• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.1-14
• /
• 2010

The back-propagation neural network (BPN) has long been successfully applied in bankruptcy prediction problems. Despite its wide application, some major issues must be considered before its use, such as the network topology, learning parameters and normalization methods for the input and output vectors. Previous studies on bankruptcy prediction with BPN have shown that many researchers are interested in how to optimize the network topology and learning parameters to improve the prediction performance. In many cases, however, the benefits of data normalization are often overlooked. In this study, a genetic algorithm (GA)-based normalization transform, which is defined as a linearly weighted combination of several different normalization transforms, will be proposed. GA is used to extract the optimal weight for the generalization. From the results of an experiment, the proposed method was evaluated and compared with other methods to demonstrate the advantage of the proposed method.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.367-374
• /
• 2022

This papter presents the use of the automatic differential method based on the backpropagation method to obtain the design sensitivity and its application to topology optimization considering the stress constraints. Solving topology optimization problems with stress constraints is difficult owing to singularities, the local nature of stress constraints, and nonlinearity with respect to design variables. To solve the singularity problem, the stress relaxation technique is used, and p-norm for stress constraints is applied instead of local stresses for global stress measures. To overcome the nonlinearity of the design variables in stress constraint problems, it is important to analytically obtain the exact design sensitivity. In conventional topology optimization, design sensitivity is obtained efficiently and accurately using the adjoint variable method; however, obtaining the design sensitivity analytically and additionally solving the adjoint equation is difficult. To address this problem, the design sensitivity is obtained using a backpropagation technique that is used to determine optimal weights and biases in the artificial neural network, and it is applied to the topology optimization with the stress constraints. The backpropagation technique is used in automatic differentiation and can simplify the calculation of the design sensitivity for the objectives or constraint functions without complicated analytical derivations. In addition, the backpropagation process is more computationally efficient than solving adjoint equations in sensitivity calculations.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.85-88
• /
• 2003

강화학습의 한가지 방법인 Q-learning은 최근에 Linear Quadratic Regulation(이하 LQR) 문제에 성공적으로 적용된 바 있다. 특히, 시스템 모델의 파라미터에 대한 구체적인 정보없이 적절한 입ㆍ출력만으로 학습을 통해 문제의 해결이 가능하므로 상황에 따라 매우 실용적인 방법이 될 수 있다. 뉴럴-큐 기법은 이러한 Q-learning의 Q-value를 MLP(multilayer perceptron) 신경망의 출력으로 대치시켜, 비선형 시스템의 최적제어 문제를 다룰 수 있게 한 방법이다. 그러나, 뉴럴-큐 기법은 신경망의 구조를 먼저 결정한 후 역전파 알고리즘을 이용해 학습하는 절차를 행하므로, 시행착오를 통해 신경망 구조를 결정해야 한다는 점, 역전파 알고리즘의 적용에 따라 신경망의 연결강도 값들이 지역적 최적해로 수렴한다는 점등의 문제점이 있다. 본 논문에서는 뉴럴-큐 학습의 도구로 KFD회귀를 이용하여 Q 함수의 근사 기법을 제안하고 관련 수식을 유도하였다. 그리고, 모의 실험을 통하여, 제안된 뉴럴-큐 방법의 적용 가능성을 알아보았다.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.6
• /
• pp.64-74
• /
• 2010

This paper proposes a new TR-based baseline-free SHM technique in which the time-reversal (TR) property of the guided Lamb waves is utilized. The new TR-based SHM technique has two distinct features when compared with the other TR-based SHM techniques: (1) The backward TR process commonly conducted by the measurement is replaced by the computation-based process; (2) In place of the comparison method, the TOF information of the damage signal extracted from the reconstructed signal is used for the damage diagnosis in conjunction with the imaging method which enables us to represent the damage as an image. The proposed TR-based SHM technique is then validated through the damage diagnosis experiment for an aluminum plate with a damage at different locations.

• Proceedings of the Korean Magnestics Society Conference
• /
• 2012.11a
• /
• pp.55-56
• /
• 2012

• Polymer(Korea)
• /
• v.30 no.2
• /
• pp.108-111
• /
• 2006

In this work, the effect of the hydrophobicity of acrylic polymers on the membrane morphology was investigated. The membranes were prepared with poly(methyl methacrylate) (PMMA), poly(ethyl methacrylate) (PEMA), poly (butyl methacrylate) (PBMA), poly(isobutyl methacrylate), and their blends using the wet phase inversion method. PMMA and PEMA having a relatively less hydrophobicity formed the channel-like structure, whereas PBMA and PIBMA having more hydrophobic units formed the finger-like structure. These morphological changes were attributed to differences in the solidification process of the polymer-rich phase determine d by the polymer/solvent/nonsolvent ternary phase diagram. The membrane structures of the blends were controlled by the main component of their blends.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.137-141
• /
• 1989

본 논문에서는 신경망 구조의 한 모델인 feed-forward multi-layered network에 역전파 학습(back-propagation learning) 기법을 이용하여 필기체 한글 숫자를 인식하고 그 가능성을 보였다. 문자 인식에 있어 입력 대상의 모양이 왜곡되거나, 대상의 크기 혹은 위치의 변화 등과 같은 잡음 (noise)에 대해서 정확히 대상을 인식하는 데는 대상의 구조 추출에 크게 관여되므로 한글의 구조 추출에 적합하다고 생각되는 bar mask 투사법을 제안하였다. 모델의 학습을 필기체 한글 숫자 16자의 입력 패턴과 타겟 ( target) 입력의 쌍을 이용해 학습시켰다. 또한, 모델의 인식 정도를 측정해 보기 위해 시험패턴을 적용하여 훈련된 패턴과 훈련되지 않은 패턴간의 인식률을 비교하여 보았다.

• Economic and Environmental Geology
• /
• v.40 no.4
• /
• pp.473-490
• /
• 2007

Strata of the Kachi-1 well, Kunsan Basin, offshore western Korea, were analyzed by using integrated stratigraphy approach. As a result, five distinct unconformity-bounded units are recognized in the well: Triassic, Late Jurassic-Early Cretaceous, Early Cretaceous, Late Cretaceous, and Middle Miocene units. Each unit represents a tectono-stratigraphic unit that provides time-sliced information on basin-forming tectonics, sedimentation, and basin-modifying tectonics of the Kunsan Basin. In the late Late Jurassic, development of second- or third-order wrench faults along the Tan-Lu fault system probably initiated a series of small-scale strike-slip extensional basins. Continued sinistral movement of these wrench faults until the Late Cretaceous caused a mega-shear in the basin, forming a large-scale pull-apart basin. However, in the Early Tertiary, the Indian Plate began to collide with the Eurasian Plate, forming a mega-suture zone. This orogenic event, namely the Himalayan Orogeny, continued by late Eocene and was probably responsible for initiation of right-lateral motion of the Tan-Lu fault system. The right-lateral strike-slip movement of the Tan-Lu fault caused the tectonic inversion of the Kunsan Basin. Thus, the late Eocene to Oligocene was the main period of severe tectonic modification of the basin. After the Oligocene, the Kunsan Basin has maintained thermal subsidence up to the present with short periods of marine transgressions extending into the land part of the present basin.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1999.12a
• /
• pp.747-757
• /
• 1999

본 논문에서는 가변구조제어기의 슬라이딩모드이득과 경계층두께(boundary layer thickness)를 신경망을 이용하여 계산하는 신경망 가변구조제어기를 제시한다. 제시된 방법은 신경망의 역전파오차 학습기능을 이용하여 슬라이딩모드이득과 경계층 범위를 계산할 수 있도록 신경망 제어기를 학습시킴으로써, 슬라이딩모드 제어법칙을 단순화 하고, 시스템 불확실성에 대하여 강인하며, 추적오차를 더욱 개선시킬 수 있다. 설계의 예와 시뮬레이션 결과를 통하여 제시된 방법에 대한 유용성을 보인다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.6
• /
• pp.591-596
• /
• 2000

본 논문에서는, 퍼지 신경망 시스템에 대한 최적의 규칙 베이스의 생성과 초기화를 이루기 위하여 웨이브릿 이론을 기반으로 한 퍼지 신경망 구조를 제안한다. 제안한 웨이브릿 기반의 퍼지 신경망 구조(WFNN)에서는 퍼지-신경망에 대하여 웨이브렛 함수의 성질과 다운스트레칭 메카니즘에 의하여 초기의 최적 퍼지 규칙 베이스를 구성하고 은닉층의 노드 개수를 최적화시키며, 에러 역전파 알고리즘에 의하여 각 파라미터의 조절과 학습이 진행된다. 역진자 시스템에 대한 모의 실험을 통하여 제안한 웨이브릿 기반의 퍼지 신경망 제어 시스템의 우수성을 검증하였다.