• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.841-843
• /
• 1999

This paper presents a design of stabilization controller for combat vehicle. A Stabilization system reject disturbances while vehicle moving. The conventional stabilization controller used to constant gain. We can improve the aiming performance by appropriate controller gain. We can find the proper controller gain for road frequencies by evolution strategy(ES). The relationship between the frequencies and proper control gains are generalized by use of the neural network. The road frequency estimated by wavelet transform of disturbance signal. The simulation result show that proposed controller is superior to the conventional stabilization controller.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.9
• /
• pp.1356-1362
• /
• 2015

Modular snake-like robots are robust for failure and have flexible locomotions for obstacle environment than of walking robot. This requires an adaptation capability which is obtained from a learning approach, but has not been analysed as well. In order to investigate the property of adaptation of locomotion for different terrains, NEAT controllers are trained for a flat terrain and tested for obstacle terrains. The input and output characteristics of the adaptation for the neural network controller are analyzed for different terrains in frequency domain.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.61-71
• /
• 1998

Genetic Algorithm(GA) is a method of approaching optimization problems by modeling and simulating the biological evolution. GA needs large time-consuming, so ti had better do on a parallel computer architecture. Our proposed system has a VLSI-oriented interconnection network, which is constructed from a viewpoint of fractal geometry, so that self-similarity is considered in its configuration. The approach to Parallel Genetic Algorithm(PGA) on our proposed system is explained, and then, we construct the classifier system such that the set of samples is classified into weveral classes based on the features of each sample. In the process of designing the classifier system, We have applied PGA to the Traveling Salesman Problem and classified the sample set in the Euclidean space into several categories with a measure of the distance.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.3
• /
• pp.58-64
• /
• 1999

Evolutionary programming is mainly characterized by two factors; one is the selection strategy and the other the mutation rule. In this paper, a new mutation rule that is the same form of well-known backpropagation learning rule of neural networks has been presented. The proposed mutation rule adapts the best individual's value as the target value at the generation. The temporal error improves the exploration through guiding the direction of evolution and the momentum speeds up convergence. The efficiency and robustness of the proposed algorithm have been verified through benchmark test functions.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.04a
• /
• pp.212-215
• /
• 2000

다수 사업체의 출현과 데이터 통신의 증가로 통신사업자의 사업환경은 급속한 변화를 겪고 있다. 이러한 사업환경 변화에 비추어 시내전화 사업자는 기존 동선 구조의 가입자망을 초고속 서비스에 적합하도록 고도화시켜야 하는 필요성을 가지고 있다. 본 연구는 기존 동선가입자망을 광가입자망으로 전환하는데 따른 시내전화 사업자의 의사결정문제에 대하여 전략적 의사결정 방법론을 제시하고자 한다. 이를 위해 본 연구에서는 ADSL 비용 모형을 개발하여 도심지역을 대상으로 현재 동선구조의 가입자망을 고도화시키기 위한 기술적 대안에 대하여 경제성 분석을 실시하였다. 또한 2010년간의 가상의 시나리오를 설정하여 통신사업자의 이익을 극대화시킬 수 있는 진화방법을 도출하였다.

• Korea-Australia Rheology Journal
• /
• v.16 no.4
• /
• pp.213-218
• /
• 2004

Linear high-density polyethylene (PE) was controlled to induce strain-hardening behavior by introducing a small amount of second component with an anisotropic structure. In order to form an anisotropic structure in the PE matrix, the polymer was extruded through a twin-screw extruder, and the structure was controlled by varying the extrusion conditions. Depending on conditions, the second component formed a film, thread and droplet structure. If the second component was kept rigid, the morphology evolution could be delayed and the second component could maintain its film or thread structure without further relaxation. In par­ticular, the second component of the thread structure made a physical network and gave rise to remarkable strain hardening behavior under high extension. This study suggests a new method that induces strain hard­ening behavior by introducing a physically networked second component into the linear polymer melt. This result is anticipated to improve the processibility of linear polymers especially when extensional flow is dominant, and to contribute to our understanding of strain hardening behavior.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.12
• /
• pp.4392-4396
• /
• 2011

Porous silicon with a complex network of nanopores is utilized for photoelectrochemical energy conversion. A novel electroless Pt deposition onto porous silicon is investigated in the context of photoelectrochemical hydrogen generation. The electroless Pt deposition is shown to improve the characteristics of the PS photoelectrode toward photoelectrochemical $H^+$ reduction, though excessive Pt deposition leads to decrease of photocurrent. Furthermore, it is found that a thin layer (< 10 ${\mu}m$) of porous silicon can serve as anti-reflection layer for the underlying Si substrate, improving photocurrent by reducing photon reflection at the Si/liquid interface. However, as the thickness of the porous silicon increases, the surface recombination on the dramatically increased interface area of the porous silicon begins to dominate, diminishing the photocurrent.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.32-37
• /
• 2009

Recently, electronic mail(E-mail) is the most popular communication manner in our society. In such conventional environments, spam increasingly congested in Internet. In this paper, Chinese spam could be effectively detected using text and image features. Using text features, keywords and reference templates in Chinese mails are automatically selected using genetic algorithm(GA). In addition, spam containing a promotion image is also filtered out by detecting the text characters in images. Some experimental results are given to show the effectiveness of our proposed method.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.348-350
• /
• 1998

시뮬레이션 환경이나 실제 환경에서 이동 로봇의 제어에 관한 많은 연구가 진행되어 왔다. 이러한 연구 중에서 이동 로봇이 장애물을 피한다거나, 움직이는 물체를 잡는 등의 행동을 유전자 알고리즘 등의 진화 알고리즘으로 만들어내는 연구가 최근 활발하다. 이전의 연구에서는 셀룰라 오토마타 상에서 진화의 방법으로 신경망을 성장시키는 모델을 제시하고, 그 유용성을 입증하고자 이동로봇의 제어에 적용하여 나름대로 만족할 만한 결과를 얻을 수 있었다. 그러나 이러한 진화의 방법은 환경에 제한된 제어기를 만들어 내는 문제점이 있어 본 논문에서는 점증적인 진화의 방법을 이용하여 좀더 다양한 환경에 적응할 수 있는 제어기를 만들어 내고자 한다. 점증적 방법은 초기에 간단한 행동으로 해결할 수 있는 환경에 맞도록 제어기를 진화시킨 다음, 점차 복잡한 행동이 요구되는 환경에서 제어기를 점증적으로 진화시킨다. 실험 결과, 점증적 진화의 방법이 좀더 효율적으로 로봇을 진화시키고 환경의 변화에 보다 강한 것을 알 수 있었다.

• Journal of the Korean Statistical Society
• /
• v.35 no.3
• /
• pp.281-303
• /
• 2006

In an earlier work, we investigated the problem of using linear programming to bound performance measures in a discrete time Jackson network. There it was assumed that the system evolution is controlled by the early arrival scheme. This assumption implies that the system can't be modelled by a Markov chain. This problem was resolved and performance bounds were calculated. In the present work, we use a modification of the early arrival scheme (without corrupting it) in order to make the system evolves as a Markov chain. This modification enables us to obtain explicit expressions for certain moments that could not be calculated explicitly in the pure early arrival scheme setting. Moreover, this feature implies a reduction in the linear program size as well as the computation time. In addition, we obtained tighter bounds than those appeared before due to the new setting.