• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.4
• /
• pp.259-264
• /
• 2023

In this study, we devised a parametric analysis workflow for efficiently analyzing the material properties of 3D woven materials. The parametric model uses wire spacing in the woven materials as a design parameter; we generated 2,500 numerical models with various combinations of these design parameters. Using MATLAB and ANSYS software, we obtained various material properties, such as bulk modulus, thermal conductivity, and fluid permeability of the woven materials, through a parametric batch analysis. We then used this large dataset of material properties to perform a regression analysis to validate the relationship between design variables and material properties, as well as the accuracy of numerical analysis. Furthermore, we constructed an artificial neural network capable of predicting the material properties of 3D woven materials on the basis of the obtained material database. The trained network can accurately estimate the material properties of the woven materials with arbitrary design parameters, without the need for numerical analyses.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.86-86
• /
• 2021

온천천은 부산광역시 금정구, 동래구, 연제구를 흐르는 도심 하천으로 부산 시민들의 도심 속 산책길, 자전거 길 등으로 활용되는 도시하천이다. 그러나 온천천 양안의 동래 곡저 평야가 시가지화 되고 온천천 발원지인 금정산 주변에서 무허가 상수도를 사용하고 각종 쓰레기와 하수의 유입으로 인해 하천 전체가 하수관으로 변해왔다. 이에 따라 부산광역시는 온천천 정비 계획을 시행하여 하천 정비와 함께 자동측정망을 설치하여 하천의 DO (dissolved oxygen), 탁도, TDS농도 등 자료를 수집하고 있다. 그러나 자동측정망으로 쌓여가는 데이터를 활용하여 DO농도 예측은 거의 이뤄지지 않고 있다. DO는 하천의 수질 오염 정도를 판단하는 수질인자로 역사적으로 하천 연구의 주요 연구 대상이 되어 왔다. 본 연구에서는 일 자료 뿐만 아니라 시 자료를 기반으로 RNN-LSTM 알고리즘을 활용한 DO예측을 시도하였다. RNN-LSTM은 시계열 학습에 뛰어난 알고리즘으로 인공신경망의 발전된 형태인 순환신경망이다. 연구에 앞서 부산광역시 보건환경정보 공개시스템으로부터 받은 자료 중에서 교정, 보수 중, 비사용, 장비전원단절 등으로 인해 누락데이터를 2014년 1월 1일부터 2018년 12월 31일의 데이터 전수조사 후 이상데이터를 확인하여 선형 보간하여 데이터를 사용하였다. 연구에서는 Google에서 개발한 딥러닝 오픈소스 라이브러리인 텐서플로우를 활용하여 부산광역시 금정구 부곡동에 위치한 부곡교 관측소의 DO농도를 시간 또는 일 예측을 하였다. 일 예측 학습에는 2014년~ 2018년의 기상자료(기온, 상대습도, 풍속, 강수량), DO농도 자료를 사용하였고, 시 예측 학습에는 연속된 자료가 가장 많은 2015년 3월 ~ 12월까지의 데이터를 활용하여 연구를 진행하였다. 모형의 검증을 위해 결정계수(R square)를 이용하여 통계분석을 실시하였다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.287-308
• /
• 2023

After launching its service in November 2022, ChatGPT has rapidly increased the number of users and is having a significant impact on all aspects of society, bringing a major turning point in the history of artificial intelligence. In particular, the inference ability of large language models such as ChatGPT is improving at a rapid pace through prompt engineering techniques. This reasoning ability can be considered as an important factor for companies that want to adopt artificial intelligence into their workflows or for individuals looking to utilize it. In this paper, we begin with an understanding of in-context learning that enables inference in large language models, explain the concept of prompt engineering, inference with in-context learning, and benchmark data. Moreover, we investigate the prompt engineering techniques that have rapidly improved the inference performance of large language models, and the relationship between the techniques.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.267-273
• /
• 2024

Using a cloud-based vertex AI platform that can develop an artificial intelligence learning model without coding, this study easily developed an artificial intelligence learning model by the non-professional general public and confirmed its clinical applicability. Nine dental diseases and 2,999 root disease X-ray images released on the Kaggle site were used for the learning data, and learning, verification, and test data images were randomly classified. Image classification and multi-label learning were performed through hyper-parameter tuning work using a learning pipeline in vertex AI's basic learning model workflow. As a result of performing AutoML(Automated Machine Learning), AUC(Area Under Curve) was found to be 0.967, precision was 95.6%, and reproduction rate was 95.2%. It was confirmed that the learned artificial intelligence model was sufficient for clinical diagnosis.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.231-237
• /
• 2024

Brain injury causes persistent disability in survivors, and epidural hematoma(EDH) and subdural hematoma (SDH) resulting from cerebral hemorrhage can be considered one of the major clinical diseases. In this study, we attempted to automatically segment and hematomas due to cerebral hemorrhage in three dimensions based on computed tomography(CT) images. An improved GVF(gradient vector flow) algorithm was implemented for automatic segmentation of hematoma. After calculating and repeating the gradient vector from the image, automatic segmentation was performed and a 3D model was created using the segmentation coordinates. As a result of the experiment, accurate segmentation of the boundaries of the hematoma was successful. The results were found to be good even in border areas and thin hematoma areas, and the intensity, direction of spread, and area of the hematoma could be known in various directions through the 3D model. It is believed that the planar information and 3D model of the cerebral hemorrhage area developed in this study can be used as auxiliary diagnostic data for medical staff.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.557-564
• /
• 2013

An important research challenge about the traditional Internet environment is to enable open networking architecture on which end users are able to innovate the Internet based on the technologies of network programmability, virtualization, and federation. The SDN (Software Defined Network) technology that includes OpenFlow protocol specifications, is suggested as a major driver for the open networking architecture, and is closely coupled with the classical Internet (non-SDN). Therefore, it is very important to keep the integrated SDN and non-SDN network infrastructure reliable from the view point of network operators and engineers. Under this background, this paper proposes an operations and management framework for the combined software defined network environment across not only a single-domain network, but also multi-domain networks. The suggested framework is designed to allow SDN controllers and DvNOC systems to interact with each other to achieve sustainable end-to-end user-oriented SDN and non-SDN integrated network environment. Plus, the proposed scheme is designed to apply enhanced functionalities on DvNOC to support four major network failure scenarios over the combined network infrastructure, mainly derived from SDN controllers, SDN devices, and the connected network paths.

• Journal of Korea Multimedia Society
• /
• v.8 no.7
• /
• pp.924-942
• /
• 2005

Recently, large-scale directories have been developed for LINUX cluster file systems to store and retrieve huge amount of data. One of them, GFS directory, has attracted much attention because it is based on extendible hashing, one of dynamic hashing techniques, to support fast access to files. One distinctive feature of the GFS directory is the flat structure where all the leaf nodes are located at the same level of the tree. Hut one disadvantage of the mode structure is that the height of the mode tree has to be increased to make the tree flat after a byte is inserted to a full tree which cannot accommodate it. Thus, one byte addition makes the height of the whole mode tree grow, and each data block of the new tree needs one more link access than the old one. Another dynamic hashing technique which can be used for directories is linear hashing and a couple of researches have shown that it can get better performance at file access times than extendible hashing. [n this research, we have designed and implemented an extendible hashing directory and a linear hashing directory for large-scale LINUX cluster file systems and have compared performance between them. We have used the semi-flat structure which is known to have better access performance than the flat structure. According to the results of the performance evaluation, the linear hashing directory has shown slightly better performance at file inserts and accesses in most cases, whereas the extendible hashing directory is somewhat better at space utilization.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.12
• /
• pp.653-662
• /
• 2016

This paper describes a test case generation algorithm for Simulink/Stateflow models based on the Rapidly exploring Random Tree (RRT) algorithm that has been successfully applied to path finding. An important factor influencing the performance of the RRT algorithm is the metric used for calculating the distance between the nodes in the RRT space. Since a test case for a Simulink/Stateflow (SL/SF) model is an input sequence to check a specific condition (called a test target in this paper) at a specific status of the model, it is necessary to drive the model to the status before checking the condition. A status maps to a node of the RRT. It is usually necessary to check various conditions at a specific status. For example, when the specific status represents an SL/SF model state from which multiple transitions are made, we must check multiple conditions to measure the transition coverage. We propose a unique distance calculation metric, based on the observation that the test targets are gathered around some specific status such as an SL/SF state, named key nodes in this paper. The proposed metric increases the probability that an RRT is extended from key nodes by imposing penalties to non-key nodes. A test case generation algorithm utilizing the proposed metric is proposed. Three models of Electrical Control Units (ECUs) embedded in a commercial vehicle are used for the performance evaluation. The performances are evaluated in terms of penalties and compared with those of the algorithm using a typical RRT algorithm.

• Journal of Internet Computing and Services
• /
• v.15 no.1
• /
• pp.29-43
• /
• 2014

The development of NGS technologies, such as scientific workflows, has reduced the time required for decoding DNA sequences. Although the automated technologies change the genome sequence analysis environment, limited computing resources still pose problems for the analysis. Most scientific workflow systems are pre-built platforms and are highly complex because a lot of the functions are implemented into one system platform. It is also difficult to apply components of pre-built systems to a new system in the cloud environment. Cloud computing technologies can be applied to the systems to reduce analysis time and enable simultaneous analysis of massive DNA sequence data. Web service techniques are also introduced for improving the interoperability between DNA sequence analysis systems. The workflow-based middleware, which supports Web services, DBMS, and cloud computing, is proposed in this paper for expecting to reduceanalysis time and aiding lightweight virtual instances. It uses DBMS for managing the pipeline status and supporting the creation of lightweight virtual instances in the cloud environment. Also, the RESTful Web services with simple URI and XML contents are applied for improving the interoperability. The performance test of the system needs to be conducted by comparing results other developed DNA analysis services at the stabilization stage.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.4
• /
• pp.135-140
• /
• 2015

The WDSS improves defensive capacity against web application layer DDoS attack by using web cache server and L7 switch which are added on the DDoS shelter system. When web DDoS attack occurs, security agents divert traffic from backbone network to sub-network of the WDSS and then DDoS protection device and L7 switch block abnormal packets. In the meantime, web cache server responds only to requests of normal clients and maintains stable web service. In this way, the WDSS can counteract the web DDoS attack which generates small traffic and depletes server-client session resource. Furthermore, the WDSS does not require IP tunneling because it is not necessary to retransfer the normal requests to original web server. In this paper, we validate operation of the WDSS and verify defensive capability against web application layer DDoS attacks. In order to do this, we built the WDSS on backbone network of an ISP. And we performed web DDoS tests by using a testing system that consists of zombie PCs. The tests were performed by three types and various amounts of web DDoS attacks. Test results suggest that the WDSS can detect small traffic of the web DDoS attacks which do not have repeat flow whereas the formal DDoS shelter system cannot.