• Journal of information and communication convergence engineering
• /
• v.6 no.4
• /
• pp.448-453
• /
• 2008

This study describes design and development techniques of estimation models for process modeling. One case study is undertaken to design a model using standard gas furnace data. Neural networks (NN) and genetic programming (GP) are each employed to model the crucial relationships between input factors and output responses. In the case study, two models were generated by using 70% training data and evaluated by using 30% testing data for genetic programming and neural network modeling. The model performance was compared by using RMSE values, which were calculated based on the model outputs. The average RMSE for training and testing were 0.8925 (training) and 0.9951 (testing) for the NN model, and 0.707227 (training) and 0.673150 (testing) for the GP model, respectively. As concern the results, the NN model has a strong advantage in model training (using the all data for training), and the GP model appears to have an advantage in model testing (using the separated data for training and testing). The performance reproducibility of the GP model is good, so this approach appears suitable for modeling physical fabrication processes.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.5 s.176
• /
• pp.1175-1182
• /
• 2000

Diffraction systematically causes error in acoustic measurements. Most probes are designed to reduce this phenomenon. On the contrary, this paper proposes a spherical probe a] lowing acoustic inten sity measurements in three dimensions to be made, which creates a diffracted field that is well-defined, thanks to analytic solution of diffraction phenomena. Six microphones are distributed on the surface of the sphere along three rectangular axes. Its measurement technique is not based on finite difference approximation, as is the case for the ID probe but on the analytic solution of diffraction phenomena. In fact, the success of sound source identification depends on the inverse models used to estimate inverse diffraction phenomena, which has nonlinear properties. In this paper, we propose the concept of nonlinear inverse diffraction modeling using a neural network and the idea of 3 dimensional sound source identification with better performances. A number of computer simulations are carried out in order to demonstrate the diffraction phenomena under various angles. Simulations for the inverse modeling of diffraction phenomena have been successfully conducted in showing the superiority of the neural network.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.786-789
• /
• 2002

A recurrent artificial neural network (ANN) model is developed to simulate hydrocarbon recovery process at petroleum-contaminated site. The groundwater extraction rate, vacuum pressure, and saturation hydraulic conductivity are selected as the input variables, while the cumulative hydrocarbon recovery volume is considered as the output variable. The experimental data fer establishing the ANN model are from implementation of a multiphase flow model for dual phase remediation process under different input variable conditions. The complex nonlinear and dynamic relationship between input and output data sets are then identified through the developed ANN model. Reasonable agreements between modeling results and experimental data are observed, which reveals high effectiveness and efficiency of the neural network approach in modeling complex hydrocarbon recovery behavior.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2176-2178
• /
• 2003

This paper presents the intelligent modeling method of chaotic systems using a DNA coding based wavelet neural network(WNN). Generally the mathematical teaming method such as gradient descent method is used to adjust the parameters of WNN, which has much computational cost. To overcome this kind of problem, we use the DNA coding method as the learning method of WNN, and then combine it with the WNN. Finally, to verify the efficiency of our method, we apply the proposed DNA coding based wavelet neural network for modeling of Duffing system, which is a representative continuous-time chaotic system.

• Geomechanics and Engineering
• /
• v.1 no.4
• /
• pp.307-321
• /
• 2009

The paper employs a feed forward neural network with back-propagation algorithm for modeling time dependent swell in clays containing carbonate in the presence of sulfuric acid. The oedometer swell percent is estimated at a nominal surcharge pressure of 6.25 kPa to develop 612 data sets for modeling. The input parameters used in the network include time, sulfuric acid concentration, carbonate percentage, and liquid limit. Among the total data sets, 280 (46%) were assigned to training, 175 (29%) for testing and the remaining 157 data sets (25%) were relegated to cross validation. The network was programmed to process this information and predict the percent swell at any time, knowing the variable involved. The study demonstrates that it is possible to develop a general BPNN model that can predict time dependent swell with relatively high accuracy with observed data ($R^2$=0.9986). The obtained results are also compared with generated non-linear regression model.

• ETRI Journal
• /
• v.45 no.4
• /
• pp.557-569
• /
• 2023

Traditional deterministic channel modeling is accurate in prediction, but due to its complexity, improving computational efficiency remains a challenge. In an alternative approach, we investigated a multilayer artificial neural network (ANN) to predict large-scale and small-scale channel characteristics in metro tunnels. Simulated high-precision training datasets were obtained by combining measurement campaign with a ray tracing (RT) method in a metro tunnel. Performance on the training data was used to determine the number of hidden layers and neurons of the multilayer ANN. The proposed multilayer ANN performed efficiently (10 s for training; 0.19 ms for prediction), and accurately, with better approximation of the RT data than the single-layer ANN. The root mean square errors (RMSE) of path loss (2.82 dB), root mean square delay spread (0.61 ns), azimuth angle spread (3.06°), and elevation angle spread (1.22°) were impressive. These results demonstrate the superior computing efficiency and model complexity of ANNs.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.777-782
• /
• 2011

Neural network technique is widely employed in the fields of signal processing, control systems, pattern recognition, etc. Learning of neural networks is an important procedure to accomplish dynamic system modeling. This paper presents a novel learning approach for differential neural network models based on the Kalman-Bucy filter theory. We construct an augmented state vector including original neural state and parameter vectors and derive a state estimation rule avoiding gradient function terms which involve to the conventional neural learning methods such as a back-propagation approach. We carry out numerical simulation to evaluate the proposed learning approach in nonlinear system modeling. By comparing to the well-known back-propagation approach and Kalman-Bucy filtering, its superiority is additionally proved under stochastic system environments.

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.193-200
• /
• 2019

The auto-encoder network which is a good candidate to handle the modeling of the signal strength attenuation is designed for denoising and compensating the distortion of the received data. It provides a non-linear mapping function by iteratively learning the encoder and the decoder. The encoder is the non-linear mapping function, and the decoder demands accurate data reconstruction from the representation generated by the encoder. In addition, the adaptive network width which supports the automatic generation of new hidden nodes and pruning of inconsequential nodes is also implemented in the proposed algorithm for increasing the efficiency of the algorithm. Simulation results show that the proposed method can improve the neural network training surface to achieve the highest possible accuracy of the signal modeling compared with the conventional modeling method.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.4
• /
• pp.83-90
• /
• 1998

In this paper, we present neural network for control of Left Ventricular Assist Device(LVAD) system with a pneumatically driven mock circulation system. Beat rate(BR), Systole-Diastole Rate(SDR) and flow rate are collected as the main variables of the LVAD system. System modeling is completed using the neural network with input variables(BR, SBR, their derivatives, actual flow) and output variable(actual flow). It is necessary to apply high perfomance control techniques, since the LVAD system represent nonlinear and time-varing characteristics. Fortunately. the neural network can be applied to control of a nonlinear dynamic system by learning capability In this study, we identify the LVAD system with neural network and control the LVAD system by PID controller and neural network feedforward controller. The ability and effectiveness of controlling the LVAD system using the proposed algorithm will be demonstrated by experiment.

• Agricultural and Biosystems Engineering
• /
• v.1 no.2
• /
• pp.67-72
• /
• 2000

A dynamic draft model is necessary to analyze mechanics of tillage and to design optimal tillage tools. In order to deal with draft dynamics, a neural network paradigm was applied to develop dynamic draft models. For the development of the models, three kinds of tillage tools were used to measure drafts in the soil bin and a time lagged recurrent neural network was developed. The neural network had a structure to predict dynamic draft, having a function of one-step-ahead prediction. A procedure for network prediction model identification was established. The results show promising modeling of the dynamic drafts with developed neural network.