• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.8
• /
• pp.927-938
• /
• 2014

A number of crime and disease relief situation show a clear increasing trend in domestic and overseas country. In particular, we desperately need a fast location information sharing with high accuracy for dealing with this situation efficiently. In this paper, we propose a DGPS framework and performance evaluation based on Web service enable increase location accuracy using low-cost GPS or AGPS. The framework consists of mobile station to realize the final service by receiving the correction values that are created in the base station closest to the current position from DGPS server, base station system to transmit the correct values to DPGS server by installing at base point and DGPS framework working at DGPS server. Our framework is fundamentally designed to respond based on XML to service request. In addition, for performance evaluation, we make use of 3 sites of Level 2 city base-station among the base stations being operated in Suncheon-si. Through performance evaluation, we show that our framework outperforms about 10%~15% in terms of error improvement rate, compared with the existing schemes. And we have the advantage that various services can be expanded owing to receiving the correction values through mobile device such as, smart phone, smart pad, net-book by using XML based Web services.

• 한국전산유체공학회:학술대회논문집
• /
• 2009.04a
• /
• pp.125-129
• /
• 2009

In this paper automatic 3D wing shape modeling program is introduced. The program is developed in Visual Basic based on Net Framework 3.5 environment by using CATIA COM Library, and it is used together with CATIA system to model 3D wings with or without flaps. With this program users can easily construct wing models by specifying geometry parameters which are usually design variables with the aid of easy-to-use GUI environment, and specifying sectional airfoil data is done either by using analytic shape functions such as NACA series airfoils or by providing input files with point data describing the airfoil shape. When all the input parameters are provided, users can either work further with the model in the CATIA system which would be automatically started by the program or save the resultant model in the format of users choice. Unstructured grid generation program is also briefly described which can make grid generation task for a 3D wing easy and efficient one when used together with the wing modeling program by choosing STL format as the model's output format.

• Journal of Energy Engineering
• /
• v.12 no.4
• /
• pp.328-338
• /
• 2003

A study is perfomed on the difference between the volume of gas purchased from Korea Gas Corporation (KGC) and that of measured gas deliveries including total sales, pipeline inventory, and other usage by gas companies at Seoul and Kyunggi area. Actual data md information from 1996 to 2001 on gas purchase from KGC, sales, loss and own company use and pipeline status of each gas company are used to identify net inventory change in pipeline, unaccounted inventory estimates based on billing cycle and their net changes. A framework to be used for the analysis of such differences and an empirical test result are being provided. As a conclusion, the hypothesis that each gas company purchased more than the volume of gas accounted-for by all the possible factors is shown to be rejected.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.1
• /
• pp.87-99
• /
• 1999

A shop floor control system(SFCS) performs the production activities required to fill orders. In order to effectively control these activities, the autonomous agent-based heterarchical shop floor control architecture is adopted where a supervisor does not exist. In this paper, we define functional perspective of the heterarchical shop floor control using planning, scheduling, and execution modules. In particular, we focus on an execution module that can coordinate the planning and scheduling modules and a general execution module that easily can be modified to execute the other equipment. The execution module can be defined informally as a module that downloads and performs a set of scheduled tasks. The execution module is also responsible for identifying and resolving various errors whether they come from hardware or software. The purpose of this research is to identify all the execution activities and solving techniques under the assumptions of the heterarchical control architecture. And we model the execution module in object-oriented modelling technique for generalization. The execution module modeled in object-oriented concept can be adopted to the other execution module easily. This paper also proposes a classification scheme for execution activities of the heterarchical control architecture. Petri-nets are used as a unified framework for modeling and controlling execution activities. For solving the nonexistence of a supervisor, a negotiation-based solution technique is utilized.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• Proceedings of the KAIS Fall Conference
• /
• 2001.05a
• /
• pp.370-373
• /
• 2001

전자상거래는 사람들에게 인터넷을 통하여 상품과 서비스를 구매할 수 있게 하였다. 초기의 전자상거래는 일반 소비자를 주요 판매 대상으로 하였다 그러나, 각각의 기업에서 인터넷이 모든 종류의 비즈니스 창구가 될 수 있음 인식하고 관심을 보이기 시작했다. 기업을 대상으로 하는 전자상거래를 B2B(Business to Business)라 한다. 그러나, B2B 분야가 아무리 더 큰 이익을 창출할 수 있다고 해도, 이를 실현하는데는 많은 문제점이 존재하고 있다. 현재 B2B 분야에서는 포괄적이면서도 단일화된 거래환경의 지원이 무엇보다 시급한 문제로 떠오르고 있다. 원활한 B2B 전자상거래 이루어지기 위해서는 세계적으로 인정되는 표준을 바탕으로 완벽한 상호운용성이 보장되며, 기업 내부의 환경에 효과적으로 대응할 수 있는 프레임워크 기술이 절실히 요구된다. 이러한 기업간 전자상거래의 문제를 해결하고자 하는 목적으로 많은 기업과 단체에서는 각자의 표준을 정립하고, 이를 지원하기 위한 프레임워크를 진행하고 있다. 현재까지 발표된 대표적인 프레임워크로는 CommerceNet의 eCo 프레임워크, RosettaNet, Microsoft의 BizTalk 프레임워크, UN/CEFACT와 OASIS의 듀 XML이 있다. 이들 대부분의 프레임워크들은 XML과 인터넷을 기반으로 하는 것이 특징이다. 본 고에서는 기업간 전자상거래에 관심을 가지고 있는 기업들에게 현재의 기술동향과 향후 방향 설정에 있어서 도움이 될 수 있기 위한 목적으로 현재 발표된 XML 기반 전자상거래 프레임 워크 기술과 향후전망에 대하여 기술한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.948-951
• /
• 2014

본 논문에서는 개미 군집 최적화 알고리즘과 센티워드넷(SentiWordNet)을 이용한 감성 분석 방법을 제안한다. 먼저, 데이터 수집 단계에서는 소설 웹(예: 페이스북)으로부터 주어 (subject), 서술어(predicate), 목적어(object)의 3 개의 요소로 구성된 RDF (Resource Description Framework)의 형태로 데이터를 수집한다. 그리고 개미 군집 최적화 알고리즘을 이용하여 수집된 RDF 튜플(tuple)을 수치화한 후, 사용자의 감성에 대하여 제안한 수식을 이용하여 페르몬(pheromone)을 계산한다. 센티워드넷을 통하여 얻은 감성 지수를 반영하여 이전 단계에서 계산된 여러 개의 페르몬 값에 대한 전체 감성 지수를 계산한다. 제안한 방법의 타당성 검증을 위하여 전체 감성 지수를 바탕으로 계산된 사용자의 감성 동향이 적절하게 분석됨을 사용자의 실제 생활과의 비교를 통하여 보인다.

• Nuclear Engineering and Technology
• /
• v.40 no.4
• /
• pp.269-276
• /
• 2008

Operational license of WWER-440/213 units at Paks NPP, Hungary is limited to the design lifetime of 30 years. Prolongation by additional 20 years of the operational lifetime is feasible. Moreover, enhancement of the reactor thermal power by 8% will increase both the net power output and the competitiveness of the plant. Paks NPP is a pioneer considering the power up-rate and preparation of long-term operation of WWER-440/213 design. Systematic preparatory work for long-term operation of Paks NPP has been started in 2000. A regulatory framework and a comprehensive engineering practice have been developed. According to the authors view, creation of a gapless engineering system via consequent application of best practices, and feed-back of experiences together with proper consideration of WWER-440/V213 features are the decisive elements of ensuring the safety of long-term operation. That systematic engineering approach is in the focus of recent paper. Key elements of justification and measures for ensuring the safety of long-term operation of Paks NPP WWER-440/213 units are identified and discussed. These are the assessment of plant condition and review of adequacy of ageing management programmes, also the review, validation and reconstitution of time limited ageing analyses as core tasks of licence renewal.

• Earthquakes and Structures
• /
• v.22 no.2
• /
• pp.109-120
• /
• 2022

Older or damaged structures can require significant retrofit to ensure they perform well in subsequent earthquakes. Supplemental damping devices are used to achieve this goal, but increase base shear forces, foundation demand, and cost. Displacement reduction without increasing base shear is possible using novel semi-active and recently-created passive devices, which offer energy dissipation in selected quadrants of the force-displacement response. Combining these devices with large, strictly passive energy dissipation devices can offer greater, yet customized response reductions. Supplemental damping to reduce response without increasing base shear enables a net-zero base shear approach. This study evaluates this concept using two incremental dynamic analyses (IDAs) to show displacement reductions up to 40% without increasing base shear, more than would be achieved for either device alone, significantly reducing the risk of response exceeding the unaltered structural case. IDA results lead to direct calculation of reductions in risk and annualized economic cost for adding these devices using this net-zero concept, thus quantifying the trade-off. The overall device assessment and risk analysis method presented provides a generalizable proof-of-concept approach, and provides a framework for assessing the impact and economic cost-benefit of using modern supplemental energy dissipation devices.