• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.4
• /
• pp.7-16
• /
• 2023

For decades, creating a desired locomotive motion in a goal-oriented manner has been a challenge in character animation. Data-driven methods using generative models have demonstrated efficient ways of predicting long sequences of motions without the need for explicit conditioning. While these methods produce high-quality long-term motions, they can be limited when it comes to synthesizing motion for challenging novel scenarios, such as punching a random target. A state-of-the-art solution to overcome this limitation is by using a GAN Discriminator to imitate motion data clips and incorporating reinforcement learning to compose goal-oriented motions. In this paper, our research aims to create characters performing combat sports such as boxing, using a novel reward design in conjunction with existing GAN-based approaches. We experimentally demonstrate that both the Adversarial Motion Prior [3] and Adversarial Skill Embeddings [4] methods are capable of generating viable motions for a character punching a random target, even in the absence of mocap data that specifically captures the transition between punching and locomotion. Also, with a single learned policy, multiple task controllers can be constructed through the TimeChamber framework.

• The korean journal of orthodontics
• /
• v.52 no.2
• /
• pp.112-122
• /
• 2022

Objective: This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. Methods: The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. Results: The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. Conclusions: The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.

• Journal of The Korean Association For Science Education
• /
• v.35 no.6
• /
• pp.1039-1048
• /
• 2015

The purpose of this study is to examine implications of pre-service science teacher training by analyzing science field integration and connection between learning content presented in 'Integrated Science' for high school students based on the 2015 revised science curriculum, and in pre-service science learning materials (textbooks) of the college of education. For this study, the 2015 revised 'Integrated Science' curriculum and 11 types of pre-service science teachers' learning materials related to physics, chemistry, biological science, and earth science were selected. The results were as follows. Most of the learning content presented in the 2015 revised 'Integrated Science' curriculum had integrated two or more science fields. Also, almost all learning content presented in the 2015 revised 'Integrated Science' curriculum were included in pre-service science teachers' education content, with educational content for chemistry introduced at the highest rate. The textbooks for pre-service science teachers had the most learning contents of 'Energy and Environment' domain of 'Integrated Science' for high school students. Accordingly, these results suggest that 'integrated science materials' should be developed for proper the curriculum implementation. Also, training courses for science teachers responsible for 'Integrated Science' are required. Furthermore, a revised curriculum for the college of education and a method to link with certification examinations for secondary school teachers are needed.

• Journal of The Korean Association For Science Education
• /
• v.35 no.1
• /
• pp.15-25
• /
• 2015

This study examined pre-service secondary physics teachers' epistemological beliefs about scientific knowledge, science learning, and science teaching in two different science content topics, Lamarckism and the impetus theory. Two sets of open-ended questionnaires, for each of the topics respectively, were developed in the same format. The pre-service teachers completed the questionnaires at one month intervals. The beliefs were analyzed in two dimensions, knowledge justification and knowledge change for each belief area. The findings show that the majority of pre-service teachers held sophisticated epistemological beliefs about scientific knowledge regardless of content topics. On the other hand, more pre-service teachers exhibited sophisticated beliefs about science learning in the context impetus theory than Lamarckism. In the area of science teaching, the majority of pre-service teachers demonstrated a sophisticated view in knowledge justification but a naive view in knowledge change. When consistency across science topics and belief areas were examined, few pre-service teachers held consistent epistemological beliefs across all topics and areas. The difference in the levels of sophistication in belief areas showed that the pre-service teachers did not connect their epistemological beliefs about science knowledge to their ideas about science teaching and learning. This disconnection seems to make the consistency across topics and areas complicated. The difference in epistemological beliefs about science learning and teaching between two science topics need further inquiry. Implications for teacher education are offered.

• Journal of The Korean Association For Science Education
• /
• v.19 no.1
• /
• pp.62-77
• /
• 1999

Idealization has an important role in the process of learning as well as in physics research. The purpose of this study was to survey students' and science teachers' recognition of the ideal conditions involved in the process of problem solving and of explaining the natural phenomena. The instrument for probing the understanding of the ideal conditions in the domains of force, electricity and heat was administered to general high and science high school students and science teachers. The framework of responses composed of three categories. The first category is "idealized conditions relevant to problem", the second "not relevant idealized conditions", which has more delicate subcategories of general/ irrelevant conditions, simple statement of formula/ law, repeating problems, uncorrect explaining/ describing conditions, and the last "no responses". The results of analysis showed that the majority of the subjects well understood the various ideal conditions, especially for science high school students. But some of them could not differentiate the ideal condition from the general conditions, or they simply repeat the problem situation or the formula. The understanding of idealization is different by the domains of physics. We discovered that the misconceptions about the ideal conditions in various physical phenomena and revealed some interconnection of researches in the fields of misconception and the ideal condition.

• Journal of The Korean Association For Science Education
• /
• v.15 no.2
• /
• pp.158-163
• /
• 1995

The 40th Annual Southern Arizona Regional Science and Engineering Fair was analyzed in terms of contents of exhibits and research methods. Elementary school students like to choose first, biology; secondly. physics; thirdly, chemistry; fourthly. consumer science; fifthly, S.T.S; sixthly. earth science area topics. Chemistry area topics are 20 %, which are much more than rates appeared in American elementary science textbooks. Elementary school students like topics such as pollutions, energy saving materials and characteristics/selection of products required in every-day life. In the most preferential area, biology, students do experiments or survey about plants growth, microbiology, learning/behavior of animals, health/exercise, which are reconcile with the analysis of American elementary science contents.

• Asian review of World Histories
• /
• v.4 no.1
• /
• pp.125-132
• /
• 2016

This paper, as a conlcusion to this special issue, presents the future work that is being carried out at NTU Singapore in collaboration with Microsoft Research and Microsoft Azure for Research. For our research team the real frontier research in world histories starts when we want to use computers to structure historical information, model historical narratives, simulate theoretical large scale hypotheses, and incent world historians to use virtual assistants and/or engage them in teamwork using social media and/or seduce them with immersive spaces to provide new learning and sharing environments, in which new things can emerge and happen: "You do not know which will be the next idea. Just repeating the same things is not enough" (Carlo Rubbia, 1984 Nobel Price in Physics, at Nanyang Technological University on January 19, 2016).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• Journal of the Korean Physical Society
• /
• v.73 no.12
• /
• pp.1908-1917
• /
• 2018

The binding affinity between the T-cell receptors (TCRs) and antigenic peptides mainly determines immunological recognition. It is not a trivial task that T cells identify the digital sequences of peptide amino acids by simply relying on the integrated binding affinity between TCRs and antigenic peptides. To address this problem, we examine whether the affinity-based discrimination of peptide sequences is learnable and generalizable by artificial neural networks (ANNs) that process the digital experimental amino acid sequence information of receptors and peptides. A pair of TCR and peptide sequences correspond to the input for ANNs, while the success or failure of the immunological recognition correspond to the output. The output is obtained by both theoretical model and experimental data. In either case, we confirmed that ANNs could learn the immunological recognition. We also found that a homogenized encoding of amino acid sequence was more effective for the supervised learning task.