• 정보학연구
• /
• 제8권1호
• /
• pp.51-56
• /
• 2005

The Back propagation algorithm is a very effective supervised training method for multi-layer feed forward neural networks. This paper studies the decision boundary formation based on the Back propagation algorithm. The discriminating powers of several neural network topology are also investigated against five manually created data sets. It is found that neural networks with multiple hidden layer perform better than single hidden layer.

• Environmental Engineering Research
• /
• 제25권4호
• /
• pp.515-521
• /
• 2020

Nowadays, due to various pollution sources, it is essential for environmental scientists to monitor water quality. Phytoplanktons form the end of the food chain in water bodies and are one of the most important biological indicators in water pollution studies. Chlorophyll-A, a green pigment, is found in all phytoplankton. Chlorophyll-A concentration indicates phytoplankton biomass directly. Therefore, Chlorophyll-A is an indirect indicator of pollutants, including phosphorus and nitrogen, and their refinement and control are important. The present study, Moderate Resolution Imaging Spectroradiometer (MODIS) satellite images were used to estimate the chlorophyll-A concentration in southern coastal waters in the Caspian Sea. For this purpose, Multi-layer perceptron neural networks (NNs) were applied which contained three and four feed-forward layers. The best three-layer NN has 15 neurons in its hidden layer and the best four-layer one has 5 in each. The three- and four- layer networks both resulted in similar root mean square errors (RMSE), 0.1($\frac{{\mu}g}{l}$), however, the four-layer NNs proved superior in terms of R² and also required less training data. Accordingly, a four-layer feed-forward NN with 5 neurons in each hidden layer, is the best network structure for estimating Chlorophyll-A concentration in the southern coastal waters of the Caspian Sea.

• Journal of Advanced Marine Engineering and Technology
• /
• 제20권3호
• /
• pp.286-286
• /
• 1996

A neural predictive tracking system for the control of structure-unknown dynamic system is presented. The control system comprises a neural network modelling mechanism for the the forward and inverse dynamics of a plant to be controlled, a feedforward controller, feedback controller, and an error prediction mechanism. The feedforward controller, a neural network model of the inverse dynamics, generates feedforward control signal to the plant. The feedback control signal is produced by the error prediction mechanism. The error predictor adopts the neural network models of the forward and inverse dynamics. Simulation results are presented to demonstrate the applicability of the proposed scheme to predictive tracking control problems.

• Journal of Advanced Marine Engineering and Technology
• /
• 제20권3호
• /
• pp.154-161
• /
• 1996

A neural predictive tracking system for the control of structure-unknown dynamic system is presented. The control system comprises a neural network modelling mechanism for the the forward and inverse dynamics of a plant to be controlled, a feedforward controller, feedback controller, and an error prediction mechanism. The feedforward controller, a neural network model of the inverse dynamics, generates feedforward control signal to the plant. The feedback control signal is produced by the error prediction mechanism. The error predictor adopts the neural network models of the forward and inverse dynamics. Simulation results are presented to demonstrate the applicability of the proposed scheme to predictive tracking control problems.

• 비파괴검사학회지
• /
• 제28권3호
• /
• pp.254-262
• /
• 2008

The objective of the proposed study is to produce a tool-condition monitoring (TCM) strategy that will lead to a more efficient and economical drilling tool usage. Drill-wear monitoring is an important attribute in the automatic cutting processes as it can help preventing damages of the tools and workpieces and optimizing the tool usage. This study presents the architectures of a multi-layer feed-forward neural network with back-propagation training algorithm for the monitoring of drill wear. The input features to the neural networks were extracted from the AE signals using the wavelet transform analysis. Training and testing were performed under a moderate range of cutting conditions in the dry drilling of steel plates. The results indicated that the extracted input features from AE signals to the supervised neural networks were effective for drill wear monitoring and the output of the neural networks could be utilized for the tool life management planning.

• 산업기술연구
• /
• 제24권A호
• /
• pp.99-107
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and the environments as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to parition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum of the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• Bulletin of the Korean Chemical Society
• /
• 제28권9호
• /
• pp.1477-1484
• /
• 2007

Artificial neural networks (ANNs), for a first time, were successfully developed for the prediction partial molar heat capacity of aqueous solutions at infinite dilution for various polar aromatic compounds over wide range of temperatures (303.55-623.20 K) and pressures (0.1-30.2 MPa). Two three-layered feed forward ANNs with back-propagation of error were generated using three (the heat capacity in T = 303.55 K and P = 0.1 MPa, temperature and pressure) and six parameters (four theoretical descriptors, temperature and pressure) as inputs and its output is partial molar heat capacity at infinite dilution. It was found that properly selected and trained neural networks could fairly represent dependence of the heat capacity on the molecular descriptors, temperature and pressure. Mean percentage deviations (MPD) for prediction set by the models are 4.755 and 4.642, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.462-462
• /
• 2000

In this paper, genetic algorithm (GA) is the technique to search for the optimal structures (i,e., the kind of neural network, the number of hidden neuron, ..) of the neural networks which are used approximating a given nonlinear function, In this paper, we used multi layer feed-forward neural network. The decision method of synapse weights of each neuron in each generation used back-propagation method. In this study, we simulated nonlinear function approximation in the temperature control system.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.49-52
• /
• 1998

Neural Network has good performance in pattern classification, control and many other fields by learning ability. However, there is effective rule or systematic approach to determine optimal structure. In this paper, we propose a new method to find optimal structure of feed-forward multi-layer neural network as a kind of pruning method. That eliminating redundant elements of neural network. To find redundant elements we analysis error and weight changing with Rough Set Theory, in condition of executing back-propagation leaning algorithm.

• Structural Engineering and Mechanics
• /
• 제32권1호
• /
• pp.71-94
• /
• 2009

In this paper a procedure for Monte Carlo simulation of univariate stationary stochastic processes with the aid of neural networks is presented. Neural networks operate model-free and, thus, circumvent the need of specifying a priori statistical properties of the process, as needed traditionally. This is particularly advantageous when only limited data are available. A neural network can capture the "pattern" of a short observed time series. Afterwards, it can directly generate stochastic process realizations which capture the properties of the underlying data. In the present study a simple feed-forward network with focused time-memory is utilized. The proposed procedure is demonstrated by examples of Monte Carlo simulation, by synthesis of future values of an initially short single process record.