• The Journal of the Korea Contents Association
• /
• v.21 no.5
• /
• pp.941-948
• /
• 2021

This study investigated the differences between active and inactive TV watching groups, in terms of residential characteristics, of class-oriented drama viewing rate. We compared Flow and Social Comparison Theories to explain the relationship between class-oriented contents in the drama and viewing rate. We collected 110,000 TV viewers data of 4 class-oriented and the other 4 dramas, aired between Feb. 2016 and March 2019, through D-Live local cable service provider. Controlling gender ratio and income level which may affect viewing rate, we found that class-oriented content significantly and positively affects viewing rate in active watching group while the same content significantly and negatively affects viewing rate in inactive watching group. These results imply that Flow and Social Comparison Theories may apply in opposite directions in different watching groups.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.517-525
• /
• 2022

In the era of big data, various data mining techniques have been proposed as major analysis methodologies. As complex and diverse data is mass-produced, data mining techniques have attracted attention as a method that forms the foundation of data science. In this paper, we focused on the decision tree, which is frequently used in practice and easy to understand as one of representative data mining methods. Specifically, we analyzed the effect of the splitting method of decision trees on the model performance. We compared the prediction power and structures of decision tree models with different split methods based on various simulated data. The results show that the linear combination split method can improve the prediction accuracy of decision trees in the case of data simulated from nonlinear models with complex structure.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2022

Objectives: The purpose of this study is to evaluate exposure characteristics of lead using data from the domestic occupational exposure literature. Methods: Occupational airborne exposure data on lead reported in the domestic literature from 1981 to 2018 were collected and re-analyzed. The exposure levels in the data were expressed as an estimated arithmetic mean and a weighted arithmetic mean (WAM) of the number of samples. Lead exposure characteristics were analyzed by industry, process, and year. Results: From a total of 14 documents, 8,305 airborne lead measurements for 17 industries were identified, and the WAM concentration in eight industries exceeded the occupational exposure limit of 50 ㎍/m³. Three industries (battery manufacturing, lead smelting, and litharge manufacturing) accounted for 95% of the total data, and exposure trends could be confirmed over 10 years. Exposure levels continue to decrease in all three industries. Conclusions: Considering the distribution outlook of lead and lead compounds, the main management targets are lead storage battery manufacturing and secondary smelting for lead regeneration.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.415-424
• /
• 2022

This study is a user experience research on the current usage of TV multiview and evaluating the usability. From traditional TV viewing to connecting laptop or mobile devices, the scope of using TV has expanded and evolved to multipurpose. Utilizing the multiview feature offers new TV experiences, but research on its usability has not been actively conducted yet. In this research, a case study and survey were held prior to usability testing to identify user needs and behavior of TV multiview. After reviewing the results, we ran a task-based usability testing and in-depth interview. As a result, users preferred different ways of accessing and using multiview based on their situation, and the current user interface needed improvement for easier, intuitive use. This study is expected to contribute to the development of improving user experience in TV multiview.

• Industry Promotion Research
• /
• v.7 no.4
• /
• pp.1-8
• /
• 2022

There are many one-shot devices that are used once and thrown away. One-shot devices such as firecrackers and ammunition are typical, and they are stored for a while after manufacture and then disposed of after use when necessary. However, unlike general operating systems, these one-shot devices have not been properly evaluated. This study first examines what the government does to secure reliability in the case of ammunition through ammunition stockpile reliability program. Next, in terms of statistical analysis, we show what the reliability analysis methods are for one-shot devices such as ammunition. Specifically, we show that it is possible to know the level of reliability if sampling inspection plan such as KS Q 0001 which is acceptance sampling plan by attributes is used. Next, non-parametric and parametric methods are introduced as ways to determine the storage reliability of ammunition. Among non-parametric methods, Kaplan-Meier method can be used since it can also handle censored data. Among parametric methods, Weibull distribution can be used to determine the storage reliability of ammunition.

• Industry Promotion Research
• /
• v.7 no.1
• /
• pp.1-8
• /
• 2022

We investigated various types of machine learning methods that can be applied to censored data. Exploratory data analysis reveals the distribution of each feature, relationships among features. Next, classification problem has been set up where the dependent variable is death_event while the rest of the features are independent variables. After applying various machine learning methods to the data, it has been found that just like many other reports from the artificial intelligence arena random forest performs better than logistic regression. But recently well performed artificial neural network and gradient boost do not perform as expected due to the lack of data. Finally Kaplan-Meier and Cox proportional hazard model have been employed to explore the relationship of the dependent variable (t_i, δ_i) with the independent variables. Also random forest which is used in machine learning has been applied to the survival analysis with censored data.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.473-478
• /
• 2022

Evaluation learning based on code testing is becoming a popular solution in programming education via Online judge(OJ). In the recent past, many papers have been published on how to detect plagiarism through source code similarity analysis to support OJ. However, deep learning-based research to support automated tutoring is insufficient. In this paper, we propose Input & Output side FiLM models to predict whether the input code will pass or fail. By applying Feature-wise Linear Modulation(FiLM) technique to GRU, our model can learn combined information of Java byte codes and problem information that it tries to solve. On experimental design, a balanced sampling technique was applied to evenly distribute the data due to the occurrence of asymmetry in data collected by OJ. Among the proposed models, the Input Side FiLM model showed the highest performance of 73.63%. Based on result, it has been shown that students can check whether their codes will pass or fail before receiving the OJ evaluation which could provide basic feedback for improvements.

• The Korean Journal of Applied Statistics
• /
• v.36 no.4
• /
• pp.337-347
• /
• 2023

Sampling designs often use stratified sampling, where elements or clusters of the study population are divided into strata and an independent sample is chosen from each stratum. The stratification strategy consists of stratification and sample allocation, which are important issues that are repeatedly considered in survey sampling. Although a stratified multistage sample design is often used in practice, the literature tends to discuss simple sampling in terms of stratum effects or stratum efficiency. This study examines an existing stratum efficiency measure for two-stage sampling and further proposes additional stratum efficiency measures using the design effect model. The proposed measures are used to evaluate the stratification strategy of the sample design for high school students of the 4^th Korean National Environmental Health Survey (KoNEHS).

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.6D
• /
• pp.703-709
• /
• 2009

This article analyzes the obtained data on consciousness survey of disabled and non-disabled pedestrians, and proposes fundamental data for public strategy in order to enhance facilities in subway stations in advance. This paper conduct literature review, new listing survey related to 'The Code for Improvement of Convenience for Moving Vulnerable Pedestrians', and Modified-Importance-Performance Analysis (M-IPA). The results show that disabled pedestrians want enhancement in information facilities as a whole. In addition, the results show that several improvements needs to be applied to accessible sidewalk, to informative notification, to alarm and evacuation system and to toilet for disabled pedestrians. This indicates that disabled pedestrians heavily concentrate on accessibility to subway station and provided information compared with disabled pedestrians.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.125-135
• /
• 2022

The number of domestic users of OTT services is gradually increasing, and users can consume content more freely through OTT services that can consume content in various ways unlike existing broadcasting systems. As the service utilization rate increases and consumption patterns diversify, useful and convenient UI design and usability should be considered from the user's point of view, but research on the app UI design of OTT service is still insufficient. Therefore, in this study, UI design components were compared and analyzed for the top five mobile apps in Korea's OTT platform utilization rate, and usability evaluation was conducted through surveys and in-depth interviews with 10 people in their 20s. Based on the analysis results, the direction of improvement of OTT service mobile apps in the future was presented, and the results of this study are expected to be used as basic data for improving UI design and usability of OTT mobile apps in the future.