• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.11-19
• /
• 2021

An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.267-297
• /
• 2017

This paper attempts a close-reading of Michel Ocelot's short animation film, (1979), and proposes it as an available text in art appreciation class for young students. stimulates the students' attention and intellectual curiosity thanks to the exotic and fantastic atmosphere, beautiful mise en scene, and intriguing plot. Ocelot's technique of decoupage used in this film rejuvenates both the traditional folk art and Lotte Reiniger's early experiments in the history of animation film. Ocelot subverts the ideal of modern male adult subject as unique possessor of scientific knowledge and technology, by adopting a female figure and a young child, who is also female, as main characters. The imaginative and subversive power of animation contributes to creating posthuman beings beyond the homocentric figure of Vitruvian Man. The posthuman condition supposes that human beings have the equal relationship of continuum with not only other humans but also non-human beings like all living things and inanimate matters. In order to teach and learn the posthuman condition, it is necessary to conceive an interdisciplinary and integrated curriculum including art, science, philosophy, history, and social sciences. Animation film serves excellently as educational text for the integrated curriculum of the posthuman.

• Korean Chemical Engineering Research
• /
• v.48 no.4
• /
• pp.483-489
• /
• 2010

An image analysis-based soft sensor is designed and applied to automatic quality classification of product appearance with color-textural characteristics. In this work, multiresolutional multivariate image analysis (MR-MIA) is used in order to analyze product images with color as well as texture. Fisher's discriminant analysis (FDA) is also used as a supervised learning method for automatic classification. The use of FDA, one of latent variable methods, enables us not only to classify products appearance into distinct classes, but also to numerically and consistently estimate product appearance with continuous variations and to analyze characteristics of appearance. This approach is successfully applied to automatic quality classification of intermediate and final products in industrial manufacturing of engineered stone countertops.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.135-141
• /
• 2012

Development of the Internet has brought many changes in methods of education and assesment. When enforcing the on-line distance education, the tests to check the outcomes of the learning are taken on the Internet. The current trends of education evaluation are focused on the types of questions and the detachments of exam proctor but verifying the authentication of answer sheet. There are several forms to make answers; selection type, short-answer type, write-out answer type, practical exercise type, etc. All the forms can be done on the Internet except the practical exercise type because the source of the examinee's answer sheet is unreliable. In this paper, we made the verification system to solve the doubt by setting the proved information on the answer sheet. Putting the information down to confirm the authenticity during the exam on the server is distinct character of this system. After the test finished, the system will operate when examinee turn in the answer sheet.

• 한국노년학
• /
• v.30 no.1
• /
• pp.141-157
• /
• 2010

This quasi-experimental study examined the experience of simulation clothes and its effects among undergraduate nursing students. Method: The experimental group consisted of 44 sophomore students in a diploma nursing program, while 41 students comprised the comparison group. Only the experimental group experienced the functional decline of aging after taking on simulation clothes. Homogeneity between the groups was analyzed using t-test, and Fisher's exact test. Paired t-test and t-test were adopted for testing changes of attitudes and awareness of supporting elders. In addition, contents of students' reports of the aging simulation experience were analyzed. Results: No significant quantitative effect was observed in attitudes toward elders and awareness of supporting elders. However, the simulation experience seemed to have enhanced students' understanding of elders and of basic elder care as well. Furthermore, the students could think of preparing for their later lives. Conclusion: The experience of simulation clothes is a meaningful learning opportunity in gerontological nursing curriculum. Students' experiences need to be shared and reinforced in a discussion session. Safety should be secured in the process of the experience. The simulation experience can be further developed to raise its quality.

• Ecology and Resilient Infrastructure
• /
• v.9 no.4
• /
• pp.218-227
• /
• 2022

This study attempted classification through deep learning-based image training for land cover classification in river spaces which is one of the important data for efficient river management. For this purpose, land cover classification analysis with the RGB image of the target section based on the category classification index of major land cover map was conducted by using the learning outcomes from the result of labeling. In addition, land cover classification of the river spaces was performed by unsupervised and supervised classification from Sentinel-2 satellite images provided in an open format, and this was compared with the results of deep learning-based image classification. As a result of the analysis, it showed more accurate prediction results compared to unsupervised classification results, and it presented significantly improved classification results in the case of high-resolution images. The result of this study showed the possibility of classifying water areas and wetlands in the river spaces, and if additional research is performed in the future, the deep learning based image train method for the land cover classification could be used for river management.