• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.558-572
• /
• 2019

Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.

• ETRI Journal
• /
• v.44 no.6
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• Journal of Digital Convergence
• /
• v.13 no.11
• /
• pp.25-33
• /
• 2015

In Korea, despite the increase in demand for Bigdata manpower, institutions and universities to educate and train Bigdata manpower are not yet much. Therefore, this study investigated the status regarding the recognition on Bigdata of universities students and presented a direction for educating Bigdata manpower at the university. In order to accomplish this purpose, this study surveyed and analyzed the students' understanding of Bigdata, the awareness of the students about the social impact of Bigdata, the learning intention of the students on Bigdata and presented Implications for Bigdata workforce development. As a result, despite of the somewhat difference in understanding for the Bigdata, it was found that their awareness about the impact of Bigdata is very positive. And this study showed the need of universities' and government' political effort for Bigdata workforce development, because it was investigated that students' intentions of learning for Bigdata is proportional to students' understanding levels and learning experience for Bigdata.

• Journal of Convergence for Information Technology
• /
• v.10 no.12
• /
• pp.9-14
• /
• 2020

Currently, NTIS (National Technology Information Service) is building an interactive search service based on artificial intelligence technology. In order to understand users' search intentions and provide R&D information, an interactive search service is built based on deep learning models and morpheme analyzers. The deep learning model learns based on the log data loaded when using NTIS and interactive search services and understands the user's search intention. And it provides task information through step-by-step search. Understanding the search intent makes exception handling easier, and step-by-step search makes it easier and faster to obtain the desired information than integrated search. For future research, it is necessary to expand the range of information provided to users.

• Korean Journal of Health Education and Promotion
• /
• v.13 no.2
• /
• pp.54-68
• /
• 1996

This study aimed at examining the risk factors of smoking behavior among middle school students and preparing school-based smoking prevention program. This study surveyed at February 1995 from 892 students at 3 middle schools in Seoul. The major findings of this study are follows; The proportion of current smoker among students in this study was 3.8%, and the proportion of intentions to smoking was 8.4%. At demographic variables male, pocket money of month was significantly positive association with smoking behavior, but economic status and education status of father were significantly negative association with smoking behavior. Results indicated that social influence variables(peer influence), alcohol, and positive attitudes of smoking were significantly positive association with smoking behavior. So implications for smoking prevention programs may be more effective at risk populations than using general adolescent population. Also ‘School-based smoking prevention programs’ may be learning social pressure resistance skills and giving knowledge and information about negative attitudes about smoking.

• International Journal of Contents
• /
• v.14 no.4
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.19 no.2
• /
• pp.187-198
• /
• 2008

If mentoring is performed in university libraries for mentors, the senior librarians with much experience and mentees, the juniors with less or no experience, how would they respond to it and what would be the mentoring they wish to do? This study aims to find those out by analyzing data. For this, it referred to literature and conducted a survey with the subject of the librarians at the P university library. As a result, they showed relatively higher intentions to participate in mentoring. Their highest interest topics were their job related advice or consultation. For the mentor-mentee matching, they wished to have such relationship from the board organized in the library, or mentees wanted to select. They chose work ability as the most important requirement for their partners involved in the mentoring. They responded that the best mentor-mentee matching would be 1:1 and less than a year would be appropriate for the mentoring period. As shown above, most of the librarians showed intentions to participate in mentoring for their professional development and self-learning opportunity; therefore, university libraries should publicize librarians' mentoring actively and develop various programs for it.

• Journal of Korean Elementary Science Education
• /
• v.40 no.2
• /
• pp.127-144
• /
• 2021

The purpose of this research was to conduct grounded-theory-based explorations on the types of motivation that make pre-service elementary school teachers learn science and on their type-based science-learning processes. One hundred thirty-two pre-service elementary school teachers' motivation types were analyzed, and amongst them, 12 were selected as the subjects to observe their science-learning processes to which grounded theory applied. As a result of analyzing their science-learning motivation types, it was found that the majority belonged to the type "accurators", followed in descending order by the types "directors", "explorers", and "coordinators". Coding various phenomena that appeared in their science-learning processes made it possible to derive 30 categories from them according to the grounded-theory paradigm model elements. Based on such categories derived, analysis could be made on their science-learning process flows by motivation types, according to the grounded-theory paradigm model. For example, the "accurators" were attending science lectures or reading science books to learn science knowledge and how to teach it, from a sense of obligation they took for granted as elementary school teachers. Although their experiences of science-learning processes could not be from pure intentions, due to the teacher certification examination, curriculum, or other environmental factors, they were found to have new perspectives on science with their individual efforts and participations.

• Journal of Technologic Dentistry
• /
• v.35 no.3
• /
• pp.243-257
• /
• 2013

Purpose: This study aims to analyze the factors affecting the dropout intentions of the dental technology students of a college. Methods: The subject of this study was 76 freshmen and 74 sophomores of dental technician major in an anonymous college. Results from the questionnaire called K-vision diagnosis program were computed by means of t-test, One-Way ANOVA, and correlation analysis. Results: 1. Total points of the drop out intention came to 782.14 points. Of the five categories concerned with the drop out intention, complain in college satisfaction(50.12points) was the highest and department satisfaction(47.51points) was the lowest. Of 16 subcategories, complaining in administrative supporting system proved the highest as 50.80 points and Inquiry to Professor the lowest(45.56 points). 2. Among the general characteristic gender (p<. 01), student group (p<.01), and credit (p<.05) made a meaningful statistical difference; no statistical significance was found in grade, admission, and dwellings. 3. Of the five categories, statistical significance was shown as follows; Department satisfaction (p<.01), College satisfaction (p<.05) under gender, Department satisfaction (p<.05) in grade, Academic integration (p<.01), Department satisfaction (p<.01) in credit. No statistical meaning was found in admission and dwellings. 4. Statistical significance was found under 16 subcategories as follows: Career identification(p<.01), Academic support system(p<.01), Social activity II(p<.05) in gender area, Inquiry to professor(p<.01), Learning(p<.05), Understanding learning I(p<.05) in grade area, Learning(p<.001), Career identification(p<.001), Understanding learning I(p<.01), Understanding learning II(p<.01), Inquiry to professor (p<.01), Learning ability (p<.05), Occupation (p<.05), Social Activity II(p<.05), Administrative support system (p<.05) in student group area, Credit (p<.001), Career identification (p<.01), Understanding learning I(p<.05) in credit area; admission and dwellings was statistically meaningless. 5. Of the 5 categories academic integration (r=.766) was most relevant to the dropout intention of the subjects and followed by department satisfaction (r=.735), college satisfaction (r=.554), service acceptability (r=.373), and statistical significance was shown as p<.01. Conclusion: Considering the results of this study, we are in a pressing need for the introduction of policies and programmes aiming at preventing the dropout rates of the dental technician majors at college. In tandem with this, qualitative and viable human resource management of the dental technicians should be implemented.

• Journal of The Korean Association of Information Education
• /
• v.16 no.1
• /
• pp.131-142
• /
• 2012

In this paper, a support plan for marriage immigrants through e-learning was studied. Currently, the number of Korean men marrying foreign women is rapidly increasing due to the increase in the imbalance of gender ratios caused by preference for boys and shunning of rural areas by Korean women. To alleviate this problem, the government is performing various social adaptation programs such as Korean language education and vocational education. Most marriage immigrants, however, are not properly educated as they are burdened by their household duties or work. In this paper, a plan for supporting marriage immigrants through e-learning was researched. To achieve this goal, a survey on intentions of the marriage immigrants to receive muticultural education through e-learning was performed. The result showed that most of marriage immigrants have a strong preference for e-learning. However, there are differences on their preference depending on the original nationality and residential region. A support plan for multicultural education through e-learning was proposed according to the above result. The support plan consists of three parts. First, education for marriage immigrants will be specialized according to their respective original nationality. Second, Korean education will be given greater emphasis in education. Third, vocation education which will benefit marriage immigrants will be prepared. Above support plans are expected to help the marriage immigrants to settle as equal members of the society instead of deteriorating into an underprivileged class by providing them with an opportunity to receive education.