• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.3
• /
• pp.77-82
• /
• 2012

It is well known that the targeted fuel efficiency could only be achieved by more than 40% reduction of the vehicle weight through improved design and extensive utilization of lightweight materials. In order to obtain the goal of the weight reduction of automobiles, the researches about lighter and stronger rear sub-frame have been studied without sacrificing the safety of rear sub-frame. In this study, the weight reduction design process of rear sub-frame could be proposed based on the variation of von-Mises stress contour by substituting an AA6061 (aluminum 6061 alloy) having tensile strength of 310 MPa grade instead of SAPH440 steels. In addition, the stress ratio variations (stress over fatigue limit) of the rear sub-frame were examined and compared carefully. It could be reached that this approach method could be well established and be contributed for light-weight design guide and the optimum design conditions of the automotive rear sub-frame development.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.5
• /
• pp.17-25
• /
• 2019

In this paper, we introduce the technology to convert a single human image into a fashion show animation video clip. The technology can help the customers confirm the dynamic fitting result when combined with the virtual try on technique as well as the interesting experience to a normal person of being a fashion model. We developed an extended technique of full human 2D to 3D inverse modeling based on SMPLify human body inverse modeling technique, and a rigged model animation method. The 3D shape deformation of the full human from the body model was performed by 2 part deformation in the image domain and reconstruction using the estimated depth information. The quality of resultant animation videos are made to be publically available for evaluation. We consider it is a promising approach for commercial application when supplemented with the post - processing technology such as image segmentation technique, mapping technique and restoration technique of obscured area.

• Journal of Software Engineering Society
• /
• v.26 no.1
• /
• pp.1-16
• /
• 2013

Variable length information message is a communication protocol standard in order for computer network systems to provide efficient delivery of information. The variable length information messages were developed for varying and controlling details of information in accordance with message receiver's required information level or information access level. In the previous studies, data compressing techniques have been in use for information message optimization technologies in order to reduce physical sizes of information messages. In optimization technologies for information messages, accuracy of information is considered as the most important factor; therefore, only non-loss compression techniques are applied to the optimization technologies. However, the non-loss compression based information message optimization methods are not efficient in data compression, and these are limited to efficient delivery of information in wireless network environments that have constraint bandwidth. In this paper, we attempt to optimize information in the variable length information messages at message fields in order to reduce physical sizes of messages more efficiently. To demonstrate the efficiency of our approach, we conduct optimization experiments for variable length information messages.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.107-107
• /
• 2017

최근 과학 기술의 발달과 정보화로 인해 다양한 분야의 방대한 정보들이 디지털화되어 저장되고, 이를 효율적으로 저장하고 관리하는 기술에 대한 수요가 증대하고 있다. 특히, 수자원 분야에서도 지점 관측 형태의 직접 계측방식이 아닌 선, 면 형태의 간접 계측방식의 기술이 개발됨에 따라 짧은 시간 동안 많은 수의 양질의 자료를 취득할 수 있게 되었다. 이에 따라 과거에 비해 방대하고 연속적인 하천공간정보가 축척되었으며, 이를 저장하고 관리하고자 하는 필요성이 대두되고 있다. 하천공간정보 중 하천단면자료는 하천기본계획수립 시 핵심이 되는 자료중 하나일 뿐만 아니라 하천의 흐름 특성을 해석하기 위한 여러 물리 모형의 입력 자료로서, 하천의 물이 흐르는 하도공간을 흐름방향의 횡방향으로 절단하였을 때 생기는 면을 기록한 자료이다. 국가에서는 하천단면자료 계측을 위해 많은 예산을 투입하고 있으며, 실제로 많은 수의 하천에서 하천단면자료를 계측하고 있다. 하지만 계측된 하천단면자료는 컴퓨터를 이용하여 제도하는 응용프로그램용 파일(CAD)로 저장되어, 하천단면자료를 지속적으로 저장 관리 모니터링하기에는 어려운 실정이다. 본 연구에서는 이러한 하천단면자료를 지속적으로 저장 관리 모니터링 할 수 있는 시스템 개발을 목적으로 현재 개발 중인 하천공간정보 표준 자료모형과 하천공간정보를 전송할 수 있는 표준자료 전송 언어인 RiverML을 활용하였다. 본 연구에서 도입한 하천공간정보 표준 자료모형은 하천망을 기반으로 한 상호연계를 기본으로 하고 있어, 하천망을 구성하는 각 하천과 해당 하천의 단면자료 간의 관계를 규명하기 쉬우며, RiverML은 이와 유사하게 하천망을 기반으로 다양한 정보를 전달하기 쉬운 전송언어이다. 또한 국가에서 개발한 공간정보 오픈 플랫폼인 브이월드(Vworld)의 API를 활용하여 저장된 하천단면자료를 표출할 수 있게 하였다. 본 연구의 결과는 하천단면자료 저장 관리 모니터링에 유용하게 사용될 수 있을 뿐만 아니라, 지속적인 개발을 통해 하천에서 계측되는 공간정보뿐만 아니라 하천의 시설물, 생태환경, 문화 등의 하천공간정보과 연계하여 효율적인 시스템을 개발할 수 있을 것으로 사료된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.521-528
• /
• 2021

Existing image analysis systems in use in the military field are carried out by readers analyzing and identifying images themselves, writing and disseminating related content, and in this process, repetitive tasks are frequent, resulting in workload. In this paper, to solve the previous problem, we proposed an algorithm that can operate the Seq2Seq model on a word basis, which operates on a sentence basis, and applied the Attention technique to improve accuracy. In addition, by applying the Beam Search technique, we would like to recommend various current identification sentences based on the past identification contents of a specific area. It was confirmed through experiments that the Beam Search technique recommends sentences more effectively than the existing greedy Search technique, and confirmed that the accuracy of recommendation increases when the size of Beam is large.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.151-157
• /
• 2022

In this paper, the performance of various blockchain consensus algorithms was compared and analyzed as a method to increase the transaction cost and processing time during NFT transactions and to increase the transaction stability requirements that occur during smart contract execution. Network reliability and TPS are evaluation items for performance comparison. TPS and the stability of the Consensus algorithm are presented for three evaluation items. In order to establish a standardized expression for each evaluation item, the reliability of the node and the success rate of the smart contract were considered as variables in the calculation formula, and the performance of the consensus algorithm of the three groups, PoW/PoS, Paxos/Raft and PBFT, was compared under the same conditions. / analyzed. As a result of the performance evaluation, the network reliability of the three groups was similar, and in the case of the remaining two evaluation items, it was analyzed that the PBFT consensus algorithm was superior to other consensus algorithms. Through the performance evaluation equations and results of this study, it was analyzed that when the PBFT consensus processing process is reflected in the consensus process, the network reliability can be guaranteed and the stability and economic efficiency of the consensus algorithm can be increased.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.13-22
• /
• 2021

The clinical decision support system uses accumulated medical data to apply an AI model learned by machine learning to patient diagnosis and treatment prediction. However, the existing black box-based AI application does not provide a valid reason for the result predicted by the system, so there is a limitation in that it lacks explanation. To compensate for these problems, this paper proposes a system model that applies XAI that can be explained in the development stage of the clinical decision support system. The proposed model can supplement the limitations of the black box by additionally applying a specific XAI technology that can be explained to the existing AI model. To show the application of the proposed model, we present an example of XAI application using LIME and SHAP. Through testing, it is possible to explain how data affects the prediction results of the model from various perspectives. The proposed model has the advantage of increasing the user's trust by presenting a specific reason to the user. In addition, it is expected that the active use of XAI will overcome the limitations of the existing clinical decision support system and enable better diagnosis and decision support.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.27 no.1
• /
• pp.27-33
• /
• 2023

Demands for eco-friendly food materials are increasing rapidly because of increased interest in well-being and health care, deterioration of air quality due to fine dust, and various soil and water pollution. Aquaponics is a system that can solve various problems such as economic activities, environmental problems, and safe food provision of the elderly population. However, techniques for deriving the optimal growth environment should be preceded. In this paper, we intend to design an intelligent plant growth measurement system that considers the characteristics of existing aquaponics. In particular, we would like to propose a module configuration plan for learning data and judgment systems when providing a uniform growth environment, focusing on designing systems suitable for production sites that do not have high-performance processing resources among intelligent aquaponics production management modules. It is believed that the proposed system can effectively perform deep learning with small analysis resources.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2022

Although 2D Object detection has been largely improved in the past years with the advance of deep learning methods and the use of large labeled image datasets, 3D object detection from 2D imagery is a challenging problem in a variety of applications such as robotics, due to the lack of data and diversity of appearances and shapes of objects within a category. Google has just announced the launch of Objectron that has a novel data pipeline using mobile augmented reality session data. However, it also is corresponding to 2D-driven 3D object detection technique. This study explores more mature 2D object detection method, and applies its 2D projection to Objectron 3D lifting system. Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a stochastic representation of object regions using Gaussian distributions. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a stochastic Intersection-over-Union. Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in available datasets. Thus, less accuracy problem that is one of several limitations of Objectron can be relaxed.

• Journal of The Korean Association of Information Education
• /
• v.24 no.2
• /
• pp.201-214
• /
• 2020

Big data is gradually expanding in diverse fields, with changing the data-related legislation. Moreover it would be interest in big data education. However, it requires a high level of knowledge and skills in order to utilize Big Data and it takes a long time for education spends a lot of money for training. We study that in order to define Universal Big Data used to the industrial field in a wide range. As a result, we make the paradigm for Big Data education for college students. We survey to the professional the Big Data definition and the Big Data perception. According to the survey, the Big Data related-professional recognize that is a wider definition than Computer Science Big Data is. Also they recognize that the Big Data Processing dose not be required Big Data Processing Frameworks or High Performance Computers. This means that in order to educate Big Data, it is necessary to focus on the analysis methods and application methods of Universal Big Data rather than computer science (Engineering) knowledge and skills. Based on the our research, we propose the Universal Big Data education on the new paradigm.