• Journal of Animal Science and Technology
• /
• v.63 no.2
• /
• pp.440-452
• /
• 2021

The purpose of this study was to determine if an 8-week therapeutic riding (TR) program was effective in improving the walking ability of students with intellectual disabilities. Thirteen students diagnosed with intellectual disabilities participated in the TR program. TR sessions were conducted twice a week (30 min per session), with a total of 16 rides taking place over an 8-week period. A gait measurement analyzer was used to measure progress based on a turn test (6-m walking and turning test), walk test (10-m walking), and timed up and go (TUG) test. Measurements were made three times: before horse-riding (P0), after 4 weeks (8 rides) of horse-riding (P1), and after 8 weeks (16 rides) of horse-riding (P2). Data analysis was conducted using SPSS software (ver. 22.0). Descriptive statistics were generated on the general characteristics of the subjects, and the Kolmogorov-Smirnov test was used to verify the normality of the data. Because of the lack of normality, the data were analyzed using a nonparametric method and the significance level was set to 0.05. Measurements of the duration of the forward gait cycle (s) in the turn test and the forward gait speed (m/s) in the walk test indicated improved walking ability after the TR program (p < 0.001); the stride length (% height) also increased significantly (p < 0.05). The walk test revealed a significant effect of the program on the duration of the forward gait cycle (p < 0.05), while there were significant improvements on the left and right of the elaborated strides (p < 0.001). No significant improvement in TUG test performance was observed after the TR program. In this study, an 8-week TR program had positive results on gait. Therefore, further research is merited, where TR programs are likely to improve the walking ability of individuals with intellectual disabilities.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.177-188
• /
• 2022

The support vector machine (SVM) has been successfully applied to various classification areas with a high level of classification accuracy. However, it is infeasible to use the SVM in analyzing massive data because of its significant computational problems. When analyzing imbalanced data with different class sizes, furthermore, the classification accuracy of SVM in minority class may drop significantly because its classifier could be biased toward the majority class. To overcome such a problem, we propose the DOC-SVM method, which uses divide-oversampling and conquers techniques. The proposed DOC-SVM divides the majority class into a few subsets and applies an oversampling technique to the minority class in order to produce the balanced subsets. And then the DOC-SVM obtains the final classifier by aggregating all SVM classifiers obtained from the balanced subsets. Simulation studies are presented to demonstrate the satisfactory performance of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.35 no.2
• /
• pp.54-69
• /
• 2022

Objectives: The purpose of this study is to reflect the patient's perspective in the process of developing Korean medicine clinical practice guideline (CPG) of puerperal wind disorder by survey. Methods: Five hundred fifty patients were surveyed from November 3rd, 2021 to November 8th, 2021 by internet. This study is an exploratory cross-sectional survey study, and descriptive statistics and frequency analysis were conducted on respondents' general characteristics, postpartum symptoms, the history of using treatment institution for puerperal wind disorder, satisfaction of medical institutions and perception of postpartum care. Results: Survey results showed that 92.0% of respondents experienced symptoms after childbirth, and 56.2% of the symptoms were arthralgia, followed by obesity with 41.8%. Among puerperal wind disorder patients, 34.2% had treatment history, and 54.3% received Korean medical treatment. Treatment satisfaction was confirmed to be higher in Korean medical treatment. The necessity of postpartum care was recognized at 95.7% of respondents, and the performance rate of traditional Korean postpartum care was also high. Conclusions: Based on a realistic patient-centered basis, it is a study that can lay the foundation for standardizing Korean medicine treatment and strengthening coverage in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.206-208
• /
• 2022

As the big data industry has recently developed significantly, interest in privacy violations caused by personal information leakage has increased. There have been attempts to automate this through named entity recognition in natural language processing. In this paper, named entity recognition data is constructed semi-automatically by identifying sentences with de-identification information from de-identification information in Korean Wikipedia. This can reduce the cost of learning about information that is not subject to de-identification compared to using general named entity recognition data. In addition, it has the advantage of minimizing additional systems based on rules and statistics to classify de-identification information in the output. The named entity recognition data proposed in this paper is classified into twelve categories. There are included de-identification information, such as medical records and family relationships. In the experiment using the generated dataset, KoELECTRA showed performance of 0.87796 and RoBERTa of 0.88.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.6
• /
• pp.287-295
• /
• 2019

The purpose of this study was to identify the factors affecting mental health status according to gender of persons with physical disabilities and to try their healthy life. Using the 6th Korean Retirement and Income Study, 333 persons with physical disabilities were included in the study. Descriptive statistics, t-test, and regression analysis were conducted to examine the general characteristics, instrumental activities of daily living, material support, and the effects on mental health status. There was no statistically significant difference in mental health status by gender, but there was a difference in Instrumental Activities of Daily Living and life satisfaction. In the case of males, instrumental daily activities performance, material support, depression, and life satisfaction were found to be influential. In the case of females, spouse, depression, and life satisfaction were factors affecting mental health status. Based on the results of this study, we will be able to understand persons with physical disabilities and use them as a basis for developing mental health promotion programs.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.603-608
• /
• 2024

Nonresponse and missing values are caused by sample dropouts and avoidance of answers to surveys. In this case, problems with the possibility of information loss and biased reasoning arise, and a replacement of missing values with appropriate values is required. In this paper, as an alternative to missing values imputation, we compare several replacement methods, which use mean, linear regression, random forest, K-nearest neighbor, autoencoder and denoising autoencoder based on deep learning. These methods of imputing missing values are explained, and each method is compared by using continuous simulation data and real data. The comparison results confirm that in most cases, the performance of the random forest imputation method and the denoising autoencoder imputation method are better than the others.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.11 no.4
• /
• pp.215-225
• /
• 2016

There is growing attention towards the performance of non-profit organizations (NPO) as cases of moral hazard have emerged as social issues and the public becomes interested in the accountability of NPOs. Social welfare is among the representative service areas of NPOs, and it is regarded as a human service because it is delivered by people. Therefore, human capital-measured by criteria such as levels of organizational commitment-significantly affects the performance of social welfare organizations. However, these organizations have a high turnover rate due to inadequate working environments, heavy workloads, intensive work, and poor remuneration. Against this background, we surveyed social welfare organizations located in Busan and examined how workers' organizational commitment affects their turnover intention and the performance of the organization. For data analysis, SPSS WIN 18.0 was used, and variable-specific frequency analysis and technical statistics were used to identify general properties. A Pearson correlation analysis and a multiple regression analysis were conducted to investigate correlations and causal relationships among main variables. The results showed that the social workers' level of organizational commitment was 3.36 for normative commitment, 3.07 for continuance commitment, and 2.75 for affective commitment. The level of normative commitment was slightly higher than moderate, continuance commitment was close to moderate, and affective commitment was lower than moderate. The surveyed social workers' turnover intention was 2.71, and organizational performance was 2.79; both of those results were slightly lower than moderate. It was observed that affective commitment, marital status, workload, and age affected social workers' turnover intention. Their affective commitment, gender, and age affected the organization's performance. These results suggest that, for launching or operating an NPO, it is important to manage human capital effectively, particularly their affective commitment, to lower workers' turnover intention and improve organizational performance.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.4
• /
• pp.211-216
• /
• 2018

This study was intended to analyze the effects of the selection of excellent design product by the KIDP(Korea Institute of Design Promotion) on the business performance of the company focused on the start-up with relatively low competitiveness. According to the statistics of KIDP in 2013, a design accounted for 27.53% of the factors affecting the sales of products and a design was the most important factor among the factors affecting the sales of products for the small sized company in terms of the scale of company. In addition, looking at the trend by industry in the data collected for this study, the technology-based industry showed a relatively higher growth rate than the retail industry and other industries. In this study, the author surveyed 186 companies of the companies that recognized the importance of design in difficult management conditions and received excellent design product certificate from KIDP(2013, 2014 and 2015) and empirically verified whether there was any difference in business performance between the start-ups with a business history of less than 7 years and the ongoing firms with a business history of more than 7 years. To evaluate the value of design, we used analytical method of measuring related values by comparison between groups. In addition, we also analyzed the difference in business performance(sales) between manufacturing companies, where the role of design was relatively large, and non-manufacturing companies among companies that received the excellent design product certificate. We have established a study hypothesis that the selection of excellent design product by the KIDP would have more positive effect on the business performance(sales) of the start-up compared to the ongoing firm, and conducted an empirical analysis by comparing both the year before and the year after the selected year. As a result, we found that the selection of excellent design product by the KIDP has a positive effect on the business performance of the start-up, and the selection of excellent design product has a significant effect on the difference in business performance between manufacturing and non-manufacturing companies. This study was conducted in the hope that the government actively supports the design-related policies so that the selection of excellent design product become an important indicator of the business performance of the start-up, and thus the design management will be a way to enhance the competitiveness of the start-up.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.2
• /
• pp.19-32
• /
• 2020

The purpose of this study was to investigate the influence factors of the university level centering on the entrepreneurial performance of the university students and full-time faculties in the situation of increasing interest in entrepreneurial university. In order to achieve the purpose of the study, a panel data was established from 2015 to 2018 on the basis of the university notification data. The panel data included universities with data on the number of university students and full-time faculty founders for at least two years. Through this, four year data from 154 universities were used for analysis. As an analysis method, frequency analysis and descriptive statistics were conducted to understand the characteristics of the university. Since then, panel negative binomial regression analysis has been conducted in consideration of the longitudinal features and distribution of the data. Also, based on the Hausman test results, the results were interpreted based on random effect model. The results of this study are as follows. First, as a result of the analysis of the entrepreneurial performance and the change trend of the domestic university from 2015 to 2018, the entrepreneurial performance of the university has been steadily increasing in the last four years, and the increase in the number of university student entrepreneurs was relatively higher than the full-time faculties. Second, economic and educational approaches need to be combined to promote university students' start-ups. The university factors that promote the start-up of university students were found to be scholarships, start-up grants, startup lectures, and startup clubs. Third, the openness and regional characteristics of the univeristy can promote the establishment of university students. Fourth, the establishment of a research environment and support for start-ups for full-time faculty members can enhance their start-up performance. The university factors that promote the start-up of full-time faculty were research funds and staffes who support start-up. The conclusions drawn from these findings are as follows. First, overall efforts are needed to develop into an entrepreneurial university. Second, in order to change into an entrepreneurial university, direct support for entrepreneurship is needed. Third, as an entrepreneurial university, it is necessary to find a way to bridge the gap by university according to region and size. Fourth, it is necessary to reinforce the support for linking the research results of universities to start-ups. Fifth, it is necessary to improve the atmosphere for full-time faculty members to be entrepreneur.