• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.171-174
• /
• 2022

Weakly-supervised learning is a widely adopted approach in video anomaly detection whereby only video labels are utilized instead of expensive frame-level annotations. Since the success of multi-instance learning (MIL), almost all recent approaches are based on maximizing the margin between the set of abnormal video snippets and those of normal video snippets. In this work, we present a simple contrastive approach for weakly supervised video anomaly detection (WS-VAD) with aims to enhance the performance of existing models. The method is generic in nature and introduces a loss function to encourage attraction of output features from the same video class and repel those from different video classes. Experimental results demonstrate our method can be applied to existing algorithms to improve detection accuracy in public video anomaly dataset.

• Journal of Korean Society of Water and Wastewater
• /
• v.38 no.2
• /
• pp.83-93
• /
• 2024

In this study, we present a sewer pipe inspection technique through a combination of active sonar technology and deep learning algorithms. It is difficult to inspect pipes containing water using conventional CCTV inspection methods, and there are various limitations, so a new approach is needed. In this paper, we introduce a inspection method using active sonar, and apply an auto encoder deep learning model to process sonar data to distinguish between normal and abnormal pipelines. This model underwent training on sonar data from a controlled environment under the assumption of normal pipeline conditions and utilized anomaly detection techniques to identify deviations from established standards. This approach presents a new perspective in pipeline inspection, promising to reduce the time and resources required for sewer system management and to enhance the reliability of pipeline inspections.

• Journal of vocational education research
• /
• v.29 no.3
• /
• pp.107-132
• /
• 2010

The purpose of this study was to investigate the effects of learning achievement by comparing project approach group and the control group on the unit of growing flowers and vegetables in practical arts education. For this purpose, the experimental study on the unit of growing flowers and vegetables was achieved with 63 students(5th grade 2 classes) in S elementary school. The project approach model (Chung, Sung-bong) was applied to the experimental group, and the traditional model to the control group. To verify the effects of each class, nonequivalent control group post test-only design was applied 10 times. The SPSSWIN(ver 12. 0. 1) was used for analyzing the frequency and t-tests. The results of this study were as follows ; First, there was significant effect of learning achievement(cognitive domain) in the project approach groups. In addition, learning achievement of the experimental group has been showed significant difference about intellectual function and ability but not about knowledge. Second, there was significant effect of learning achievement(psychomotor domain) in the project approach groups. In other words, there has been showed significant difference in basic skill and integrated skill for growing flowers and vegetables but not in elemental skill for planting. Third, as the post test, there existed significant effect(affective domain) in the project approach groups. In other words, there was a meaningful difference in acceptance, value, belief, actualization but not in interest. Based on these results, It is believed that the project approach model in the unit of 'growing flowers and vegetables' is more effective than the traditional learning method in learning achievement of learners' cognitive, psychomotor and affective domain.

• The Journal of Korean Philosophical History
• /
• no.39
• /
• pp.53-83
• /
• 2013

This paper aims to examine how issues related to the heaven-human relation (or nature-culture relation) affected Joseon intellectuals in the eighteenth century by considering Huang Yun Seok as a reference. As a significant indicator, the heaven-human relation issue has traditionally been a critical theme in the history of Confucianism. Since Huang Yun Seok accepted Western Learning based on Zhuxi Learning, he is a good example for examining this issue. Huang's ideas didn't depart too much from Confucianism, but he naturally became interested in Western Learning because of the enthusiastic admiration he had of Ancient Learning since he was a child. Principle-Number was consistent with Ancient Learning and Western Learning, and this was somewhat different from the original notion of numerology. It was used for understanding and explaining astronomical phenomenon. In understanding astronomical phenomenon, Huang used both fact-determined and value-centered approaches. Western astronomy allowed him to make an advance in terms of fact-determined approach while the value-centered approach gave him a portentological perspective on astronomical variation such as solar and lunar eclipses. This indicates one of the ways to keep Zhuxi Learning's identity itself amidst an inflow of new learnings.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.197-204
• /
• 2020

In this paper, we present a learning platform for robotic grasping in real world, in which actor-critic deep reinforcement learning is employed to directly learn the grasping skill from raw image pixels and rarely observed rewards. This is a challenging task because existing algorithms based on deep reinforcement learning require an extensive number of training data or massive computational cost so that they cannot be affordable in real world settings. To address this problems, the proposed learning platform basically consists of two training phases; a learning phase in simulator and subsequent learning in real world. Here, main processing blocks in the platform are extraction of latent vector based on state representation learning and disentanglement of a raw image, generation of adapted synthetic image using generative adversarial networks, and object detection and arm segmentation for the disentanglement. We demonstrate the effectiveness of this approach in a real environment.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.26 no.2
• /
• pp.111-122
• /
• 2020

Purpose: In the Fourth Industrial Revolution, nursing education will change in a different way than before. The purpose of this study was to analyze characteristics of qualitative research on learning experiences for nursing students, and to suggest directions for nursing education geared to the needs of the future. Methods: An integrative review method was used. Based on Whittemore & Knafl's approach, five steps were applied. Results: Eleven papers met the selection criteria and had above average ratings in quality appraisals. Three characteristics related to the learning experiences of nursing students were derived: (1) overcoming difficulties in the learning process and concentrating on problem-solving, (2) improving self-efficacy through experiencing achievement in the learning process, (3) establishing nursing professionalism, (4) identifying the importance of self-directed and self-reflected learning, and (5) developing teamwork. Conclusion: This review found that various learning experiences were conducted for practical experience and learner-oriented learning. Nursing students overcame difficulties to achieve their learning outcomes, and developed their professionalism. Further study is required to comprehensively explore research including other countries, and the experiences of instructors.

• Journal of Information Technology Applications and Management
• /
• v.26 no.5
• /
• pp.27-39
• /
• 2019

The Internet of Things (IoT) is a new paradigm that is revolutionizing computing. It is intended that all objects around us will be connected to the network, providing "anytime, anywhere" access to information. This study introduces IoT with Kolb's learning style in order to enhance the learning experience especially for inclusive education for primary and secondary schools where delivery of knowledge is not limited to physical, cognitive disabilities, human diversity with respect to ability, language, culture, gender, age and of other forms of human differences. The article also emphasizes the role of learning style as a discovery process that incorporates the characteristics of problem solving and learning. Kolb's Learning Style was chosen as it is widely used in research and in practical information systems applications. A consistent pattern of finding emerges by using a combination of Kolb's learning style and internet of things where specific individual differences, learning approach differences and IoT application differences are taken as a main research framework. Further several suggestions were made by using this combination to IoT architecture and smart environment of internet of things. Based on these suggestions, future research directions are proposed.

• Journal of Korean Home Economics Education Association
• /
• v.10 no.1
• /
• pp.137-151
• /
• 1998

The purpose of this study is (1)to develop the teaching plan based on Cooperative Learning approach and (2)to investigate the effect of students'Interest on Subject matter and Teaching method and Attitudes to others of the area of Foreign food in Home Economics class. Among those various types of Cooperative Learning's models, this study adopted 'Learning Together'developed by Johnsons. To investigate these purpose, subject matter were analyzed and reconstructed for Cooperative Learning. The tests were developed to evaluate the interest on the Subject matter and teaching methods, and the attitude to others of the students. 108 femail high school students were divided into two groups with 54 students-traditional learning condition, Cooperative Learning condition-and had a 5 session. The subject of the class was Foreign food including Western, Chinese, and Japanes food. Before and after the class, students were tested. The statistical methods used for the study methods used for the study were t-test. The research findings are as follows : When the students in the Cooperative Learning classes were compared before and after the test, (1)Interest on Subject matter were improved considerably(p〈.001) (2)Interest on Teaching methods were improved considerably(p〈.05) (3)Attitude to Others were improved considerably(p〈.001) Therefore when the teaching-learning model based on Cooperative Liarning was used in Home Economics class, their interest on the subject and teaching methods and attitude to others were improved.

• Journal of The Korean Association of Information Education
• /
• v.10 no.1
• /
• pp.143-152
• /
• 2006

The aim of this study was to analyze effects of a blended learning program based on case study approach and to suggest implications in appropriately evaluating blended learning in practices for corporate education and training. In order to achieve the goal, issues such as the ones related to blended learning including development and status quo of blended learning programs in the field of corporate education and training and operation models for the blended learning were reviewed. Then, the outcomes of a blended learning program were completely analyzed through systems approach. The methodology of the study was a mixed research method which was comprised of quantitative and qualitative approaches. The results of quantitative analysis showed that blended learning itself seemed to have significant effects on the leadership capability in general assessment and self assessment. The most viable effects of blended learning in leadership training are said to be actual change of actions and activities in leadership capability of the participants followed by changes in their job tasks contributing to improving the managerial performance of the company, good transfer to current job tasks, and implementation of the practice plans.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.30-45
• /
• 2024

This study introduces an effective method for predicting individual local tax delinquencies using prevalent machine learning and deep learning algorithms. The evaluation of credit risk holds great significance in the financial realm, impacting both companies and individuals. While credit risk prediction has been explored using statistical and machine learning techniques, their application to tax arrears prediction remains underexplored. We forecast individual local tax defaults in Republic of Korea using machine and deep learning algorithms, including convolutional neural networks (CNN), long short-term memory (LSTM), and sequence-to-sequence (seq2seq). Our model incorporates diverse credit and public information like loan history, delinquency records, credit card usage, and public taxation data, offering richer insights than prior studies. The results highlight the superior predictive accuracy of the CNN model. Anticipating local tax arrears more effectively could lead to efficient allocation of administrative resources. By leveraging advanced machine learning, this research offers a promising avenue for refining tax collection strategies and resource management.