• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1889-1890
• /
• 2008

본 연구에서는 퍼지 추론 메커니즘에 기반 한 Polynomial RBF Neural Network(p-RBFNN)를 설계하고 얼굴인식 문제로 적용하여 분류기로서의 성능을 분석한다. 제안된 p-RBFNN 구조는 FCM 클러스터링에 기반 한 분할 함수를 활성 함수로 사용하며, 다항식 함수로 구성된 연결가중치를 사용함으로서 기존 신경회로망 분류기의 선형적인 특성을 개선한다. p-RBFNN 구조는 언어적 해석관점에서 "If-then"의 퍼지 규칙으로 표현되며 퍼지 추론 메커니즘에 의해 구동된다. 즉 조건부, 결론부, 추론부 세 가지의 기능적 모듈로 나뉘어 네트워크 구조가 형성된다. 조건부는 FCM 클러스터링을 사용하여 입력 공간을 분할하고, 결론부는 분할된 로컬 영역을 다항식 함수로 표현한다. 마지막으로, 네트워크의 최종출력은 추론부의 퍼지추론에 의한다. 또한 제안된 p-RBFNN을 얼굴인식 문제로 적용하여 성능을 분석한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.449-455
• /
• 2011

In this paper, a time-delay problem of a tele-operated control system is investigated and compensated by neural network. The smith predictor requires an exact system model to deal with a time-delay in the system. To compensate for modeling errors in the configuration of the Smith predictor, a neural network approach is presented. Based on forming the Smith predictor structure, the radial basis function(RBF) neural network estimator is used. Simulation and experimental studies are conducted to show the functionality of the proposed method.

• Journal of the Korean Ceramic Society
• /
• v.41 no.5
• /
• pp.353-358
• /
• 2004

Spray drying is a unique drying process for powder production. Spray dried product must be free-flowing in order to fill the pressing dies rapidly, especially in the ceramic production. The important powder characteristics are; the particle size distribu-tion and moisture content of the finished product that can be estimated and adjusted by the spray dryer operation, within limits, through regulation of atomizer and drying conditions. In order to estimate the moisture content of the resultant dried product, we modeled the control system of the drying process using two different Artificial Neural Network (ANN) approaches, namely the Back-Propagation Multiplayer Perceptron (BPMLP) algorithm and the Radial Basis Function (RBF) network. It was found out that the performance of both of the artificial neural network models were quite significant and the total testing error for the 100 data was 0.8 and 0.7 for the BPMLP algorithm and the RBF network respectively.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.2
• /
• pp.168-175
• /
• 1999

In this paper, a modified RBF(Radial Basis Function) network structure is suggested for the prediction of a time-series with non-linear, non-stationary characteristics. Coventional RBF network predicting time series by using past outputs sense the trajectory of the time series and react when there exists strong relation between input and hidden activation function's RBF center. But this response is highly sensitive to level and trend of time serieses. In order to overcome such dependencies, hidden activation functions are modified to react to the increments of input variable and multiplied by increment(or dectement) for prediction. When the suggested structure is applied to prediction of Macyey-Glass chaotic time series, Lorenz equation, and Rossler equation, improved performances are obtained.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.297-300
• /
• 2001

Artificial neural networks have become important tools in many fields. This paper describes a new algorithm fur training an RBF network. This algorithm has two main advantages: higher accuracy and a too stable learning process. In addition, it can be used as a good classifier in pattern recognition.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.7
• /
• pp.694-699
• /
• 2009

This paper presents the implementation of the real-time object tracking control of the ROBOKER head. The visual servoing technique is used to track the moving object, but suffers from ill-estimated Jacobian of the virtual link design. To improve the tracking performance, the RBF(Radial Basis Function) network is used to compensate for uncertainties in the kinematics of the robot head in on-line fashion. The reference compensation technique is employed as a neural network control scheme. Performances of three schemes, the kinematic based scheme, the Jacobian based scheme, and the neural network compensation scheme are verified by experimental studies. The neural compensation scheme performs best.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.474-479
• /
• 2003

In this paper, we proposed the novel method for the recognition of English calling cards by using the projection method and the enhanced RBF (Radial Basis Function) network. The recognition of calling cards consists of the extraction phase of character areas and the recognition phase of extracted characters. In the extraction phase, first of all, noises are removed from the images of calling cards, and the feature areas including character strings are separated from the calling card images by using the horizontal smearing method and the 8-directional contour tracking method. And using the image projection method, the feature areas are split into the areas of individual characters. We also proposed the enhanced RBF network that organizes the middle layer effectively by using the enhanced ART1 neural network adjusting the vigilance threshold dynamically according to the homogeneity between patterns. In the recognition phase, the proposed neural network is applied to recognize individual characters. Our experiment result showed that the proposed recognition algorithm has higher success rate of recognition and faster learning time than the existing neural network based recognition.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.657-660
• /
• 2003

Control of multi-link robot arms is a very difficult problem because of the highly nonlinear dynamics. Decentralized control scheme is developed for control of robot manipulators based on RBF(Radial Basis Function) Neural Networks. RBF Neural Networks is used to approximate the coupling forces among the joints, coriolis force, centrifugal force, gravitational force, and frictional force. The compensation controller is also proposed to estimate the bound of approximation error so that the chattering effect of the control effort can be reduced. The proposed scheme does not require an accurate manipulator dynamic, and it is proved that closed-loop system is asymptotic stable despite the gross robot parameter variations. Numerical simulations for two-link robot manipulator are included to show the effectiveness of controller.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.9
• /
• pp.103-110
• /
• 2010

This paper presents the optimized approximation of finite element modeling for a complex tool holder spindle using both DOE (Design of Experiment) with Optimal Latin Hypercube (OLH) method and approximation modeling method with Radial Basis Function (RBF) neural network structure. The complex tool holder is used for holding a (milling/drilling) tool of a machine tool. The engineering problem of complex tool holder results from the twisting of spindle of tool holder. For this purpose, we present the optimized approximation of finite element modeling for a complex tool holder spindle using both DOE (Design of Experiment) with Optimal Latin Hypercube (OLH) method (specifically a module of $iSight^{(R)}$ FD-3.1) and approximation modeling method with Radial Basis Function (RBF) (another module of $iSight^{(R)}$ FD-3.1) neural network structure

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.394-396
• /
• 1997

This paper describes RBF network controller based on fuzzy control rules for intelligent control of nonlinear systems. The proposed scheme is derived from the functional equivalence between RBF networks and fuzzy inference systems. The design procedure of the proposed scheme is realized by first transforming the fuzzy control rules into the parameters of RBF networks. The optimized RBF network controller is then performed through the gradient descent learning mechanism to an error function. The proposed method is rigorously tested using a nonlinear and unstable nonlinear system. Simulation is performed to demonstrate the feasibility and effectiveness of the proposed scheme.