• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.709-715
• /
• 2023

In this study, the performance evaluation of image quality for noise reduction was implemented using the U-net deep learning architecture in computed tomography (CT) images. In order to generate input data, the Gaussian noise was applied to ground truth (GT) data, and datasets were consisted of 8:1:1 ratio of train, validation, and test sets among 1300 CT images. The Adagrad, Adam, and AdamW were used as optimizer function, and 10, 50 and 100 times for number of epochs were applied. In addition, learning rates of 0.01, 0.001, and 0.0001 were applied using the U-net deep learning model to compare the output image quality. To analyze the quantitative values, the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. Based on the results, deep learning model was useful for noise reduction. We suggested that optimized hyper parameters for noise reduction in CT images were AdamW optimizer function, 100 times number of epochs and 0.0001 learning rates.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.803-812
• /
• 2022

With the increasing number of mobile device users worldwide, utilizing mobile edge computing (MEC) devices close to users for content caching can reduce transmission latency than receiving content from a server or cloud. However, because MEC has limited storage capacity, it is necessary to determine the content types and sizes to be cached. In this study, we investigate a caching strategy that increases the hit ratio from small base stations (SBSs) for mobile users in a heterogeneous network consisting of one macro base station (MBS) and multiple SBSs. If there are several SBSs that users can access, the hit ratio can be improved by reducing duplicate content and increasing the diversity of content in SBSs. We propose a Deep Q-Network (DQN)-based caching strategy that considers time-varying content popularity and content redundancy in multiple SBSs. Content is stored in the SBS in a divided form using maximum distance separable (MDS) codes to enhance the diversity of the content. Experiments in various environments show that the proposed caching strategy outperforms the other methods in terms of hit ratio.

• Journal of Educational Research in Mathematics
• /
• v.19 no.1
• /
• pp.1-24
• /
• 2009

The applications of ratio and similarity have been in need of everyday life from ancient times. Euclid's elements Ⅴand Ⅵ cover ratio and similarity respectively. In this note, we have done a comparative analysis to button down the contents of ratio and similarity covered by the math text books used in Korea, Euclid's elements and the math text books used in Japan and America. As results, we can observe some differences between them. When math text books used in Korea introduce ratio, they presented it by showing examples unlike math text books used in America and Japan which present ratio by explaining the definition of it. In addition, in the text books used in Korea and Japan, the order of dealing with condition of similarity of triangles and the triangle proportionality is different from that of the text books used in America. Also, condition of similarity of triangles is used intuitively as postulate without any definition in text books used in Korea and Japan which is different from America's. The manner of teaching depending on the way of introducing learning contents and the order of presenting them can have great influence on student's understanding and application of the learning contents. For more desirable teaching in math it is better to provide text books dealing with various learning contents which consider student's diverse abilities rather than using current text books offering learning contents which are applied uniformly.

• Knowledge Management Research
• /
• v.17 no.2
• /
• pp.205-229
• /
• 2016

Owing to the current economic downturn, one of the most important goals of the organizations who are actively involved in Information Technology Outsourcing (ITO) is the cost efficiency. We focus on supplier firm's domain understanding to make the cost efficiency; therefore, we examine how the disadvantages from lower domain knowledges affect outsourcing performance moderated by outsourcing ratio and knowledge change environments. That is, if clients can endure disadvantage from service providers' lower domain knowledge, they can achieve cost efficiency by choosing lower domain knowledge suppliers with less expensive cost. To examine performance gap depending on the environments, we applied 'A Learning Model of IT Outsourcing' which is suggested by previous literature. As a result, we suggest five strategies for clients to contract with suppliers which have lower domain knowledge: (1) Prepare the strategy to endure disadvantages from the early stage. (2) Make the strategy depending on outsourcing ratio. (3) Knowledge transfer between organizations is important. (4) Make a short-term contract if they do not have good environments for organizational learning. (5) Client's knowledge change environments are more important than those of supplier's. Finally, we offer various implications for clients and suppliers in IT outsourcing.

• Journal of Korean Elementary Science Education
• /
• v.23 no.4
• /
• pp.273-278
• /
• 2004

According to Piaget, children aged 11 are in the middle of concrete operation period and formal operation period. So, it is necessary to adopt the Learning Cycle Model (LCM) which helps students improve their cognitive development. After determining the test for the Science Concept of Matter (SCOM), the experimental group showed higher average than the comparative group in the post-test. In the sound understanding, the experimental group showed higher ratio than the comparative group. And in the ratio of imperfect, wrong understanding and no response, the experimental group was lower than the comparative group. On the questions that were needed the complicated inquiry, many students of both groups still couldn't find the fundamental cause. In forming the scientific conceptualization, there was a meaningful difference (p < .001) after post-test Analysis of Covariance (ANCOVA) with pre-test result. After determining the test for the Test Inquiry Science Process (TISP), the experimental group showed higher average than the comparative group in the post-test. In the category of basic inquiry process which is needed in concrete operation, there was a meaningful difference (p < .05). In the category of unified inquiry process which is needed in formal operation, they showed no meaningful difference (p > .05). Therefore, applying the LCM to the chapter of 'Solution and Dissolving' is more effective on improving the scientific conceptualization and on helping the concrete operation abilities than the teacher centered learning.

• Structural Engineering and Mechanics
• /
• v.86 no.2
• /
• pp.181-195
• /
• 2023

To predict the rheological behaviours along with the compressive strength of self-compacting concrete that incorporates environmentally friendly ingredients as cement substitutes, a comparative evaluation of machine learning methods is conducted. To model four parameters, slump flow diameter, L-box ratio, V-funnel time, as well as compressive strength at 28 days-a complete mix design dataset from available pieces of literature is gathered and used to construct the suggested machine learning standards, SVM, MARS, and Mp5-MT. Six input variables-the amount of binder, the percentage of SCMs, the proportion of water to the binder, the amount of fine and coarse aggregates, and the amount of superplasticizer are grouped in a particular pattern. For optimizing the hyper-parameters of the MARS model with the lowest possible prediction error, a gravitational search algorithm (GSA) is required. In terms of the correlation coefficient for modelling slump flow diameter, L-box ratio, V-funnel duration, and compressive strength, the prediction results showed that MARS combined with GSA could improve the accuracy of the solo MARS model with 1.35%, 11.1%, 2.3%, as well as 1.07%. By contrast, Mp5-MT often demonstrates greater identification capability and more accurate prediction in comparison to MARS-GSA, and it may be regarded as an efficient approach to forecasting the rheological behaviors and compressive strength of SCC in infrastructure practice.

• Asian Journal of Business Environment
• /
• v.12 no.1
• /
• pp.11-16
• /
• 2022

Purpose: This study is aimed to map the provinces in Indonesia based on the education and ICT indicators using several unsupervised learning algorithms. Research design, data, and methodology: The education and ICT indicators such as student-teacher ratio, illiteracy rate, net enrolment ratio, internet access, computer ownership, are used. Several approaches to get deeper understanding on provincial strength and weakness based on these indicators are implemented. The approaches are Ensemble K-Mean and Fuzzy C Means clustering. Results: There are at least three clusters observed in Indonesia the education quality, participation, facilities and ICT Access. Cluster with high education quality and ICT access are consist of DKI Jakarta, Yogyakarta, Riau Islands, East Kalimantan and Bali. These provinces show rapid economic growth. Meanwhile the other cluster consisting of six provinces (NTT, West Kalimantan, Central Sulawesi, West Sulawesi, North Maluku, and Papua) are the cluster with lower education quality and ICT development which impact their economic growth. Conclusions: The provinces in Indonesia are clustered into three group based on the education attainment and ICT indicators. Some provinces can directly implement e-learning; however, more provinces need to improve the education quality and facilities as well as the ICT infrastructure before implementing the e-learning.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1171-1176
• /
• 2023

In this paper, we predicts the estimated price using the DNBP (Deep learning Network to predict Budget Price) model with bidding data obtained from the bidding websites, ElecNet and OK EMS. We use the DNBP model to predict four lottery preliminary price, calculate their arithmetic mean, and then estimate the expected budget price ratio. We evaluate the model's performance by comparing it with the actual expected budget price ratio. We train the DNBP model by removing some of the 15 input nodes. The prediction results showed the lowest RMSE of 0.75788% when the model had 6 input nodes (a, g, h, i, j, k).

• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.1
• /
• pp.61-69
• /
• 2001

This paper presents a two stage game model which examines the effect of learning-by-doing and spillover. Increases in the firm’s cumulative experience lower its unit cost in future period. However, the firm’s rival also enjoys the experience via spillover. Unlike previous theoretical research model, a cost asymmetric market entry game model is developed between the incumbent firm and new entrant. Mathematical results show that the incumbent firm exploits the learning curve to gain future cost advantage, and that the diffusion of learning to the new entrant induces the incumbent firm to choose decreasing output strategically. As a main result, we show that the relative magnitude between the learning and spillover rate determines the market share ratio of competing firms.

• Journal of Information Technology Applications and Management
• /
• v.15 no.1
• /
• pp.225-242
• /
• 2008

PM (Inconsistency Pattern Modeling) is a hybrid supervised learning technique using the inconsistence pattern of input variables in mining data sets. The IPM tries to improve prediction accuracy by combining more than two different supervised learning methods. The previous related studies have shown that the IPM was superior to the single usage of an existing supervised learning methods such as neural networks, decision tree induction, logistic regression and so on, and it was also superior to the existing combined model methods such as Bagging, Boosting, and Stacking. The objectives of this paper is explore the characteristics of the IPM. To understand characteristics of the IPM, three experiments were performed. In these experiments, there are high performance improvements when the prediction inconsistency ratio between two different supervised learning techniques is high and the distance among supervised learning methods on MDS (Multi-Dimensional Scaling) map is long.