• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.59-76
• /
• 2023

Since the COVID-19 era, the rise in apartment prices has been unconventional. In this uncertain real estate market, price prediction research is very important. In this paper, a model is created to predict the actual transaction price of future apartments after building a vast data set of 870,000 from 2015 to 2020 through data collection and crawling on various real estate sites and collecting as many variables as possible. This study first solved the multicollinearity problem by removing and combining variables. After that, a total of five variable selection algorithms were used to extract meaningful independent variables, such as Forward Selection, Backward Elimination, Stepwise Selection, L1 Regulation, and Principal Component Analysis(PCA). In addition, a total of four machine learning and deep learning algorithms were used for deep neural network(DNN), XGBoost, CatBoost, and Linear Regression to learn the model after hyperparameter optimization and compare predictive power between models. In the additional experiment, the experiment was conducted while changing the number of nodes and layers of the DNN to find the most appropriate number of nodes and layers. In conclusion, as a model with the best performance, the actual transaction price of apartments in 2021 was predicted and compared with the actual data in 2021. Through this, I am confident that machine learning and deep learning will help investors make the right decisions when purchasing homes in various economic situations.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.27-40
• /
• 2023

With the increase in the spread of smart devices and the impact of COVID-19, the consumption of media contents through smart devices has significantly increased. Along with this trend, the amount of media contents viewed through OTT platforms is increasing, that makes contents recommendations on these platforms more important. Previous contents-based recommendation researches have mostly utilized metadata that describes the characteristics of the contents, with a shortage of researches that utilize the contents' own descriptive metadata. In this paper, various text data including titles and synopses that describe the contents were used to recommend similar contents. KLUE-RoBERTa-large, a Korean language model with excellent performance, was used to train the model on the text data. A dataset of over 20,000 contents metadata including titles, synopses, composite genres, directors, actors, and hash tags information was used as training data. To enter the various text features into the language model, the features were concatenated using special tokens that indicate each feature. The test set was designed to promote the relative and objective nature of the model's similarity classification ability by using the three contents comparison method and applying multiple inspections to label the test set. Genres classification and hash tag classification prediction tasks were used to fine-tune the embeddings for the contents meta text data. As a result, the hash tag classification model showed an accuracy of over 90% based on the similarity test set, which was more than 9% better than the baseline language model. Through hash tag classification training, it was found that the language model's ability to classify similar contents was improved, which demonstrated the value of using a language model for the contents-based filtering.

• Journal of Korean Society on Water Environment
• /
• v.39 no.3
• /
• pp.231-239
• /
• 2023

Public sewage treatment facilities are a necessary infrastructure for public health that treat sewage generated in cities and basin living areas and discharge it into rivers or seas. Recently, the role of public sewage treatment is receiving attention as a place of use of wastewater-based epidemiology (WBE), which analyzes human specific metabolic emissions or biomarkers present in sewage to investigate the environment to which the population is exposed in the water drain. WBE is mainly applied to investigate legal and water-law drug use or to predict and analyze the lifestyle of local residents. WBE has also been applied to predict and analyze the degree of infectious diseases that are prevalent worldwide, such as COVID-19. Since sewage flowing into public sewage treatment facilities includes living information of the population living in the drainage area, it is easy to collect basic data to predict the confirmation and spread of infectious diseases. Therefore, it is necessary to establish a new role of public sewage treatment facilities as an infrastructure necessary for WBE that can obtain information on the confirmation and spread of infectious diseases other than the traditional role of public sewage treatment. In South Korea, the sewerage supply rate is about 95.5% and the number of public sewage treatment facility is 4,209. This means that the infrastructure of sewerage is fully established. However, to successfully drive for WBE , research on monitoring and big-data analysis is needed.

• Journal of the Korean Applied Science and Technology
• /
• v.40 no.1
• /
• pp.113-122
• /
• 2023

This study attempted to investigate the effects of experience of non-contact lectures on learning flow against college students majoring in cosmetology and provide basic data to beauty education industry in the with-COVID-19 era. For this, a self-administered questionnaire survey was performed against 300 college students majoring in cosmetology from June 7 to 21, 2022. A total of 286 copies were collected and used for final analysis. The collected data were analyzed by frequency analysis, factor analysis, exploratory factor analysis, descriptive statistics, correlation analysis and multiple regression analysis, using SPSS 21.0, and the results found the followings: According to analysis of non-contact lecture experience factors, two course satisfaction factors were obtained. In learning flow, learning pleasure and learning flow were found. Specifically, class activities had a positive influence on 'learning pleasure (𝛽=.279, p<.007)' and 'learning flow (𝛽=.221, p<.031)' with statistical significance (p<.05). In addition, course satisfaction revealed a positive effect on 'learning flow (𝛽=.223, p<.041)' with statistical significance (p<.05). The above results confirm that experience of non-contact lectures affects learning flow. Therefore, it is anticipated that there would be more efforts to seek an efficient non-contact learning plan in this new era.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.3
• /
• pp.191-210
• /
• 2023

The purpose of this study is to draw implications through domestic and international best case studies of library programs, and to suggest ways to improve a public library reading programs through analysis based on the 3rd Reading Culture Promotion Basic Plan in line with the changing role of future libraries. there is To this end, first, prior studies were analyzed from various angles to derive clustering standards for library programs. Based on this, programs of various domestic and foreign libraries were analyzed based on clustering criteria. And based on the clustering criteria of library programs and the 13 key tasks under the 4 strategies of the 3rd Reading Culture Promotion Basic Plan, the status of a specific public library reading programs was analyzed. Through this, in consideration of the demand of users in the era of the 4th Industrial Revolution, participatory reading promotion programs are expanded, and in response to the post-COVID-19 era, beyond face-to-face library services, non-face-to-face and non-contact library services are also considered. A development plan was presented. It is expected that this analysis and application attempt will ultimately go beyond the unit library and contribute to improving the public library service in Korea into a library program closely related to the lives of users.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.75-91
• /
• 2023

As the business-to-customer (B2C) online market expands after the COVID-19 pandemic, the logistics industry has been constructing automated warehouses to handle multi-product, low-volume logistics. When constructing a logistics automation warehouse, it is crucial to validate that the facility's performance and operational logic are designed to meet the required throughput of the automated warehouse from the system design phase. This study proposes simulation-based validation and optimal alternatives for an H logistics automation warehouse in Iksan, Jeollabuk-do. Firstly, we focused on the box supply and packing processes, which are related to the release process, among the entire logistic processes. Then, we analyzed the potential bottlenecks in the target process and designed and implemented a discrete-event simulation model based on the analysis results. The simulation experiments showed that the facility parameters and operational logic identified in the system design phase did not satisfy the performance requirements of the entire automated warehouse. Additional experiments were conducted to suggest alternatives to meet the system performance requirements by changing the facility parameters and operational logic. We expect that the proposed study will be utilized in the future, not only in the system design phase but also in the system construction phase, for verification purposes to ensure that the construction proceeds according to the design.

• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.62-67
• /
• 2023

Due to the prolonged impact of COVID-19, the demand for Information Technology (IT) products is increasing, and their production facilities are expanded. Consequently, the use of harmful and dangerous chemicals are increased, the risk of fire(s) and explosion(s) is also elevated. In order to mitigate these risks, the government sets standards, such as KS C IEC 60079-10-1, and manages explosion-prone hazardous facilities where flammable substances are manufactured, used, and handled. However, using the standards of KS, it is difficult to predict the actual possibility of an explosion in a facility, because ventilation (an important factor) is not considered when setting up a hazardous work environment. In this study, the SEMI S6, Tracer Gas Test was applied to the chemical vapor deposition (CVD) facility, a major part of the display industry, to evaluate ventilation performance and to confirm the possibility of creating a less explosive environment. Based on the results, it was confirmed that the ventilation performance in the assumed scenarios met the standards stipulated in SEMI S6, along with supporting the possibility of creating a less explosive working condition. Therefore, it is recommended to use the prediction tool using engineering techniques, as well as KS standards, in such hazardous environments to prevent accidents and/or reduce economic burden following accidents.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.115-122
• /
• 2022

With the outbreak of COVID-19 a few years ago, video conferencing and electronic document work have increased, and for this reason, the proportion of computer work among modern people's daily routines is increasing. However, as more and more people work on computers in the wrong posture for a long time, the number of patients with poor eyesight and text neck is increasing. Until recently, many studies have been published to correct posture, but most of them have limitations that users may experience discomfort because they have to correct posture by wearing equipment. A posture correction sensor algorithm is proposed to prevent access to the minimum distance between a computer monitor and a person using an ultrasonic sensor device. At this time, an algorithm for minimizing false alarms among warning alarms that sound at the minimum distance is also proposed. Because the ultrasonic sensor device is used, posture correction can be performed without attaching a device to the body, and the user can relieve discomfort. In addition, experimental results showed that accuracy can be improved by reducing false alarms by removing more than half of the noise generated during distance measurement.

• Physical Therapy Korea
• /
• v.30 no.1
• /
• pp.50-58
• /
• 2023

Background: This study was carried out to determine whether non-face-to-face physical therapy would have similar exercise effects to face-to-face physical therapy. Hence, we developed an approach for patients, unable to visit hospitals due to circumstances such as the COVID-19 pandemic, to conduct physical therapy comfortably at home. Objects: This study aimed to compare the effects of a face-to-face and a non-face-to-face physical therapy treatment on improving a rounded shoulder posture. Methods: The participants with rounded shoulders were randomly divided into a face-toface group (n = 15) and a non-face-to-face group (n = 15), and each group performed exercises for four weeks. The exercise program consisted of the bare hands exercise, Thera-Band exercise, and foam roller exercise. The participants in the face-to-face group came to a designated place to perform their exercises, and those in the non-face-to-face group performed the exercises at their own home using Google Meet (Google). Acromial height, total scapular distance (TSD), shoulder pain and dysfunction index (SPADI), and pectoralis minor thickness were measured. Data analysis was performed using the R Statistical Software (R Core Team), and a normality test was performed using the Shapiro-Wilk test. Results: There were no significant differences between the face-to-face and the non-face-toface groups (p > 0.05). When comparing the differences before and after the exercises, both the face-to-face and the non-face-to-face groups showed significant differences in acromial height, SPADI, and pectoralis minor thickness (p < 0.05), and both groups showed no significant difference in TSD before and after the exercises (p > 0.05). Conclusion: The results of this study support the results of previous studies reporting that shoulder stabilization exercise and pectoralis minor stretching training improves round shoulders. In addition, this study revealed that both the face-to-face and the non-face-to-face physical therapy treatments had therapeutic effects.

• Journal of Korea Trade
• /
• v.26 no.6
• /
• pp.20-40
• /
• 2022

Purpose - In recent times, the international trade environment has been changing rapidly, centering on the online market. In the post-COVID-19 era, small and medium-sized trading companies are facing the problem of not being properly provided with overseas market research, market trend analysis, and trade-related information. Cloud-based digital trade is being sought as an alternative to solve these problems; however, there is a lack of research on the intention to switch to digital trade among small and medium-sized trading companies. Therefore, this study empirically analyzes the intention to switch to digital trade based on the migration theory, and through this, attempts to identify each factor that affects the intention to switch to digital trade. Design/methodology - In this study, in order to identify factors influencing intention to switch to digital trade and innovation resistance of small and medium-sized trading companies, through previous research on migration theory and the PPM (Push, Pull, Mooring) model, each variable was selected for the purpose of the study. Based on this, a research model was established for the factors affecting switching to digital trade of small and medium-sized trading companies and empirically analyzed. In addition, considering the differences in the innovation propensity and maturity of information infrastructure of trading companies as the recipients of innovation, this study analyzes the moderating effect of the mooring effect and seeks ways to establish specific strategies according to the degree. Findings - As a result of empirical analysis, the pull effect was found to have the greatest influence on intention to switch to digital trade. However, the pull factor was found to have an effect on user resistance, and it was confirmed that it was a factor simultaneously inducing positive and negative consumption behaviors among users. In addition, it was found that the higher the company's innovation propensity, the higher the pull effect's influence on the intention to switch, and analysis showed that the push effect had no influence. In addition, companies with high information infrastructure maturity were expected to have a relatively high level of intention to switch compared to companies with low information infrastructure maturity, and the difference between the two groups was found not to be statistically significant. Originality/value - This study is a timely study in that it demonstrated the effect on the switching to cloud-based digital trade for small and medium-sized trading companies and that the cloud system related to digital trade is in full swing. There are academic implications in that it revealed that the pull effect is an important factor in the intention to switch to cloud service. Practical implications were presented in that small and medium-sized trading companies suggested ways to increase the value of the cloud system for switching to digital trade and a way to increase the switching ratio by minimizing the mooring effect. In addition, the study argues that active institutional support from the government is needed to activate cloud service.