• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.25-33
• /
• 2023

Noise generated during the acquisition and transmission of CT images acts as a factor that degrades image quality. Therefore, noise removal to solve this problem is an important preprocessing process in image processing. In this paper, we remove noise by using a deformable convolutional autoencoder (DeCAE) model in which deformable convolution operation is applied instead of the existing convolution operation in the convolutional autoencoder (CAE) model of deep learning. Here, the deformable convolution operation can extract features of an image in a more flexible area than the conventional convolution operation. The proposed DeCAE model has the same encoder-decoder structure as the existing CAE model, but the encoder is composed of deformable convolutional layers and the decoder is composed of conventional convolutional layers for efficient noise removal. To evaluate the performance of the DeCAE model proposed in this paper, experiments were conducted on CT images corrupted by various noises, that is, Gaussian noise, impulse noise, and Poisson noise. As a result of the performance experiment, the DeCAE model has more qualitative and quantitative measures than the traditional filters, that is, the Mean filter, Median filter, Bilateral filter and NL-means method, as well as the existing CAE models, that is, MAE (Mean Absolute Error), PSNR (Peak Signal-to-Noise Ratio) and SSIM. (Structural Similarity Index Measure) showed excellent results.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.91-100
• /
• 2023

This study is a case study comparing and examining the effects of non-face-to-face(NFTF) classes in the 2021-2 semester and face-to-face(FTF) classes in the 2022-2 semester on learning immersion, learning stress, and learning satisfaction. The learning immersion and learning satisfaction of 240 students were analyzed in NFTF and FTF classes of department S of C junior college where the same textbook, same subject, and same professor were taught. For data processing, SPSS Ver. 23.0 was used. The data is used to measure reliability by Cronbach's α, t-test, Pearson's correlation coefficient, and multiple regression analysis. The results of this study are as follows. First, learners' learning immersion was higher in FTF than NFTF classes among engineering major subjects. Second, it was found that there was a difference in learning stress according to the types of FTF and NFTF classes in engineering major subjects. Third, it was found that there were differences in practice content, communication, and task performance of sub-factors of learning satisfaction according to FTF and NFTF class types in engineering major subjects. In conclusion, it was found that FTF classes had a more positive effect on learning immersion and satisfaction, and NFTF classes had a more negative effect on learning stress.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.17-26
• /
• 2023

In this paper, we propose a several smoothing techniques are compared and applied to increase the application of the LSTM-based learning model and its effectiveness. The applied smoothing technique is Savitky-Golay, exponential smoothing, and weighted moving average. Through this study, the LSTM algorithm with the Savitky-Golay filter applied in the preprocessing process showed significant best results in prediction performance than the result value shown when applying the LSTM model to Bitcoin data. To confirm the predictive performance results, the learning loss rate and verification loss rate according to the Savitzky-Golay LSTM model were compared with the case of LSTM used to remove complex factors from Bitcoin price prediction, and experimented with an average value of 20 times to increase its reliability. As a result, values of (3.0556, 0.00005) and (1.4659, 0.00002) could be obtained. As a result, since crypto-currencies such as Bitcoin have more volatility than stocks, noise was removed by applying the Savitzky-Golay in the data preprocessing process, and the data after preprocessing were obtained the most-significant to increase the Bitcoin prediction rate through LSTM neural network learning.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.45-58
• /
• 2023

KVMF(Korean Variable Message Format) 1.0 protocol is the Army's standard tactical datalink protocol that defines standard messages and communication methods to enable data communication between various weapon systems through bitwise variable message processing. The protocol has been applied to a variety of Army weapon systems over the past decade and has contributed to upgrade the Army's operational capabilities by enabling the implementation of Network Centric Warfare (NCW), the core of modern warfare. Since the KVMF 1.0 protocol was applied, new weapon systems with new technologies have been introduced over time, and new weapon systems have new messages based on the characteristics of the weapon system. As a result, compatibility problems arose due to different message versions with existing weapon systems, and it was expected that these problems would continue to emerge in the future, considering the need for continuous message revisions. Therefore, it became necessary to solve this problem, so this paper proposed a KVMF 2.0 protocol design that guarantees compatibility between forward and backward versions. In this paper, we implemented the design as SW, and confirmed that the design worked successfully by test between forward and backward versions on test environment. Therefore, when the KVMF 2.0 protocol design is applied to a weapon system, we can expect that the weapon system can be compatible with the forward and backward versions working with the existing weapon systems as well as with the future weapon systems.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.583-593
• /
• 2022

The harvesting system in South Korea faces the problems of aging workers and high wages, so it is necessary to improve the operation system and train workers to use high-performance forestry machines. This study compared the effectiveness and costs of yarding and processing operations between a multi-operation system using a tower yarder (HAM300) and a processor (KESLA 20SH) with those of a single-system using a forestry combi-machine. A whole-tree (cable) yarding operation was conducted in the clear-cutting area located at Compartment 15, Gwangneung Experimental Forest, National Institute of Forest Science, and the productivity and cost of multi- and single-system were analyzed. The productivity of the single-system was 1.5 m³/PMH and 1.6 m³/PMH higher than that of the multi- system because the single-system produced 1 log/cycle more than the multi-system in the yarding operation. The cost was approximately 12.1% lower for the single-system (￦36,113/m³) than for the multi-system (￦41,065/m³). The costs of the single-system and multi-system were decreased by maximums of 22.6% and 15.9%, respectively, by decreasing the idle time.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.31-40
• /
• 2023

Various policies and services are being implemented in Korea and other countries, such as the expansion of convenience facilities for mobility support, the provision of special means of transportation, and the establishment of public transportation route plans and fare policies based on data and AI-based movement pattern analysis to ensure the mobility rights of the weak in transportation. However, A research is still needed to improve service convenience in order to more conveniently use the desired means of transportation in a necessary situation from the viewpoint of the transportation vulnerable. This study examines the policies and services for the promotion of mobility for the transportation disadvantaged, and presents a MyData-based service model for mobility support for the transportation disadvantaged. In the proposed service model, the transportation-disabled person can freely choose and use the means of transportation according to individual circumstances, and receive the same transportation welfare voucher benefits provided by the state or government. The proposed service model defines the MyData platform that supports the safe collection and use of personal data, the authentication of traffic welfare recipients based on MyData, and the payment function for fee settlement after using the service as key components. In this research, the service satisfaction from the user's point of view was investigated by implementing the proposed service model and providing a demonstration service for the transportation vulnerable in Daejeon.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.1-18
• /
• 2023

Similar software is often developed with the Clone-And-Own (CAO) approach that copies and modifies existing artifacts. The CAO approach is considered as a bad practice because it makes maintenance difficult as the number of cloned products increases. Software product line engineering is a methodology that can solve the issue of the CAO approach by developing a product family through systematic reuse. Migrating product families that have been developed with the CAO approach to the product line engineering begins with finding, integrating, and building them as reusable assets. However, cloning occurs at various levels from directories to code lines, and their structures can be changed. This makes it difficult to build product line code base simply by finding clones. Successful migration thus requires unifying the source code's file path, class name, and method signature. This paper proposes a clustering method that identifies a set of similar codes scattered across product variants and some of their method full paths are different, so path unification is necessary. In order to show the effectiveness of the proposed method, we conducted an experiment using the Apo Games product line, which has evolved with the CAO approach. As a result, the average precision of clustering performed without preprocessing was 0.91 and the number of identified common clusters was 0, whereas our method showed 0.98 and 15 respectively.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.12
• /
• pp.91-101
• /
• 2022

The 1995 Kobe earthquake caused a massive damage to the Port of Kobe. Therefore, it was pointed out that it was impossible to design port structures for Level II (Mw 6.5) earthquakes with quasi-static analysis and Allowable Stress Design methods. In Japan and the United States, where earthquakes are frequent, the most advanced design standards for port facilities are introduced and applied, and the existing seismic design standards have been converted to performance-based design. Since 1999, the Korean Port Seismic Design Act has established a definition of necessary facilities and seismic grades through research on facilities that require seismic design and their seismic grades. It has also established a performance-based seismic design method based on experimental verification. In the performance-based seismic design method of the breakwater proposed in this study, the acceleration time history on the surface of the original ground was subjected to a fast Fourier transform, followed by a filter processing that corrected the frequency characteristics corresponding to the maximum allowable displacement with respect to performance level of the breakwater and the filtered spectrum. The horizontal seismic coefficient for the equivalent static analysis considering the displacement was calculated by inversely transforming (i.e., subjected to an inverse fast Fourier transform) into the acceleration time history and obtaining the maximum acceleration value. In addition, experiments and numerical analysis were performed to verify the performance-based seismic design method of breakwaters suitable for domestic earthquake levels.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.21 no.4
• /
• pp.21-28
• /
• 2022

This study analyzes the reality of the overall operating system, such as recognition and satisfaction with school field support work system of the Education Facilities Management Center, recognition level of restructuring of work areas, and the direction of improvement for school facility maintenance support in various types of future learning environments. To analyze the problem of this study, a survey was conducted on 290 education administrative officials in Gyeonggi-do. First, school site awareness and work performance satisfaction of the Educational Facilities Management Center were evaluated as "below average," and it is necessary to improve the qualitative work area that is practically helpful to schools. Second, in the area of organizational operation, it is desirable to avoid simple tasks with a low evaluation of "below average" and to switch to an operating system that improves efficiency. Third, the need for the facility environment area (professionalism, safety) was the highest, but the center's ability and work processing level were evaluated very low as "below average," so it is urgent to improve the center's capacity. Fourth, in the area of social and educational policy change, the center received a high score for the need for access from the perspective of a learning environment linked to future education. Therefore, a policy review on the restructuring and improvement of work areas suitable for this is necessary.