• International Journal of Control, Automation, and Systems
• /
• v.6 no.1
• /
• pp.24-34
• /
• 2008

A novel neural network model, termed the standard neural network model (SNNM), similar to the nominal model in linear robust control theory, is suggested to facilitate the synthesis of controllers for delayed (or non-delayed) nonlinear systems composed of neural networks. The model is composed of a linear dynamic system and a bounded static delayed (or non-delayed) nonlinear operator. Based on the global asymptotic stability analysis of SNNMs, Static state-feedback controller and dynamic output feedback controller are designed for the SNNMs to stabilize the closed-loop systems, respectively. The control design equations are shown to be a set of linear matrix inequalities (LMIs) which can be easily solved by various convex optimization algorithms to determine the control signals. Most neural-network-based nonlinear systems with time delays or without time delays can be transformed into the SNNMs for controller synthesis in a unified way. Two application examples are given where the SNNMs are employed to synthesize the feedback stabilizing controllers for an SISO nonlinear system modeled by the neural network, and for a chaotic neural network, respectively. Through these examples, it is demonstrated that the SNNM not only makes controller synthesis of neural-network-based systems much easier, but also provides a new approach to the synthesis of the controllers for the other type of nonlinear systems.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1013-1016
• /
• 1993

This paper describes a new type of neuron model, the inputs of which are interfered with one another. It has a high mapping ability with only single unit. The learning speed is considerably improved compared with the conventional linear type neural networks. The proposed neuron model was successfully applied to the prediction problem of chaotic time series signal.

• Communications for Statistical Applications and Methods
• /
• v.13 no.1
• /
• pp.73-88
• /
• 2006

In this paper, we construct data-base for fetal heart rate (FHR) data and develop the FHR Monitering system to diagnose fetus, HYFM-III. For diagnostic system, a few statistical decision making mechanism are adopted, such as approximate entropy, neural networks, and logistic discrimination. Since FHR data is very chaotic, we mostly adopt nonlinear statistical methods. On the basis of this system, we expect to develop expert system for early detection of abnormal fetus.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2183-2185
• /
• 1998

In this paper, we propose a method of designing neural networks using biological inspired developmental and evolutionary concept. The living things are best information processing system in themselves. One individual is developed from a generative cell. And a species of this individual have adapted itself to the environment by evolution. Ontogeny of organism is embodied in cellular automata and phylogeny of species is realized by evolutionary algorithms. The connection among cells is determined by a rule of cellular automata. In order to obtain the best neural networks in the environment, we evolve the arrangement of initial cells. The cell, that is neuron of neural networks, is modeled on chaotic neuron with firing or rest state like biological neuron. A final output of network is measured by frequency of firing state. The effectiveness of the proposed scheme is verified by applying it to navigation problem of robot.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.396-401
• /
• 2006

It is well-known that a neural network with cyclic connections generates plural limit cycles, thus, being used as a memory system for storing large number of dynamic information. In this paper, a continuous-time cyclic connection neural network was built so that each neuron is connected only to its nearest neurons with binary synaptic weights of ${\pm}1$. The type and the number of limit cycles generated by such network has also been demonstrated through simulation. In particular, the effect of chaos signal for transition between limit cycles has been tested. Furthermore, it is evaluated whether the chaotic noise is more effective than random noise in the process of the dynamical neural networks.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.71-74
• /
• 2002

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.06a
• /
• pp.361-366
• /
• 2002

It has been reported that neural network with cyclic connections generates limit cycles. The dynamics of discrete time network with cyclic connections has been analyzed. But the dynamics of cyclic network in continuous time has not been known well due to its huge calculation complexity. In this paper, we study the dynamics of the continuous time network with cyclic connections and the effect of chaotic signal in the network for transitions between limit cycles.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1155-1157
• /
• 1996

In this paper, the direct adaptive control using neural networks is presented for the control of chaotic nonlinear systems. The direct adaptive control method has an advantage that the additional system identification procedure is not necessary. Two direct adaptive control methods are applied to a Duffing's equation and the simulation results show the effectiveness of the controllers.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.4
• /
• pp.22-28
• /
• 2002

It has been reported that neural network with cyclic connections generates limit cycles. The dynamics of discrete time network with cyclic connections has been analyzed. But the dynamics of cyclic network in continuous time has not been known well due to its huge calculation complexity. In this paper, we study the dynamics of the continuous time network with cyclic connections and the effect of chaotic signal in the network for transitions between limit cycles.

• Journal of Intelligence and Information Systems
• /
• v.4 no.1
• /
• pp.133-147
• /
• 1998

Recently, many researchers have been involved in finding deterministic equations which can accurately predict future event, based on chaotic theory, or fractal theory. The theory says that some events which seem very random but internally deterministic can be accurately predicted by fractal equations. In contrast to the conventional methods, such as AR model, MA, model, or ARIMA model, the fractal equation attempts to discover a deterministic order inherent in time series data set. In discovering deterministic order, researchers have found that neural networks are much more effective than the conventional statistical models. Even though prediction accuracy of the network can be different depending on the topological structure and modification of the algorithms, many researchers asserted that the neural network systems outperforms other systems, because of non-linear behaviour of the network models, mechanisms of massive parallel processing, generalization capability based on adaptive learning. However, recent survey shows that prediction accuracy of the forecasting models can be determined by the model structure and data structures. In the experiments based on actual economic data sets, it was found that the prediction accuracy of the neural network model is similar to the performance level of the conventional forecasting model. Especially, for the data set which is deterministically chaotic, the AR model, a conventional statistical model, was not significantly different from the MLP model, a neural network model. This result shows that the forecasting model. This result shows that the forecasting model a, pp.opriate to a prediction task should be selected based on characteristics of the time series data set. Analysis of the characteristics of the data set was performed by fractal analysis, measurement of Hurst index, and measurement of Lyapunov exponents. As a conclusion, a significant difference was not found in forecasting future events for the time series data which is deterministically chaotic, between a conventional forecasting model and a typical neural network model.