• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 학술대회 논문집 정보 및 제어부문
• /
• pp.247-248
• /
• 2008

본 논문에서는 TYPE-2 퍼지 추론 기반의 RBF 뉴럴 네트워크(TYPE-2 Radial Basis Function Neural Network, T2RBFNN)를 설계하고 PSO(Particle Swarm Optimization) 알고리즘을 이용하여 모델의 파라미터를 동정한다. 제안된 모델의 은닉층은 TYPE-2 가우시안 활성 함수로 구성되며, 출력층은 Interval set 형태의 연결가중치를 갖는다. 여기에서 규칙 전반부 활성함수의 중심 선택은 C-means 클러스터링 알고리즘을 이용하고, 규칙 후반부 Interval set 형태의 연결가중치 결정에는 경사 하강법(Gradient descent method)을 이용한 오류 역전파 알고리즘을 사용하여 학습한다. 또한, 최적의 모델을 설계하기 위한 학습율 및 활성함수의 활성화 영역 결정에는 입자 군집 최적화(PSO; Particle Swarm Optimization) 알고리즘으로 동조한다. 마지막으로, 제안된 모델의 평가를 위하여 모의 데이터 집합(Synthetic dadaset)을 적용하고 근사화 및 일반화 능력에 대하여 토의한다.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1899-1909
• /
• 2015

Glaucoma is one of the most common causes of blindness which is caused by increase of fluid pressure in the eye which damages the optic nerve and eventually causing vision loss. An automated technique to diagnose glaucoma disease can reduce the physicians’ effort in screening of Glaucoma in a person through the fundal retinal images. In this paper, optimal hyper analytic wavelet transform for Glaucoma detection technique from fundal retinal images is proposed. The optimal coefficients for transformation process are found out using the hybrid GSO-Cuckoo search algorithm. This technique consists of pre-processing module, optimal transformation module, feature extraction module and classification module. The implementation is carried out with MATLAB and the evaluation metrics employed are accuracy, sensitivity and specificity. Comparative analysis is carried out by comparing the hybrid GSO with the conventional GSO. The results reported in our paper show that the proposed technique has performed well and has achieved good evaluation metric values. Two 10- fold cross validated test runs are performed, yielding an average fitness of 91.13% and 96.2% accuracy with CGD-BPN (Conjugate Gradient Descent- Back Propagation Network) and Support Vector Machines (SVM) respectively. The techniques also gives high sensitivity and specificity values. The attained high evaluation metric values show the efficiency of detecting Glaucoma by the proposed technique.

• 대한교통학회지
• /
• 제17권5호
• /
• pp.111-122
• /
• 1999

소화물 일관 운송 과정에서 발생하는 직접비용을 최소화하는 수리 모형과 해법이 제안되었다. 고려되는 비용으로는 화물 운송을 위한 차량 운행에 필요한 제반 비용인 링크 비용과 터미널에서 일어나는 하차, 분류, 재적 재등 하역 작업에서 발생하는 노드 비용을 감안하였고 총비용을 줄이기 위한 화물의 운송 경로가 모형의 결정변수이다. 해법으로는 최종해의 품질은 다소 미흡하나 계산 시간이 짧은 Steepest Descent Method와 최종해의 품질이 우수하나 계산 시간이 많이 소요되는 Simulated Annealing Method를 활용한 두개의 알고리즘이 고안되었다. 최적해를 찾아가기 위한 탐색의 출발점이 되는 초기해는 Dijkstra의 최단경로 알고리즘을 수정하여 찾는다. 예제를 통하여 알고리즘의 계산 과정을 설명하였고 제시된 두 방법의 최종해는 초기해에 비하여 비용 측면에서 각각 12%. 15%의 절감 효과가 있음을, 적재율 측면에서 초기해의 62.6%에서 각각 774%. 87.4% 향상됨을 확인하였다.

• 한국연소학회지
• /
• 제3권1호
• /
• pp.21-29
• /
• 1998

Mathematical modeling of combustion characteristics in HVOF thermal spray processes was carried out on the basis of equilibrium chemistry. The main objective of this work was the development of a computation code which allows to determine chemical composition of combustion products, adiabatic flame temperature, thermodynamic and transport properties. The free energy minimization method was employed with the descent Newton-Raphson technique for numerical solution of systems of nonlinear thermochemical equations. Adiabatic flame temperature was calculated by using a Newton#s iterative method incorporating the computation module of chemical composition. The performance of this code was verified by comparing computational results with data obtained by ChemKin code and in the literature. Comparisons between the calculated and measured flame temperatures showed a deviation less than 2%. It was observed that adiabatic flame temperature augments with increase in combustion pressure; the influence was significant in the region of low pressure but becomes weaker and weaker with increase in pressure. Relationships of adiabatic flame temperature, dissociation ratio and combustion pressure were also analyzed.

• 전기학회논문지
• /
• 제56권7호
• /
• pp.1183-1190
• /
• 2007

This paper proposes the improved fault decision algorithm using DWT(Discrete Wavelet Transform) and ANNs for the FRTU(Feeder Remote Terminal Unit) on the feeder in the power distribution system. Generally, the FRTU has the fault decision scheme detecting the phase fault, the ground fault. Especially FRTU has the function for 2000ms. This function doesn't operate FI(Fault Indicator) for the Inrush current generated in switching time. But it has a defect making it impossible for the FI to be operated from the real fault current in inrush restraint time. In such a case, we can not find the fault zone from FI information. Accordingly, the improved fault recognition algorithm is needed to solve this problem. The DWT analysis gives the frequency and time-scale information. The neural network system as a fault recognition was trained to distinguish the inrush current from the fault status by a gradient descent method. In this paper, fault recognition algorithm is improved by using voltage monitoring system, DWT and neural network. All of the data were measured in actual 22.9kV power distribution system.

• 한국콘텐츠학회논문지
• /
• 제8권3호
• /
• pp.41-46
• /
• 2008

PAPR을 극복하기 위해서 SLM, PTS, SPW와 GD 같은 많은 연구들이 진행되었다. 본 논문에서는 PAPR을 줄이고 늘어난 계산량을 GD방식과 Radix-2 DIF IFFT 과정을 통하여 성능을 향상시키는 방법을 제시한다. 그리고 특정값을 설정하여 일정한 특정값을 만족하는 경우에는 제안된 방식의 일부분만으로 특정값을 만족하는 데이터 시퀀스를 선택하여 전송할 수 있고, 그렇지 못한 경우는 성능 향상을 위해 남은 부분을 수행하여 가장 적은 PAPR을 갖는 데이터 시퀀스를 선택하여 전송하는 방식이다.

• International Journal of Aeronautical and Space Sciences
• /
• 제18권1호
• /
• pp.165-173
• /
• 2017

The aeromechanics predictions of HART I rotor obtained using a computational structural dynamics (CSD) code are evaluated against the wind tunnel test data. The flight regimes include low speed descending flight at an advance ratio of ${\mu}=0.151$ and cruise condition at ${\mu}=0.229$. A lifting-line based unsteady airfoil theory with C81 table look-up is used to calculate the aerodynamic loads acting on the blade. Either rolled-up free wake or multiple-trailer wake with consolidation (MTC) model is employed for the free vortex wake representation. The measured blade properties accomplished recently are used to analyze the rotor for the up-to-date computations. The comparison results on airloads and structural loads of the rotor show good agreements for descent flight and fair for cruise flight condition. It is observed that MTC model generally improves the correlation against the measured data. The structural loads predictions for all measurement locations of HART I rotor are investigated. The dominant harmonic response of the structural loads is clearly captured with MTC model.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2011년도 제37회 추계학술대회논문집
• /
• pp.135-138
• /
• 2011

한국형 달착륙선 개발을 위한 기초연구로 달착륙선 지상시험용 추진시스템의 개발을 진행 중이다. 착륙선의 하강을 위한 추력기는 200 N 급으로 설계유량 100 g/s, 연소실 압력 200 psi, 진공추력 220 N을 목표로 설계/제작 하였다. 연소시험을 위해 LM guide(Linear Motion Guide)를 이용한 추력시험장치를 꾸며 연소시험을 수행하였으며, 그 결과 연소실 압력 210 psi 일 때 유량은 96.1 g/s가 흘렀으며 그에 따른 추력은 약 160 N으로 측정되었다.

• Clinical and Experimental Pediatrics
• /
• 제46권9호
• /
• pp.934-938
• /
• 2003

저자들은 신생아기에 경련을 보였던 환아에서 소변의 N-acetylaspartic acid의 정량검사를 통해 확진하였으며, 뇌자기공명 소견상 뇌백질의 퇴행성변화를 보였던 Canavan 병 1례를 경험하였기에 문헌 고찰과 함께 보고하는 바이다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 추계학술대회 논문집 학회본부
• /
• pp.56-59
• /
• 1988

The main purpose of Set-up control of hot strip mill plant is to obtain the most regular thickness. Then the learning or adaptive computer control in hot strip rolling mill has been developed. But it is very difficult to keep the inter-stands load distribution ratio uniform; so that the deviation of strip flatness is not avoidable. This leads to the degradation of quality of the products. In this report, an improved method base on the steepest descent method including the computation of optimum step size. This method is applied to the off-line simulation. In consequence, the better balances of inter-stands load distribution is achieved in addition to improvements of output thickness of hot strip mill in POSCO.