• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.3
• /
• pp.252-258
• /
• 1997

This paper presents neural networks for hybrid position/force control which is a type of position and force control for robot manipulators. The performance of conventional hybrid position/force control is excellent in the case of the exactly-known dynamic model of the robot, but degrades seriously as the uncertainty of the model increases. Hence, the neural network control scheme is presented here to overcome such shortcoming. The introduced neural term is designed to learn the uncertainty of the robot, and to control the robot through uncertainty compensation. Further more, the learning rule of the neural network is derived and is shown to be effective in the sense that it requires neither desired output of the network nor error back propagation through the plant. The proposed scheme is verified through the simulation of hybrid position/force control of a 6-dof robot manipulator.

• Journal of Environmental Science International
• /
• v.11 no.3
• /
• pp.201-207
• /
• 2002

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.463-471
• /
• 1999

This paper presents a vector controlled induction motor is implemented by neural networks system compared with PI controller for the speed control. The design employed the training strategy with Neural Network Controller(NNC) and Neural Network Emulator(NNE) for speed. In order to update the weights of the controller First of all Emulator updates its parameters by identifying the motor input and output next it supplies the error path to the output stage of the controller using backpropagation algorithm, As Controller produces an adequate output to the system due to neural networks learning capability Vector controlled induction motor characteristics actual motor speed with based on neural network system follows the reference speed better than that of linear PI speed controller.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.407-412
• /
• 2017

In this paper, we propose a speech emotion recognition method using a deep neural network based on the attention mechanism. The proposed method consists of a combination of CNN (Convolution Neural Networks), GRU (Gated Recurrent Unit), DNN (Deep Neural Networks) and attention mechanism. The spectrogram of the speech signal contains characteristic patterns according to the emotion. Therefore, we modeled characteristic patterns according to the emotion by applying the tuned Gabor filters as convolutional filter of typical CNN. In addition, we applied the attention mechanism with CNN and FC (Fully-Connected) layer to obtain the attention weight by considering context information of extracted features and used it for emotion recognition. To verify the proposed method, we conducted emotion recognition experiments on six emotions. The experimental results show that the proposed method achieves higher performance in speech emotion recognition than the conventional methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.501-507
• /
• 2021

Neural networks with differentiable activation functions are differentiable with respect to input variables. We improve the approximation capability of neural networks by using the gradient and Hessian of neural networks to satisfy the differential equations of the problems of interest. We apply differential neural networks to the pricing of financial options, where stochastic differential equations and the Black-Scholes partial differential equation represent the differential relation of price of option and underlying assets, and the first and second derivatives of option price play an important role in financial engineering. The proposed neural network learns - (a) the sample paths of option prices generated by stochastic differential equations and (b) the Black-Scholes equation at each time and asset price. Experimental results show that the proposed method gives accurate option values and the first and second derivatives.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.346-348
• /
• 2004

In this rarer, we introduce a new Fuzzy Polynomial Neural Networks (FPNNs)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNs based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNs-like structurenamed Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. In considering the structures of FPNN-like networks such as FPNN and FSPNN, they are almost similar. Therefore they have the same shortcomings as well as the same virtues on structural side. The proposed design procedure for networks' architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IG) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using gas furnace process dataset.

• Journal of Wetlands Research
• /
• v.12 no.3
• /
• pp.79-97
• /
• 2010

The purpose of this research is to apply the neural networks models for the hydrologic disaggregation of the yearly pan evaporation(PE) data in Republic of Korea. The neural networks models consist of multilayer perceptron neural networks model(MLP-NNM) and support vector machine neural networks model(SVM-NNM), respectively. And, for the evaluation of the neural networks models, they are composed of training and test performances, respectively. The three types of data such as the historic, the generated, and the mixed data are used for the training performance. The only historic data, however, is used for the testing performance. The application of MLP-NNM and SVM-NNM for the hydrologic disaggregation of nonlinear time series data is evaluated from results of this research. Four kinds of the statistical index for the evaluation are suggested; CC, RMSE, E, and AARE, respectively. Homogeneity test using ANOVA and Mann-Whitney U test, furthermore, is carried out for the observed and calculated monthly PE data. We can construct the credible monthly PE data from the hydrologic disaggregation of the yearly PE data, and the available data for the evaluation of irrigation and drainage networks system can be suggested.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1561-1564
• /
• 1997

In the study, simulation result was studied by connecting PID controller in series to the established Neural Networks Controller. Neural Network model is composed of two layers to evaluate tracking performance improvement. The reqular dynamic characteristics was also studied for the expected error to be minimized by using Widrow-Hoff delta rule. As a result of the study, We identified that tracking performance inprovement was developed more in case of connecting PID than Neural Network Contoller and that tracking plant parameter in 251 sample was approached rapidly case of time variable.

• Journal of applied mathematics & informatics
• /
• v.6 no.2
• /
• pp.599-609
• /
• 1999

Neural networks are explored as an alternative to a regres-sion model for prediction of the number of daily household vehicular trips. This study focuses on contrasting a neural network model with a regression model in term of variable selection as well as the appli-cation of these models for prediction of extreme observations, The differences in the models regarding data transformation variable selec-tion and multicollinearity are considered. The results indicate that the neural network model is a viable alternative to the regression model for addressing both messy data problems and limitation in variable structure specification.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.468-471
• /
• 1999

In this paper, we present a solution for combining multiple neural networks. Each neural network is trained with different features. And the neural networks are combined by four methods. The recognition rates by four combination methods are compared. The experimental results for handwritten digit recognition shows that the combination at hidden layers by single layer neural network is superior to any other methods. The reasons of the results are explained.