• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.137-146
• /
• 2008

Fault localization plays a significant role in enormous distributed system because it can identify root cause of observed faults automatically, supporting self-managing which remains an open topic in managing and controlling complex distributed systems to improve system reliability. Although many Artificial Intelligent techniques have been introduced in support of fault localization in recent research especially in increasing complex ubiquitous environment, the provided functions such as diagnosis and prediction are limited. In this paper, we propose fault localization for self-managing in performance evaluation in order to improve system reliability via learning and analyzing real-time streams of system performance events. We use probabilistic reasoning functions based on the basic Bayes' rule to provide effective mechanism for managing and evaluating system performance parameters automatically, and hence the system reliability is improved. Moreover, due to large number of considered factors in diverse and complex fault reasoning domains, we develop an efficient method which extracts relevant parameters having high relationships with observing problems and ranks them orderly. The selected node ordering lists will be used in network modeling, and hence improving learning efficiency. Using the approach enables us to diagnose the most probable causal factor with responsibility for the underlying performance problems and predict system situation to avoid potential abnormities via posting treatments or pretreatments respectively. The experimental application of system performance analysis by using the proposed approach and various estimations on efficiency and accuracy show that the availability of the proposed approach in performance evaluation domain is optimistic.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.504-509
• /
• 1995

컴퓨터에 의한 생산시스템의 통합체계화와 온-라인화에 따라 자동화된 설비진단 방법이 요구되어지고 있다. 이에 따라 기계설비에 각종 센서를 부착하여 실시간으로 수집된 출력신호를 이용하여 기계설비를 온-라인으로 감시하는 여러가지 기법들이 제시되고 있다. 본 연구에서는 진동센서로부터의 신호를 radial 함수에 근거한 다단계 뉴럴 네트워크(Neural Network)로 모형화하여 기계설비 상태를 감시하는 방법을 제시한다. 또한 다단계 모델링 분석을 통하여 신호를 예측하고 설비고장 원인을 분류하며, 다른 모형과의 비교를 통하여 효율성 평가와 최적 단계수를 결정하였다. 온라인 학습 알고리즘은 recursive least squares와 clustering 방법을 이용한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.279-280
• /
• 2015

본 연구는 건물 에너지 효율 향상을 위한 단기 저비용 건물 에너지 통합 평가 진단 시스템 기술을 지원하는 스마트 미터링 인프라 구축 기술 개발에 대한 연구로, 단기 저비용 네트워크 구축을 위해 통신 라인을 신설하지 않는 PLC 기술 및 무선 통신 기술을 적용하여 빌딩내 스마트 미터링 인프라 구축에 대한 적용 사례에 대한 연구이다.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.689-690
• /
• 2007

전력 텔레매트릭스 시스템은 전력계통의 사고에 신속하게 대처하고 계통설비의 합리적인 유지보수 및 운영을 통해 계통의 신뢰도를 높이고자 고안된 시스템이다. 이 시스템은 전력기반설비들에 다양한 센서 및 센서네트워크를 구성하여 전력설비를 통합적으로 감시하고 변전소 보호IED의 데이터들과 함께 전력계통의 유지보수 스케쥴링 및 설비건전성평가와 더불어 고장시에 신속한 고장복구를 위해 고장정보를 운영자에게 보여주는 구조를 가지고 있다. 본 논문에서는 이러한 전력 텔레매트릭스 시스템중에서 하부 센서및 센서네트워크의 데이터와 보호IED의 데이터를 중간처리하고 상위 시스템으로 전송하는 역할을 하는 진단IED의 개발에 관한 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.614-617
• /
• 2022

인공지능의 발전으로 의료영상 분야에서 딥러닝 기반 질병 진단 연구가 활발하다. 그러나 모델 개발 시 학습 데이터의 개수와 품질은 매우 중요한데, 의료 분야 특성상 접근 가능한 데이터셋이 적으며 오픈 데이터셋은 서로 다른 기관에서 배포되거나 웹상에서 수집된 것으로 진단에 적합한 품질을 기대하기 어렵다. 또한, 기존 연구는 데이터셋이 학습에 적합한지에 대한 품질검증 없이 사용한다. 따라서 본 논문에서는 임상에서 사용하는 화질 평가 요소에 근거를 두고 영역별 화소값 분석을 통한 흉부 X선 영상 품질 평가 기법을 제안한다. 오픈 데이터셋 JSRT, Chest14와 국내 A 병원 데이터셋 AUH에 제안한 기법을 적용한 결과 민감도 91.5%, 특이도 96.1%의 우수한 성능을 확인하였다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.152-161
• /
• 2014

In this paper, a multi-node real-time diagnostic and management system based on zigbee sensor network is proposed, which is to monitor and diagnose multiple nodes as well as to control the data generated from the various multiple sensors collectively. The proposed system is designed to transmit the collected wireless and wired data to the server for monitoring and controling efficiently the condition for multi-nodes by taking the corresponding actions according to the analysis. The system is implemented to make it possible to manage the sensor data by classifying them, of which data are issued from the clustered sources with a number of the remote sensors. In order to evaluate the performance of the proposed system, we measure and analyze both the transmission delay time according to the distance and the data loss rate issued from multiple sensors. The results shows that the proposed system has a good performance.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.3
• /
• pp.42-48
• /
• 2016

Extensive research effort has been made during the last decade to utilize wireless smart sensors for evaluating and monitoring structural integrity of civil engineering structures. The wireless smart sensor commonly has sensing and embedded computation capabilities as well as wireless communication that provide strong potential to overcome shortcomings of traditional wired sensor systems such as high equipment and installation cost. However, sensor malfunctioning particularly in case of long-term monitoring and unreliable wireless communication in harsh environment are the critical issues that should be properly tackled for a wider adoption of wireless smart sensors in practice. This study presents a wireless smart sensor network(WSSN) that can estimate unmeasured responses for the purpose of data recovery at unresponsive sensor nodes. A software program that runs on WSSN is developed to estimate the unmeasured responses from the measured using the Kalman filter. The performance of the developed network software is experimentally verified by estimating unmeasured acceleration responses using a simply-supported beam.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.1135-1139
• /
• 2007

청계천 복원의 효과가 하천의 형상, 종 조성, 종 다양성 변화의 유연성 및 환경 개선 효과 측면에서 검토되었다. 복원된 청계천은 하천의 종단 및 횡단 형상에서 모두 낮은 자연성을 나타내었다. 종 조성은 부분적으로 자연하천과 유사한 조성을 보였으나 전반적으로 낮은 자연성을 보였다. 종 다양성은 비교적 낮았지만 복원의 역사를 고려할 때 양호한 것으로 평가되었다. 하류와 수변에서는 홍수 후 많은 변화를 가져와 자연으로 회귀할 가능성도 보였지만 상류와 홍수터 이상에서는 변화의 유연성이 낮아 자연으로 회귀하는데 많은 시간이 소요될 것으로 평가되었다. 인공위성 영상 분석 결과, 복원된 청계천은 기온 완화 효과를 나타내었다. 그 밖에 복원된 청계천은 그 주변의 분산된 녹지를 연결하여 그린네트워크를 구축하고자 할 때 핵심적 역할을 할 것으로 기대되어 경관생태적 측면에서의 환경개선효과도 기대되었다.

• KIISE Transactions on Computing Practices
• /
• v.21 no.6
• /
• pp.393-402
• /
• 2015

Human resources are one of the most essential elements of an organization. In particular, the more closed a group is, the higher the value each member has. Previous studies have focused on personal attributes of individual, such as medical history, and have depended upon self-diagnosis to manage structures. However, this method has weak points, such as the timeconsuming process required, the potential for concealment, and non-disclosure of participants' mental states, as this method depends on self-diagnosis through extensive questionnaires or interviews, which is solved in an interactive way. It also suffers from another problem in that relations among people are difficult to express. In this paper, we propose a multi-faced diagnosis model based on social network analysis which overcomes former weaknesses. Our approach has the following steps : First, we reveal the states of those in a social network through 9 questions. Next, we diagnose the social network to find out specific individuals such as victims or leaders using the proposed algorithm. Experimental results demonstrated our model achieved 0.62 precision rate and identified specific people who are not revealed by the existing methods.

• Convergence Security Journal
• /
• v.13 no.4
• /
• pp.11-17
• /
• 2013

All u-Health system has security vulnerabilities. This vulnerability locally(local) or network(network) is on the potential risk. Smart environment of health information technology, Ad-hoc networking, wireless communication environments, u-health are major factor to increase the security vulnerability. u-health care information systems user terminal domain interval, interval public network infrastructure, networking section, the intranet are divided into sections. Health information systems by separating domain specific reason to assess vulnerability vulnerability countermeasure for each domain are different. u-Healthcare System 5 layers of security risk assessment system for domain-specific security vulnerability diagnosis system designed to take the security measures are needed. If you use this proposed model that has been conducted so far vaguely USN-based health information network security vulnerabilities diagnostic measures can be done more systematically provide a model.