• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.371-393
• /
• 2023

Crack detection in structures plays a vital role in ensuring their safety, durability, and reliability. Traditional crack detection methods sometimes need significant manual inspections, which are laborious, expensive, and prone to error by humans. Deep learning algorithms, which can learn intricate features from large-scale datasets, have emerged as a viable option for automated crack detection recently. This study presents an in-depth review of crack detection methods used till now, like image processing, traditional machine learning, and deep learning methods. Specifically, it will provide a comparative analysis of crack detection methods using deep learning, aiming to provide insights into the advancements, challenges, and future directions in this field. To facilitate comparative analysis, this study surveys publicly available crack detection datasets and benchmarks commonly used in deep learning research. Evaluation metrics employed to check the performance of different models are discussed, with emphasis on accuracy, precision, recall, and F1-score. Moreover, this study provides an in-depth analysis of recent studies and highlights key findings, including state-of-the-art techniques, novel architectures, and innovative approaches to address the shortcomings of the existing methods. Finally, this study provides a summary of the key insights gained from the comparative analysis, highlighting the potential of deep learning in revolutionizing methodologies for crack detection. The findings of this research will serve as a valuable resource for researchers in the field, aiding them in selecting appropriate methods for crack detection and inspiring further advancements in this domain.

• International Journal of Quality Innovation
• /
• v.6 no.1
• /
• pp.43-57
• /
• 2005

Action learning motivates students to solve open-ended problems by 'developing skills through doing'. This paper reviews the concept of action learning and discusses the adoption of action learning approach to teach operations management at universities. It presents the design and delivery of an action-learning course at City University of Hong Kong. The course incorporates classroom lectures, tutorials and an action-learning workshop. The experience gained proves that action learning facilitates student participation and teamwork and provides a venue of accelerating learning where enables students to handle dynamic problem situations more effectively. The paper concludes that adopting action-learning approach can help lecturers to enhance quality teaching in operations management courses, and provide an alternate means of effective paradigm other than traditional classroom teaching and/or computer-based training at universities.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.189-191
• /
• 2014

This paper provides an overview of the E-learning service education on the last decade, In the early 2000's the emphasis of educational technology was on interactive multimedia- stand alone packages on computer hard disks or portable memory, which integrated a range of media forms in the lately. Customers handle finding the best sources of content.The system then uses social signals such as those coming from Facebook, Twitter, LinkedIn, delicious as well as clicks and views. The SNS and network infrastructure is sufficiently mature that the focus should shift to how to use the technology most appropriately to facilitate learning. As we study environmental conditions of the traditional internet and the mobile internet users in some ways. In this paper, analyze the nature of learning, role of educational and suggest alternative policy, innovation of e-learning service and effective e-learning environment in developing technology.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• Journal of Korean Physical Therapy Science
• /
• v.30 no.3
• /
• pp.84-90
• /
• 2023

Background: This study aimed to investigate the effects of flipped learning education on academic motivation and class satisfaction in physical therapy students. Design: Cross-sectional study. Methods: Participants included 72 physical therapy students (experimental group=36, control group=36). In order to compare the effects of flipped learning education, flipped learning and lecture-style learning were provided in a class titled Acticities of Daily Living and Practice. An independent t-test was used to compare academic motivation and class satisfaction between two groups. Results: The flipped learning group showed a significantly higher level of academic motivation and class satisfaction compared to the traditional learning group (p<0.05). Conclusion: These results showed that flipped learning education is an effective learning strategy for improving the academic motivation and class satisfaction of physical therapy students.

• Journal of Ginseng Research
• /
• v.44 no.3
• /
• pp.442-452
• /
• 2020

Backgroud: Sleep deprivation (SD) impairs learning and memory by inhibiting hippocampal functioning at molecular and cellular levels. Abnormal autophagy and apoptosis are closely associated with neurodegeneration in the central nervous system. This study is aimed to explore the alleviative effect and the underlying molecular mechanism of stem-leaf saponins of Panax notoginseng (SLSP) on the abnormal neuronal autophagy and apoptosis in hippocampus of mice with impaired learning and memory induced by SD. Methods: Mouse spatial learning and memory were assessed by Morris water maze test. Neuronal morphological changes were observed by Nissl staining. Autophagosome formation was examined by transmission electron microscopy, immunofluorescent staining, acridine orange staining, and transient transfection of the tf-LC3 plasmid. Apoptotic event was analyzed by flow cytometry after PI/annexin V staining. The expression or activation of autophagy and apoptosis-related proteins were detected by Western blotting assay. Results: SLSP was shown to improve the spatial learning and memory of mice after SD for 48 h, accomanied with restrained excessive autophage and apoptosis, whereas enhanced activation of phosphoinositide 3-kinase/protein kinase B/mammalian target of rapamycin signaling pathway in hippocampal neurons. Meanwhile, it improved the aberrant autophagy and apoptosis induced by rapamycin and re-activated phosphoinositide 3-kinase/Akt/mammalian target of rapamycin signaling transduction in HT-22 cells, a hippocampal neuronal cell line. Conclusion: SLSP could alleviate cognitive impairment induced by SD, which was achieved probably through suppressing the abnormal autophagy and apoptosis of hippocampal neurons. The findings may contribute to the clinical application of SLSP in the prevention or therapy of neurological disorders associated with SD.

• Journal of Korean Academy of Nursing
• /
• v.35 no.1
• /
• pp.65-76
• /
• 2005

Objective: The aim of this study is to explore the variation in perceptions about problem-based learning(PBL) according to the level of academic achievement and learning attitude in the nursing students of a junior college (3-year program). Method: Students (n=39) learned the respiratory and cardiac system with seven PBL packages and group-based learning for a semester in 2002. Students were asked to write reflective journals that focused on their learning perception after an experience with each learning package. A total of 208 journals were used for analysis. Result: Students positively perceived that PBL making them increase their sense of responsibility for learning and felt satisfaction with the learning process, and had a confidence in the use of clinical nursing interventions. On the other hand, they negatively perceived that PBL was a burden because it took more time than traditional learning tasks, and they experienced an anxiety about regular tests and felt conflicts and diffidences in the learning process. The negative perceptions were expressed more often from students with a low academic achievement and low learning attitude compared to others. Conclusion: Students perceived the PBL as effective in understanding the learning concepts in the clinical practice environment. PBL need to be supplemented by feedback-based lecture and facilitative strategies for academically low-achieved students.Objective: The aim of this study is to explore the variation in perceptions about problem-based learning(PBL) according to the level of academic achievement and learning attitude in the nursing students of a junior college (3-year program). Method: Students (n=39) learned the respiratory and cardiac system with seven PBL packages and group-based learning for a semester in 2002. Students were asked to write reflective journals that focused on their learning perception after an experience with each learning package. A total of 208 journals were used for analysis. Result: Students positively perceived that PBL making them increase their sense of responsibility for learning and felt satisfaction with the learning process, and had a confidence in the use of clinical nursing interventions. On the other hand, they negatively perceived that PBL was a burden because it took more time than traditional learning tasks, and they experienced an anxiety about regular tests and felt conflicts and diffidences in the learning process. The negative perceptions were expressed more often from students with a low academic achievement and low learning attitude compared to others. Conclusion: Students perceived the PBL as effective in understanding the learning concepts in the clinical practice environment. PBL need to be supplemented by feedback-based lecture and facilitative strategies for academically low-achieved students.

• Journal of the Korean Chemical Society
• /
• v.44 no.6
• /
• pp.600-610
• /
• 2000

The purpose of this study was to design the new teaching strategy based on the particulate model facilitating the reflective thinking (RE-PM) in the learning of the particulate nature of matter, and to investigate the effect of the new teaching strategy in compare with the traditional teaching strategy (TS-PM) after treating with new teaching strategy on preliminary teachers of elementary school. The problems of traditional teaching strategy are as follows: 1) Most of students didn't think the particulate model connected with practical material. 2) Most of students have a tendency of the rote memory on learning of the traditional particulate model. 3) The ratio of changing the view of continuous matter into the view of particulate nature of matter was very low, after learning the particulate model using of the traditional teaching strategy. The new teaching strategy facilitating the reflective thinking was more effective on the understanding of particulate nature of matter and the driving of motivation than the traditional teaching strategy in the learning of the particulate nature of matter.

• Journal of Educational Research in Mathematics
• /
• v.23 no.3
• /
• pp.373-388
• /
• 2013

This paper is to investigate how two elementary school teacher's belief mathematics as educational content, and teaching and learning mathematics as a part of educational methodology, and what the two teachers believe towards gifted children and their education, and what the classes demonstrate and its effects on the sociomathematical norms. To investigate this matter, the study has been conducted with two teachers who have long years of experience in teaching gifted children, but fall into different belief categories. The results of the study show that teacher A falls into the following category: the essentiality of mathematics as 'traditional', teaching mathematics as 'blended', and learning mathematics as 'traditional'. In addition, teacher A views mathematically gifted children as autonomous researchers with low achievement and believes that the teacher is a learning assistant. On the other hand, teacher B falls into the following category: the essentiality of mathematics as 'non-traditional', teaching mathematics as 'non-traditional, and learning mathematics as 'non-traditional.' Also, teacher B views mathematically gifted children as autonomous researchers with high achievement and believes that the teacher is a learning guide. In the teacher A's class for gifted elementary school students, problem solving rule and the answers were considered as important factors and sociomathematical norms that valued difficult arithmetic operation were demonstrated However, in the teacher B's class for gifted elementary school students, sociomathematical norms that valued the process of problem solving, mathematical explanations and justification more than the answers were demonstrated. Based on the results, the implications regarding the education of mathematically gifted students were investigated.