• The Transactions of the Korea Information Processing Society
• /
• v.4 no.10
• /
• pp.2461-2469
• /
• 1997

Target detection and recognition problems, in which neural networks are widely used, require translation invariant and real-time processing in addition to the requirements that general pattern recognition problems need. This paper presents a novel architecture that meets the requirements and explains effective methodology to train the network. The proposed neural network is an architectural extension of the shared-weight neural network that is composed of the feature extraction stage followed by the pattern recognition stage. Its feature extraction stage performs correlational operation on the input with a weight kernel, and the entire neural network can be considered a nonlinear correlation filter. Therefore, the output of the proposed neural network is correlational plane with peak values at the location of the target. The architecture of this neural network is suitable for implementing with parallel or distributed computers, and this fact allows the application to the problems which require realtime processing. Net training methodology to overcome the problem caused by unbalance of the number of targets and non-targets is also introduced. To verify the performance, the proposed network is applied to detection and recognition problem of a specific automobile driving around in a parking lot. The results show no false alarms and fast processing enough to track a target that moves as fast as about 190 km per hour.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 1996.11a
• /
• pp.211-216
• /
• 1996

This paper propose a fuzzy regression method using fuzzy neural networks when a membership value is attached to each input-output pair. First, an architecture o fuzzy neural networks with fuzzy weights and fuzzy biases is shown. Next, a cost function is defined using the fuzzy output from the fuzzy neural network and the corresponding target output with a membership value. A learning algorithm is derived from the cost function. The derived learning algorithm trains the fuzzy neural network so 솜 t the level set of the fuzzy output includes the target output. Last, the proposed method is applied to the quality evaluation problem of injection molding

• Honam Mathematical Journal
• /
• v.35 no.4
• /
• pp.729-738
• /
• 2013

In this paper, we investigate a localized approximation of a continuously differentiable function by neural networks. To do this, we first approximate a continuously differentiable function by B-spline functions and then approximate B-spline functions by neural networks. Our proofs are constructive and we give numerical results to support our theory.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.147-150
• /
• 1996

This paper describes controller design and implementation method for controlling the temperature distribution in a thermal stratified wind tunnel(TSWT) by using a neural network algorithm. It is impossible to derive a mathematical model of the relation between heat inputs and temperature outputs in the test section of the TSWT governed by a nonlinear turbulent flow. Thus inverse neural network models with a multi layer perceptron structure are used in a feedforward control loop and feedback control loop to generate an arbitrary temperature distribution in the test section of the TSWT.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.878-883
• /
• 1991

In this paper, we propose the fuzzy-neural controller which is fuzzy controller with learning ability of neural network. The neural network in this controller is same as the membership function in current fuzzy controller and a parts of inference rules. And, it can be easily extend the control algorithm to multivariable systems. We can show effectiveness of the control algorithm through experiment of the inverted pendulum system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.210-213
• /
• 1999

Anyone observes that information processing in animal brains is depended on neural networks. On the other hand, engineering models for the neural networks are well known now, and they have been studied, and learning facility is found in the model. We are sure there is a potential in order to create a non Neuman-machine in the engineering models. We studied iteration forms including the engineering neural network models, taking a first step for the creation.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1033-1036
• /
• 1999

This paper proposes an efficient fault diagnosis for digital circuits using multilayer neural networks. The efficient learning algorithm is also proposed for the multilayer neural network, which is combined the steepest descent for high-speed optimization and the dynamic tunneling for global optimization. The fault-diagnosis system using the multilayer neural network of the proposed algorithm has been applied to the parity generator circuit. The simulation results shows that the proposed system is higher convergence speed and rate, in comparision with system using the backpropagation algorithm based on the gradient descent.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.143-143
• /
• 2000

A neural net based generalized predictive control(NNGPC) is presented for a hydraulic servo position control system. The proposed scheme employs generalized predictive control, where the future output being generated from the output of artificial neural networks. The proposed NNGPC does not require an accurate mathematical model for the nonlinear hydraulic system and takes less calculation time than GPC algorithm if the teaming of neural network is done. Simulation studies have been conducted on the position control of a hydraulic motor to validate and illustrate the proposed method.

• Proceedings of the KAIS Fall Conference
• /
• 2008.11a
• /
• pp.191-196
• /
• 2008

The intent of this paper is to describe a neural network structure called dynamic neural processor(DNP), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the DNP, are described. Computer simulations are provided to demonstrate the effectiveness of the proposed learning using the DNP.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1996.10a
• /
• pp.108-113
• /
• 1996

Concrete mix degign and adjustments are somewhat complicated and time-consuming tasks in which various uncertainties and errors are involved and depend on the quality control test results. In this paper, as a tool to minimize the uncertainties and errors the neural network is applied to the concrete mix design. Input data to train and test the neural network are obtained from the results of design and adjustments following the concrete standard specifications of Korea. The results show that neural networks have a strong potential as a tool for concrete mix design.