• 한국산학기술학회논문지
• /
• 제21권6호
• /
• pp.374-382
• /
• 2020

본 연구에서 저장탄약 신뢰성평가(ASRP: Ammunition Stockpile Reliability Program)의 데이터 특성을 고려하여 입력변수를 줄이는 정규화기법을 제안함으로써 분류성능의 저하 없이 저장탄약 신뢰성분류 인경신경망모델의 학습 속도향상을 목표로 하였다. 탄약의 성능에 대한 기준은 국방규격(KDS: Korea Defense Specification)과 저장탄약 시험절차서(ASTP: Ammunition Stockpile reliability Test Procedure)에 규정되어 있으며, 평가결과 데이터는 이산형과 연속형 데이터가 복합적으로 구성되어 있다. 이러한 저장탄약 신뢰성평가의 데이터 특성을 고려하여 입력변수는 로트 추정 불량률(estimated lot percent nonconforming) 또는 고장률로 정규화 하였다. 또한 입력변수의 unitary hypercube를 유지하기 위하여 최소-최대 정규화를 2차로 수행하는 2단계 정규화 기법을 제안하였다. 제안된 2단계 정규화 기법은 저장탄약 신뢰성평가 데이터를 이용하여 비교한 결과 최소-최대 정규화와 유사하게 AUC(Area Under the ROC Curve)는 0.95 이상이었으며 학습속도는 학습 데이터 수와 은닉 계층의 노드 수에 따라 1.74 ~ 1.99 배 향상되었다.

• Computers and Concrete
• /
• 제14권6호
• /
• pp.727-743
• /
• 2014

The management of existing concrete bridges has become a major social concern in many developed countries due to the large number of bridges exhibiting signs of significant deterioration. This problem has increased the demand for effective maintenance and renewal planning. In order to implement an appropriate management procedure for a structure, a wide array of corrective strategies must be evaluated with respect to not only the condition state of each defect but also safety, economy and sustainability. This paper describes a new performance evaluation system for existing concrete bridges. The system evaluates performance based on load carrying capability and durability from the results of a visual inspection and specification data, and describes the necessity of maintenance. It categorizes all girders and slabs as either unsafe, severe deterioration, moderate deterioration, mild deterioration, or safe. The technique employs an expert system with an appropriate knowledge base in the evaluation. A characteristic feature of the system is the use of neural networks to evaluate the performance and facilitate refinement of the knowledge base. The neural network proposed in the present study has the capability to prevent an inference process and knowledge base from becoming a black box. It is very important that the system is capable of detailing how the performance is calculated since the road network represents a huge investment. The effectiveness of the neural network and machine learning method is verified by comparing diagnostic results by bridge experts.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.43-48
• /
• 1992

The automation system oriented as one of the second year automation projects for the small and medium sized enterprises(SME) was developed for the improvement of the production rate and cut the required manpower in the field of the relay which is one of the small electric components used in various industrial fields. The objectives of this study are not only improving the international competition of the relay itself but also partially solving the technical and financial problems featured by common bottlenecks of the SME for efficient assembly automation. For the purpose of these objectives, several topics are studied as followings. - Analyzing the adjustment process and determining the specification of the automation system. - Determining the layout for the automation system to meet the determined specification. - Detail design of the automation system for relay adjustment and inspection. - Control system design - Automation system development and performance test.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.209-210
• /
• 1998

Noise characteristics of preamplifier, the most essential part of on-chip signal processing circuitry for the active semiconductor neural probe, is the important factor determining the overall signal-to-noise-ratio (SNR). We present a systematic design method for the optimization of SNR, based on the spectral characteristics of the electrode, circuit noise and extracelluar action potential. Analytical expression is derived to calculate total output noise power. Output SNR of 2-stage CMOS preamplifier is tailored to meet the given specification while the layout area is minimized.

• Journal of Mechanical Science and Technology
• /
• 제16권12호
• /
• pp.1604-1612
• /
• 2002

Rollers in the continuous process systems are ones of key components that determine the quality of web products. The condition of rollers (e.g. eccentricity, runout) should be consistently monitored in order to maintain the process conditions (e.g. tension, edge position) within a required specification. In this paper, a new diagnosis algorithm is suggested to detect the defective rollers based on the frequency analysis of web tension signals. The kernel of this technique is to use the characteristic features (RMS, Peak value, Power spectral density) of tension signals which allow the identification of the faulty rollers and the diagnosis of the degree of fault in the rollers. The characteristic features could be used to train an artificial neural network which could classify roller conditions into three groups (normal, warning, and faulty conditions) The simulation and experimental results showed that the suggested diagnosis algorithm can be successfully used to identify the defective rollers as well as to diagnose the degree of the defect of those rollers.

• 한국전산구조공학회논문집
• /
• 제25권1호
• /
• pp.51-56
• /
• 2012

회전익 항공기에 광범위하게 적용되고 있는 내충격성 연료셀은 항공기 추락 시 탑승자의 생존성 향상에 크게 기여하고 있다. 미육군에서는 항공기 추락 후 화재에 의한 인명손실을 원천적으로 방지하기 위해 군용 회전익기 역사의 초기 단계부터 연료셀 고유의 내충격성에 관련된 군사규격을 제정하여 적용해 왔다. 국외 전문제작 업체들은 장기간의 경험에 의존하여 연료셀을 개발하고 있으며, 충돌충격시험에 따른 시행착오의 결과를 설계 및 제작과정에 재반영하고 있다. 이러한 연료셀 충돌충격시험은 시편자체의 제작비용 및 준비기간이 상당히 소요되므로, 설계 초기단계부터 충돌충격시험에 대한 일련의 수치적 모사를 통해 실물에 의한 시행착오의 가능성을 최소화해야 한다. 본 연구에서는 충돌모사 프로그램인 Autodyn으로 연료셀 충돌충격시험에 대한 다수의 수치해석을 수행, 등가응력 분석을 통해 적절한 설계변수를 선정하였다. 또한 인공신경망과 모의풀림 방법을 연동시켜 연료셀 형상을 내충격성능 측면에서 최적화하였다.

• 정보처리학회논문지B
• /
• 제18B권6호
• /
• pp.375-384
• /
• 2011

본 논문에서는 사람의 표정이 아닌 애니메이션 캐릭터의 표정을 주색상과 특징점을 효과적으로 분석하여 인식하는 방법을 제안한다. 제안된 방법에서는 먼저 캐릭터의 특성에 맞게 간략화한 메쉬모델을 정의하고 캐릭터 얼굴과 얼굴의 구성요소를 주색상을 이용하여 검출한 후 각 구성요소의 에지를 활용하여 표정인식을 위한 특징점을 추출한다. 그런 다음, 각 특징점의 위치와 모양 정보를 신경망 학습을 통해 해당 AU로 분류하고, 제안된 표정 AU 명세서를 이용해 최종적으로 표정을 인식한다. 실험에서는 제안된 애니메이션 캐릭터의 표정인식 방법이 무표정을 포함하여 기쁨, 슬픔, 놀람, 화남, 공포의 6가지 표정을 비교적 신뢰성 있게 인식함을 애니메이션 영상을 이용한 실험을 통해 보여준다.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.835-843
• /
• 2017

Humans have often been used gesture to communicate with each other. The communication between computer and person was also not different. To interact with a computer, we command with gesture, keyboard, mouse and extra devices. Especially, the gesture is very useful in many environments such as gaming and VR(Virtual Reality), which requires high specification and rendering time. In this paper, we propose a gesture recognition method based on CNN model to apply to gaming and real-time applications. Deep learning for gesture recognition is processed in a separated server and the preprocessing for data acquisition is done a client PC. The experimental results show that the proposed method is in accuracy higher than the conventional method in game environment.

• 국제학술발표논문집
• /
• The 7th International Conference on Construction Engineering and Project Management Summit Forum on Sustainable Construction and Management
• /
• pp.301-312
• /
• 2017

Quality evaluation and control represent increasingly important concerns for construction quality management. There is an evident need for a standard data model to be used as the basis for computer-aided quality management. This study focuses on how to realize evaluation of construction quality based on BIM and database technology. In this paper, the reinforced concrete main structure is taken as an example, and the BP neural network evaluation model is established by inquiring current construction quality acceptance specification and evaluation standard. Furthermore, IFC standard is extended to integrate quality evaluation information and realize the mapping of evaluation information in BIM model, contributing to the visualization and transfer sharing of evaluation information. Furthermore, the conceptual entity model is designed to build quality evaluation database, and this paper select MySQL workbench system to achieve the establishment of the database. This study is organized to realize the requirement of visualization and data integration on construction quality evaluation which makes it more effective, convenient, intuitive, easy to find quality problems and provide more comprehensive and reliable data for the quality management of construction enterprises and official construction administratiors.

• The Korean Journal of Physiology and Pharmacology
• /
• 제20권1호
• /
• pp.41-51
• /
• 2016

Adult hippocampal dentate granule neurons are generated from neural stem cells (NSCs) in the mammalian brain, and the fate specification of adult NSCs is precisely controlled by the local niches and environment, such as the subventricular zone (SVZ), dentate gyrus (DG), and Toll-like receptors (TLRs). Epigallocatechin-3-gallate (EGCG) is the main polyphenolic flavonoid in green tea that has neuroprotective activities, but there is no clear understanding of the role of EGCG in adult neurogenesis in the DG after neuroinflammation. Here, we investigate the effect and the mechanism of EGCG on adult neurogenesis impaired by lipopolysaccharides (LPS). LPS-induced neuroinflammation inhibited adult neurogenesis by suppressing the proliferation and differentiation of neural stem cells in the DG, which was indicated by the decreased number of Bromodeoxyuridine (BrdU)-, Doublecortin (DCX)- and Neuronal Nuclei (NeuN)-positive cells. In addition, microglia were recruited with activating TLR4-NF-${\kappa}B$ signaling in the adult hippocampus by LPS injection. Treating LPS-injured mice with EGCG restored the proliferation and differentiation of NSCs in the DG, which were decreased by LPS, and EGCG treatment also ameliorated the apoptosis of NSCs. Moreover, pro-inflammatory cytokine production induced by LPS was attenuated by EGCG treatment through modulating the TLR4-NF-${\kappa}B$ pathway. These results illustrate that EGCG has a beneficial effect on impaired adult neurogenesis caused by LPS-induced neuroinflammation, and it may be applicable as a therapeutic agent against neurodegenerative disorders caused by inflammation.