• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.43-58
• /
• 2014

As the use of trading systems has increased rapidly, many researchers have become interested in developing effective stock market prediction models using artificial intelligence techniques. Stock market prediction involves multifaceted interactions between market-controlling factors and unknown random processes. A successful stock prediction model achieves the most accurate result from minimum input data with the least complex model. In this research, we develop a combination model of ${\pi}$-fuzzy logic and support vector machine (SVM) models, using a genetic algorithm to optimize the parameters of the SVM and ${\pi}$-fuzzy functions, as well as feature subset selection to improve the performance of stock market prediction. To evaluate the performance of our proposed model, we compare the performance of our model to other comparative models, including the logistic regression, multiple discriminant analysis, classification and regression tree, artificial neural network, SVM, and fuzzy SVM models, with the same data. The results show that our model outperforms all other comparative models in prediction accuracy as well as return on investment.

• Journal of Preventive Medicine and Public Health
• /
• v.39 no.3
• /
• pp.229-234
• /
• 2006

Objectives: Cardiovascular disease is one of the main causes of death and morbidity in Korea. In this study, the prevalence and incidence of developing hypertension in a male-workers' cohort were investigated during 3-years follow-up with a view to find the risk factors that affected the development of hypertension. Methods: Among the 5,374 people who participated in a routine health check up, 3,852 people with normal blood pressure and who had no history of hypertension were prospectively followed up for 3 years. The classification of hypertension was based on the JNC7 report (the Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure). Life style factors and underlying diseases that were related to the risk factors of hypertension were collected by using a self-report questionnaires via the internet. Results: The prevalence of hypertension was 28.3% (1,520/5,374) at the first screening (2001). It was found that the incidence in 2004 of hypertension for the follow-up subjects (3,711) who had normal blood pressure in 2001 was 7.6 per 100 person-year. Multiple logistic regression analysis of the variables related to the risk factors of hypertension was carried out. The relative risks were 1.037 (95% CI=1.022-1.053) as the age increased 1 year and 1.039 (95% CI=1.023-1.055) as the body mass index increased $1kg/m^2$. The relative risk for the prehypertensive group was 2.501 (95% CI=1.986-3.149) compared to the normotensive group. These results showed that age, body mass index and the baseline blood pressure were significantly related to the incidence of hypertension. Conclusions: The incidence of hypertension was 7.6 per 100 person-year during follow-up. It was concluded that the risk factors for developing hypertension in the short-term were age, BMI, and prehypertension; Especially, this showed that it is necessary for prehypertensives to manage their body weight and blood pressure to prevent hypertension in middle-age by modifying their life style.

• Journal of Preventive Medicine and Public Health
• /
• v.28 no.3 s.51
• /
• pp.663-677
• /
• 1995

Special health examination institute has done periodic health examination for workers who have worked in the hazardous workplace. However, assessment on outcome in special health examination institute about detection ability of occupational disease has not been. In this circumstances, we studied on the differences of health examination outcome among special health examination institutes and identified related factors which affected outcome of special health examination in the special health examination institutes. The summary of the results were as follows. 1. 50 special health examination institutes were examined in this study. Among them, university institutes were 13 cases(26.0%), hospitals were 20 cases(40.0%), a corporation aggregates were 9 cases(18.0%) and an auxiliary organs of company were 8 cases(16.0%). There were 29(58.0%) institutes with a preventive medicine specialist, but 21 institutes(42.0%) were not. 2. Total workers examined in 50 institutes were 606,948 and workers diagnosed as occupational disease$(D_1)$ were 3,156. The rate of occupational disease was 6 workers per 1,000 examined workers. Workers needed for close observation(C) were 95,809 and the rate of workers needed for close observation was 141 per 1,000 examined workers. 3. The rate of occupational disease of university institutes was highest(11.3 per 1,000 examined workers), and followed by hospitals(6.0 per 1,000 examined workers), a corporation aggregates(4.2 per 1,000 examined workers), and an auxiliary organs of company(1.2 per 1,000 examined workers). The difference of the rate of occupational disease between university institutes and an auxiliary organs of company was statistically moderate significant(p<.1). The rate of occupational disease in special health examination institutes with establishment duration was more than 10 years was statistically higher than institutes with establishment duration was less than 10 years(p<.1). 4. The results of multiple regression, $R^2$ was 0.3394(adjusted $R^2$ was 0.2109), F-value was 2.6416(p<.05), and statistically significant variables were establishment duration(p<.01), number of examined workers per one doctor(p<.1), and auxiliary organs of company(p<.1), which dependent variable was the rate of occupational disease and independent variables were number of examined workers per one doctor, classification of institute, the rate of working environment exceeding TLV, duration of institute establishment, presence of a preventive medicine specialist.

• Journal of Korean society of Dental Hygiene
• /
• v.3 no.1
• /
• pp.25-43
• /
• 2003

In Korea, changes in children's diet patterns accelerate their physical growth and development: frequent snacking has been presumed to be a major cause of increasing dental caries. The present study attempts to clarify the relationship between the physical development of growing children and their tooth decay. For this purpose, 632 six-grade children in 4 elementary school located in Urban(Seoul) and Rural(Po-gok, Yang-In) were classified into three groups based on the Weight Length Index(WLI), known to reflect the nutritional conditions of school-age children, and the relationship was analyzed between each group and the variables considered to be related with dental caries. The result is as follows: The average weight and height of the male is $44.88{\pm}10.89$ kg, $148.49{\pm}7.33$ cm and female is $43.35{\pm}9.60$ kg, $149.23{\pm}6.73$ cm, respectively, which are in the similar level with the Korean Physical Standard. The classification of the children by the WLI reveals a relatively high distribution of over-weighted child ren - 212 persons, 335% of the entire population. The DMFT Index was a little high in the rural area(3.15 teeth in urban and 3.31, in rural). Among the groups of children classified by the WLI, the over-weight group have the highest DMFT index(3.69 teeth). The relationship between the frequency of taking in basic nutrients and the DMFT index is also found: the relationship is not evident in case of the foods containing rich calcium, protein, as well as fruits and vegetables. But, in the protein-rich food, higher frequency of its intake means significantly lower DMFT index in the normal-weight group of the urban children. In case of carbohydrate, higher frequency of its intake means significantly higher DMFT index in all the groups of the rural children. The DMFT index has some correlations with the relevant variables: the index has a positive correlation with the frequency of snacking, and a negative correlation with the economic status. That is, the higher the frequency of snacking is, and the lower the economic status is, the higher the DMFT index may be. In the logistic multiple regression analysis conducted with the presence of DMFT as a dependent variable, only the frequency of tooth brushing is turned to be a variable affecting the presence of either decayed, missing, or filled teeth. Based on the above result, the variables affecting the DMFT index are a time spent on eating, frequency of intake of protein and carbohydrate for a week, frequency of snacking, regular dental check-ups, preventive behaviors for oral health(fluoride gargling, tooth brusing after each meal, proper tooth brushing method). These variables have a relationship with the DMFT index, but the degree is somewhat different between the groups classified either by the region or by the WLI. Therefore, appropriate nutrition management should be conducted according to the individual's nutritional conditions when the services like nutritional education are provided based on the closely-examined characteristics of each target group. And, at the same time, oral health education should be strengthened, and its importance should also be emphasized so that people can pay attention to their own oral health.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.330-338
• /
• 2002

Spontaneous speech is ungrammatical as well as serious phonological variations, which make recognition extremely difficult, compared with read speech. In this paper, for conversational speech recognition, we analyze the transcriptions of the real conversational speech, and then classify the characteristics of conversational speech in the speech recognition aspect. Reflecting these features, we obtain the baseline system for conversational speech recognition. The classification consists of long duration of silence, disfluencies and phonological variations; each of them is classified with similar features. To deal with these characteristics, first, we update silence model and append a filled pause model, a garbage model; second, we append multiple phonetic transcriptions to lexicon for most frequent phonological variations. In our experiments, our baseline morpheme error rate (WER) is 31.65%; we obtain MER reductions such as 2.08% for silence and garbage model, 0.73% for filled pause model, and 0.73% for phonological variations. Finally, we obtain 27.92% MER for conversational speech recognition, which will be used as a baseline for further study.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.177-187
• /
• 2014

This paper proposes a fast subspace tracking methods, which is called GVFF FAPI, based on FAPI (Fast Approximated Power Iteration) method and GVFF RLS (Gradient-based Variable Forgetting Factor Recursive Lease Squares). Since the conventional FAPI uses a constant forgetting factor for estimating covariance matrix of source signals, it has difficulty in applying to non-stationary environments such as continuously changing DOAs of source signals. To overcome the drawback of conventioanl FAPI method, the GVFF FAPI uses the gradient-based variable forgetting factor derived from an improved means square error (MSE) analysis of RLS. In order to achieve the decreased subspace error in non-stationary environments, the GVFF-FAPI algorithm used an improved forgetting factor updating equation that can produce a fast decreasing forgetting factor when the gradient is positive and a slowly increasing forgetting factor when the gradient is negative. Our numerical simulations show that GVFF-FAPI algorithm offers lower subspace error and RMSE (Root Mean Square Error) of tracked DOAs of source signals than conventional FAPI based MUSIC (MUltiple SIgnal Classification).

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.4
• /
• pp.203-230
• /
• 2010

This study analyzed the development and growth of folksonomy by examining tags associated with 40 bestsellers on LibraryThing.com in 6-month intervals. It was found that tag values do not decrease but grow in terms of quantity and quality. Accordingly, we examined the major significances of the tags and their potential utilization as an expression of subjects. Our findings were as follows. First, the motivations for tagging can be categorized into personal information for search purposes, self-fulfillment such as sense of achievement, display of emotion and sharing of one's experience with others, or an altruistic objective that emphasizes sociality with a desire that one's actions might provide social benefits. According to our analysis, 74.12% of tags had a social motivation. Second, the total number of tags and the frequency of usage increased with time. Third, the categories that showed a high increase in tag usage were dates of publication and reading, key words, main characters, and book reviews. Tags related to subjects had the highest ratio. Fourth, among Library of Congress Subject Headings (LCSH), multiple genres, key words and main characters were assigned to books, and specific key words and other properties were added as time progressed. There was also a slight increase in the number of tags consistent with LCSH. Fifth, we found that key tags could serve as a compilation of terms that reflects the knowledge base of the corresponding era. Thus, folksonomy should be continuously monitored for its quantitative and qualitative development of the tags to make improvements on its formative disadvantages, and identify internal semantic significance, be actively utilized in conjunction with taxonomy as a flexible compilation of terms that incorporate the history of a specific era.

• Archives of Craniofacial Surgery
• /
• v.21 no.5
• /
• pp.288-293
• /
• 2020

Background: Pilomatrixoma is a benign tumor that originates from the hair follicle matrix. It usually presents as a hard, slow growing, solitary mass that can be easily misdiagnosed as other skin masses. The aim of this study was to clinically analyze a case series of pilomatrixoma in pediatric patients from Korea. Methods: A total of 165 pediatric patients from 2011 to 2018 with a histological diagnosis of pilomatrixoma were included. A retrospective review was performed using the electronic medical records, including patient demographics, number and location of the mass, clinical and imaging presentation, and postoperative outcomes. Results: There were 61 male and 104 female patients with 152 solitary and 13 multiple pilomatrixomas. Among solitary pilomatrixomas, the lesion commonly occurred in the head and neck (84.2%), followed by upper limbs (11.2%), lower limbs (3.3%), and trunk (1.3%). The pilomatrixoma lesion presented as the following types based on our clinical classification: mass (56.02%), pigmentation (25.31%), mixed (12.65%), ulceration (4.82%), and keloid-like (1.2%). Ultrasonography showed a high positive predictive value (95.56%). There were no specific complications observed except for two cases of recurrence. Conclusion: Pilomatrixoma has various clinical feature presentations and commonly occurs in the head and neck. Ultrasonography is a helpful diagnostic tool. Surgical removal of the lesion is the main treatment method with a low recurrence rate.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.2
• /
• pp.1083-1087
• /
• 2013

Background: Colorectal cancer has several modifiable behavioural risk factors but their relationship to the risk of colon and rectum cancer separately and between countries with high and low incidence is not clear. Methods: Data from participants in the Asia Pacific Cohort Studies Collaboration (APCSC) were used to estimate mortality from colon (International Classification of Diseases, revision 9 (ICD-9) 153, ICD-10 C18) and rectum (ICD-9 154, ICD-10 C19-20) cancers. Data on age, body mass index (BMI), serum cholesterol, height, smoking, physical activity, alcohol and diabetes mellitus were entered into Cox proportional hazards models. Results: 600,427 adults contributed 4,281,239 person-years follow-up. The mean ages (SD) for Asian and Australia/New Zealand cohorts were 44.0 (9.5) and 53.4 (14.5) years, respectively. 455 colon and 158 rectum cancer deaths were observed. Increasing age, BMI and attained adult height were associated with increased hazards of death from colorectal cancer, and physical activity was associated with a reduced hazard. After multiple adjustment, any physical activity was associated with a 28% lower hazard of colon cancer mortality (HR 0.72, 95%CI 0.53-0.96) and lower rectum cancer mortality (HR 0.75, 95%CI 0.45-1.27). A 2cm increase in height increased colon and all colorectal cancer mortality by 7% and 6% respectively. Conclusions: Physical inactivity and greater BMI are modifiable risk factors for colon cancer in both Western and Asian populations. Further efforts are needed to promote physical activity and reduce obesity while biological research is needed to understand the mechanisms by which they act to cause cancer mortality.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.325-336
• /
• 2019

The purpose of this study is to analyze the structural relationship between internal capabilities and job satisfaction using the 7S model and propose measures to improve management performance through internal factors. For this study, seven research hypotheses were set up, and the survey conducted among members of all professions working in general hospitals in small and medium-sized cities in the provinces. From September 20 to October 20, 2016, 385 people were surveyed, and 327 pieces of data (84.9%) used for the study. Multiple regression analyses were performed to verify the effects of internal capabilities on job satisfaction. The analysis results showed that the explanatory power of the research model was suitable by showing 69.1%, and among the 7S factors, the leadership style (β=.392^**), the organizational structure (β=.129^*), the membership (β=.232^**), and the management technique (β=.204^*) showed a positive influence on job satisfaction. That has been confirmed to affect job satisfaction as the standardized factor values increase. Relationships between strategies, systems, and shared values on job satisfaction could not be identified. Significantly observed in the relationship between some internal capacity factors and job satisfaction is that internal capacity can be used as an alternative to an organization's performance improvement measures. Internal capacity can be affected by various environmental variables, such as establishment classification, size, and location. Further implications will also be provided for measuring future internal satisfaction levels separately from internal and external factors.