• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2663-2665
• /
• 2001

역전파 신경망은 반도체 공정 모델링에 효과적으로 응용이 되고 있으며, 최근 선형뉴런을 비선형 함수 대신 출력층에 이용하여 모델의 예측정확도를 향상 시킨 바 있다. 본 연구에서는 그 원인을 규명하기 위한 모델의 평가지표로서의 유클리디언 웨이트 거리(Euclidean Weight Distance)를 제안한다. 이 지표를 이용하여 신경망의 입력층과 은닉층, 그리고 은닉층과 출력층의 웨이트를 감시하였으며, 그 결과 예측정확도의 향상이 이 지표의 감소에 기인하고 있음을 알았다. 모델링에 이용한 실험데이터는 다중 유도결합형 플라즈마 장비로부터 Langmuir Probe 진단 시스템을 이용하여 수집하였다.

• Journal of Korean Society of Transportation
• /
• v.18 no.4
• /
• pp.95-105
• /
• 2000

The Purpose of this study is to present a new Trip Generation Model using Backpropagation Neural Networks. For this purpose, it is compared the performance between existing linear/nonlinear Regression models and a new TriP Generation model using Neural Networks. The study was performed according to the below. First, it is analyzed the limits of conventional Regression models, next Proved the superiority of Neural Networks model in theoretical and empirical aspects, and lastly Presented a new approach of Trip Generation methodology. The results show that Backpropagation Neural Networks model is predominant in estimation and Prediction comparable to Regression analysis. Such results mean the possibility of Neural Networks\` application in Trip Generation modeling. Specially under the circumstances of the chancing transportation situations and unstable transportation on vironments, its application in transportation fields will be extended.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.175-183
• /
• 2022

The collision between a ship and bridge across a waterway may result in extremely serious consequences that may endanger the safety of life and property. Therefore, factors affecting ship bridge collision must be investigated, and the impact force should be discussed based on various collision conditions. In this study, a finite element model of ship bridge collision is established, and the peak impact force of a ship bridge collision based on 50 operating conditions combined with three input parameters, i.e., ship loading condition, ship speed, and ship bridge collision angle, is calculated via numerical simulation. Using neural network models trained with the numerical simulation results, the prediction model of the peak impact force of ship bridge collision involving an extremely short calculation time on the order of milliseconds is established. The neural network models used in this study are the basic backpropagation neural network model and Elman neural network model, which can manage temporal information. The accuracy of the neural network models is verified using 10 test samples based on the operating conditions. Results of a verification test show that the Elman neural network model performs better than the backpropagation neural network model, with a mean relative error of 4.566% and relative errors of less than 5% in 8 among 10 test cases. The trained neural network can yield a reliable ship bridge collision force instantaneously only when the required parameters are specified and a nonlinear finite element solution process is not required. The proposed model can be used to predict whether a catastrophic collision will occur during ship navigation, and thus hence the safety of crew operating the ship.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1801-1802
• /
• 2007

자기 연관 시계열 신경망을 이용하여 식각종말점 패턴-기반 플라즈마 상태를 진단하는 방법을 제안한다. 식각종말점 패턴은 Oxide 박막의 식각공정 중 Optical Emission Spectroscopy를 이용하여 수집하였으며, 역전파 신경망을 이용하여 진단 모델을 개발하였다. 진단 모델은 단일 신경망과 모듈러신경망을 이용하여 개발하였으며, 비교평가결과 모듈러 신경망이더 우수한 성능을 보였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.301-306
• /
• 2006

본 연구에서는 강우의 시 공간적 분포의 불규칙한 변동성을 고려한 강우-유출예측을 위해 인공신경망(Artificial Neural Networks: ANNs)의 기법의 일종인 자기조직화(Self Organizing Map: SOM) 이론과 역전파 학습 알고리즘(Back Propagation Algorithm: BPA) 이론을 복합적으로 이용하였다. 기존의 인공신경망 연구에서 야기된 저..갈수기의 유출량에 대한 과대평가, 홍수기의 유출량에 대한 과소평가, 예측값이 선행 유출량의 지속성을 갖는 Persistence 현상을 해결하기 위하여 패턴분류 성능을 지닌 SOM 이론을 도입하여 예측모형의 전처리 과정으로 이용하였다. 이는 기존의 인공신경망 모형이 하나의 모형을 구성하여 유출량의 전 범위에 해당하는 자료를 예측하는 방법을 개선한 것으로 SOM에 의해 패턴이 분류된 강우-유출관계의 각 패턴별 예측모형을 통해 분류된 자료들의 예측을 수행하는 방법이다. 이와 같이 SOM을 강우-유출예측모형의 전처리과정으로 이용함으로서 기존의 인공신경망 연구에서 야기된 현상들을 해결할 수 있었고, 예측력 또한 기존의 인공신경망 모형의 결과에 비해 우수하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.5
• /
• pp.1393-1402
• /
• 1999

This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.255-262
• /
• 2007

This paper proposes an enhanced skin color-based detection method to find a region of human face in color images. The proposed detection method combines three color spaces, RGB, $YC_bC_r$, YIQ and builds color union histograms of luminance and chrominance components respectively. Combined color union histograms are then fed in to the back-propagation neural network for training and Levenberg-Marquadt algorithm is applied to the iteration process of training. Proposed method with Levenberg-Marquadt algorithm applied to training process of neural network contributes to solve a local minimum problem of back-propagation neural network, one of common methods of training for face detection, and lead to make lower a detection error rate. Further, proposed color-based detection method using combined color union histograms which give emphasis to chrominance components divided from luminance components inputs more confident values at the neural network and shows higher detection accuracy in comparison to the histogram of single color space. The experiments show that these approaches perform a good capability for face region detection, and these are robust to illumination conditions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.374-378
• /
• 1998

신경망은 복잡하게 나타나는 비선형성을 가지는 실제의 다양한 문제들에 적용이 가능할 뿐만 아니라, 정보들이 가중치에 분산되어 저장됨으로서 강인성을 가지고 있다. 그러나 전방향 다층 신경망 구조를 학습할 수 있는 역전파 알고리즘은 초기 가중치의 영향에 의하여 학습된 결과가 지역 최소점에 빠지기 쉬운 경향이 있다. 본 논문에서는 이러한 문제점을 해결하기 위한 한가지 방법으로서 유전자 알고리즘을 이용하여 전방향 다층 신경망의 가중치를 학습하여, 지역 최소점에 빠지지 않고 학습이 이루어짐을 보인다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1994.04a
• /
• pp.148-148
• /
• 1994