• Journal of Electrical Engineering and Technology
• /
• 제12권6호
• /
• pp.2388-2398
• /
• 2017

In this study, we propose a robust face recognition system to pose variations based on automatic pose estimation. Radial basis function neural network is applied as one of the functional components of the overall face recognition system. The proposed system consists of preprocessing and recognition modules to provide a solution to pose variation and high-dimensional pattern recognition problems. In the preprocessing part, principal component analysis (PCA) and 2-dimensional 2-directional PCA ($(2D)^2$ PCA) are applied. These functional modules are useful in reducing dimensionality of the feature space. The proposed RBFNNs architecture consists of three functional modules such as condition, conclusion and inference phase realized in terms of fuzzy "if-then" rules. In the condition phase of fuzzy rules, the input space is partitioned with the use of fuzzy clustering realized by the Fuzzy C-Means (FCM) algorithm. In conclusion phase of rules, the connections (weights) are realized through four types of polynomials such as constant, linear, quadratic and modified quadratic. The coefficients of the RBFNNs model are obtained by fuzzy inference method constituting the inference phase of fuzzy rules. The essential design parameters (such as the number of nodes, and fuzzification coefficient) of the networks are optimized with the aid of Particle Swarm Optimization (PSO). Experimental results completed on standard face database -Honda/UCSD, Cambridge Head pose, and IC&CI databases demonstrate the effectiveness and efficiency of face recognition system compared with other studies.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• 한국식품과학회지
• /
• 제29권3호
• /
• pp.509-515
• /
• 1997

식품공업과 의학, 의료, 화장품 등 많은 분야에서 널리 이용되고 있는 단백질 분해 효소의 하나인 papain을 papaya 유액으로부터 추출해내기 위한 최적 조건을 반응표면 분석법(RSM)을 이용하여 결정하였다. 중심 합성법에 의한 실험 계획을 설정하여 부분요인 실험법에 의하여 crude papain을 추출 및 분리하고 선정된 독립 인자의 반응 표면에 대한 영향을 분석하여 다중 회귀 분석으로 다음과 같은 모델식(Y)을 얻었으며, EDTA는 다중 회귀 분석에 의하여 제거되었다. $Y=29.0630-2.5812X_3+149.3208X_4+{13.1705X_1}^{2}+{0.0208X_3}^2-{9.8494X_4}^2$. 따라서 이 결과 papain 추출은 $NaHSO_3$, 농도가 4%, 추출 시간은 120분, pH는 7.6일때 최적 조건이 된다. 이러한 최적 추출 조건으로 얻은 효소 단백질 추출 양의 실험치는 793.16 mg prot./g latex로, 이는 효소 단백질 추출 예측치인 795.60 mg prot./g latex와 매우 근접한 값을 나타냄으로써 r=0.9951의 높은 상관 관계를 입증하였다.

• 한국식품영양과학회지
• /
• 제37권4호
• /
• pp.497-504
• /
• 2008

본 연구는 새로운 드레싱을 개발하기 위하여 복분자를 이용한 샐러드드레싱을 만들었을 때 최적의 혼합비를 찾기 위하여 혼합물 실험계획법(mixture design) 중 D-optimal design을 이용하였다. 샐러드드레싱의 품질에 가장 영향을 미치는 복분자즙, 기름, 식초의 첨가율을 독립변수로 설정하였고, 범위는 예비실험을 거쳐 각각 $15.70\sim47.10%$, $23.50\sim39.20%$, $3.90\sim19.60%$로 하였다. 실험 결과를 모델링하여 유의성을 검증한 결과, 점도, 적색도, 황색도, 총색차, 유화안정성과 관능검사 항목 중 색이 linear 모델로, 명도와 관능검사 항목 중 냄새, 맛과 전반적인 기호도는 quadratic 모델로 결정되었다. 모델의 적합성을 분석한 결과 모든 항목에서 probability가 모두 0.05% 이내에서 유의성을 보여 모델로서 적합함이 인정되었다. 복분자즙을 이용한 샐러드드레싱의 최적 재료 혼합비율은 수치 최적화에서는 복분자즙 36.02%, 기름 26.48%, 식초 12.00%이었고, 모형적 최적화에서는 desirability가 0.577에 해당하는 복분자즙 36.00%, 기름 26.44%, 식초 12.06%로 수치 최적화 점과 거의 일치하는 수치를 보였다. 이는 드레싱을 만들 때 복분자의 활용 가능성을 제시하여 새로운 드레싱 제품 개발의 기초자료를 제공하고, 새로운 것을 추구하는 소비자들의 욕구를 충족시킬 수 있을 것으로 기대된다.

• 한국항공우주학회지
• /
• 제44권11호
• /
• pp.989-996
• /
• 2016

본 연구는 비선형 응답모델과 실수기반의 혼합형 유전자 알고리즘을 적용하여 로터의 트?-발란스(RTB) 기법을 개발하는 데 목적이 있다. 트?-발란스 조절 파라미터의 변화에 따른 트림해석 결과를 이용하여 2차의 근사함수를 이용하는 비선형 응답모델을 개발하였다. 트?편차와 기체의 진동응답을 최소화하기 위해 균형추 무게, 트림 탭(Trim Tab) 및 피치링크 길이를 최적화하기 위한 비선형계획 문제를 정식화하였다. 정식화 결과는 수렴성 향상을 위해 군집최적화 기법을 실변수기반의 유전자 알고리즘에 통합한 혼합형 유전자 기법을 사용함으로써 효율적인 해석이 가능하였다. 비선형 모델을 이용한 본 연구의 방법을 선형모델의 결과와 비교하여 본 연구의 방법을 검증하였으며 비선형모델을 사용하는 경우 선형모델의 결과보다 향상된 응답특성을 계산할 수 있음을 밝혔다.

• Journal of Astronomy and Space Sciences
• /
• 제14권1호
• /
• pp.142-149
• /
• 1997

잘 알려진 최적제어 이론의 선형제차조절법을 정지궤도 위성의 위치보존 궤도조정 문제에 적용하였다. 정지궤도 위성의 운동에 가장 큰 영향을 미치는 섭동향을 선택하여 동서방향과 남북방향 궤도조정의 경우 각각 14일간 지구비대칭 중력장의 영향, 28일간 태양과 달의 영향을 예측한 결과로 궤도조정할 경계조건을 적절하게 설정하였다. 비선형방정식을 선형화하여 리카티 방정식(Riccati Equation)을 두 번 적분함으로써 최적궤도와 이에 상응하는 추진 가속도를 알아내었다. 선형제차조절법으로 구한 속도변화량과 기하학적으로 계산한 ${\Delta}V$(속도변화량)을 비교해 봄으로써 제어이론을 통한 궤도조정 방법이 실제상황에 거의 근사한 해를 제공할 수 있는가와 제어이론을 위치보존 궤도조정 문제에 적용한 방법이 경제적인 측면에서의 연료최적화와 이에 따른 정지궤도 위성의 수명연장에 기여할 수 있는가에 대한 해석을 시도하였다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제19권6호
• /
• pp.816-824
• /
• 2006

This study was conducted to evaluate the shoot height at which the yield and nutritive value of wormwood (Artemisia montana) is optimized in order to provide information on its potential to support animal production (Experiment 1). A second objective was to determine how the essential oil (EO) concentration in wormwood hay and silage differ (Experiment 2). In Experiment 1, Artemisia montana was harvested at five different shoot heights (20, 40, 60, 80 and 100 cm) from triplicate $1.8{\times}1.8m$ plots. Dry matter (DM) yield was measured at each harvest date and the harvested wormwood was botanically separated into leaf, stalk and whole plant fractions and analyzed for chemical composition and in vitro dry matter digestibility (DMD). Values for total digestible nutrients (TDN), digestible energy (DE) and metabolizable energy (ME) were subsequently calculated using prediction equations. Dry matter yields of stalk and whole plant increased linearly (p<0.001) and leaf yield increased quadratically (p<0.01) with shoot height, whereas the leaf/stalk ratio decreased linearly (p<0.001). As shoot height increased, there was a linear increase (p<0.001) in leaf DM, ether extract (EE) and neutral detergent fiber (NDF) contents and a quadratic increase (p<0.05) in leaf acid detergent fiber (ADF) and nitrogen free extract (NFE) contents, and stalk and whole plant DM (p<0.001), organic matter (OM, p<0.01 and p<0.05), NDF (p<0.001 and 0.05) and NFE (p<0.05) contents. However, there were decreases in leaf crude protein content (CP, quadratic, p<0.001) and stalk and whole plant EE content (linear, p<0.001), CP (quadratic, p<0.05) and ash (quadratic, p<0.05) contents. Digestibility of DM and TDN, and DE and ME value in leaves were not affected by increasing shoot height, but these measures linearly decreased (p<0.001) in stalk and whole plant. In Experiment 2, the hay had higher DM and CP concentrations, but lower EE concentration than the silage. Essential oil (EO) content in wormwood silage (0.49 g/100 g DM) was higher (p<0.05) than that in wormwood hay (0.32 g/100 g DM). Wormwood hay contained 25 essentail oils (EO) including camphor (10.4 g/100 g), 1-borneol (11.6 g/100 g) and caryophyllene oxide (27.7 g/100 g), and wormwood silage had 26 EO constituents including 3-cyclohexen-1-ol (8.1 g/100 g), trans-caryophyllene (8.6 g/100 g) and ${\gamma}$-selinene (16.8 g/100 g). It is concluded that the most ideal shoot height for harvesting wormwood is 60 cm based on the optimization of DM yield and nutritive value. Wormwood silage had a greater quantity and array of EO than wormwood hay.

• 전기학회논문지
• /
• 제60권12호
• /
• pp.2352-2360
• /
• 2011

In this paper, we introduce a comprehensive design methodology of Radial Basis Function Neural Networks (RBFNN) that is based on mechanism of clustering and optimization algorithm. We can divide some clusters based on similarity of input dataset by using clustering algorithm. As a result, the number of clusters is equal to the number of nodes in the hidden layer. Moreover, the centers of each cluster are used into the centers of each receptive field in the hidden layer. In this study, we have applied Fuzzy-C Means(FCM) and K-Means(KM) clustering algorithm, respectively and compared between them. The weight connections of model are expanded into the type of polynomial functions such as linear and quadratic. In this reason, the output of model consists of relation between input and output. In order to get the optimal structure and better performance, Particle Swarm Optimization(PSO) is used. We can obtain optimized parameters such as both the number of clusters and the polynomial order of weights connection through structural optimization as well as the widths of receptive fields through parametric optimization. To evaluate the performance of proposed model, NXT equipment offered by National Instrument(NI) is exploited. The situation awareness system-related intelligent model was built up by the experimental dataset of distance information measured between object and diverse sensor such as sound sensor, light sensor, and ultrasonic sensor of NXT equipment.

• 한국공간구조학회:학술대회논문집
• /
• 한국공간구조학회 2008년도 춘계 학술발표회 논문집
• /
• pp.101-106
• /
• 2008

본 연구에서는 서로 상이한 최적화기법인 유전알고리듬과 수학적 프로그래밍기법을 이용하여 지오데식 돔 구조물을 최적화하고 그 결과를 분석하였다. 본 연구에서 도입한 유전알고리즘은 유전연산자인 선택, 교배, 돌연변이 이외에도 재생기법을 도입하여 최적해의 검색성능을 높였다. 그리고 수학적인 프로그래밍기법은 유한차분법을 이용하여 목적함수의 설계민감도를 계산하였으며 세 가지의 다른 검색기법을 이용하여 돔의 크기최적화를 수행하였다. 지오데식 돔의 중앙에 작용하는 집중하중에 저항하는 돔의 각 부재의 크기패턴을 자체 개발된 $ISADO-GA{\alpha}$와 ISADO-OPT를 이용하여 최적 설계하였다. 본 연구를 통하여 제시된 최적결과는 정해가 존재하지 않는 실제 구조물의 최적 값에 대한 유용한 정보를 제공할 뿐만이 아니라 향후 대공간구조의 새로운 구조시스템 개발의 밑거름이 될 것으로 판단된다.

• Structural Engineering and Mechanics
• /
• 제56권6호
• /
• pp.959-982
• /
• 2015

In this study, a non-stationary random earthquake Clough-Penzien model is used to describe earthquake ground motion. Using stochastic direct integration in combination with an equivalent linear method, a solution is established to describe the non-stationary response of lead-rubber bearing (LRB) system to a stochastic earthquake. Two parameters are used to develop an optimization method for bearing design: the post-yielding stiffness and the normalized yield strength of the isolation bearing. Using the minimization of the maximum energy response level of the upper structure subjected to an earthquake as an objective function, and with the constraints that the bearing failure probability is no more than 5% and the second shape factor of the bearing is less than 5, a calculation method for the two optimal design parameters is presented. In this optimization process, the radial basis function (RBF) response surface was applied, instead of the implicit objective function and constraints, and a sequential quadratic programming (SQP) algorithm was used to solve the optimization problems. By considering the uncertainties of the structural parameters and seismic ground motion input parameters for the optimization of the bearing design, convex set models (such as the interval model and ellipsoidal model) are used to describe the uncertainty parameters. Subsequently, the optimal bearing design parameters were expanded at their median values into first-order Taylor series expansions, and then, the Lagrange multipliers method was used to determine the upper and lower boundaries of the parameters. Moreover, using a calculation example, the impacts of site soil parameters, such as input peak ground acceleration, bearing diameter and rubber shore hardness on the optimization parameters, are investigated.