• Korean Journal of Remote Sensing
• /
• v.36 no.6_3
• /
• pp.1711-1720
• /
• 2020

Particulate matter (PM) that has been artificially generated during the recent of rapid industrialization and urbanization moves and disperses according to weather conditions, and adversely affects the human skin and respiratory systems. The purpose of this study is to predict the PM10 concentration in Seoul using meteorological factors as input dataset for multiple linear regression (MLR), support vector machine (SVM), and random forest (RF) models, and compared and evaluated the performance of the models. First, the PM10 concentration data obtained at 39 air quality monitoring sites (AQMS) in Seoul were divided into training and validation dataset (8:2 ratio). The nine meteorological factors (mean, maximum, and minimum temperature, precipitation, average and maximum wind speed, wind direction, yellow dust, and relative humidity), obtained by the automatic weather system (AWS), were composed to input dataset of models. The coefficients of determination (R2) between the observed PM10 concentration and that predicted by the MLR, SVM, and RF models was 0.260, 0.772, and 0.793, respectively, and the RF model best predicted the PM10 concentration. Among the AQMS used for model validation, Gwanak-gu and Gangnam-daero AQMS are relatively close to AWS, and the SVM and RF models were highly accurate according to the model validations. The Jongno-gu AQMS is relatively far from the AWS, but since PM10 concentration for the two adjacent AQMS were used for model training, both models presented high accuracy. By contrast, Yongsan-gu AQMS was relatively far from AQMS and AWS, both models performed poorly.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.279-286
• /
• 2021

The purpose of this study is to compare the predictive power of the Bagging and Boosting algorithm of ensemble method based on the motion information that occurs in woman handball matches and to analyze the availability of motion information. To this end, this study analyzed the predictive power of the result of 15 practice matches based on inertial motion by analyzing the predictive power of Random Forest and Adaboost algorithms. The results of the study are as follows. First, the prediction rate of the Random Forest algorithm was 66.9 ± 0.1%, and the prediction rate of the Adaboost algorithm was 65.6 ± 1.6%. Second, Random Forest predicted all of the winning results, but none of the losing results. On the other hand, the Adaboost algorithm shows 91.4% prediction of winning and 10.4% prediction of losing. Third, in the verification of the suitability of the algorithm, the Random Forest had no overfitting error, but Adaboost showed an overfitting error. Based on the results of this study, the availability of motion information is high when predicting sports events, and it was confirmed that the Random Forest algorithm was superior to the Adaboost algorithm.

• The Journal of Korean Society for School & Community Health Education
• /
• v.22 no.4
• /
• pp.49-60
• /
• 2021

Objectives: Laboratories have various latent physical, chemical, biological, and ergonomical factors according to the diversification and fusion of research and development activities. This study aims to investigate the chemical exposure concentrations of college laboratories and evaluate their health risks, and use them as basic data to promote the health of college students. Methods: The sampling and analysis of harmful chemicals in the air in laboratories were performed using Method 1500 of the U.S. National Institute for Occupational Safety and Health (NIOSH)의 Method 1500. The harmful chemicals in the laboratories were divided into carcinogenic and non-carcinogenic chemicals. Risk assessment was performed using the cancer risk (CR) for carcinogenic chemicals and using the hazard index (HI) for non-carcinogenic chemicals. Results: The harmful chemicals in college laboratories consisted of acetone, diethyl ether, methylene chloride, n-hexane, ethyl acetate, chloroform, tetrahydrofuran, toluene, and xylenes. They showed the highest concentrations in laboratories A (acetone 0.001~2.34ppm), B (chloroform 0.95~6.35ppm), C (diethyl ether 0.08~8.68ppm), and D (acetone 0.07~14.96ppm). The risk assessment result for non-carcinogenic chemicals showed that the HI of methylene chloride was 2.052 for men and 2.333 for women, the HI of N-hexane was 4.442 for men and 5.05 for women. Thus, the HI values were higher than 1. The risk of carcinogenic chemicals is determined by an excess cancer risk (ECR) value of 1.0×10^-5, which means that one in 100,000 people has a cancer risk. The ECRs of chloroform exceeded 1.0×10^-5 for both men and women, indicating the possibility of cancer risk. Conclusion: College laboratories showed the possibility of non-carcinogenic health risks for methylene chloride, n-hexane, tetrahydrofuran (THF), toluene, and xylenes, and carcinogenic health risks for chloroform, methylene chloride. However, this study used the maximum values of measurements to determine the worst case, and assumed that the subjects were exposed to the corresponding concentrations continuously for 8 hours per day for 300 days per year. In consideration of the nature of laboratory environment in which people are intermittently exposed, rather than continuously, to the chemicals, the results of this study has an element of overestimation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.278-287
• /
• 2021

The purpose of this study is to research how a teaching personality and ethics in teaching affect the competence of students majoring in early childhood education. Questionnaires were distributed to 211 early childhood education students residing in I-city. For this study, frequency analysis, averages, and standard deviation were calculated by using SPSS 22.0, with Cronbach's alpha for the reliability test. To determine the relevance of each variable, correlation analysis and multiple regression analysis were done, with results as follows. First, the teaching personalities perceived most by the students were morality and educational principles. Ethics for infants and ethics for households were most perceived in the ethics of teaching; for competency, understanding of the curriculum, understanding infant protection, and learning support were perceived the most. Second, there is a statistically significant correlation among a teacher's personality, ethics, and competence. Third, the sub-factors of both personality and ethics have a positive effect on competence. The above results indicate that there should be multilateral research into students majoring in early childhood education to ensure they have correct and positive competency so they can provide high-quality early childhood education services, recognizing the importance of competence.

• Journal of Engineering Education Research
• /
• v.24 no.4
• /
• pp.3-20
• /
• 2021

As we have become more interested in 'competency' that means ability to do something around the world, the competency of the best performers has also been introduced in the university curriculum as a concept of core competency. Research continues on why this competency-based education is needed compared to existing academic-oriented education, how it can be introduced into existing curricula, and how it can be developed and evaluated in detail. This study develops and validates core competency assessment tools that can diagnose core competencies of engineering students. Therefore, this research paper conducted a literature review related to core competencies and also core competency assessment tools of university students. It seeks to explore the implications of core competency assessment tools for engineering students and then lay the foundation for competency-based teaching and learning at engineering colleges. And also it defines the concepts of core competencies and each core competency of engineering students through prior research analysis of competence, core competence, and core competence of university students. The primary core competency assessment tool consisted of sub-factors and questions of core competencies. It were modified through the expert validation of the primary one and then it was used as a core competency assessment tools for preliminary investigation. The core competency assessment tools for engineering students are consisted of 6 competencies, 22 sub-factors, and 91 questions. There are core competencies as follows: engineering basic competencies, major engineering competencies, self-management competencies, communication competencies, interpersonal competencies, global competencies. The preliminary survey was conducted on 426 engineering students attending the Engineering Education FESTA 2019. The preliminary findings were derived by conducting exploratory factor analysis, confirmatory factor analysis, question characteristics analysis, and reliability analysis for validation. The core competency assessment tools developed through this study can be used to verify the effectiveness of the curriculum and programs for students at engineering colleges. In addition, the developed core competencies, sub-factors, and questions can be utilized in a series of courses that design, conduct, and evaluate engineering curricula and programs as competency-based curriculum. The significance of this study is to lay the groundwork for providing competency-based education engineering students to develop core competencies.

• Journal of the Korean Chemical Society
• /
• v.66 no.6
• /
• pp.493-508
• /
• 2022

Chemistry is the subject which includes properties, change, and composition of matter. Chemistry has the system which explains observable properties and change with microscopic level, it explains them using scientific theory and laws. In the national-level curriculum, the properties and changes of matter are continuously dealt with from elementary school to high school, and the curriculum are organized so that students could strengthen their understanding about matter. In other words, understanding of the properties and changes of matter is the base to explain everyday life with the view of chemistry, and these two are classified as domains of chemistry in the 2015 revised science curriculum. In this study, we confirmed students' understanding about properties of matter and change of matter, through the analysis about results of the National Assessment of Educational Achievement (NAEA). For that purpose, this study analyzed the 12 items about properties of matter, and 19 items about change of matter, which were used in the NAEA from 2015 to 2019. According to the results of classifying and analyzing questions according to the core concept, the understanding about the two domains significantly changed between the proficient achievement-level students and basic achievement-level students. Depending on the achievement-level, there was a difference in explaining the phenomenon by using the perspective of particles, and by associating scientific concepts and models, or there was a difference in understanding the inquiry related to these two domains. Based on this analysis, this study discussed some implications to be improved on teaching-learning for 'properties of matter', and 'change of matter'.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• Therapeutic Science for Rehabilitation
• /
• v.11 no.3
• /
• pp.81-92
• /
• 2022

Objectives : This study aimed to investigate the effect of beat-keeping games in smartphone applications on improving executive functions in children with developmental delays. Methods : Three children diagnosed with developmental delay were included in this study. The ABA design used a single-subject experimental research design. The independent variable was the beat-keeping game. The game was held three times a week for a total of seven times for 20 minutes, including breaks. The dependent variable, "Visual-motor speed," was measured every session to assess if the beat-keeping game was effective in improving the participant's executive function. Further, before and after the intervention, "Children's Color Trails Test (CCTT)", "Block design," and "Finding hidden picture" were measured. Results : All three participants showed improvement in the performance of the beat-keeping game and the executive functions of "Visual-motor speed" and visual attention. Conclusions : Based on the results of this study, various effective applications for learning and intervention can be developed and applied to children with developmental delays who have difficulty in motivating themselves and lack attention.

• Journal of Korean Home Economics Education Association
• /
• v.33 no.4
• /
• pp.1-13
• /
• 2021

The purpose of this study is to identify trends and potential themes of research on consumption of children and adolescents for 20 years by analyzing keywords. The keywords of 869 studies on consumption of children and adolescents published in journals listed in Korean Citation Index were analyzed using text mining techniques. The most frequent keywords were found in the order of youth, youth consumers, consumer education, conspicuous consumption, consumption behavior, and character. As a result of analyzing the frequency of keywords by dividing into five-year periods, it was confirmed that the frequency of consumer education was significantly higher betwn 2006 and 2010. Research on ethical consumption has been active since 2011, and research has been conducted on various topics instead of without a prominent keyword during the most recent 5-year period. Looking at the keywords based on the TF-IDF, the keywords related to the environment and the Internet were the main keywords between 2001 and 2005. From 2006 to 2010, the TF-IDF values of media use, advertisement education, and Internet items were high. From 2011 to 2015, fair trade, green growth, green consumption, North Korean defector youths, social media, and from 2016 to 2020, text mining, sustainable development education, maker education, and the 2015 revised curriculum appeared as important themes. As a result of topic modeling, eight topics were derived: consumer education, mass media/peer culture, rational consumption, Hallyu/cultural industry, consumer competency, economic education, teaching and learning method, and eco-friendly/ethical consumption. As a result of network analysis, it was found that conspicuous consumption and consumer education are important topics in consumption research of children and adolescents.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.5
• /
• pp.780-790
• /
• 2022

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.