor analysis, correlation analysis, and multiple regression analysis were carried out. The results of this study ran be summarized as follows. First, the results of factor analysis showed important categories of conceptual themes of career success. The initial conceptual factor model did not accord with the empirical one. A three-factorial model revealed categories of personal, family, and organizational factor respectively. The personal factor was composed of the self-esteem and self-efficiency. The family factor was consisted of the multi-roles stress and the number of children. Finally, the organizational factor was composed of the capacity for utilizing resources, networking, and the frequency of mentoring. In addition, the total 10 sub areas of career success were divided by two important aspects; the subjective career success and the objective career success. Second, both research participant groups seemed to be influenced by their occupational types. However, all predictive variables excluding the wage rate and the average length of work years had significant impact on job success for the disabled work group, while all the variables excluding the frequency of advice and length of working years had significant impact on job success for the non-disabled worker group. Third, the turnover rate was significantly influenced by the age and the experience of turnover of the research participants. However, the number of co-workers was the strongest predictive variable for the worker group with disabilities, but the occupation choice variable for the worker group without disabilities. For the disabled worker group, the turnover rate was differently influenced by the type of occupation, the length of working years, while multi-role stress and the average working years at the time of turnover for the worker group without disabilities. Fifth, as a result of verifying the hypothetical path model, it showed that the first model was somewhat proper and could predict the career success on both research participant groups. In the second model, the Chi-square, the degree of freedom (($x^2=64.950$, df=61, P=0.341), and the adjusted Goodness of Fit Index (AGFI) were .964, and the Comparative Fit Index (CFI) were .997, and the Root Mean Squared Residual (RMR) was respectively. .038. The model was best fitted and could predict the career success more highly because the goodness of fit index in the whole models was within the allowed range. In conclusion, the following research implications can be suggested. First, the occupational type of research participants was one of the most important variables to predict the career success for both research participant groups. It means that people with disabilities require human development services including education. They need to improve themselves in this knowledge-based society. Furthermore, for maintaining the career success, people with disabilities should be approached by considering the subjective career success aspects including wages and the promotion opportunities than the objective career success aspects.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.6
• /
• pp.871-877
• /
• 1995

Background: The index which could predict the prognosis of critically ill patients is needed to find out high risk patients and to individualize their treatment. The APACHE III scoring system was established in 1991, but there has been only a few studies concerning its prognostic value. We wanted to know whether the APACHE III scores have prognostic value in discriminating survivors from nonsurvivors in sepsis. Methods: In 48 patients meeting the Bones criteria for sepsis, we retrospectively surveyed the day 1(D1), day 2(D2) and day 3(D3) scores of patients who were admitted to intensive care unit. The scores of the sepsis survivors and nonsurvivors were compared in respect to the D1 score, and also in respect to the changes of the updated D2 and D3 scores. Results: 1) Of the 48 sepsis patients, 21(43.5%) survived and 27(56.5%) died. The nonsurvivors were older($62.7{\pm}12.6$ vs $51.1{\pm}18.1$ yrs), presented with lower mean arterial pressure($56.9{\pm}26.2$ vs $67.7{\pm}14.2\;mmHg$) and showed greater number of multisystem organ failure($1.2{\pm}0.8$ vs $0.2{\pm}0.4$) than the survivors(p<0.05, respectively). There were no significant differences in sex and initial body temperature between the two groups. 2) The D1 score was lower in the survivors (n=21) than in the nonsurvivors ($44.1{\pm}14.6$, $78.5{\pm}18.6$, p=0.0001). The D2 and D3 scores significantly decreased in the survivors (D1 vs D2, $44.1{\pm}14.6$ : $37.9{\pm}15.0$, p=0.035; D2 vs D3, $37.9{\pm}15.0$ : $30.1{\pm}9.3$, p=0.0001) but showed a tendency to increase in the nonsurvivors (D1 vs D2 (n=21), $78.5{\pm}18.6$ : $81.3{\pm}23.0$, p=0.1337; D2 vs D3 (n=11), $68.2{\pm}19.3$ : $75.3{\pm}18.8$, p=0.0078). 3) The D1 scores of 12 survivors and 6 nonsurvivors were in the same range of 42~67 (mean D1 score, $53.8{\pm}10.0$ in the survivors, $55.3{\pm}10.3$ in the nonsurvivors). The age, sex, initial body temperature, and mean arterial pressure were not different between the two groups. In this group, however, D2 and D3 was significantly decreased in the survivors(D1 vs D2, $53.3{\pm}10.0$ : $43.6{\pm}16.4$, p=0.0278; D2 vs D3, $43.6{\pm}16.4$ : $31.2{\pm}10.3$, p=0.0005), but showed a tendency to increase in the nonsurvivors(D1 vs D2 (n=6), $55.3{\pm}10.3:66.7{\pm}13.9$, p=0.1562; D2 vs D3 (n=4), $64.0{\pm}16.4:74.3{\pm}18.6$, p=0.1250). Among the individual items of the first day APACHE III score, only the score of respiratory rate was capable of discriminating the nonsurvivors from the survivors ($5.5{\pm}2.9$ vs $1.9{\pm}3.7$, p=0.046) in this group. Conclusion: In sepsis, nonsurvivors had higher first day APACHE III score and their updated scores on the following days failed to decline but showed a tendency to increase. Survivors, on the other hand, had lower first day score and showed decline in the updated APACHE scores. These results suggest that the first day and daily updated APACHE III scores are useful in predicting the outcome and assessing the response to management in patients with sepsis.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.5
• /
• pp.660-668
• /
• 1995

Background: It is said that tuberculous pleuritis responds well to anti-tuberculous drug in general, so no further aggressive therapeutic management is unnecesarry except in case of diagnostic thoracentesis. But in clinical practice, we often see some patients who need later decortication due to dyspnea caused by pleural loculation or thickening despite several months of anti-tuberculous drug therapy. Therefore, we want to know the clinical difference between a group who received decortication due to complication of tuberculous pleuritis despite of anti-tuberculous drug and a group who improved after 9 months of anti-tuberculous drug only. Methods: We reviewed 20 tuberculous pleuritis patients(group 1) who underwent decortication due to dyspnea caused by pleural loculation or severe pleural thickening despite of anti-tuberculous drug therapy for 9 or more months, and 20 other tuberculous pleuritis patients(group 2) who improved by anti-tuberculous drug only and had similar degrees of initial pleural effusion and similar age, sex distribution. Then we compared between the two groups the duration of symptoms before anti-tuberculous drug treatment and pleural fluid biochemistry like glucose, LDH, protein and pleural fluid cell count and WBC differential count, and we also wanted to know whether there was any difference in preoperative PFT value and postoperative PFT value in the patients who underwent decortication, and obtained following results. Results: 1) Group 1 patients had lower glucose level{$63.3{\pm}30.8$(mg/dl)} than that of the group 2{$98.5{\pm}34.2$(mg/dl), p<0.05}, and higher LDH level{$776.3{\pm}266.0$(IU/L)} than the group 2 patients{$376.3{\pm}123.1$(IU/L), p<0.05}, and also longer duration of symptom before treatment{$2.0{\pm}1.7$(month)} than the group 2{$1.1{\pm}1.2$(month), p<0.05}, respectively. 2) In group 1, FVC changed from preoperative $2.55{\pm}0.80$(L) to postoperative $2.99{\pm}0.78$(L)(p<0.05), and FEV1 changed from preoperative $2.19{\pm}0.70$(L/sec) to postoperative $2.50{\pm}0.69$(L/sec)(p<0.05). 3) There was no difference in pleural fluid protein level($5.05{\pm}1.01$(gm/dL) and $5.15{\pm}0.77$(gm/dl), p>0.05) and WBC differential count between group 1 and group 2. Conclusion: It is probable that in tuberculous pleuritis there is a risk of complication in the case of showing relatively low pleural fluid glucose or high LDH level, or in the case of having long duraton of symptom before treatment. We thought prospective study should be performed to confirm this.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.5
• /
• pp.1058-1066
• /
• 1998

Background: Actinomycotic infection is uncommon and primary actinomycosis of the lung and chest wall has been less frequently reported. This disease may present as chronic debilitating illness with radiologic manifestation simulating lung tumor, pulmonary infiltrating lesion, or chronic suppuration. Diagnosis of choice was not definded yet and role of bronchoscopy on diagnosis was not described yet. Methods: From 1989 to 1998, we experienced 17 cases of thoracic actinomycosis. We have reviewed the case notes of 17 patients with thoracic actinomycosis. The mean age at presentation was $53{\pm}13$ years, 11 were male. Results: Cough, hemoptysis, sputum production, chest pain and weight loss were the commonest symptoms. The mean delay between presentation and diagnosis was $6.6{\pm}7.8$ months. There were six patients who presented with a clinical picture of a suppurative lesion and eleven patients were suspected of having primary lung tumor initially. In no cases was made an accurate diagnosis at the time of hospital admission. Associated diseases were emphysema (1 case), bronchiectasis (2 cases) and tuberculosis (2 cases). Bronchoscopic findings were mucosal swelling and stenosis(n=4), mucosal swelling, stenosis and necrotic covering (n=2), mass (n=3), mass and necrotic covering (n=1) and normal(n=6). Radiologic findings were mass lesion(n=8), pneumonitis(n=3), atelectasis(n=3), pleural effusion(n=2), and normal(n=3). Final diagnosis was based on percutaneous needle aspiration and biopsy (n=3), bronchoscopic biopsy specimens (n=9), mediastinoscopic biopsy (n=1) and histologic examination of resected tissue in the remaining patients(n=4) who received surgical excision. Among 17 patients, 13 were treated medically and the other 4 received surgical intervention followed by antibiotic treatment. Regarding the surgically treated patients, suspected malignancy is the most common indication for operation. However. both medically and surgically treated patients achieved good clinical results. Conclusion: Thoracic actinomycosis is rare. but should still be considered in the differential diagnosis of a chrinic, localized pulmonary lesion. Thoracic actinomycosis may co-exist with pulmonary tuberculosis or lung cancer. If the lesion is located in the central of the lung. the bronchoscopy is recommanded for the diagnosis.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.31 no.4
• /
• pp.569-578
• /
• 2004

The purpose of this study was to clarify the palatal arch length, width and height in the primary and permanent dentition. Samples were consisted of normal occlusions both in the primary dentition(50 males and 50 females) and in the permanent dentition(50 males and 50 females). With their upper plaster casts were used and through 3-dimensional laser scanning(3D Scanner, DS4060, LDI, U.S.A.), cloud data, polygonization, section curve and loft surface, fit and horizontal plane were based to measure the palatal arch length, width and height(Surfacer 10.0, Imageware, U.S.A.). T-tests were applied for the statistical analyze of the data. The results were as follows : 1. In the measurement values, the values of the male were higher than those of the female except primary anterior palatal height. There were not only statistically significant differences in anterior palatal width(p<0.05) and posterior palatal width(p<0.01) in primary dentition but palatal width(p<0.05), anterior palatal length(p<0.01), middle and posterior palatal length(p<0.05) in permanent dentition between male and female. 2. In the indices of palate, there were statistically significant differences in height-length index(p<0.05) and width-length index(p<0.01) between male and female in primary dentition. In permanent dentition, there was statistically difference between male and female. 3. In the measurement values, posterior palatal width was increased most greatly. Posterior palatal height, anterior palatal width and anterior palatal length were followed by descending order. On the other hand, anterior palatal height and posterior palatal length were decreased. 4. In the indices of palate, the height-length index, the width-length index and posterior height-width index were increased, but the others were decreased.