• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1319-1325
• /
• 2021

It is important to remove fog for accurate object recognition and detection during preprocessing because images taken in foggy adverse weather suffer from poor quality of images due to scattering and absorption of light, resulting in poor performance of various vision-based applications. This paper proposes an end-to-end deep learning-based single image de-fogging method using U-Net architecture. The loss function used in the algorithm is a loss function based on Mahalanobis distance with fog features, which solves the problem of domain shifts, and demonstrates superior performance by comparing qualitative and quantitative numerical evaluations with conventional methods. We also design it to generate fog through the VGG19 loss function and use it as the next training dataset.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.1
• /
• pp.1-12
• /
• 2005

In this paper, we analyze the course 'computer' on middle and high schools. and propose new organization of the course to enhance the ability of self-directed learning. We also develop a learning system for new organization, based on self-directed teaching and learning principles. The developed learning system makes students choose the topics according to their interest and advance learning by the schedule they set by themselves. To promote students' participation, the teacher also gives students various learning tasks. Through e-board and Q&A, we also accelerate mutual communication among teachers and students, to do teaching-learning activities vigorously.

• Journal of the Society of Naval Architects of Korea
• /
• v.54 no.5
• /
• pp.421-429
• /
• 2017

It is very important to manage the position of the blocks in the shipyard where the work is completed, or the blocks need to be moved for the next process operation. The moving distance of the block increases according to the position of the block stockyard. As the travel distance increases, the number of trips and travel distance of the transporter increases, which causes a great deal of operation cost. Currently, the selection of the block position in the shipyard is based on the know-how of picking up a transporter worker by the production schedule of the block, and the location where the block is to be placed is determined according to the situation in the stockyard. The know-how to select the position of the block is the result of optimizing the position of the block in the shipyard for a long time. In this study, we used the accumulated data as a result of the operation of the yard in the shipyard and tried to select the location of blocks by learning it. Decision tree learning algorithm was used for learning, and a prototype was developed using it. Finally, we prove the possibility of selecting a block stockyard through this algorithm.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.63-66
• /
• 2000

WBI provides new opportunities to realize the flexible learning environment based on hypermedia and to support distance learning with a diverse interaction. The instructors or learners in WBI claim to be able to resolve reluctant fluctuations such as disorientation and cognitive overload. To overcome these phenomena, a supplementary tool able to manage learning space organized by the instructor's or learner's own way and offer effective navigation techniques is presented in this paper. A learning space management and navigation tool called HyperMap dynamically represents the learning space in the form of a two-dimensional labeled graph. This HyperMap also can be used for an instruction design tool, learner's portfolio for the exchange of learning experiences. and the assessment of WBI.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.108-113
• /
• 2022

The deep-learning-based measurement method with the through-focus scanning optical microscopy (TSOM) estimated the size of the object using the classification. However, the measurement performance of the method depends on the number of subdivided classes, and it is practically difficult to prepare data at regular intervals for training each class. We propose an approach to measure the size of an object in the TSOM image using the deep-learning regression model instead of using classification. We attempted our proposed method to estimate the top critical dimension (TCD) of through silicon via (TSV) holes with 2461 TSOM images and the results were compared with the existing method. As a result of our experiment, the average measurement error of our method was within 30 nm (1σ) which is 1/13.5 of the sampling distance of the applied microscope. Measurement errors decreased by 31% compared to the classification result. This result proves that the proposed method is more effective and practical than the classification method.

• Smart Structures and Systems
• /
• v.30 no.3
• /
• pp.287-301
• /
• 2022

The machine-vision based structural displacement measurement methods are widely used due to its flexible deployment and non-contact measurement characteristics. The accuracy of vision measurement is directly related to the image resolution. In the field of computer vision, super-resolution reconstruction is an emerging method to improve image resolution. Particularly, the deep-learning based image super-resolution methods have shown great potential for improving image resolution and thus the machine-vision based measurement. In this article, we firstly review the latest progress of several deep learning based super-resolution models, together with the public benchmark datasets and the performance evaluation index. Secondly, we construct a binocular visual measurement platform to measure the distances of the adjacent corners on a chessboard that is universally used as a target when measuring the structure displacement via machine-vision based approaches. And then, several typical deep learning based super resolution algorithms are employed to improve the visual measurement performance. Experimental results show that super-resolution reconstruction technology can improve the accuracy of distance measurement of adjacent corners. According to the experimental results, one can find that the measurement accuracy improvement of the super resolution algorithms is not consistent with the existing quantitative performance evaluation index. Lastly, the current challenges and future trends of super resolution algorithms for visual measurement applications are pointed out.

• Journal of Convergence for Information Technology
• /
• v.10 no.7
• /
• pp.33-40
• /
• 2020

This work tackles the problem of conventional reinforcement learning scheme which has a relatively long training time to reduce energy consumption in underwater network. The enhanced scheme adjusts the learning range of reinforcement learning based on distance estimation. It can be reduce the scope of learning. To take account the fact that the distance estimation may not be accurate due to the underwater wireless network characteristics. this research added noise in consideration of the underwater environment. In simulation result, the proposed AQ-NAV scheme has completed learning much faster than existing method. AQ-NAV can finish the training process within less than 40 episodes. But the existing method requires more than 120 episodes. The result show that learning is possible with fewer attempts than the previous one. If AQ-NAV will be applied in Underwater Networks, It will affect energy efficiency. and It will be expected to relieved existing problem and increase network efficiency.

• Journal of The Korean Association of Information Education
• /
• v.2 no.2
• /
• pp.209-214
• /
• 1998

The advent of powerful hardware and advances in high speed networks enabled synchronous learning, with teachers and students being geographically distributed but connected via computer networks. Today's synchronous learning systems are mainly based on video conferencing technology which provides audio, video, and joint editing of documents only, but does not take into account the specific requirements of teaching, for instance, controlling the course of instruction, raising hands, or reference pointing. A shared whiteboard is often the core part of these systems. Therefore, in this paper, we look into implementation issues in whiteboards of distance learning systems. Particularly, system architectures and concurrency control mechanisms are considered.

• The Journal of Korean Association of Computer Education
• /
• v.4 no.1
• /
• pp.1-10
• /
• 2001

Internet accelerates the speed of Information society causing changes the method and purpose of education. The word "life-long learning" is no longer a new tenn for many of the world citizens, and they ask for a system to fulfill their need to learn. Information communication technology enables and provides technical base for such needs. Web based cyber education, especially, is known to be an important and alternative instructional method to mediate learning at a distance. At the present, however, with the breakneck pace of growth and interests on Web-based distance education, there are no guidelines provided to assure the quality. In this study, we have identified guiding principles to design and develop quality assurance model for effective distance education. This is critical, especially in Korea, since 9 distance. education institutions have been accredited to offer degree programs starting 2001 spring semester. Using this model, distance education providers and consumers can develop or select effective on-line courses.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.19-27
• /
• 2020

Recently, rapid and accurate 3D models creation is required in various applications using virtual reality and augmented reality technology. In this paper, we propose an on-site learning based shape deformation method which transforms the clothed 3D human model into the shape of an input point cloud. The proposed algorithm consists of two main parts: one is pre-learning and the other is on-site learning. Each learning consists of encoder, template transformation and decoder network. The proposed network is learned by unsupervised method, which uses the Chamfer distance between the input point cloud form and the template vertices as the loss function. By performing on-site learning on the input point clouds during the inference process, the high accuracy of the inference results can be obtained and presented through experiments.