• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1255-1263
• /
• 2021

While it could become an alternative water resource, fog could undermine traffic safety and operational performance of infrastructures. To reduce such adverse impacts, it is necessary to have spatially continuous fog risk information. In this work, tree-based machine-learning models were developed in order to quantify fog risks with routine meteorological observations alone. The Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), and Random Forests (RF) were chosen for the regional fog models using operational weather and visibility observations within the Jeollabuk-do province. Results showed that RF seemed to show the most robust performance to categorize between fog and non-fog situations during the training and evaluation period of 2017-2019. While the LGB performed better than in predicting fog occurrences than the others, its false alarm ratio was the highest (0.695) among the three models. The predictability of the three models considerably declined when applying them for an independent period of 2020, potentially due to the distinctively enhanced air quality in the year under the global lockdown. Nonetheless, even in 2020, the three models were all able to produce fog risk information consistent with the spatial variation of observed fog occurrences. This work suggests that the tree-based machine learning models could be used as tools to find locations with relatively high fog risks.

• Journal of Korean Society of Forest Science
• /
• v.110 no.4
• /
• pp.610-621
• /
• 2021

The soil creep, primarily caused by earthquakes and torrential rainfall events, has widely occurred across the country. The Korea Forest Service attempted to quantify the soil creep susceptible areas using a discriminant value table to prevent or mitigate casualties and/or property damages in advance. With the advent of advanced computer technologies, machine learning-based classification models have been employed for managing mountainous disasters, such as landslides and debris flows. This study aims to quantify the soil creep susceptibility using several classifiers, namely the k-Nearest Neighbor (k-NN), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM) models. To develop the classification models, we downscaled 292 data from 4,618 field survey data. About 70% of the selected data were used for training, with the remaining 30% used for model testing. The developed models have the classification accuracy of 0.727 for k-NN, 0.750 for NB, 0.807 for RF, and 0.750 for SVM against test datasets representing 30% of the total data. Furthermore, we estimated Cohen's Kappa index as 0.534, 0.580, 0.673, and 0.585, with AUC values of 0.872, 0.912, 0.943, and 0.834, respectively. The machine learning-based classifications for soil creep susceptibility were RF, NB, SVM, and k-NN in that order. Our findings indicate that the machine learning classifiers can provide valuable information in establishing and implementing natural disaster management plans in mountainous areas.

• The Journal of the Korea Contents Association
• /
• v.21 no.7
• /
• pp.222-237
• /
• 2021

The purpose of this study is to develop an ACT group counseling program for the purpose of alleviating and healing the job stress and burnout of nursing care workers and to verify the effectiveness of the ACT group counseling program. To this end, the goal and theoretical model, content, operation and evaluation of the program were composed and applied according to the procedure. The main research results are as follows. First, as a result of measuring the job stress of the study subjects, there was a positive change in the group participating in the program. Second, as a result of measuring the level of job burnout of the study subjects, there was a positive change in the group participating in the program. Third, as a result of measuring the level of role conflict of the study subjects, there was a positive change in the group participating in the program. Fourth, as a result of measuring the level of over-role of the study subjects, there was a positive change in the group participating in the program. Fifth, as a result of measuring the level of role ambiguity of the study subjects, there was a positive change in the group participating in the program. As a practical implication, by including the ACT theory and practice plan in various nursing care providers training courses, the ability to respond to job burnout and job stress is increased, and ultimately, by increasing the psychological flexibility of nursing care workers, the opportunity for essential change in attitude toward work and life describe what to provide.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.85-92
• /
• 2019

A 3D virtual character playing a role in a digital story-telling has a unique style in its appearance and motion. Because the style reflects the unique personality of the character, it is very important to preserve the style and keep its consistency. However, when the character's motion is directly controlled by a user's motion who is wearing motion sensors, the unique style can be discarded. We present a novel character motion control method that uses only a small amount of animation data created only for the character to preserve the style of the character motion. Instead of machine learning approaches requiring a large amount of training data, we suggest a search-based method, which directly searches the most similar character pose from the animation data to the current user's pose. To show the usability of our method, we conducted our experiments with a character model and its animation data created by an expert designer for a virtual reality game. To prove that our method preserves well the original motion style of the character, we compared our result with the result obtained by using general human motion capture data. In addition, to show the scalability of our method, we presented experimental results with different numbers of motion sensors.

• Journal of the Society of Disaster Information
• /
• v.15 no.2
• /
• pp.223-238
• /
• 2019

Purpose: This study aims at exploring implications of discourse and social practice produced by various stakeholders in politics, economy and society to provide useful material for effective disaster response in South Korea. Method: Applying the Critical Discourse Analysis model of Fairclough, this study analyzes the newspaper articles of three domestic press companies mainly about the November 2017 Pohang earthquake. Results: As a result, first, the three media companies point out the low effectiveness of disaster response manuals and evacuation training. Second, strengthening shelter services and expanding support for the victims are important for recovery from the earthquake. Third, to prevent the future damages, they suggest the implementation efforts to improve the seismic design and short message service based disaster alert system. Conclusion: Based on the findings, this study suggests to improve the practicality and effectiveness of disaster prevention measures, establish an organic and integrated disaster response system, emphasize the roles and participation of citizens, check the responsibility of experts, and make the media to form sound discourse on disaster response.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.6
• /
• pp.67-77
• /
• 2018

Currently, there are many problems due to the decline in school-age population. Moreover, Korea has the largest number of universities compared to the population, and the university enrollment rate is also the highest in the world. As a result, the minimum student retention rate required for the survival of each university is becoming increasingly important. The purpose of this study was to examine the effects of reducing the number of graduates of education and the social climate that prioritizes employment. And to determine what the basic direction is for students to manage the student retention rate, which can be maintained from admission to graduation, to determine the optimal input variables, Based on the input parameters, we will make associative analysis using apriori algorithm to collect training data that is most suitable for maintenance rate management and make base data for development of the most efficient Deep Learning module based on it. The accuracy of Deep Learning was 75%, which is a measure of graduation using decision trees. In decision tree, factors that determine whether to graduate are graduated from general high school and students who are female and high in residence in urban area have high probability of graduation. As a result, the Deep Learning module developed rather than the decision tree was identified as a model for evaluating the graduation of students more efficiently.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.394-403
• /
• 2019

This research focuses on the perception of security screeners using a full body scanner at airport which had been newly introduced to terminal 2 of Incheon Int'l airport. To accomplish the purpose of research, this paper used UTAUT (Unified Theory of Acceptance and Use of Technology) model. Through an empirical analysis, it was proven the factors consisting of technological acceptance and how those factors affect both organizational innovation at airport and job satisfaction of security screeners. According to an empirical analysis, it was found out all the factors of technological acceptance have a significant effect on both organizational innovation and job satisfaction. However, only the effort expectation was shown to have a significant negative effect on the two dependant variables contrary to the other variables (performance expectation, behavioral intention and self efficacy. It was also proven organizational innovation had a moderating effect between technological acceptance and job satisfaction. Such results suggested organizational innovation at airport security division is necessary to enhance job satisfaction using a newly introduced full body scanner.

• Journal of vocational education research
• /
• v.37 no.5
• /
• pp.1-23
• /
• 2018

The purpose of this study was to explore the direction of school system reorganization in order to strengthen the educational competitiveness of Meister high school. Specifically, the first one was to review prior research related to the school system reorganization of vocational education at the secondary level, and to propose school system reorganization plans of Meister high school. And second one was to analyze the perceptions of related parties about this reorganization plans and to derive important implications. The results of this study were as follows. First, based on the results of the analysis of precedent research, school system reorganization plans of Meister high school was composed of (1) introduction of credit system, (2) introduction of 3-semester system, and (3) expansion of school year. Second, as a result of the questionnaire survey conducted by 138 Meister high school teachers and 185 Meister high school graduates, both group seemed to agree on the necessity of school system reorganization of Meister high school. In addition, the necessity of introducing the proposed reorganization plans was more than a certain level, but the applicability was recognized as somewhat lower than the necessity of introduction. Third, the results of the FGI analysis on industrial personnel showed a positive response, especially regarding the operation of advanced course due to the expansion of school year. Based on this results, it was proposed to design a more systematic reorganization model and provide policy support, to examine the whole scale expansion through pilot application, and to collect opinions more systematically from industrial field experts on school system reorganization plans.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.37-45
• /
• 2019

In recent years, the emergence of virtual reality (VR Virtual Reality) technology has provided a new model of safety education, enabling users to learn and respond to disasters in a virtual safety education environment. However, the related VR products related to domestic and foreign R & D are relatively simple, there is no practical training on specific accident, and it is not practical enough to play a sufficient role in safety education. In this paper, the problems and disadvantages of VR technology applied in the field of automobile safety education as an example of automobile accident among the types of disasters are examined, and a system framework of automotive safety education based on VR technology is proposed. The vehicle safety education system proposed in this paper will help users to improve driving safety consciousness, to acquire safety knowledge in driving, and to acquire driving safety skill which is very important for automobile safety education. In addition, the design and production methods of safety education based on VR technology are considered to have important reference implications for the application of modern teaching and teaching theory by integrating with VR technology and developing related teaching materials products and finally introducing education.