• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.254-257
• /
• 2002

In previous study about combinatorial optimization problem solver by using neural network, since Hopfield method, to converge into the optimum solution sooner and certainer is regarded as important. Namely, only static states are considered as the information. However, from a biological point of view, the dynamical system has lately attracted attention. Then we propose the "dynamical" combinatorial optimization problem solver using hysteresis neural network. In this article, the proposal system is evaluated by the N-Queen problem.

• 대한전기학회논문지:전력기술부문A
• /
• 제49권1호
• /
• pp.26-30
• /
• 2000

Switching of the transmission lines(T/L) is one of the methods for wuppressing the short circuit capacity. This paper presents the T/L switching operation by using the Hopfield neural network(HNN). The switching of T/L can make the line powers and the bus voltages deteriorated, as well as the fault current decreased. Such an insecure state should be avoided when the T/L is operated to be open. In this studies, the inequality constraints are formulated into the objective function to be incorporated with the HNN. Test results show that the convergence characteristics of HNN lead to the adequate solution of T/L switching.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 추계학술대회 논문집 학회본부 A
• /
• pp.232-235
• /
• 1999

This paper presents a HNN(Hopfield Neural Network) model to solve the ORP(Optimal Routing Problem) in DSP(Distribution System Planning). This problem is generally formulated as a combinatorial optimization problem with various equality and inequality constraints. Precedent study[3] considered only fixed cert, but in this paper, we proposed the capability of optimization by fixed cost and variable cost. And suggested the corrected formulation of energy function for improving the characteristics of convergence. The proposed algorithm has been evaluated through the sample distribution planning problem and the simmulation results are presented.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.757-759
• /
• 1996

This paper proposes an application of artificial neural networks to the bus-bar separation in a substation for radial network operation. For the effective bus-bar operation, the insecurity index of transmission line load is introduced. For the radial network operation. the constraints of bus-bar switch is formulated in the performance function with the insecurity index. The determination of bus-bar switching is to find the states of 0 or 1 in the circuit breakers. In this paper, it is tested that the bus-bar separation of binary optimization problem can be solved by Hopfield networks with adequate manipulations.

• 대한조선학회논문집
• /
• 제33권2호
• /
• pp.44-55
• /
• 1996

1960년대 중반 전산기를 이용한 선체 구조설계가 최초로 시도된 후 국내에서도 1980년부터 중앙단면 최적설계에 관한 많은 연구가 이루어져 왔다. 선급규정에 의한 선체 중앙단면 최적설계를 할 경우, 야기되는 문제로서는 부재 치수, 부재 개수와 같은 이산변수를 다루어야 하는 어려움이 있어, 이러한 문제를 해결하고자 유전자 알고리즘이나 인공신경망 등의 새로운 최적화 기법의 개발에 관한 연구 등이 진행되고 있다. 이와 같은 관점에서 본 연구에서는 선체 구조설계 문제에 효율적인 최적화 방법을 개발함에 있어, 홉필드 네트워크 모델과 시뮬레이티드 어닐링을 결함하여 Neuro-Optimizer를 개발하고, 이를 토대로 구조공학 문제의 하나인 간단한 트러스 구조물의 최적설계와 선체의 중앙단면 최적설계에 적용하여, 새로운 최적화 기법으로서 가능성이 있음을 확인하였다.

• 대한전자공학회논문지
• /
• 제26권6호
• /
• pp.108-114
• /
• 1989

Hopfield 모델에 화소당 가주치를 도입하고 이를 최적화하여, 서로간에 상관관계가 높은 "0"에서 "9"까지의 10가지 숫자를 성공적으로 기억, 재생시킬 수 있는 $6{}8$ nodes 연상기억 시스템을 소개한다. 다른 많은 신경회로와는 달리, 이 모델은 "6","8","3","9"와 같이 상관관계가 매우 큰 영상에 대해서도 높은 오차 교정 능력을 가짐을 볼 수 있다. 화소당 가중치의 최적화 무제는 최소자승평균 오차 알고리듬에 기초한 적응학습 과정으로 볼 수 있으며, 이는 또한 Widrow-Hoff 신경회로로 구현 할 수 있다. 가중치 최적화 회로의 전기 . 광학적 구현을 위한 설계도 소개한다.

• 전자공학회논문지C
• /
• 제35C권1호
• /
• pp.55-63
• /
• 1998

This paper presents a new maching algorithm by Hopfield Neural Network for 3-D object recognition. In the proposed method, a model object is represented by a set of polygons in a single coordinate. And each polygon is described by a set of features; feature attributes. In case of 3-D object recognition, the scale and poses of the object are important factors. So we propose a strategy for 3-D object recognition independently to its scale and poses. In this strategy, the respective features of the input or the model objects are changed to the startegical constants when they are compared with one another. Finally, we show that the proposed method has a robustness through the results of experiments which included the classification of the input objects and the matching sequence to its 3-D rotation and scale.

• 전자공학회논문지C
• /
• 제34C권12호
• /
• pp.61-69
• /
• 1997

This paper proposes a new method for improving the performances of the neural network for optimization using a hyubrid of gradient descent method and dynamic tunneling system. The update rule of gradient descent method, which has the fast convergence characteristic, is applied for high-speed optimization. The update rule of dynamic tunneling system, which is the deterministic method with a tunneling phenomenon, is applied for global optimization. Having converged to the for escaping the local minima by applying the dynamic tunneling system. The proposed method has been applied to the travelling salesman problems and the optimal task partition problems to evaluate to that of hopfield model using the update rule of gradient descent method.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1993년도 학술논문발표회 논문집 제12권 1호
• /
• pp.201-205
• /
• 1993

A decision-theoretic concept is introduced to investigate whether targets of interest in array sensor systems are present at some steering direction or not. The solutions to this problem are described as a set of simple numbers 0 or 1 corresponding to the direction under consideration. This coded number representation is transplanted in the optimisation technique based on the Hopfield neural network, which may provide a new aspect of determining the direction of arrival (DOA) of sources. To cast the perspectives of the proposed approach and illustrate its effectiveness in source direction finding in array sensor systems, simulation results and related discussions are presented in this paper.

• 한국지능시스템학회논문지
• /
• 제10권4호
• /
• pp.379-389
• /
• 2000

A cellular automaton is well-known for self-organizing and dynamic behavions in the filed of artifial life. This paper addresses a new neuronic architecture called an evolvable celluar classifier which evolves with the genetic rules (chromosomes) in the non-uniform cellular automata. An evolvable cellular classifier is primarily based on cellular programming, but its mechanism is simpler becaise it utilizes only mutations for the main genetic operators and resmbles the Hopfield network. Therefore, the desirable bit-patterns could be obtained through evolutionary processes for just one individual agent, As a rusult, an evolvable hardware is derived which is applicable to clessification of bit-string information.