• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.9-14
• /
• 2004

Rational sense is affected by emotion. If we add the factor of estimated emotion by environment information into robots, we may get more intelligent and human-friendly robots. However, various sensory information and pattern classification are prescribed for robots to learn emotion so that the networks are suitable for the necessity of robots. Neural network has superior ability to extract character of system but neural network has defect of temporal cross talk and local minimum convergence. To solve the defects, many kinds of modular neural networks have been proposed because they divide a complex problem into simple several subproblems. The modular neural network, introduced by Jacobs and Jordan, shows an excellent ability of recomposition and recombination of complex work. On the other hand, the recurrent network acquires state representations and representations of state make the recurrent neural network suitable for diverse applications such as nonlinear prediction and modeling. In this paper, we applied recurrent network for the expert network in the modular neural network structure to learn data pattern based on emotional assessment. To show the performance of the proposed network, simulation of learning the environment and behavior pattern is proceeded with the real time implementation. The given problem is very complex and has too many cases to learn. The result will show the performance and good ability of the proposed network and will be compared with the result of other method, general modular neural network.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.8
• /
• pp.782-791
• /
• 1991

In the fields of pattern recognition such as speech recognition, several new techniques using Artifical Neural network Models have been proposed and implemented. In particular, the Multilayer Perception Model has been shown to be effective in static speech pattern recognition. But speech has dynamic or temporal characteristics and the most important point in implementing speech recognition systems using Artificial Neural Network Models for continuous speech is the learning of dynamic characteristics and the distributed cues and contextual effects that result from temporal characteristics. But Recurrent Multilayer Perceptron Model is known to be able to learn sequence of pattern. In this paper, the results of applying the Recurrent Model which has possibilities of learning tedmporal characteristics of speech to phoneme recognition is presented. The test data consist of 144 Vowel+ Consonant + Vowel speech chains made up of 4 Korean monothongs and 9 Korean plosive consonants. The input parameters of Artificial Neural Network model used are the FFT coefficients, residual error and zero crossing rates. The Baseline model showed a recognition rate of 91% for volwels and 71% for plosive consonants of one male speaker. We obtained better recognition rates from various other experiments compared to the existing multilayer perceptron model, thus showed the recurrent model to be better suited to speech recognition. And the possibility of using Recurrent Models for speech recognition was experimented by changing the configuration of this baseline model.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.4
• /
• pp.41-49
• /
• 2017

Word sense disambiguation(WSD) that determines the exact meaning of homonym which can be used in different meanings even in one form is very important to understand the semantical meaning of text document. Many recent researches on WSD have widely used NNLM(Neural Network Language Model) in which neural network is used to represent a document into vectors and to analyze its semantics. Among the previous WSD researches using NNLM, RNN(Recurrent Neural Network) model has better performance than other models because RNN model can reflect the occurrence order of words in addition to the word appearance information in a document. However, since RNN model uses only the forward order of word occurrences in a document, it is not able to reflect natural language's characteristics that later words can affect the meanings of the preceding words. In this paper, we propose a WSD scheme using Bidirectional RNN that can reflect not only the forward order but also the backward order of word occurrences in a document. From the experiments, the accuracy of the proposed model is higher than that of previous method using RNN. Hence, it is confirmed that bidirectional order information of word occurrences is useful for WSD in Korean language.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.9
• /
• pp.781-788
• /
• 2005

This paper proposes an identification method using a self recurrent wavelet neural network (SRWNN) for dynamic systems. The architecture of the proposed SRWNN is a modified model of the wavelet neural network (WNN). But, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN has the ability to store the past information of the wavelet. Thus, in the proposed identification architecture, the SRWNN is used for identifying nonlinear dynamic systems. The gradient descent method with adaptive teaming rates (ALRs) is applied to 1.am the parameters of the SRWNN identifier (SRWNNI). The ALRs are derived from the discrete Lyapunov stability theorem, which are used to guarantee the convergence of an SRWNNI. Finally, through computer simulations, we demonstrate the effectiveness of the proposed SRWNNI.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1860-1861
• /
• 2006

In this paper, we design a robust controller of biped robot system with uncertainties, using recurrent neural network. In our proposed control system, we use the self-recurrent wavelet neural network (SRWNN). The SRWNN makes up for the weak points in wavelet neural network(WNN). While the WNN has fast convergence ability, it dose not have a memory. So the WNN cannot confront unexpected change of the system. However, the SRWNN, having advantage of WNN such as fast convergence, can easily encounter the unexpected change of the system. For stable walking control of biped robot, we use sliding mode control (SMC). Here, uncertainties are predicted by SRWNN. The weights of SRWNN are trained by adaptive laws based on Lyapunov stability theorem. Finally, we carry out computer simulations with a biped robot model to verify the effectiveness of the proposed control system,.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.315-317
• /
• 2006

In this paper, we design a terminal sliding mode controller based on neural network for nonlinear systems with uncertainties. Terminal sliding mode control (TSMC) method can drive the tracking errors to zero within finite time. Also, TSMC has the advantages such as improved performance, robustness, reliability and precision by contrast with classical sliding mode control. For the control of nonlinear system with uncertainties, we employ the self-recurrent wavelet neural network(SRWNN) which is used for the prediction of uncertainties. The weights of SRWNN are trained by adaptive laws based on Lyapunov stability theorem. Finally, we carry out simulations to illustrate the effectiveness of the proposed control.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.325-327
• /
• 2005

In this paper, we propose the design of active queue management (AQM) control system using the self-recurrent wavelet neural network (SRWNN). By regulating the queue length close to reference value, AQM can control the congestions in TCP network. The SRWNN is designed to perform as a feedback controller for TCP dynamics. The parameters of network are tunes to minimize the difference between the queue length of TCP dynamic model and the output of SRWNN using gradient-descent method. We evaluate the performances of the proposed AQM approach through computer simulations.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.699-704
• /
• 2001

ABSTRACT In this paper, a new hybrid modular recurrent TDNN (time-delay neural network)-HMM (hidden Markov model) architecture for speech recognition has been studied. In TDNN, the recognition rate could be increased if the signal window is extended. To obtain this effect in the neural network, a high-level memory generated through a feedback within the first hidden layer of the neural network unit has been used. To increase the ability to deal with the temporal structure of phonemic features, the input layer of the network has been divided into multiple states in time sequence and has feature detector for each states. To expand the network from small recognition task to the full speech recognition system, modular construction method has been also used. Furthermore, the neural network and HMM are integrated by feeding output vectors from the neural network to HMM, and a new parameter smoothing method which can be applied to this hybrid system has been suggested.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.2
• /
• pp.209-214
• /
• 1998

In this paper, we are dealing with the problem of controlling unknown nonlinear dynamical system by using neural networks. A novel error self-recurrent(ESR) neural model is presented to perform black-box identification. Through the various outcome of the experiment, a new neural network is seen to be considerably faster than the BP algorithm and has advantages of being less affected by poor initial weights and learning rate. These characteristics make it flexible to design the controller in real-time based on neural networks model. In addition, we design an adaptive PID controller that Keyser suggested by using ESR neural networks, and present a method on the implementation of adaptive controller based on neural network for practical applications. We obtained good results in the case of robot manipulator experiment.