• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.166-171
• /
• 2023

With significant advancements in the field of artificial intelligence, many novel algorithms and technologies have emerged. Currently, AI painting can generate high-quality images based on textual descriptions. However, it is often challenging to control details when generating images, even with complex textual inputs. Therefore, there is a need to implement additional control mechanisms beyond textual descriptions. Based on ControlNet, this passage describes a combined utilization of various local controls (such as edge maps and depth maps) and global control within a single model. It provides a comprehensive exposition of the fundamental concepts of ControlNet, elucidating its theoretical foundation and relevant technological features. Furthermore, combining methods and applications, understanding the technical characteristics involves analyzing distinct advantages and image differences. This further explores insights into the development of image generation patterns.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.417-422
• /
• 2023

AI blockchain technology, which is attracting attention as a core technology of the 4th Industrial Revolution, is a technology that can be used as an important means of innovation not only in the current gaming industry but also in various industrial fields. This paper extracts the platforms and types of blockchain games currently ranked within the top 100 on the blockchain app (DApp) sites State Of The DApps, DApp.com, and Dapp Rader and introduces the top games on major platforms. As a result of extracting platforms and types, the top games were mainly based on Ethereum, EOS, and Steam. However, the results showed that there are significantly more games based on the Ethereum platform, which are stable, easy to apply, and have a low barrier to entry due to the large number of users and DApps. We plan to improve awareness of blockchain games by studying the characteristics that only blockchain games have.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.11a
• /
• pp.17-18
• /
• 2023

This study aims to compare the hardness value development characteristics according to the water-cement ratio during a series of experiments to develop a setting estimator for an AI-based concrete finishing automation system. For the test variables, water-cement ratios are varied with 30, 40 and 50%. Proctor penetration test and surface hardness test by setting time estimator are conducted to estimate the setting time. For the effect of water-cement ratios, they did not affect the surface hardness either, while initial set time and final set time are not constant with water-cement ratios.

• Proceedings of the SAREK Conference
• /
• 2008.06a
• /
• pp.194-202
• /
• 2008

In this study, we investigated the tribology behaviour of two different bearing materials. One of these alloys content is Cu(90)-Sn(10) alloy and is widely used in the automotive industry.The other is Al alloy. This bearing content is Al-Sn-Si-Cu. Therefore, it is required to study on the lublicating characteristics of bearing according to different materials. In this study, compressor bearings made by respectively "PTFE solid lubricant" and "AI alloy with superior load carrying capacity, rubbing and impact endurance", have gone through journal bearing test. Lubrication and abrasion characteristics are evaluated by analyzing the material characteristics of a scroll compressor bearing bush. The AI alloy bearing showed the most excellent lubrication and abrasion characteristics than Cu-Sn alloy under high load condition.

• Proceedings of the Korea Society of Poultry Science Conference
• /
• 2006.11a
• /
• pp.90-91
• /
• 2006

To reduce the economic impact and control Low pathogenic avian influenza (LPAI), vaccination with inactivated vaccine has been considered in this country. We tried to develop inactivated vaccine with reassorted H9N3 AI virus which has different type of neuraminidase compare to those of field AI virus. Before reassorted vaccine was produced, we confirm the virus as master seed by limiting dilution, RT-PCR and sequencing method. Also, we evaluate the biological characteristics of the virus to find out the possibility of prevention against field infection of AI virus. Finally, we evaluate the safety and efficacy of the vaccine made of reassorted AI virus in the specific pathogen free (SPF) chickens. After limiting dilution, we choose RV7CE4 as a vaccine candidate and compare the gene sequence of this vaccine strain to those of AI05GA which is parents strain. Compared to amino acid sequences of specific gene of AI05GA and RV7CE4, exhibited a high degree of amino acid sequence homology. In the safety and efficacy test, there were no specific clinical signs or mortality. Reassorted H9N3 viruses were reisolated in cloaca swab on 5 days post inoculation. In the vaccine study, once or twice vaccination was performed and challenged with H9N2 field virus (01310). Vaccine has no adverse effect on birds and formed good immune capability which reduce viral shedding in the birds infected with 01310. Based on the above result, we developed reassorted H9N3 vaccine which will efficiently prevent the low pathogenic AIV (H9N2) infection in the poultry farms.

• Journal of the Korean Society of Combustion
• /
• v.19 no.3
• /
• pp.26-33
• /
• 2014

We examined the characteristics of $NO_x$ emission for CH4/air non-premixed flames using the exhaust gas recirculation(EGR) methods, which are the air-induced EGR(AI-EGR) and fuel-induced EGR(FI-EGR) methods. Our experimental results show that the $NO_x$ emission index($EI_{NOx}$) decreased with increasing EGR ratio. In the range needed to form a stable flame, the reduction rate of $EI_{NOx}$ for the FI-EGR method was approximately 29% when the EGR ratio was 20%, and the reduction rate for the AI-EGR method was approximately 28% with 25% of the EGR ratio. According to the flame structure based on numerical results, high temperature regions for the FI-EGR method were narrower and lower than those for the AI-EGR method at the same EGR ratio. Furthermore, based on the experimental results for swirl flames, the reduction rate of $EI_{NOx}$ for the FI-EGR method was approximately 49% with 15% of the EGR ratio, while the maximum reduction rate for AI-EGR method was approximately 45% with 25% of the EGR ratio. Consequently, we verified that the FI-EGR method was more effective than the AI-EGR method in reducing $NO_x$ emission for non-premixed flames with EGR. We expect that the results of this study will provide fundamental information relating to hybrid combustion systems, which can be used in the design of combustion systems in the future.

• Journal of Animal Reproduction and Biotechnology
• /
• v.36 no.4
• /
• pp.230-238
• /
• 2021

This study attempted to determine the characteristic features of postpartum dairy cows during their return to estrus. Moreover, it investigated the effects of abnormal ovarian cycles (AOC) on subsequent reproductive performance and the relationship between normal ovarian cycles (NOC) and the blood urea nitrogen (BUN) level postpartum. Incidentally, 56.3% of the Holstein cows and 66.7% of the Jersey cows had NOC, whereas the 43.7% and 33.3% of the Holstein and Jersey, respectively, had AOC. Within 100 days of calving, the cows with AOC had significantly lower rates of artificial insemination (AI) submission as well as pregnancy and a significantly longer interval to first AI, as compared to that in the cows with NOC. Additionally, the cows with NOC had a significantly higher first AI conception rate than that in the cows with AOC. In this study, of the 32 Holstein cows, 8 resumed their ovarian cycle within 20 days of calving, 10 resumed the cycle with 21-40 days of calving, 8 within 41-60 days of calving, while the remaining 6 did not resume their ovarian cycles until 60 days postpartum. Furthermore, the likelihood ratios of incidence of NOC are 0.93, 1.94, and 0.38, respectively, in the groups with BUN levels < 15, 15-19.9, and ≥ 20 mg/dl. In conclusion, AOC postpartum adversely affects reproductive performance such as AI submission rate, pregnancy rate, interval to first AI and first AI conception rate; moreover, an increase or decrease in the BUN levels beyond 15-19.9 mg/dL leads to the AOC postpartum.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.2-5
• /
• 2022

With the advent of deep learning and the rapid development of ICT (Information and Communication Technology), research using artificial intelligence is being actively conducted in various fields of society such as politics, economy, and culture and so on. Deep learning-based artificial intelligence technology is subdivided into various domains such as natural language processing, image processing, speech processing, and recommendation system. In particular, as the industry is advanced, the need for a recommendation system that analyzes market trends and individual characteristics and recommends them to consumers is increasingly required. In line with these technological developments, this paper extracts and classifies attribute information from structured or unstructured text and image big data through deep learning-based technology development of 'language processing intelligence' and 'image processing intelligence', and We propose an artificial intelligence-based 'customized fashion advisor' service integration system that analyzes trends and new materials, discovers 'market-consumer' insights through consumer taste analysis, and can recommend style, virtual fitting, and design support.

• The Journal of Information Systems
• /
• v.32 no.3
• /
• pp.205-224
• /
• 2023

Purpose This study investigates the impact of organizational characteristics on organizational performance through case studies of smart factory implementation in the context of Korean small and medium Enterprises (SMEs). To achieve this goal, this study adopts the smart factory index of KOSMO (Korea Smart Manufacturing Office) established by Korean Ministry of SMEs and Startups. We visited 3 firms implemented smart factory projects. This study presents the results of field study in detail with evaluation criteria on how organizational competences like AI technology adoption and facility automation can be exploited to positively influence organizational performance through smart factory implementation. Design/methodology/approach There are not so many results of empirical studies related to smart factories in Korea. This is because organizational support and user involvement are required for facility AI platform service beyond factory automation after the start of the 4th Industrial Revolution. Korean government's KOSMO (Korean Smart Manufacturing Office) has developed and proposed a level measurement index for smart factory implementation. This study conducts case studies based on the level measurement method proposed by KOSMO in the process of conducting case studies of three companies belonging to the root and mechanic industries in Korea. Findings The findings indicate that organizational competences, such as facility AI platform adoption and user involvement, are antecedents to influence smart factory implementation, while smart factory implementation has significant relationship with organizational performance. This study provides a better understanding of the connection between organizational competences and organizational performance through smart factory case studies. This study suggests that SMEs should focus on enhancing their organizational competences for improving organizational performance through implementing smart factory projects.