• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.

• Convergence Security Journal
• /
• v.22 no.3
• /
• pp.25-32
• /
• 2022

Recently, the image processing industry has been activated as deep learning-based technology is introduced in the image recognition and detection field. With the development of deep learning technology, learning model vulnerabilities for adversarial attacks continue to be reported. However, studies on countermeasures against poisoning attacks that inject malicious data during learning are insufficient. The conventional countermeasure against poisoning attacks has a limitation in that it is necessary to perform a separate detection and removal operation by examining the training data each time. Therefore, in this paper, we propose a technique for reducing the attack success rate by applying modifications to the training data and inference data without a separate detection and removal process for the poison data. The One-shot kill poison attack, a clean label poison attack proposed in previous studies, was used as an attack model. The attack performance was confirmed by dividing it into a general attacker and an intelligent attacker according to the attacker's attack strategy. According to the experimental results, when the proposed defense mechanism is applied, the attack success rate can be reduced by up to 65% compared to the conventional method.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.31-41
• /
• 2022

Steel is one of the most fundamental components to mechanical industry. However, the quality of products are greatly impacted by the surface defects in the steel. Thus, researchers pay attention to the need for surface defects detector and the deep learning methods are the current trend of object detector. There are still limitations and rooms for improvements, for example, related works focus on developing the models but don't take into account real-time application with practical implication on industrial settings. In this paper, a real-time application of steel surface defects detection based on YOLOv4 is proposed. Firstly, as the aim of this work to deploying model on real-time application, we studied related works on this field, particularly focusing on one-stage detector and YOLO algorithm, which is one of the most famous algorithm for real-time object detectors. Secondly, using pre-trained Yolov4-Darknet platform models and transfer learning, we trained and test on the hot rolled steel defects open-source dataset NEU-DET. In our study, we applied our application with 4 types of typical defects of a steel surface, namely patches, pitted surface, inclusion and scratches. Thirdly, we evaluated YOLOv4 trained model real-time performance to deploying our system with accuracy of 87.1 % mAP@0.5 and over 60 fps with GPU processing.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.1
• /
• pp.71-77
• /
• 2023

With the continuous industrial development, not only natural resource depletion, waste generation, but also various weather conditions are becoming more frequent. Efforts are continuing to recycle industrial by-products to overcome the climate crisis and save resources. Slag is a representative by-product generated in the steel industry, and it is characterized by improving rutting resistance and moisture sensitivity by increasing strength and reducing deformation when used as a material for asphalt concrete. On the other hand, slag has expansion properties so it is used as a relatively low-value-added material such as embankment and refilling materials. In order to expand the application of slag, an experiment was conducted to evaluate the crack resistance of slag asphalt concrete pavement. As a result of the indirect tensile strength test, it was found that the asphalt mixture using slag aggregate showed a value 1.13 times higher than that of the general HMA with the same particle size, and the toughness was 1.17 units, improving crack resistance. In addition, it was found that the failure number of the 4-point beam fatigue experiment and the slag asphalt mixture was 20,409, which was more than doubled compared to the general HMA. Furthermore, Overlay Test showed a tensile load residual rate of 4 times or more, improving crack resistance to repeated fatigue. Accordingly, the use of slag aggregate will likely have various advantages in improving the performance of asphalt concrete pavement.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.825-834
• /
• 2023

The demands of people who purchase fashion products on Internet shopping are gradually increasing, and attempts are being made to provide user-friendly images with 3D contents and web 3D software instead of pictures and videos of products provided. As a reason for this issue, which has emerged as the most important aspect in the fashion web shopping industry, complaints that the product is different when the product is received and the image at the time of purchase has been heightened. As a way to solve this problem, various image processing technologies have been introduced, but there is a limit to the quality of 2D images. In this study, we proposed an automatic conversion technology that converts 2D images into 3D and grafts them to web 3D technology that allows customers to identify products in various locations and reduces the cost and calculation time required for conversion. We developed a system that shoots a mannequin by placing it on a rotating turntable using only 8 cameras. In order to extract only the clothing part from the image taken by this system, markers are removed using U-net, and an algorithm that extracts only the clothing area by identifying the color feature information of the background area and mannequin area is proposed. Using this algorithm, the time taken to extract only the clothes area after taking an image is 2.25 seconds per image, and it takes a total of 144 seconds (2 minutes and 4 seconds) when taking 64 images of one piece of clothing. It can extract 3D objects with very good performance compared to the system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2D
• /
• pp.249-258
• /
• 2008

Korean engineering firms need to improve their performance in order to stay competitive in the globalize environments which has been led by some international movements including World Trade Organization (WTO) and Free Trade Agreements (FTA). There have been various activities and researches focusing on how to improve competitiveness of Korean engineering firms and the out-of-fashion Engineering Project Delivery System (EPDS) has repetitively identified as one of main barriers to deter advancements of Korean engineering industry. Therefore, this research attempted to investigate global standards of EPDS such as International Federation of Consulting Engineers (FIDIC), American Federal Acquisition Regulations (FAR), Brooks Act, and so on. The procedures of international EPDSs along with a few case studies were comprehensively analyzed and compared with Korean EPDS in order to propose recommendations of improving Korean EPDS. Some major differences between international and Korean EPDS were identified and they includes emphasis on qualifications of engineers and/or firms rather than their proposed cost, extensive use of long and short-list, common use of negotiation process, etc. Research findings are envisioned to guide the Korean public engineering sector to innovate Korean EPDS.

• Asia Marketing Journal
• /
• v.13 no.4
• /
• pp.191-212
• /
• 2012

With the introduction of the Capital Market Integration Act in 2009, the new competitive scope and paradigm is opened in Korean financial services market. The change of financial industry and institutions will lead to the behavioral change of customers who consume and choose financial services. While researches from the financial perspective have been conducted, works from the marketing or customer oriented approach has long been relatively ignored. The purpose of this study is to investigate influencing factors and process of financial services customers' choice behavior. More specifically, the main theme is how to enhance customer brand loyalty and purchase intention through the perception of overall quality of the service product. An integrated conceptual model including antecedents, mediating variables and consequences is established through comprehensive literature reviews of extant works on environmental change, customer behavioral change and choice behaviors. Hypothesis testing is done with SEM analysis. According to the results, the attractiveness of financial product, the reputation of financial firm, and self-brand image congruence among exogenous variables make a positive effect on perceived overall quality. And perceived overall quality has a significant effect on brand loyalty.

• Journal of Software Assessment and Valuation
• /
• v.15 no.2
• /
• pp.111-119
• /
• 2019

The existing smart grid device authentication system is concentrated on DCU, meter reading FEP and MDMS, and the authentication system for smart meters is not established. Although some cryptographic chips have been developed at present, it is difficult to complete the PKI authentication scheme because it is at the low level of simple encryption. Unlike existing power grids, smart grids are based on open two-way communication, increasing the risk of accidents as information security vulnerabilities increase. However, PKI is difficult to apply to smart meters, and there is a possibility of accidents such as system shutdown by sending manipulated packets and sending false information to the operating system. Issuing an existing PKI certificate to smart meters with high hardware constraints makes authentication and certificate renewal difficult, so an ultra-lightweight password authentication protocol that can operate even on the poor performance of smart meters (such as non-IP networks, processors, memory, and storage space) was designed and implemented. As a result of the experiment, lightweight cryptographic authentication protocol was able to be executed quickly in the Cortex-M3 environment, and it is expected that it will help to prepare a more secure authentication system in the smart grid industry.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.6
• /
• pp.63-65
• /
• 2023

BIM and AR technologies have been assessed as a means of enhancing productivity within the construction industry, through the provision of effortless access to critical data on site, achieved via the projection of 3D models and associated information onto actual structures. However, most of the previous researches for applying AR technology in construction quality management has been performed for construction projects in general, resulting in only overall on-site management solutions. Also, a few previous researches for the application of AR in the quality management of specific elements like reinforcements focused only on simple projection, so conducting specific quality inspection was impossible. Hence, this study aimed to develop a practically applicable BIM-based AR quality management system targeted for reinforcements. For the development of this system, the reinforcement inspection items on the quality checklist used at railway construction sites were analyzed, and four types of AR functions that can effectively address these items were developed and installed. The validation result of the system for the actual railway bridge showed a degradation of projection stability. This problem was solved through model simplification and enhancement of the AR device's hardware performance, and then the normal operation of the system was validated. Subsequently, the final developed reinforcement quality inspection system was evaluated for practical applicability by on-site quality experts, and the efficiency of inspection would significantly increase when using the AR system compared to the current inspection method for reinforcements.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.11 no.4
• /
• pp.349-354
• /
• 2023

This study wa s conducted a s pa rt of ma ximizing the use of ca rbon dioxide by a pplying CCU(Ca rbon Ca pture, Utiliza tion) a mong technologies for reducing CO₂ in the cement industry. In a carbon dioxide curing environment, changes in carbonation depth and changes in basic physical properties by age due to the mixing of carbonation reaction accelerators were usually targeted at Portland cement paste. In addition, in order to check the fixed amount of CO₂ in the concrete field, a thermal analysis method was applied to evaluate CaCO₃ decarbonization at high temperatures. As a result of the evaluation, it was confirmed that the carbonation depth in the cured body significantly increased due to the incorporation of CRA in the carbonation depth diffusion performance. In addition, it was confirmed that the weight reduction rate increased by 23.8 % and 40.77 %, respectively, compared to Plain, in the order of curing conditions for constant temperature and humidity and curing conditions for carbonation chambers, so it was confirmed that the amount of excellent CaCO₃ produced by the addition of CRA increased as the concentration of CO₂ increased.