• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.326-334
• /
• 2024

Extra-oral imaging techniques such as Panoramic X-rays (PXs) and Cone Beam Computed Tomography (CBCT) are the most preferred imaging modalities in dental clinics owing to its patient convenience during imaging as well as their ability to visualize entire teeth information. PXs are preferred for routine clinical treatments and CBCTs for complex surgeries and implant treatments. However, PXs are limited by the lack of third dimensional spatial information whereas CBCTs inflict high radiation exposure to patient. When a PX is already available, it is beneficial to reconstruct the 3D oral structure from the PX to avoid further expenses and radiation dose. In this paper, we propose 3DentAI - an U-Net based deep learning framework for 3D reconstruction of oral structure from a PX image. Our framework consists of three module - a reconstruction module based on attention U-Net for estimating depth from a PX image, a realignment module for aligning the predicted flattened volume to the shape of jaw using a predefined focal trough and ray data, and lastly a refinement module based on 3D U-Net for interpolating the missing information to obtain a smooth representation of oral cavity. Synthetic PXs obtained from CBCT by ray tracing and rendering were used to train the networks without the need of paired PX and CBCT datasets. Our method, trained and tested on a diverse datasets of 600 patients, achieved superior performance to GAN-based models even with low computational complexity.

• Journal of The Korean Association For Science Education
• /
• v.42 no.1
• /
• pp.61-75
• /
• 2022

Recently, lifelong learning ability was newly proposed as scientific literacy, the goal of the science curriculum. To solve various science-related problems students encounter in life, lifelong learning abilities related to science beyond school science education are required, but empirical evidence shows that students can solve problems they actually face through scientific literacy. It is not easy to find in the existing science education research. In addition, there is a lack of discussion on how to cultivate lifelong learning ability suggested in the curriculum through school science education. In this study, attention was paid to SSI education as a method for students to cultivate lifelong learning ability through school science education and to develop their ability to solve science-related problems encountered in life. In this context, statements in the existing SSI education studies were reviewed to discover discourses related to lifelong learning, and their types and characteristics were distinguished. It was possible to confirm lifelong learning and its applicability with focus on science education research through this. For the study, 18 literature materials on the subject of SSI education were selected, and the discourses related to lifelong learning in the SSI education research were discovered by examining the statements revealed in the data. As a result of the study, there are four categories of discourses related to lifelong learning: 'awareness of science,' 'connection between science and everyday life', 'promotion of participatory citizenship', and 'construction of identity'. Various SSI education studies have already had lifelong learning perception in various contexts, and the four types of discourses related to lifelong learning could be linked to the four types of learning presented in the UNESCO Lifelong Learning Report. SSI education tends to view students' life experiences as part of their learning and aims to help students develop the character and capacity to make responsible decisions on social issues related to science and put them into practice. This competency can be continuously connected to the real-life of students outside of school as a lifelong learning ability. This study requires expanding the discourse related to lifelong learning in science education and operating and managing the overall educational system to foster students' lifelong learning ability.

• Korean Journal of Human Ecology
• /
• v.21 no.2
• /
• pp.165-180
• /
• 2012

The purpose of the study was to prove the effect of the "Picture Book Reading Program for Mothers" developed to enhance the language competence of married immigrant women and their children. Twenty immigrant mothers with three-year-olds were recruited, and they participated in an 8-week-Picture Book Reading Program developed by the reseacher. The REVT and U-TAP were used to measure linguistic abilities for mothers while PRES was used to measure their children's linguistic abilities. Lee(2004)'s "Effect of dialogic picture book reading teacher training program for toddlers" was used to measure the mother's and children's verbal and non-verbal behaviors. The results of the study were as follows: First, by participating in the PBRPM, the mother's linguistic ability as well as children's vocabulary and receptive language have increased. Second, by participating in the PBRPM in terms of mother-child interaction, mother's verbal behaviors to children (i.e. attention and inquiring) and children's verbal behaviors(i.e. responding and imitation) have increased. In conclusion, "PBRPM" for married immigrant women and their children proved to be effective in enhancing the language competence and verbal interactions between married immigrant women and their children.

• 한국균학회소식:학술대회논문집
• /
• 2015.05a
• /
• pp.20-20
• /
• 2015

Endophytic fungi are microorganisms inhabiting living plant tissues without causing apparent harm to the host. They are drawing increasing attention due to their ability to produce various bioactive compounds as well as their effects on host growth and resistance to biotic and abiotic stresses. As a first step to assess biodiversity of plant associated fungi in Korea and the following evaluation on diverse biological activities, we are collecting endophytic fungi from plant in wild followed by systematic long-term storage in liquid nitrogen. Molecular identification using ITS sequences was also incorporated for pure culture by hyphal tip isolation. As of April 2015, about 1,400 fungal strains had been isolated from about 170 plant taxa. Fungal isolates belonging to Pleosporales, Diaporthales, Glomerellales, Hypocreales, and Xylariales were the most abundant. These collections are being used for several complementary researches, including screening of isolates with novel bioactive compounds or conferring drought stress resistance, phylogenetic and genomic study. Genome sequencing was performed for 3 isolates, one Xylaria sp. strain JS573 producing griseofulvin, an antifungal compound, and two Fusarium spp. strains JS626 and JS1030, which are assumed to be new species found in Korea. More detailed analysis on these genomes will be presented. These collections and genome informations will serve as invaluable resources for identifying novel bioactive materials in addition to expand our knowledge on fungal biodiversity.

• Journal of the Korean Society of Earth Science Education
• /
• v.4 no.2
• /
• pp.186-193
• /
• 2011

The aim of this study is to find out the effect of reading aloud science books on change of attitude toward the science, interest of instruction. Participants included 52 elementary school students. For this study, two classes were divided into experimental class and control class. The control class takes a regular instructions and the experimental class takes a reading aloud instructions. Two chapter were selected, 'Volcano and Rocks' and 'Family of the Sun', for this study. Students were treated for 12 hours. All the results were analyzed quantitatively and following conclusions were made. The students' scientific attitude in the experimental class were higher than those of students in the control class. However, according to statistical analysis, this result is meaningless. In the sub-parts, critical ability, cooperation and creativity were improved meaningfully. Instruction with reading aloud science books didn't show a meaningful difference in interest of instruction. However, in the sub-part, they showed meaningful improvement in attention and relevance.

• English Language & Literature Teaching
• /
• v.11 no.1
• /
• pp.17-36
• /
• 2005

The purpose of this study is to examine the ways in which CALL apply to enhance the motivational aspects of second language learning. Theories relevant to social, cognitive, and affective foundations of motivation are first reviewed to demonstrate the important role of motivational influences in improving learners' affect and achievements. Then, implications arising from such theories in strengthening the motivational aspects of CALL are explicated in the second part. With the spread of computer technology in language classrooms, the innovative role of CALL in the development and maintenance of intrinsic motivation can be illustrated. Specifically, CALL may provide cognitively supportive instruction geared towards improving students' performance. Also, it has been reported from the affective perspective that CALL can captivate learners' attention, promote their feelings and expectations of success, improve perceptions of control, and increase positive attributions to effort and ability. Finally, from a social learning perspective, CALL may enhance learners' self-efficacy and foster their achievement and positive affect through social interactions, proximal goal-setting, and attributional feedback. In the framework of CALL, students seem to be benefited by the immediacy and authenticity of contact with target languages and cultures made at their choices and decisions.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.138-141
• /
• 2003

Recently reinforcement learning has attracted attention of many researchers because of its simple and flexible learning ability for any environments. And so far many reinforcement learning methods have been proposed such as Q-learning, actor-critic, stochastic gradient ascent method and so on. The reinforcement learning system is able to adapt to changes of the environment because of the mutual action with it. However when the environment changes periodically, it is not able to adapt to its change well. In this paper we propose the reinforcement learning system that is able to adapt to periodical changes of the environment by introducing the time-varying parameters to be adjusted. It is shown that the proposed method works well through the simulation study of the maze problem with aisle that opens and closes periodically, although the conventional method with constant parameters to be adjusted does not works well in such environment.

• International Commerce and Information Review
• /
• v.5 no.1
• /
• pp.39-59
• /
• 2003

The purpose of this paper is to examine the possibility of whether B2B e-marketplaces continue to grow. There are numerous barriers to the growth of e-marketplace, but certain key factors can push e-marketplaces beyond these obstacles. In the stage of generating traffic, it is essential to find a vertical area to attract buyers and sellers which can generate B2B transaction through e-marketplace. Generating traffic is possible only for e-marketplaces established by those who have vertical knowledges and strong off-line relationship in the vertical areas. In the stage of concentrating traffic, more attention should be given to reach critical mass and to increase transaction through e-marketplace. Currently, there seems to be a tendency that having major buyers as members of a e-marketplace is an true factor for the successful e-marketplace. Finally, to attain the locking traffic, e-marketplace needs to have the ability to generate revenue through B2B transaction. What we have learn from this study is that having the software-technology is not a sufficient condition to successfully operate B2B e-marketplace. It is important for e-marketplace to attract major players in order to increase B2B transaction, and also to make profit by them.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1282-1290
• /
• 2017

Since the mitigation of fear of crime significantly enhances the consumptions in a city, studies focusing on urban safety analysis have received much attention as means of revitalizing the local economy. In addition, with the development of computer vision and machine learning technologies, efficient and automated analysis methods have been developed. Previous studies have used global features to predict the safety of cities, yet this method has limited ability in accurately predicting abstract information such as safety assessments. Therefore we used a Convolutional Context Neural Network (CCNN) that considered "context" as a decision criterion to accurately predict safety of cities. CCNN model is constructed by combining a stacked auto encoder with a fully connected network to find the context and use it in the CNN model to predict the score. We analyzed the RMSE and correlation of SVR, Alexnet, and Sharing models to compare with the performance of CCNN model. Our results indicate that our model has much better RMSE and Pearson/Spearman correlation coefficient.