• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.495-509
• /
• 2011

According to the rapid technological development such as ubiquitous environments, there has been growing interest in learning with social media as known as social learning. This study was conducted to analyze various participation types of social media contents aiming to explore strategies for facilitating learning. Specifically, the research model was established by two aspects in using social media contents. First was classified by writings and readings in contents, which consists of prosumers, producers, consumers, and non-participants. Second criterion was categorized by instruction-related and instruction-nonrelated, which is learning contents, learning management, emotional expression, and social activities. In order to acquire empirical data, a set of fourteen undergraduate students participated in this research for eight weeks using a microblog. Based on the analyses on the data through learning activities, three learning strategies were suggested to facilitate social media based learning: analysis on learners, role of the instructor, and instructional model design.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.1008-1018
• /
• 2014

The purpose of this study is to investigate whether there are differences in academic self-efficacy and test anxiety between two groups(depending on gender and English achievement levels) of Korean middle school students. The subjects are 98 students who are 36 male and 62 female students. Two Questionnaires were administered to measure the learners' academic self-efficacy and test anxiety level. And the collected data were analyzed by t-test to examine the differences between two groups. The results of this study showed that there were statistically very significant differences in academic self-efficacy and test anxiety between two(male-female) groups. But there were no differences statistically in academic self-efficacy and test anxiety between two(high level-low level) groups. Further studies need to be conducted carefully considering the limitations of this study in terms of its instruments and subjects. Also the differences in other affective variables between two groups need to be studied in the future.

• Journal of the Korea Convergence Society
• /
• v.11 no.2
• /
• pp.323-330
• /
• 2020

This study is to identify the types and meaning of 'Good Leisure' that married immigrant women perceived. 32 Q samples were extracted from the interviews and questions and 40 immigrant women were selected as P samples. The conclusion are as follows; First, the types of 'Good Leisure' were classified as 4 types. Second, the type 1, 'Psychological Stability Pursue Type' recognizes 'Good Leisure' when they feel comfort and relaxed through activities. The type 2, 'Emotional Stability and Self-development Type' recognized 'Good Leisure' when they are pleased, or engaged in self-development activities. The type 3, 'Practical Use Pursue and Information Acquisition Type', recognizes 'Good Leisure' when they learn things necessary for living with less cost, and type 4, 'Acculturation and Exchange Type' recognizes 'Good Leisure' when they learn Korean culture or interact with Korean people. Third, regardless of each type, married immigrant women perceived in having a good time with people as 'Good Leisure'.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.415-424
• /
• 2021

The life of studying abroad includes not only school life, but also various areas such as economy, social relationship, and culture, so the level of satisfaction in each area could be differently shown in each individual. Based on this critical mind, this study aims to analyze the satisfaction with life of studying abroad in the multidimensional perspective. To analyze this, a latent class analysis was applied to identify subgroups, and a multinomial logistic regression model was applied to verify factors influencing group classification. The results of the analysis could be summarized into two. First, there were sub-groups showing different satisfaction with life of studying abroad. The sub-groups showed different levels of satisfaction in five areas such as housing, economy, social relationship, study, and culture, which were not discerned in single dimension. Second, the classification of group was complexly influenced by academic factor, psychological/emotional factor, and environmental factor. Especially, the predictive factor had different influences on each sub-factor. Based on such results of this study, this study aims to seek for the practical and policy-level suggestions for improving foreign students' satisfaction with life of studying abroad.

• Korean Journal of Culture and Social Issue
• /
• v.25 no.3
• /
• pp.203-229
• /
• 2019

The purpose of this study was to identify the factors that constitute masculine norms of masculine in Korean society. The definition of masculinity was to conform to the male-dominated standard formed socially and culturally. The results of in-depth interviews with 20 male participants were used for a concept mapping analysis to explore the configural representations of Korean masculine norms. After extracting the key sentences related to masculine norms, the participants sorted the 55 key sentences based on similarities and assessed the importance, which was then analyzed with multidimensional scaling method and cluster analysis. The result showed two dimensions, one representing social-personal domain and the other implying dominance-support domain as well as six clusters of caregiver, leadership, emotion suppression, job ability and organizational social adaptation, Expects the masculine abilities, power and control. Finally, the implications of this study, limitations, and the suggestions for future research were discussed.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.968-975
• /
• 2023

Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.

• Journal of Science Education
• /
• v.45 no.2
• /
• pp.187-200
• /
• 2021

This study was conducted to identify students' meaningful scientific experiences and to ascertain the path through which the experience led to learning. The subjects of 'Understanding of the History of Science' were asked to write an essay on the subject of 'Effects of science on my life' to 81 students in the department of literature and 125 students in the science department. After that Classification criteria were established through scientific experts' seminars, and the scientific experiences that affected students and their effects were examined. The results from analyses were summarized as follows: First, As a result of study about Science Education experience that has impacted students' lives, the students were influenced by images, most of which were influenced by scientific videos. They were also influenced by science classes and science books. As a result of classifying science experience, most of the experience is composed of Informal Science Learning. Second, as a result of examining how students were influenced by their scientific experience, they found that they were affected by their daily life or influenced by science. As a result of the research, it can be confirmed that Informal Science Learning experience is an important learning form that has a great influence on students. Therefore, appropriate Informal Science Learning experience should be introduced into the class, and research and development on the Informal Science Learning experience preferred by the students should be done.

• Korean Journal of School Psychology
• /
• v.16 no.3
• /
• pp.315-337
• /
• 2019

This study was intended to verify that the Revised PAI-A scale reflected the internalization and externalization classification of adolescence problem behavior. For this purpose, exploratory factor analysis and confirmatory factor analysis were conducted using PAI-A restandardization data. In addition, 31 Revised PAI-A sub-scales and SUI scale were used to identify the detailed factor structures. As a result of the analysis, the classification of internalization and externalization factors was similar to that of previous studies. In detail, the sub-scales of ANX·DEP and SUI were classified into internalization, the sub-scales of ANT and AGG were classified into externalization. It is noteworthy that each sub-scale of PAI-A was separated into internalization or externalization. For example, BOR-A, BOR-I, and BOR-N were loaded into internalization, but BOR-S into externalization. Next, in order to confirm whether the structure of the derived internalization and externalization factors can be applied to new samples, 350 samples were randomly extracted and confirmatory factor analysis was conducted, but exclusive of the samples used for exploratory factor analysis. As a result of confirmatory factor analysis, the appropriate indices of internalization and externalization classification was close to the good level. Therefore, the Revised PAI-A scales have theoretical relevance to internalization and externalization classification of problem behaviors. Based on the results of this study, it is expected that it can be used helpfully in the school settings in the future. Finally, the significance and limitations of this study were discussed.

• Journal of Digital Contents Society
• /
• v.15 no.3
• /
• pp.387-393
• /
• 2014

This study investigates the worlds most favorite SNS, the Facebook, with the theory of Empathy, that there will be an effect to users due to their characteristics. We approach the data scientifically with using an Eye tracker, by analyzing the vision and attention of users of Facebook with stimuli of whether it's an image or text filled contents in newsfeed of Facebook. With the result of an eye tracker, we cross analyzed with General Empathy Scale to compare that users limit of feeling of empathy gave effect on contents of Facebook. Discussion and implications are discussed in terms of empathy.