• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.359-366
• /
• 2021

A number of construction companies in Korea invest considerable human and financial resources to construct a system for managing apartment defect data and for categorizing repair tasks. Thus, this study proposes machine learning models to automatically classify defect complaint text-data into one of the sub categories of 'finishing work' (i.e., one of the defect repair tasks). In the proposed models, we employed two word representation methods (Bag-of-words, Term Frequency-Inverse Document Frequency (TF-IDF)) and two machine learning classifiers (Support Vector Machine, Random Forest). In particular, we conducted both binary- and multi- classification tasks to classify 9 sub categories of finishing work: home appliance installation work, paperwork, painting work, plastering work, interior masonry work, plaster finishing work, indoor furniture installation work, kitchen facility installation work, and tiling work. The machine learning classifiers using the TF-IDF representation method and Random Forest classification achieved more than 90% accuracy, precision, recall, and F1 score. We shed light on the possibility of constructing automated defect classification systems based on the proposed machine learning models.

• Journal of Chest Surgery
• /
• v.55 no.1
• /
• pp.49-54
• /
• 2022

Background: We compared the safety and effectiveness of robotic anatomical resection and video-assisted thoracoscopic surgery (VATS). Methods: A retrospective analysis was conducted of the records of 4,283 patients, in whom an attempt was made to perform minimally invasive anatomical resection for lung cancer at Seoul National University Hospital from January 2011 to July 2020. Of these patients, 138 underwent robotic surgery and 4,145 underwent VATS. Perioperative outcomes were compared after propensity score matching including age, sex, height, weight, pulmonary function, smoking status, performance status, comorbidities, type of resection, combined bronchoplasty/angioplasty, tumor size, clinical T/N category, histology, and neoadjuvant treatment. Results: In total, 137 well-balanced pairs were obtained. There were no cases of 30-day mortality in the entire cohort. Conversion to thoracotomy was required more frequently in the VATS group (VATS 6.6% vs. robotic 0.7%, p=0.008). The complete resection rate (VATS 97.8% vs. robotic 98.5%, p=1.000) and postoperative complication rate (VATS 17.5% vs. robotic 19.0%, p=0.874) were not significantly different between the 2 groups. The robotic group showed a slightly shorter hospital stay (VATS 5.8±3.9 days vs. robotic 5.0±3.6 days, p=0.052). N2 nodal upstaging (cN0/pN2) was more common in the robotic group than the VATS group, but without statistical significance (VATS 4% vs. robotic 12%, p=0.077). Conclusion: Robotic anatomical resection in lung cancer showed comparable early outcomes when compared to VATS. In particular, robotic resection presented a lower conversion-to-thoracotomy rate. Furthermore, a robotic approach might improve lymph node harvesting in the N2 station.

• Journal of Christian Education in Korea
• /
• v.70
• /
• pp.175-206
• /
• 2022

In this study, a mixed research method that collects and analyzes qualitative and quantitative data together was used to broaden the understanding of young children's faith. First of all, the contents of interviews with 18 research participants were divided into categories, and the frequency of each category was calculated. From 75 statements made in the interview, the importance of each was evaluated with a 5-point Likert scale. The means and standard deviations of the evaluation score were calculated, and sub-factors were identified through exploratory factor analysis. The frequency of categories mentioned in the qualitative interview was in the following order: faith manifested in difficulties, religious activities, Christian education at home, Christian education in the church, love and faith in God, and the formation of a Christian worldview (identity). The statement on the perception of God, theological concepts, religious activities, and Christian education at home and in the church received high scores. On the other hand, statements on developmentally difficult or abstract content, value judgment or conflict resolution based on the Word, and evangelism showed low scores. The sub-factors extracted through factor analysis were faith education through home and church, awareness of God and religious activities, identity based on the gospel, character based on the gospel, and overcoming a crisis through faith. In conclusion, the results of each of the mixed methods of looking at young children's faith were very similar-relationships with God, religious activities, Christian worldview (identity), Christian education at home and church were highlighted, even though various methods were used. This study is meaningful in that it suggests what and how to teach in early childhood Christian education.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.267-279
• /
• 2023

This research assessed the feasibility of using high-resolution aerial images and deep learning algorithms for estimating the land-use and land-cover areas at the Approach 3 level, as outlined by the Intergovernmental Panel on Climate Change. The results from different sampling densities of high-resolution (51 cm) aerial images were compared with the land-cover map, provided by the Ministry of Environment, and analyzed to estimate the accuracy of the land-use and land-cover areas. Transfer learning was applied to the VGG16 architecture for the deep learning model, and sampling densities of 4 × 4 km, 2 × 4 km, 2 × 2 km, 1 × 2 km, 1 × 1 km, 500 × 500 m, and 250 × 250 m were used for estimating and evaluating the areas. The overall accuracy and kappa coefficient of the deep learning model were 91.1% and 88.8%, respectively. The F-scores, except for the pasture category, were >90% for all categories, indicating superior accuracy of the model. Chi-square tests of the sampling densities showed no significant difference in the area ratios of the land-cover map provided by the Ministry of Environment among all sampling densities except for 4 × 4 km at a significance level of p = 0.1. As the sampling density increased, the standard error and relative efficiency decreased. The relative standard error decreased to ≤15% for all land-cover categories at 1 × 1 km sampling density. These results indicated that a sampling density more detailed than 1 x 1 km is appropriate for estimating land-cover area at the local level.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.159-172
• /
• 2023

In general, social problem-solving research aims to create important social value by offering meaningful answers to various social pending issues using scientific technologies. Not surprisingly, however, although numerous and extensive research attempts have been made to alleviate the social problems and issues in nation-wide, we still have many important social challenges and works to be done. In order to facilitate the entire process of the social problem-solving research and maximize its efficacy, it is vital to clearly identify and grasp the important and pressing problems to be focused upon. It is understandable for the problem discovery step to be drastically improved if current social issues can be automatically identified from existing R&D resources such as technical reports and articles. This paper introduces a comprehensive dataset which is essential to build a machine learning model for automatically detecting the social problems and solutions in various national research reports. Initially, we collected a total of 700 research reports regarding social problems and issues. Through intensive annotation process, we built totally 24,022 sentences each of which possesses its own category or label closely related to social problem-solving such as problems, purposes, solutions, effects and so on. Furthermore, we implemented four sentence classification models based on various neural language models and conducted a series of performance experiments using our dataset. As a result of the experiment, the model fine-tuned to the KLUE-BERT pre-trained language model showed the best performance with an accuracy of 75.853% and an F1 score of 63.503%.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.81-90
• /
• 2009

It is inevitable for college students to be confused when they first face university education, which requires them to be self-reliant and responsible, after finishing their course of education, which is passive under control of period and environment, in primary, middle, and high schools. Introduction to college courses, which require students to be subjective and responsible, to be taken after chronically and environmentally controlled primary and secondary education, are but confusing. In this stage, college education should provide ground for educational system so that students can escape from repetitively enforced way of studying of fixed curriculums and study creatively and subjectively while befitting each individual's aptitude. For instance, in programming classes in engineering school, students scholastic achievements are closely interrelated with the professor's educational principles. A change in method of education, from one previously focused on theoretical contents to one centered on practices and experiments, can reap good results. Also, as the need arose for introduction of practice-focused evaluation system, from recognition-centered professor evaluating system to enablement of actively developing creative and self-reliant way of learning, we applied the Rublic System. It is a feedback system that all or most students become the evaluators, of which the indicators of evaluation such as category, standard, and score are public. We have looked into whether or not there has been an improvement in GPAs of students, and if there exists an improvement then what efforts should be made to solidify the system.

• Journal of The Korean Association For Science Education
• /
• v.28 no.4
• /
• pp.350-358
• /
• 2008

The purpose of this study was to investigate the effects of interview with a scientist and engineer on service performance assessment on science career orientation and image of scientists. Science track students in the 11th grade carried out the interviews and made powerpoint presentations. After the students' presentation in the chemistry class, the teacher made comments on the contents of the interviews. Students gave presentation in each class for a year. Before starting this assessment, students took science career orientation questionnaire and DAST (draw-a-scientist-test). These two tests were conducted again at the end of the year. The results of this study showed that there was no significant difference between pre- and post-test score for the science career orientation. However, a significant difference was observed in the 'preference for science learning' category. These results showed that the career decision of a high school student has already been fixed rigidly. On the other hand, there was a significant difference (p < 0.01) between pre- and post-test on the image of scientists. This demonstrated that the stereotypic image for a scientist was reduced by the interview performance assessment and that, students came to have an affirmative perception of scientists on service.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.2
• /
• pp.45-55
• /
• 2024

This study analyzed the efficiency determinants of specialty construction companies by industry using the DEA model and the Tobit model. The analysis targets are 394 specialty construction companies as of 2022. As a result of analysis of efficiency determinants using 12 company characteristics as independent variables, the biggest problem for specialty construction companies was overall efficiency reduction due to rising labor costs. In addition, in a situation where construction companies' loan regulations are severe, the debt ratio was found to have a positive effect on efficiency. Company size had a different impact by industry, and the number of businesses held, credit score, and total capital turnover had an effect only on some industries. This study presents results that are an advance on existing research in that it strategically analyzes factors for improving the efficiency of specialty construction companies. However, it has limitations such as limiting the analysis to only specialty construction companies subject to external audit, insufficient number of companies subject to analysis by industry, and analyzing relative efficiency in the same category for each industry.

• Journal of dental hygiene science
• /
• v.18 no.6
• /
• pp.357-366
• /
• 2018

The purpose of this study was to evaluate the validity of dental hygienist job according to judgment standard of medical practice in medical law. In this study, we conducted a self-administered questionnaire survey to evaluate the validity of dental hygienist job for 12 professors of dental college in Gangneung-Wonju National University from November 10 to 20, 2017. We investigated whether the dental hygienist job conforms to the three criteria of medical practice such as disease prevention and treatment, patient care, and health hazard. The response rates were scored and classified into four categories according to the final score. As a result of this study, dental hygienist job are classified into four categories according to judgment standard of medical practice. The higher the level of the category, the higher the degree of difficulty, and the higher the level of expertise and skills required. More than 50% of respondents answered that measuring the gingival pocket, bleeding on probing, professional tooth cleaning, oral health education, counseling after dental treatment are all three criteria for medical treatment. And these were classified into Level 4 group which requires the difficulty and expertise in the final score 4.3. It is necessary to develop and utilize standardized guidelines on the level of knowledge, education, and qualification standards required for dental practice in order to effectively allocate work among the dental personnel while ensuring the health rights of patients in the dental clinic field in Korea. In addition, there is a need to evaluate the various aspects of cost effectiveness, dental health service productivity, and health promotion contribution to dental hygienist jobs, And based on this evidence, it is necessary to continue to expand and adjust the dental hygienist job and to reorganize the dental workforce system.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.6
• /
• pp.70-83
• /
• 2022

This study aims to select evaluation items that can be used in planning park creation to evaluate the proposal to solve the environmental and social problems in promoting private-initiated park development projects. To this end, evaluation items that can consider various aspects of the development project were selected, and the indicators' validity and appropriateness were carried out through an expert Focus Group Interview (FGI). Firstly, an expert FGI was performed for six major categories and 50 evaluation items derived from literature reviews and brainstorming. As a result, five major and 27 middle category items were selected. Based on the derived major and middle classification items, 95 detailed items were selected. Secondly, 55 sub-items were derived through a suitability questionnaire. As a result of the suitability survey, the average scores of the subcategories for the major categories of natural environment, function of parks, and use of land were relatively high. The average scores for environmental index items such as ecology/vegetation, topography and slope, landscape, park service, wildlife, wide-area ecosystem, and park items were high in the middle classification. The average score of indicators in the natural environment was relatively high, and the average score in the function of parks also soared. In the environmental impact assessment, the occurrence of plan change issues, including the reappraisal of the location, led to unclear detailed evaluation factors for the faithfulness of the plan and the appropriateness of the plan direction. This study is significant in that it is a study on the selection of evaluation items that can minimize the problem of plan alteration and achieve objective evaluation when promoting development projects. This study could be used to forward development projects in the future and evaluate long-term unexecuted urban parks.