• Korean Journal of Heritage: History & Science
• /
• v.54 no.3
• /
• pp.106-125
• /
• 2021

This paper presents several reasons for the necessity of archaeological hands-on training and strategies for its implementation. First, it is necessary to produce a specialized manual for local cultural heritage education that can enhance the specialization and educational effectiveness of archaeological experience education. In addition, in order to secure professionalism in hands-on education and conduct it systematically, the ability of instructors to conduct education is important, so instructor competence reinforcement education needs to be conducted regularly. In addition, hands-on education needs a strategy of planning and content development of archaeological education programs, with consideration given to the subjects of learning, and the establishment of a cooperative network. It is time to cooperate with various experts to establish an education system necessary for cultural heritage education in the region and develop customized content for local archaeological heritage supplementary textbooks. Finally, due to Covid-19, we agonized over effective education plans for online archaeological heritage education, which requires active interaction class design and a strategy to promote interaction between professors and learners. In addition, such archaeological heritage education should be compatible with the goal of providing customized lifelong education.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.403-410
• /
• 2020

In addition to the research on noise removal and super-resolution using the data restoration (Output result) function of Autoencoder, research on the performance improvement of clustering using the dimension reduction function of autoencoder are actively being conducted. The clustering function and data restoration function using Autoencoder have common points that both improve performance through the same learning. Based on these characteristics, this study conducted an experiment to see if the autoencoder model designed to have excellent data recovery performance is superior in clustering performance. Skip connection technique was used to design autoencoder with excellent data recovery performance. The output result performance and clustering performance of both autoencoder model with Skip connection and model without Skip connection were shown as graph and visual extract. The output result performance was increased, but the clustering performance was decreased. This result indicates that the neural network models such as autoencoders are not sure that each layer has learned the characteristics of the data well if the output result is good. Lastly, the performance degradation of clustering was compensated by using both latent code and skip connection. This study is a prior study to solve the Hanja Unicode problem by clustering.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.177-186
• /
• 2020

Entrepreneurship education has been emphasized worldwide and the number of universities that open related subjects have been increasing. K University, located in Gyeonggi-do, was selected as one of the leading universities in entrepreneurship in 2014, and has continued to grow quantitatively by providing support and education related to entrepreneurship on and off campus. In addition, major issues in entrepreneurship education were derived by conducting written or face-to-face interviews and advisory meetings with instructors, field experts, and education demanders for environmental analysis. Based on this, three major tracks(venture start-up, entrepreneurship convergence, and social venture activation) were derived, and major competency and learning goals for each track were presented. On the other hand, in order for this study to be more effectively accepted, it is necessary to present the objectives of each track, the capabilities pursued, and the courses that help students' progress. Therefore, in the future research, it is necessary to design and present the goals for each track, the curriculum road map, and the detailed curriculum of the convergence major, and at the same time, research to match the appropriate teaching method for each newly opened subject will be required to increase educational effectiveness.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2021

This study developed low-cost and high-efficiency pavement condition monitoring technology to produce the key information required for pavement management. A noise and artificial intelligence-based monitoring system was devised to compensate for the shortcomings of existing high-end equipment that relies on visual information and high-end sensors. From idea establishment to system development, functional definition, information flow, architecture design, and finally, on-site field evaluations were carried out. As a result, confidence in the high level of artificial intelligence evaluation was secured. In addition, hardware and software elements and well-organized guidelines on system utilization were developed. The on-site evaluation process confirmed that non-experts could easily and quickly investigate and visualized the data. The evaluation results could support the management works of road managers. Furthermore, it could improve the completeness of the technologies, such as prior discriminating techniques for external conditions that are not considered in AI learning, system simplification, and variable speed response techniques. This paper presents a new paradigm for pavement monitoring technology that has lasted since the 1960s.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.561-568
• /
• 2020

Wave measurements using X-band radar have many advantages compared to other wave gauges including wave-rider buoy, P-u-v gauge and Acoustic Doppler Current Profiler (ADCP), etc.. For example, radar system has no risk of loss/damage in bad weather conditions, low maintenance cost, and provides spatial distribution of waves from deep to shallow water. This paper presents new methods for estimating significant wave heights of X-band marine radar images using Artificial Neural Network (ANN). We compared the time series of estimated significant wave heights (Hs) using various estimation methods, such as signal-to-noise ratio (${\sqrt{SNR}}$), both and ${\sqrt{SNR}}$ the peak period (TP), and ANN with 3 parameters (${\sqrt{SNR}}$, TP, and Rval > k). The estimated significant wave heights of the X-band images were compared with wave measurement using ADCP(AWC: Acoustic Wave and Current Profiler) at Hujeong Beach, Uljin, Korea. Estimation of Hs using ANN with 3 parameters (${\sqrt{SNR}}$, TP, and Rval > k) yields best result.

• Journal of The Korean Association of Information Education
• /
• v.24 no.5
• /
• pp.433-441
• /
• 2020

The advent of the intelligent information society and artificial intelligence education for fostering future talents is attracting the attention of the education community, and the AI graduate course for teachers is also being opened and operated. The curriculum of the AI education graduate school, which was established this year, is self-contained considering the conditions of each university. Are organized. Accordingly, this study seeks to explore the direction of curriculum development so that AI curriculum that can be more effective and enhance educational value in the graduate school of education can be developed in the future. Based on the Backward design, the AI curriculum proposed in this study includes Bloom's digital taxonomy, Bruner's spiral curriculum composition principle, and three elements such as 'content domain', 'level', and 'teacher learning method'. It was intended to consist of. Based on the direction of AI curriculum development suggested in the study, we hope that the AI curriculum of domestic graduate schools of education will be more substantial, and this framework will be revised and supplemented in the future to be used in the composition of the AI curriculum in elementary and secondary schools.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.3
• /
• pp.101-109
• /
• 2021

Wave observations using a marine X-band radar are conducted by analyzing the backscattered radar signal from sea surfaces. Wave parameters are extracted using Modulation Transfer Function obtained from 3D wave number and frequency spectra which are calculated by 3D FFT of time series of sea surface images (42 images per minute). The accuracy of estimation of the significant wave height is, therefore, critically dependent on the quality of radar images. Wave observations during Typhoon Maysak and Haishen in the summer of 2020 show large errors in the estimation of the significant wave heights. It is because of the deteriorated radar images due to raindrops falling on the sea surface. This paper presents the algorithm developed to increase the accuracy of wave heights estimation from radar images by adopting convolution neural network(CNN) which automatically classify radar images into rain and non-rain cases. Then, an algorithm for deriving the Hs is proposed by creating different ANN models and selectively applying them according to the rain or non-rain cases. The developed algorithm applied to heavy rain cases during typhoons and showed critically improved results.

• Journal of the Korean Society of Earth Science Education
• /
• v.14 no.3
• /
• pp.225-235
• /
• 2021

The purpose of this study is to obtain implications for the improvement direction of astronomical education methods and development of educational materials or software. In connection with the 5th grade 1st semester elementary science 'Solar System and Stars' unit, elementary pre-service teachers were given a reorganization task to compare the relative distances from the sun to the planets, and then this was analyzed. Pre-service teachers are 11 male and 19 female students in the second year of the music education department at the elementary school teacher training university in B city. The implications of the study results are as follows. First, the 'distance comparison activity using a roll of tissue paper' is suitable for simply comparing the distances from the sun to the planet, but it has limitations in allowing students to experience the vastness of the solar system or inducing student participation-centered classes. Second, it is necessary to develop software materials for elementary school students that can simultaneously reflect the size of the planet and the distance to the planet that can be applied indoors, and also experience the vastness of the solar system, as well as a wide learning space. Third, textbook materials for students have an important influence on the class design of pre-service teachers.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.4
• /
• pp.3-14
• /
• 2022

Autonomous equipment requires a large amount of data from various environments. However, it takes a lot of time and cost for an experiment in a real construction sites, which are difficulties in data collection and processing. Therefore, this study aims to develop a virtual environment for autonomous tower cranes technology development and validation. The authors defined automation functions and operation conditions of tower cranes with three performance criteria: operational design domain, object and event detection and response, and minimum functional conditions. Afterward, this study developed a virtual environment for learning and validation for autonomous functions such as recognition, decision making, and control using the Unity game engine. Validation was conducted by construction industry experts with a fidelity which is the representative matrix for virtual environment assessment. Through the virtual environment platform developed in this study, it will be possible to reduce the cost and time for data collection and technology development. Also, it is also expected to contribute to autonomous driving for not only tower cranes but also other construction equipment.