• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.44-52
• /
• 2001

This paper describes an off-line method for recognizing totally unconstrained handwritten digits using modified chaotic neural networks(MCNN). The chaotic neural networks(CNN) is modified to be a useful network for solving complex pattern problems by enforcing dynamic characteristics and learning process. Since the MCNN has the characteristics of highly nonlinear dynamics in structure and neuron itself, it can be an appropriate network for the robust classification of complex handwritten digits. Digit identification starts with extraction of features from the raw digit images and then recognizes digits using the MCNN based classifier. The performance of the MCNN classifier is evaluated on the numeral database of Concordia University, Montreal, Canada. For the relative comparison of recognition performance, the MCNN classifier is compared with the recurrent neural networks(RNN) classifier. Experimental results show that the classification rate is 98.0%. It indicates that the MCNN classifier outperforms the RNN classifier as well as other classifiers that have been reported on the same database.

• Proceedings of the KIEE Conference
• /
• 2001.07a
• /
• pp.279-281
• /
• 2001

This paper presents a chaotic neural networks to solve the distribution feeder reconfiguration problem for loss reduction. Feeder reconfiguration problem is the determination of switching option that minimizes the power losses for a particular set of loads in distribution systems. A chaotic neural networks is used to determine the switching combinations, select the status of the switches, and find the best combination of switches for minimum loss. The proposed method has been tested on 32 bus system, and the results indicate that it is able to determine the appropriate switching options for optimal configuration.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.5
• /
• pp.45-53
• /
• 2000

This paper presents an analysis of the dynamical behavor in the chaotic neuron fabricated using 0.8${\mu}{\textrm}{m}$ single poly CMOS technology. An approximated empirical equation models for the sigmoid output function and chaos generative block of the chaotic neuron are extracted from the measurement data. Then the dynamical responses of the chaotic neuron such as biurcation diagram, frequency responses, Lyapunov exponent, and average firing rate are calculated with numerical analysis. In addition, we construct the chaotic neural networks which are composed of two chaotic neurons with four synapses and obtain bifurcation diagram according to synaptic weight variation. And results of experiments in the single chaotic neuron and chaotic neural networks by two neurons with the $\pm$2.5V power supply and sampling clock frequency of 10KHz are shown and compared with the simulated results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.24-30
• /
• 2003

In this paper, we propose a novel predictive control method, which uses a wavelet neural network as a predictor, for the control of chaotic systems. In our method, we use the gradient descent method for training the parameter of a wavelet neural network. The control signals are directly obtained by minimizing the difference between a reference signal and the output of a wavelet neural network. To verify the efficiency of our method, we apply it to the Doffing and the Henon system, which are a representative continuous and discrete time chaotic system respectively, and compare with the results of generalized predictive control using multi-layer perceptron.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.172.4-172
• /
• 2001

In this paper, the Generalized Predictive Control(GPC) method based on Fuzzy Neural Networks(FNNs) is presented for the control of chaotic nonlinear systems without precise mathematical models. In our method, FNNs is used as the predictor whose parameters are tuned by the error between the actual output of nonlinear chaotic system and that of FNNs model. The parameters of GPC controller are adjusted via the gradient descent method where the difference between the actual output and the reference signal is used as a control error. Finally, computer simulation on the representative continuous-time chaotic system(Duffing system) is presented to demonstrate the effectiveness of our chaos control method.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.400-402
• /
• 1997

This paper investigates the direct and adaptive control of mechatronic servo systems using modified chaotic neural networks (CNNs). For the performance evaluation of the proposed neural networks, we simulate the trajectory control of the X-Y table with direct control strategies. The CNN based controller demonstrates accurate tracking of the planned path and also shows superior performance on convergence and final error comparing with recurrent neural network(RNN) controller.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.530-532
• /
• 1998

In this paper, We Designed the torque compensatory controller for robot manipulator using modified chaotic neural networks with self feedback loop. The proposed torque compensatory controller compensate torque of the PD controller. In order to estimate the proposed controller, we implemented to the Cartesian space control of three-axis PUMA robot and compared the simulation results with recurrent neural networks(RNNs) controller. Simulation results show that the learning error drastically decrease at on-line learning. The proposed CNNs controller shows much better control performance and shorter processing time compared to the recurrent neural network controller in the robot trajectory control.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.118-124
• /
• 2004

In this paper, we present a indirect adaptive control method using a wavelet neural network (WNN) for the control of chaotic nonlinear systems without precise mathematical models. The proposed indirect adaptive control method includes the off-line identification and on-line control procedure for chaotic nonlinear systems. In the off-line identification procedure, the WNN based identification model identifies the chaotic nonlinear system by using the serial-parallel identification structure and is trained by the gradient-descent method. And, in the on-line control procedure, a WNN controller is designed by using the off-line identification model and is trained by the error back-propagation algorithm. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with applications to the chaotic nonlinear systems.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.437-440
• /
• 1998

In this paper, the design method of fuzzy neural network(FNN) controller using indirect adaptive control technique is presented for controlling chaotic nonlinear systems. Firstly, the fuzzy model identified with a FNN in off-line process. Secondly, the trained fuzzy model tunes adaptively the control rules of the FNN controller in on-line process. In order to evaluate the proposed control method, Indirect adaptive control method is applied to the representative continuous-time chaotic nonlinear systems, that is, the Duffing system and the Lorenz system. Simulations are done to verify the effectivencess of controller.

• Transactions on Control, Automation and Systems Engineering
• /
• v.4 no.2
• /
• pp.124-129
• /
• 2002

This paper demonstrates that the largest Lyapunov exponent λ of recurrent neural networks can be controlled efficiently by a stochastic gradient method. An essential core of the proposed method is a novel stochastic approximate formulation of the Lyapunov exponent λ as a function of the network parameters such as connection weights and thresholds of neural activation functions. By a gradient method, a direct calculation to minimize a square error (λ - λ$\^$obj/)$^2$, where λ$\^$obj/ is a desired exponent value, needs gradients collection through time which are given by a recursive calculation from past to present values. The collection is computationally expensive and causes unstable control of the exponent for networks with chaotic dynamics because of chaotic instability. The stochastic formulation derived in this paper gives us an approximation of the gradients collection in a fashion without the recursive calculation. This approximation can realize not only a faster calculation of the gradient, but also stable control for chaotic dynamics. Due to the non-recursive calculation. without respect to the time evolutions, the running times of this approximation grow only about as N$^2$ compared to as N$\^$5/T that is of the direct calculation method. It is also shown by simulation studies that the approximation is a robust formulation for the network size and that proposed method can control the chaos dynamics in recurrent neural networks efficiently.