• 제어로봇시스템학회논문지
• /
• 제16권12호
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• 한국공간구조학회논문집
• /
• 제4권2호
• /
• pp.89-97
• /
• 2004

최적설계기법을 사용한 경제적인 설계의 필요성은 오래 전부터 요구되어 왔으나, 종전의 설계가 설계자의 경험에 의한 시행착오적인 반복설계를 통하여 이루어져 왔기 때문에 구조물의 형상이 복잡한 경우에는 계산상의 어려움과 반복계산을 되풀이해야 하는 번거로움으로 진정한 최적설계는 기대하기 어려웠다. 최적설계법이 구조물의 설계에 매우 유용하다는 사실이 증명되고 있긴 하지만, 아직도 최적설계의 의미를 제대로 이해하지 못하고 있는 실정이며, 더구나 설계실무자는 어디까지나 사용자이기 때문에 수리적 계획수법에 친숙할 필요까지는 없지만 최소한 이런 기법의 가능성과 중요성을 이해할 필요는 있는데 대부분 그러하지 못하고 있는 실정이다. 일반적으로 트러스 구조물 설계 시 주어진 부재의 응력에 따라 단면적을 산출하여 그 단면적에 역학적으로 가장 합리적인 단면을 선정하여 경제적인 설계단면을 구한다. 그러나 트러스의 형상, 트러스 높이에 따른 경제성의 문제는 보통 설계자의 경험과 직관에 의하여 결정되고, 특별한 검토가 이루어지지 않고 설계가 수행되는데, 실제 트러스 구조물에서 트러스의 형상과 높이가 전체 건설공사비에 크게 영향을 미친다. 그러므로, 트러스 구조물의 최적설계에서 트러스 형상, 라이즈 비(rise ratio : 높이/스팬) 및 격간 수(number of panel)를 고려하는 것이 필요하다. 트러스 형상과 스팬에 따른 최적형상과 최적높이 및 격간 수에 대해 설계자의 초기 구조계획 시 주관적 선택의 어려움을 해결하고, 실제의 지붕형 트러스 구조에 설계하중을 작용시켜 응력해석에서부터 부재 단면설계까지의 자동화된 최적설계 알고리즘을 개발할 필요가 있다. 따라서 본 연구는 플랫 트러스의 형상, 격간 수, 격간의 간격 및 부재단면 등에 대하여 이산적인 변수의 처리와 넓은 설계 공간의 탐색능력과 더불어 문제의 비선형성과 관계없이 전체 최적해를 찾아낼 수 있는 유전자 알고리즘을 이용한다. 또한, 강 구조 한계상태설계기준(대한건축학회, 1998)을 기준으로 하여 자동으로 플랫 트러스의 구조계획과 단면이산화 최적설계를 동시에 수행할 수 있는 최적화 알고리즘을 제시하는 것을 목적으로 한다.

• 한국세라믹학회지
• /
• 제53권3호
• /
• pp.317-324
• /
• 2016

Continued miniaturization and increasingly exact requirements for thin film deposition in the semiconductor industry is driving the search for new effective, efficient, selective precursors and processes. The requirements of defect-free, conformal films, and precise thickness control have focused attention on atomic layer deposition (ALD). ALD precursors so far have been developed through a trial-and-error experimental approach, leveraging the expertise and tribal knowledge of individual research groups. Precursors can show significant variation in performance, depending on specific choice of co-reactant, deposition stage, and processing conditions. The chemical design space for reactive thin film precursors is enormous and there is urgent need for the development of computational approaches to help identify new ligand-metal architectures and functional co-reactants that deliver the required surface activity for next-generation thin-film deposition processes. In this paper we discuss quantum mechanical simulation (e.g. density functional theory, DFT) applied to ALD precursor reactivity and state-of-the-art automated screening approaches to assist experimental efforts leading toward optimized precursors for next-generation ALD processes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권3호
• /
• pp.1119-1143
• /
• 2014

Lightweight trust mechanism with lightweight cryptographic primitives has emerged as an important mechanism in resource constraint wireless sensor based mobile devices. In this work, outlier detection in lightweight Mobile Ad-hoc NETworks (MANETs) is extended to create the space of reliable trust cycle with anomaly detection mechanism and minimum energy losses [1]. Further, system is tested against outliers through detection ratios and anomaly scores before incorporating virtual programmable nodes to increase the efficiency. Security in proposed system is verified through ProVerif automated toolkit and mathematical analysis shows that it is strong against bad mouthing and on-off attacks. Performance of proposed technique is analyzed over different MANET routing protocols with variations in number of nodes and it is observed that system provide good amount of throughput with maximum of 20% increase in delay on increase of maximum of 100 nodes. System is reflecting good amount of scalability, optimization of resources and security. Lightweight modeling and policy analysis with lightweight cryptographic primitives shows that the intruders can be detection in few milliseconds without any conflicts in access rights.

• 한국추진공학회지
• /
• 제18권1호
• /
• pp.42-49
• /
• 2014

설계성능이 검증된 70 N급 하이드라진 추력기에 대한 성능평가 시험이 수행되었다. 각각의 개발모델 추력기는 추력실 직경 변화에 따라 펄스모드로 연소시험이 수행되었으며, 비추력, 임펄스 비트 및 특성속도 등의 성능변수로 평가되었다. 추력실 직경의 증가와 감소에 따라 비추력과 특성속도가 감소하였으며, 성능평가 결과 표준모델의 성능특성이 가장 우수한 것으로 확인되었다.

• Nuclear Engineering and Technology
• /
• 제52권9호
• /
• pp.2025-2033
• /
• 2020

Signature-based safeguards (SBS) is being developed to assist tradition nuclear material accountancy methods in tracking material in pyroprocessing facilities. SBS involves identifying off-normal scenarios that would result in improper movement of material in a pyroprocessing facilities and determining associated sensor response signatures. SBS investigations are undertaken in the computational space utilizing an electrochemical transport code known as enhanced REFIN with anodic dissolution (ERAD) to calculate the affect of off-normal conditions in the electrorefiner (ER) on material movement. Work is undertaken to experimentally validate the predictions and assumptions made by ERAD for off-normal occurrences. These experiments were undertaken on a benchtop scale and involved operating an electrochemical cell at 10 separate current densities for constant current operations to deposit U and Gd at a W cathode. These experiments were then modeled using ERAD to compare calculated predictions versus analytical experimental results it was found. It was discovered both the experimental and calculated results reflect a trend of increased codeposition of U and Gd with increasing current density. ERAD was thus demonstrated to be useful for predicting trends from anomalous operation but will require further optimization to be utilized as a quantitative design tool.

• 한국해양공학회지
• /
• 제20권1호
• /
• pp.69-76
• /
• 2006

The design of efficient search path to maximize the Cumulative Detection Probability(CDP) is mainly dependent on experience and intuition when searcher detect the target using SONAR in the ocean. Recently with the advance of modeling and simulation method, it has been possible to access the optimization problems more systematically. In this paper, a method for the optimal search path calculation is developed based on the combination of the genetic algorithm and the calculation algorithm for detection range. We consider the discrete system for search path, space, and time, and use the movement direction of the SONAR for the gene of the genetic algorithm. The developed algorithm, OASPP(Optimal Acoustic Search Path Planning), is shown to be effective, via a simulation, finding the optimal search path for the case when the intuitive solution exists. Also, OASPP is compared with other algorithms for the measure of efficiency to maximize CDP.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 추계학술대회 학술발표 논문집 제15권 제2호
• /
• pp.95-98
• /
• 2005

This paper presents intelligent digital redesign method of global approach for hybrid state space fuzzy-model-based controllers. For effectiveness and stabilization of continuous-time uncertain nonlinear systems under discrete-time controller, Takagi-Sugeno(TS) fuzzy model is used to represent the complex system. And global approach design problems viewed as a convex optimization problem that we minimize the error of the norm bounds between nonlinearly interpolated linear operators to be matched. Also by using the power series, we analyzed nonlinear system's uncertain parts more precisely. When a sampling period is sufficiently small, the conversion of a continuous-time structured uncertain nonlinear system to an equivalent discrete -time system have proper reason. Sufficiently conditions for the global state -matching of the digitally controlled system are formulated in terms of linear matrix inequalities (LMls). Finally, we prove the effectiveness and stabilization of the proposed intelligent digital redesign method by applying the chaotic Lorentz system.

• Journal of Welding and Joining
• /
• 제28권6호
• /
• pp.76-83
• /
• 2010

The purpose of this study is to propose a method to decide near-optimal settings of the constant current fuzzy control parameters using a controlled random search. This method tries to find the near-optimal settings of the constant current fuzzy control parameters through experiments. It has an advantage of being able to carry out searches in the search domain which includes some irregular points. The method suggested in this study was used to determine the fuzzy control parameters by which the desired welding current were formed during inverter DC resistance spot welding. The output variable was the ITAE (integral of time multiplied by the absolute error). This output variable was determined according to the input variables, which are the GE, GDE, and GDU. This study described how to obtained near-optimal welding current condition over a wide search space conducting a relatively small number of experiments.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권6호
• /
• pp.383-389
• /
• 2016

This paper presents a novel automatic white balance (AWB) algorithm for consumer imaging devices. While existing AWB methods require reference white patches to correct color, the proposed method performs the AWB function using only an input image in two steps: i) white point detection, and ii) color constancy gain computation. Based on the dark channel prior assumption, a white point or region can be accurately extracted, because the intensity of a sufficiently bright achromatic region is higher than that of other regions in all color channels. In order to finally correct the color, the proposed method computes color constancy gain values based on the Y component in the XYZ color space. Experimental results show that the proposed method gives better color-corrected images than recent existing methods. Moreover, the proposed method is suitable for real-time implementation, since it does not need a frame memory for iterative optimization. As a result, it can be applied to various consumer imaging devices, including mobile phone cameras, compact digital cameras, and computational cameras with coded color.