• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.3
• /
• pp.183-192
• /
• 2017

k-nearest neighbor (K-NN) is a well-known classification algorithm, being feature space-based on nearest-neighbor training examples in machine learning. However, K-NN, as we know, is a lazy learning method. Therefore, if a K-NN-based system very much depends on a huge amount of history data to achieve an accurate prediction result for a particular task, it gradually faces a processing-time performance-degradation problem. We have noticed that many researchers usually contemplate only classification accuracy. But estimation speed also plays an essential role in real-time prediction systems. To compensate for this weakness, this paper proposes correlation coefficient-based clustering (CCC) aimed at upgrading the performance of K-NN by leveraging processing-time speed and plurality rule-based density (PRD) to improve estimation accuracy. For experiments, we used real datasets (on breast cancer, breast tissue, heart, and the iris) from the University of California, Irvine (UCI) machine learning repository. Moreover, real traffic data collected from Ojana Junction, Route 58, Okinawa, Japan, was also utilized to lay bare the efficiency of this method. By using these datasets, we proved better processing-time performance with the new approach by comparing it with classical K-NN. Besides, via experiments on real-world datasets, we compared the prediction accuracy of our approach with density peaks clustering based on K-NN and principal component analysis (DPC-KNN-PCA).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1136-1139
• /
• 2012

본 연구에서는 EPCIS(전자상품코드 정보 서비스) 시스템의 요구사항인 추상화, 고성능, 확장성, 상호 운용성을 기반으로 EPCIS 시스템의 구조를 설계하고 구현한다. EPCIS 시스템의 추상화를 위해 기존에 존재하는 다양한 데이터 베이스 시스템과 상호 운용을 위한 공통 인터페이스를 구현하고 내부적으로 확장 질의 인터페이스, 공통 질의 언어를 가진다. 연속 질의 처리 시간을 감소 시키고 중복된 결과를 효과적으로 처리하기 위한 연속 질의 처리 모듈을 구현한다. 또한 RFID(전자 태그)의 이력 추적 질의의 고성능을 지원하기 위해 RFID 환경에 최적화된 색인 기술과 질의 처리를 위한 구성 요소(Component)를 추가하여 EPCIS 시스템의 고성능 질의 처리를 가능하게 한다. 또한 확장성을 위해 저장소(EPCIS Repository) 관리자를 구현하여 비즈니스 이벤트의 메타 데이터의 스키마를 정의하여 새로운 종류의 비즈니스 이벤트를 쉽게 등록하고 사용할 수 있도록 하였다. 또한 기업의 응용 시스템과 협력 기업간에 정보 교환을 위해서 EPC 글로벌에서 제시하는 웹 서비스를 지원하며 표준 데이터 형식인 확장성 생성 언어(XML)를 사용한다.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.20 no.3
• /
• pp.269-278
• /
• 2022

The buffer is a critical barrier component in an engineered barrier system, and its purpose is to prevent potential radionuclides from leaking out from a damaged canister by filling the void in the repository. No experimental parameters exist that can describe the buffer expansion phenomenon when Kyeongju bentonite, which is a buffer candidate material available in Korea, is exposed to groundwater. As conventional experiments to determine these parameters are time consuming and complicated, simple swelling pressure tests, numerical modeling, and machine learning are used in this study to obtain the parameters required to establish a numerical model that can simulate swelling. Swelling tests conducted using Kyeongju bentonite are emulated using the COMSOL Multiphysics numerical analysis tool. Relationships between the swelling phenomenon and mechanical parameters are determined via an artificial neural network. Subsequently, by inputting the swelling tests results into the network, the values for the mechanical parameters of Kyeongju bentonite are obtained. Sensitivity analysis is performed to identify the influential parameters. Results of the numerical analysis based on the identified mechanical parameters are consistent with the experimental values.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.15 no.2
• /
• pp.151-159
• /
• 2017

A deep geological disposal at a depth of 500 m in stable host rock is considered to be the safest method with current technologies for disposal of spent fuels classified as high-level radioactive waste. The most important requirement is that the temperature of the bentonite buffer, which is a component of the engineered barrier, should not exceed $100^{\circ}C$. In Korea, the amount of spent fuel generated by nuclear power generation, which accounts for about 30% of the total electricity, is continuously increasing and accumulating. Accordingly, the area required to dispose of it is also increasing. In this study, various duplex disposal concepts were derived for the purpose of improving the disposal efficiency by reducing the disposal area. Based on these concepts, thermal analyses were carried out to confirm whether the critical disposal system requirements were met, and the thermal stability of the disposal system was evaluated by analyzing the results. The results showed that upward 75 m or downward 75 m apart from the reference disposal system location of 500 m depth would qualify for the double layered disposal concept. The results of this study can be applied to the establishment of spent fuel management policy and the design of practical commercial disposal system. Detailed analyses with data of a real disposal site are necessary.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.1
• /
• pp.63-69
• /
• 2018

Bearing is an essential component in many rotary machineries. To prevent its unpredicted failures and undesired downtime cost, many researches have been made in the field of Prognostics and Health Management(PHM), in which the key issue is to establish a proper feature reflecting its current health state properly at the early stage. However, conventional features have shown some limitations that make them less useful for early diagnostics and prognostics because it tends to increase abruptly at the end of life. This paper proposes a new feature extraction method using the envelope analysis and weighted sum with correlation coefficient. The developed method is demonstrated using the IMS bearing data given by NASA Ames Prognostics Data Repository. Results by the proposed feature are compared with those by conventional approach.

• The Journal of the Korea Contents Association
• /
• v.12 no.3
• /
• pp.421-433
• /
• 2012

AMGA service, which is one of the EMI gLite middleware components, is widely used for analysis of distributed large scale experiments data as metadata repository by scientific and technological researchers and the use of AMGA is extended farther to include general industries needing metadata Catalogue as well. However AMGA, based unix and Grid UI, has the weakness of being absence of general-purpose user interfaces in comparison to other commercial database systems and that's why it's difficult to use and diffuse it although it has the superiority of the functionality. In this paper, we developed AMGA GUI toolkit to provide work convenience using object-oriented modeling language(UML). Currently, AMGA has been used as the main component among many user communities such as Belle II, WISDOM, MDM, and so on, but we expect that this development can not only lower the barrier to entry for AMGA beginners to use it, but lead to expand the use of AMGA service over more communities.

• The Plant Pathology Journal
• /
• v.32 no.6
• /
• pp.489-499
• /
• 2016

Green shoot cuttings of 10 different grapevine species were inoculated with Agrobacterium vitis to find disease-related metabolites in the grapevine. Crown galls formed 60 days after inoculation varied in gall severity (GS) evaluated by gall incidence (GI) and gall diameter (GD), which were classified into three response types as RR (low GI and small GD), SR (high GI and small GD), and SS (high GI and large GD), corresponding to resistant, moderately resistant, and susceptible responses, respectively. In this, 4, 4, and 2 Vitis species were classified into RR, SR, and SS, respectively. Gas chromatography mass spectrometry (GC-MS) analysis of the grapevine stem metabolites with A. vitis infection showed 134 metabolites in various compound classes critically occurred, which were differentially clustered with the response types by the principal component analysis. Multivariate analysis of the metabolite profile revealed that 11 metabolites increased significantly in relation to the response types, mostly at post-inoculation stages, more prevalently (8 metabolites) at two days after inoculation than other stages, and more related to SS (7 metabolites) than RR (3 metabolites) or SR (one metabolite). This suggests most of the disease-related metabolites may be rarely pre-existing but mostly induced by pathogen infection largely for facilitating gall development except stilbene compound resveratrol, a phytoalexin that may be involved in the resistance response. All of these aspects may be used for the selection of resistant grapevine cultivars and their rootstocks for the control of the crown gall disease of the grapevine.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.633-648
• /
• 1998

Rapid computing environment, change of the application structure, and various user demand will increase the demand of the software development. Version control is helpful to improve productivity using delta, and useful to establish component from existing data of source code. This paper presents the design and implementation of the version control system. which is composed of retrieval system and delta management system. In retrieval system, vanous retrieve methods arc proposed. This methods provides the process methodology with filename, content, size and date. Various retrieve methods arc important for the effective delta management. Meta data can be easily composed for the delta management by these methods. Compared with other systems, this implemented version control system has some advantage. First, for delta management, version maintenance for delta management becomes easier by integrating the forward and back-ward methods. Second, delta managent part of a project is to unite the forward and backward method. the effieiency of this system is to increased in management. Also, this system supports a thechnique of using the database and files for project repository and makes the version management more effective.

• Conservation Science in Museum
• /
• v.24
• /
• pp.99-116
• /
• 2020

This study examines the results of analyses of the lead isotope ratio and chemical composition of lead glass and green glaze from ancient Northeast Asia in order to suggest their production sites and reveal further characteristics. The comparison of the lead isotope ratio of lead glass and green glaze from two Baekje remains in Iksan-the Wanggung-ri Site and Mireuksa Temple Site-suggests that they were produced to the west of the South Gyeonggi Massif (Zone 4) using lead extracted from the same area. With a few exceptions, it has proved difficult to identify the production sites of most of the green-glazed roof tiles from Unified Silla-period Buddhist temples across Northeast Asia. The major component of the lead glass from Baekje, Silla, China, and Japan during the seventh century is PbO, SiO₂, Al₂O₃, CuO, and Fe₂O₃, with a ratio of PbO and SiO₂ of 70 and 30 wt.%, respectively. The green-glazed roof tiles excavated from a temple from the Unified Silla period have a high proportion of lead, ranging from 64 to 90 wt.%. Green-glazed lozenge tiles excavated from the Sacheonwangsa Temple site in Gyeongju were shown to contain PbO, SiO₂, Al₂O₃, and CuO, a similar composition with lead glass. An experiment was conducted to reproduce a glaze according to the production method mentioned in the Zō hotokesho sakumotsu-chō (Buddhist statue workshop crop book) in the Shosoin Repository. In this experiment, an identical ratio of PbO was observed for Japanese green-glazed ceramics from the eighth to eleventh century as that found in Chinese lead-glazed ceramics excavated from kilns operated from the seventh to tenth century in Henan. This indicates that production methods for lead glass and glaze were shared across Northeast Asia.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.173-193
• /
• 2010

The World Wide Web is transitioning from being a mere collection of documents that contain useful information toward providing a collection of services that perform useful tasks. The emerging Web service technology has been envisioned as the next technological wave and is expected to play an important role in this recent transformation of the Web. By providing interoperable interface standards for application-to-application communication, Web services can be combined with component-based software development to promote application interaction and integration within and across enterprises. To make Web services for service-oriented computing operational, it is important that Web services repositories not only be well-structured but also provide efficient tools for an environment supporting reusable software components for both service providers and consumers. As the potential of Web services for service-oriented computing is becoming widely recognized, the demand for an integrated framework that facilitates service discovery and publishing is concomitantly growing. In our research, we propose a framework that facilitates Web service discovery and publishing by combining clustering techniques and leveraging the semantics of the XML-based service specification in WSDL files. We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the Web service domain. We have developed a Web service discovery tool based on the proposed approach using an unsupervised artificial neural network and empirically evaluated the proposed approach and tool using real Web service descriptions drawn from operational Web services repositories. We believe that both service providers and consumers in a service-oriented computing environment can benefit from our Web service discovery approach.