• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.383-392
• /
• 2006

In this paper, we propose a new relevance feedback algorithm using Probabilistic Neural Networks(PNN) while supporting multi-class learning. Then, to validate the effectiveness of our feedback approach, we incorporate the proposed algorithm into our region-based image retrieval tool, FRIP(Finding Regions In the Pictures). In our feedback approach, there is no need to assume that feature vectors are independent, and as well as it allows the system to insert additional classes for detail classification. In addition, it does not have a long computation time for training because it only has four layers. In the PNN classification process, we store the user's entire past feedback actions as a history in order to improve performance for future iterations. By using a history, our approach can capture the user's subjective intension more precisely and prevent retrieval performance errors which originate from fluctuating or degrading in the next iteration. The efficacy of our method is validated using a set of 3000 images derived from a Corel-photo CD.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.699-701
• /
• 2004

This paper proposes the algorithm of servo- writing based on feedback error learning neural networks. The controller consists of feedback controller using PID and feedforward controller using gaussian radial basis function network. Because the RBFNs are trained by on-line rule, the controller has adaptation capability. The performance of the proposed controller is compared to that of conventional PID controller. Proposed algorithm shows better performance than PID controller.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.7
• /
• pp.1298-1301
• /
• 2007

The problem of designing dynamic output feedback sliding mode controllers for uncertain multivariable linear systems is considered. Using linear matrix inequalities(LMIs), a feasibility condition for the design problem is derived. Explicit fomulas of the gain matrices of a full order output feedback sliding mode controller in terms of the solution matrices of the LMI condition is given. A simple LMI-based algorithm for designing output feedback sliding mode controllers is also given. Finally, numerical design examples are given to show the effectiveness of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1632-1636
• /
• 2005

This paper presents synchronization of two identical Modified Chua's circuits using two strategies of error feedback coupling. In the first method the synchronization is achieved by linear unidirectional and in the second one by linear bidirectional error feedback coupling. Both proposed methods can make the states of the Modified Chua's circuits globally asymptotically synchronized. Numerical results are provided to show the effectiveness of the proposed approaches and to compare them together based on different criteria.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.107.6-107
• /
• 2002

$\textbullet$ An autonomous mobile robot was controlled through the Internet. $\textbullet$ For the direct control, the feedback data should be provided properly. $\textbullet$ Therefore, an efficient communication scheme should be defined. $\textbullet$ To overcome the transmission delay, the highly abstracted message format was used. $\textbullet$ As the feedback data, the real image sequences may suffer the transmission delay or loss of content. $\textbullet$ To resolve this, the feature information was used to construct the synthetic feedback information. $\textbullet$ By doing this, the operator could feel the hands-on control with an Internet-based robot.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.120-124
• /
• 1987

Linear time invariant systems are considered. It is assumed that only partial state variables are observable for feedback control. In this study, a new method is presented for designing a stat e feedback controller. It is based on augmenting the original system by additional integrator and using time delayed feedback of observable variables. Several examples and its computer simulation results are given to show the effectiveness of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.534-534
• /
• 2000

This paper proposes a dynamic compensation scheme for input-constrained feedback linearizable nonlinear systems to cope with the windup phenomenon. Given a feedback linearizing controller for such a nonlinear system designed without considering its input constraint, an additional dynamic compensator is proposed to account for the constraint. This dynamic anti-windup is based on the minimization of a reasonable performance index, and some stability properties of the resulting closed-loop are presented.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.466-471
• /
• 1994

To make a dynamic system a given desired motion trajectory, a new feedback error learning scheme is proposed which is based on the repeatability of dynamic system motion. This method is composed of feedforward and feedback control laws. A benefit of this control scheme is that the input pattern that generates the desired motion can be formed without estimating the physical parameters of system dynamics. The numerical simulations show the good performance of the proposed scheme

• Proceedings of the Safety Management and Science Conference
• /
• 2000.11a
• /
• pp.203-216
• /
• 2000

In this paper, we Investigate rationales for feedback adjustment using some techniques associated with automatic process control based on some nonstatioary disturbance models. Feedback-control schemes are often operated so that the nature of the disturbance that is being compensated is concealed and unusual deviations from the target cannot be taken account of. In this connection feedback control schemes is useful to extend the idea of common causes and special causes to such systems. Minimum-cost feedback schemes are discussed for some simple ,but practically interesting ,models.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.3
• /
• pp.349-354
• /
• 2007

This paper considers the problem of designing static output feedback controllers for nonlinear systems represented by Takagi-Sugeno (T-S) fuzzy models. Based on linear matrix inequality technique, a new method is developed for designing fuzzy stabilizing controllers via static output feedback. Furthermore, the result is also extended to $H_{\infty}$ control. Examples are given to illustrate the effectiveness of the proposed methods.