• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.459-462
• /
• 2000

In this paper, we propose the initial optimized structure of the Radial Basis Function Network which is more simple in the part of the structure and converges more faster than Neural Network with the analysis method using Time-Frequency Localization. When we construct the hidden node with the Radial Basis Function whose localization is similar with an approximation target function in the plane of the Time and Frequency, we make a good decision of the initial structure having an ability of approximation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.404-409
• /
• 1998

In this paper, we propose a learning algorithm of fuzzy neural networks with trapezoidal fuzzy weights. This fuzzy neural networks can use fuzzy numbers as well as real numbers, and represent linguistic information better than standard neural networks. We construct trapezodal fuzzy weights by the composition of two triangles, and devise a learning algorithm using the two triangular membership functions, The results of computer simulations on numerical data show that the fuzzy neural networks have high fitting ability for target output.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.413-416
• /
• 1998

In this paper we first show that uniform PR systems and half independent PR systems have same dynamics, and then an important property of this two kinds of systems is derived. The most important property of uniform PR systems is that they have the ability of classifying m-dimensional problabilistic vector into in classes. The significance of studying the dynamics of uniform PR systems are tried from the beginning with a uniform PR system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.154.1-154
• /
• 2001

The paper describes a new type of robot called "artificial liferobot" which is able to learn, make decisions, and behave by itself based on a brain-type computing technique called "artificial brain". The artificial liferobot has self-learning ability from the environment by the interactions between human being and it. The artificial brain makes the artificial liferobot to behave by itself with its intensions like living things as human being. We briefly introduce one attempt of our researches for developing cognitive and behavioral intelligent artificial liferobot in out laboratory. One of our purposes is the development of the artificial liferobot, which plays an Important role in taking care of elderly and infirm people in a rapidly aging society.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.216-221
• /
• 1989

Most of industrial robots are reprogrammable for various operations. while the gripper is only used for on - off grasping. If the gripper has the intelligent ability to interact with its environment, it will be very useful in many fine motion application. For this pur pose, an electric gripper system is, developed through experiments and simulation. This paper describes a method of the contact position between the gripper and the grasped object by using strain gauge sensors, and presents the related experimental results.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.1
• /
• pp.22-29
• /
• 2007

Two fuzzy controllers defined by 2 input variables cooperate to control a cartpole system in terms of balancing as well as centering. The cooperation is due to the BOXES scheme that selects one of the fuzzy controllers for each time step according to the content of box that is established through the critic of the control action by the fuzzy controllers. It is found that the control scheme is good at controlling the cartpole system so that the system is stabilized fast while the BOXES develops its ability to select proper fuzzy controller through experience.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.3 no.1
• /
• pp.29-40
• /
• 1993

The role of principles of minimum uncertainty in dealing with the reconstruction problem of systems with dynamic properties is discussed. The aim of the reconstruction problem, one of two problems addressed by reconstruct ability analysis, is to determine the smallest possible sub-systems by which a given overall system can be adequately represented.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.49-52
• /
• 1998

Neural Network has good performance in pattern classification, control and many other fields by learning ability. However, there is effective rule or systematic approach to determine optimal structure. In this paper, we propose a new method to find optimal structure of feed-forward multi-layer neural network as a kind of pruning method. That eliminating redundant elements of neural network. To find redundant elements we analysis error and weight changing with Rough Set Theory, in condition of executing back-propagation leaning algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.3
• /
• pp.271-276
• /
• 2004

This paper is a research on the dynamic signature verification of error rate which are false rejection rate and false acceptance rate, the size of signature verification engine, the size of the characteristic vectors of a signature, the ability to distinguish similar signatures, the processing speed and so on. Also, we present our efficient user interface and performance results.

• 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.