• Journal of Mechanical Science and Technology
• /
• 제14권1호
• /
• pp.113-120
• /
• 2000

This study has developed a new liquid crystal calibration technique using Neural networks with median filtering and applied this technique to heat transfer measurements. To verify the validity of this new measurement technique, the local Nusselt numbers on a flat plate surface subjected to an axisymmetric impinging jet were measured and compared with the results by the conventional Hue-temperature calibration technique under the same conditions. Because the Neural networks predict the non-linear relations between temperatures and corresponding R, G, B values, Neural networks-median filtering calibration technique can utilize a much wider color band in the experiment than the Hue-temperature calibration technique, resulting in a significant reduction in the experimental time.

• Computers and Concrete
• /
• 제30권4호
• /
• pp.237-242
• /
• 2022

This paper is concerned with exponential stability in mean square for stochastic static neutral neural networks with varying delays. By using Lyapunov functional method and with the help of stochastic analysis technique, the sufficient conditions to guarantee the exponential stability in mean square for the neural networks are obtained and some results of related literature are extended.

• 제어로봇시스템학회논문지
• /
• 제5권8호
• /
• pp.932-940
• /
• 1999

In this paper, a new neural networks and neural network based sliding mode controller are proposed. The new neural networks are an mor self-recurrent neural networks which use a recursive least squares method for the fast on-line leammg. The error self-recurrent neural networks converge considerably last than the back-prollagation algorithm and have advantage oi bemg less affected by the poor initial weights and learning rate. The controller for suspension system is designed according to sliding mode technique based on new proposed neural networks. In order to adapt shding mode control mnethod, each frame dstance hetween ground and vehcle body is estimated md controller is designed according to estimated neural model. The neural networks based sliding mode controller approves good peiformance throllgh computer sirnulations.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 춘계학술대회 논문집
• /
• pp.178-182
• /
• 1995

The technique of neural networks is applied to cold forging design system. A user can select more desirable plans in cold forging design by being advised with expert's opinion from neural networks. The neural networks are learned with 3 parts which are most important in cold forging design-undercut, narrow hole, sharp corner. Using the neural networks, the cold forging design system built in this study determines forming possibility about variable shapes in product. We can get available result using the system.

• Structural Engineering and Mechanics
• /
• 제23권1호
• /
• pp.75-95
• /
• 2006

Two-step identification approaches for effective bridge health monitoring are proposed to alleviate the issues associated with many unknown parameters faced in real structures and to improve the accuracy in the estimate results. It is suitable for on-line monitoring scheme, since the damage assessment is not always needed to be carried out whereas the alarming for damages is to be continuously monitored. In the first step for screening potentially damaged members, a damage indicator method based on modal strain energy, probabilistic neural networks and the conventional neural networks using grouping technique are utilized and then the conventional neural networks technique is utilized for damage assessment on the screened members in the second step. The effectiveness of the proposed methods is investigated through a field test on the northern-most span of the old Hannam Grand Bridge over the Han River in Seoul, Korea.

• 한국정보과학회논문지:정보통신
• /
• 제32권3호
• /
• pp.301-309
• /
• 2005

시스템 호출 감사자료기반 기계학습기법을 사용한 프로그램 행위 학습방법은 효과적인 호스트 기반 침입탐지 방법이며, 규칙 학습, 신경망, 통계적 방법, 은닉 마크로프 모델 등의 방법이 대표적이다. 그 중에서 신경망은 시스템 호출 시퀀스를 학습하는데 있어 적합하다고 알려져 있는데, 실제 문제에 적용하여 좋은 성능을 내기 위해서는 그 구조를 결정하는 것이 중요하다 하지만 보통의 신경망은 그 구조를 찾기 위한 방법이 알려져 있지 않아 침입탐지에 효과적인 구조를 찾기 위해서는 많은 시간이 요구된다. 본 논문에서는 기존 신경망 기반 침입탐지시스템의 단점을 보완하고 성능을 향상시키기 위해 진화신경망을 이용한 방법을 제안한다. 진화 신경망은 신경망의 구조와 가중치를 동시에 학습하기 때문에 일반 신경망보다 빠른 시간에 더 좋은 성능의 신경망을 얻을 수 있다는 장점이 있다. 1999년의 DARPA IDEVAL 자료로 실험한 결과 기존의 연구보다 좋은 탐지율을 보여 진화신경망이 침입탐지에 효과적임을 확인할 수 있었다.

• 한국정보통신학회논문지
• /
• 제10권6호
• /
• pp.1032-1037
• /
• 2006

채널은 무선망에 있어서 한정된 주요 자원 중의 하나이다. 다양한 채널 관리 기법들이 제시되어 왔으며, 최근 들어 가드채널의 최적화 문제가 부각되고 있다. 본 논문에서는 신경망을 이용한 지능적인 채널 관리 기법을 제안한다. 신경망의 학습 데이터 생성과 성능분석을 위하여 SRN(Stochastic Reward Net) 채널 할당 모델이 개발된다. 제안된 기법에서 신경망은 지도학습 방법인 역전파 알고리즘을 이용하여 최적의 가드채널 값 g를 계산하도록 학습한다. 학습된 신경망을 이용하여 최적의 g를 계산하고, 이를 SRM모델에서 구해진 결과와 비교한다. 실험 결과는 신경망에서 구한 가드채널 수와 SRM모델로부터 구한 가드채널 수의 상대적 차이가 없음을 보여준다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.242-245
• /
• 2000

In this paper, we present a color interpolation technique based on artificial neural networks for a single-chip CCD (charge-coupled device) camera with a Bayer color filter array (CFA). Single-chip digital cameras use a color filter array and an interpolation method in order to regenerate high quality color images from sparsely sampled images. We applied 3-layer feedforward neural networks in order to interpolate missing pixel from surrounding pixels. And we compared the proposed method with conventional interpolation methods such as the proposed interpolation algorithm based on neural networks provides a better performance than the conventional interpolation algorithms.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.591-593
• /
• 1997

When input circumstance is changed abrubtly, many nodes of Competitive Learning Neural Networks far from new input vector may never win, and therefore never learn. Various techniques to prevent these phenomena have been reported. We proposed a new technique based on Self Creating and Organizing Neural Networks, and which is compared to Self Organizing Feature Map and Frequency Sensitive Neural Networks.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.43.2-43
• /
• 2001

In this paper, we consider the problems of the evolutionary designed neural networks structures by genetic algorithm. Neural networks has been applied to various application fields since back-propagation algorithm was proposed, e.g. function approximation, pattern or character recognition and so on. However, one of difficulties to use the neural networks. It is how to design the structure of the neural network. Researchers and users design networks structures and training parameters such as learning rate and momentum rate and so on, by trial and error based on their experiences. In the case of designing large scales neural networks, it is very hard work for manually design by try and error. For this difficulty, various structural learning algorithms have been proposed. Especially, the technique of using genetic algorithm for networks structures design has been ...