Earticle

In this paper, we propose a new hybrid intelligent modeling using context clustering and Extreme Learning Machine (ELM) mechanism. It has been a sensitive issue that the ELM mechanism assigns initial parameters randomly, despite of its superior performance. The proposed approach focuses on initial parameters determination of the modeling to improve the accuracy of the ELM mechanism, through removing randomness of assignment. To accomplish it, a context clustering based on Gaussian Mixture Model (GMM), considering a relationship between input-output spaces will be adopted to a Radial Basis Function Network (RBFN) of the ELM. In addition, the proposed approach will reduce the randomness of results from the original ELM. Simulations and the results show usefulness of the proposed approach with improved performance accuracy.

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields, however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an Adaptive Tracking Control of Nonlinear System the radial basis function network (RBFN) that is a kind of neural networks. The learning method involves structural adaptation and parameter adaptation. No prior knowledge of the plant is assumed, and the controller has to begin with exploration of the state space. The exploration versus exploitation dilemma of reinforcement learning is solved through smooth transitions between the two modes. The controller is capable of asymptotically approaching the desired reference trajectory, which is showed in simulation result.

This paper presents a method of recognizing high impedance fault(HIF) of electrical power systems and classifying fault patterns based on chaos attractors. Two dimensional chaos attractors are reconstructed from neutral point current waveforms. Reliable features for HIF pattern classification are obtained from the chaos attractors. Radial basis function network, trained with two types of HIF data generated by the electromagnetic transient program and measured form actual faults. The RBFN successfully classifies normal and the three types of fault patterns according to the features generated from the chaos attractors.

멀티 에이전트 강화학습에서 중요한 이슈 중의 하나는 자신의 성능에 영향을 미칠 수 있는 다른 에이전트들이 존재하는 동적 환경에서 어떻게 최적의 행동 정책을 학습하느냐 하는 것이다. 멀티 에이전트 강화 학습을 위한 기존 연구들은 대부분 단일 에이전트 강화 학습기법들을 큰 변화 없이 그대로 적용하거나 비록 다른 에이전트에 관한 별도의 모델을 이용하더라도 현실적이지 못한 가정들을 요구한다. 본 논문에서는 상대 에이전트에 대한RBFN기반의 행동 정책 모델을 소개한 뒤, 이것을 이용한 강화 학습 방법을 설명한다. 본 논문에서는 제안하는 멀티 에이전트 강화학습 방법은 기존의 멀티 에이전트 강화 학습 연구들과는 달리 상대 에이전트의 Q 평가 함수 모델이 아니라 RBFN 기반의 행동 정책 모델을 학습한다. 또한, 표현력은 풍부하나 학습에 시간과 노력이 많이 요구되는 유한 상태 오토마타나 마코프 체인과 같은 행동 정책 모델들에 비해 비교적 간단한 형태의 행동 정책 모델을 이용함으로써 학습의 효율성을 높였다. 본 논문에서는 대표적이 절대적 멀티 에이전트 환경인 고양이와 쥐 게임을 소개한 뒤, 이 게임을 테스트 베드 삼아 실험들을 전개함으로써 제안하는 RBFN 기반의 정책 모델의 효과를 분석해본다.

In this paper, we propose an adaptive controller using RBFN(radial basis function network) for robot manipulators The structure of the proposed controller consists of a RBFN and VSC-1 ike control. RBFN is used in order to approximate かon system, and VSC-like control to guarantee robustness On the basis of the Lyapunov stability theorem, we guarantee the stability for the total system. And the learning law of RBFN is established by the Lyapunov method, Finally, we apply the proposed controller to tracking control for a 2 link SCARA type robot manipulator.

This paper investigates the direct adaptive control of nonlinear systems using RBFN(radial basis function networks). The structure of the controller consists of a fixed PD controller and a RBFN controller in parallel. An adaptation law for the weight adjustment is developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Also, the tracking errors between the system outputs and the desired outputs converge to zero asymptotically. To evaluate the performance of the controller, the proposed method is applied to the trajectory control of the two-link manipulator.

This paper presents an adaptive quantization of image sequences using the Radial Basis Function Network(RBFN) which classifies interframe image blocks. The clssification algorithm consists of two steps. Blocks are classified into NA(No Activity), SA(Small Activity), VA(Verical Activity), and HA(Horizontal Activity) classes according to edges, image activity and AC anergy distribution. RBFN is trained using the classification results of the above algorithm, which are nonlinear classification features are acquired from the complexity and variability of difference blocks. Simulation result shows that the the adaptive quantization using the RBFN method produced better results better results than that of the sorting and MLP methods.

개층형 신경망은 교사신호들의 학습으로 원하는 입출력간의 매핑을 할 수 있으므로 패턴분류를 위해 사용되어왔다. 본 논문은 계층형 신경망의 일종인 RBFN 중 GPFN 과 PNN으로 한국어 음소인식을 수행하였다. RBFN 의 구조는 계층형 신경망과 유사하나 차이점으로는 은닉층에서 시그모이드 함수, 참조벡터 및 학습알고리듬의 선택이 다르다. 특히 PNN 의 시그모이드 함수는 지수를 포함한 함수들로 대체되며 학습없이 패턴을 분류하므로 계산시간이 빠르게 수행된다. 본 실험에서는 한국어 단음절에서 모음과 자음을 추출하여 음소인식을 수행하였다. 실험 결과 학습과 평가데이타에 의한 인식률은 계층형 신경망과 비교하여 향상 되었으며, Hybrid 구성에 의한 실험에서도 항상된 인식률을 얻을 수 있었다.

This paper proposes an RBFN-based adaptive tracking controller for an electrically driven mobile robot with parametric uncertainties and external disturbances. A mobile robot model considered in this paper includes all models of the robot body and actuators with uncertain kinematic and dynamic parameters, and uncertain frictions and external disturbances. The proposed controller consists of an RBFN(Radial Basis Function Network) and a robust adaptive controller. The presented RBFN is used to approximate unknown nonlinear robot dynamic functions. The proposed controller is adjusted by the adaptation laws obtained through the Lyapunov stability analysis. The proposed control scheme does not a priori need the accurate knowledge of all parameters in the robot kinematics, robot dynamics and actuator dynamics. Also, nominal parameter values are not required in the controller. The global stability of the closed-loop robot control system is guaranteed using the Lyapunov stability theory. Simulation results show the validity and robustness of the proposed control scheme.

This paper describer a design expert system which determines the design values of shadow mask using Case-Based Reasoning. In Case-Based Reasoning, it is important to both retrieve similar cases and adapt the cases to meet the design specifications exactly. Especially, the difficulty in automating the adaptation process will prevent the designers from using the design expert systems efficiently and easily. This paper explains knowledge-based design support systems for shadow mask through neural network-based case adaptation. Specifically, we developed 1) representing design knowledge and 2) adaptive case-based reasoning method using RBFN (Radial Basis Function Network).

This paper investigates the direct adaptive control of nonlinear systems using RBFN(radial basis function networks). The structure of the controller consists of a fixed PD controller and a RBFN controller in parallel. An adaptation law for the parameters of RBFN is developed based on the Lyapunov stability theory to guarantee the stability of the overall control system. The filtered tracking error between the system output and the desired output is shown to be UUB(uniformly ultimately bounded). To evaluate the performance of the controller, the proposed method is applied to the trajectory contro of the two-link manipulator.

본 논문에서 제안한 예측형 RBFN(Radial Basis Function Network)은 HMM과 신경망을 결합한 하이브리드 구조이다. 이 신경망은 HMM으로 추정한 확률분포 파라미터를 사용하여 중간층의 활성화 함수의 출력을 결정하고, 중간층과 출력층의 연결강도만 네트워크 내에서 학습한다. 그리고 HMM으로 추정한 확률분포 파라미터는 두 가지 방법으로 예측형 RBFN에 이용하였다. 첫 번째는 HMM의 각 상태의 혼합수 만큼의 중간층 유니트를 주는 방법이고, 두 번째는 HMM의 혼합수$\times$출력분포수 만큼의 중간층 유니트를 주는 방법이다. 실험결과, 예측형 RBFN은 다른 방법들의 결과보다 $4.5\~6.5\%$ 저하된 결과를 보였지만 다른 신경망에 비해서 학습 반복 횟수를 작게할 수 있었으며 전체 학습시간을 대폭 단축할 수 있었다.

Partial discharge pulse shapes from variable PD (partial discharge) sources sustain many characteristics such as types of PD. Ultra high frequency antennas have wide bandwidth from 30KHz to 2㎓. Therefore, signals taken from a UHF antenna have important attributes (rising time, falling time, shape factor, etc.) for electromagnetic sources, such as PD sources. We investigated PD pulse shapes from several PD sources using a UHF antenna and the results were used for classification of PD sources. Features for discrimination are extracted from frequency distribution and LPC (Linear Prediction Coefficient) of time signal. RBFN are used for investigating the possibility of classification of multi-PD sources.

본 논문은 선형회귀(LR: Linear Regression)와 국부적인 방사기저함수 네트워크(RBFN: Radial Basis Function Networks)를 결합한 점진적인 모델(incremental model)의 설계와 관련되어진다. 전형적인 RBFN에 의한 모델링과는 달리, 제안된 방법의 근본적인 원리는 두 단계에 의해 고려되어진다. 첫째, 전체 모델의 설계과정에서 전역적인 모델로써 선형회귀에 의해 데이터의 선형부분을 구축한다. 다음으로, 모델링 오차는 오차가 존재하는 국부적인 공간에서 RBFN에 의해 보상되어진다. 여기서, 오차의 분포로부터 RBFN을 설계하기 위해 컨텍스트 기반 퍼지 클러스터링(CFC: Context-based Fuzzy Clustering)를 통해 정보입자의 형태로 구축되어진다. 실험은 자동차 mpg 연료소비량 예측과 부동산 가격예측문제를 통해 제안된 방법의 우수성을 증명한다.

본 논문은 선형회귀(LR: Linear Regression)와 국부적인 방사기저함수 네트워크(RBFN: Radial Basis Function Networks)를 결합한 점진적인 모델(incremental model)의 설계와 관련되어진다. 전형적인 RBFN에 의한 모델링과는 달리, 제안된 방법의 근본적인 원리는 두 단계에 의해 고려되어진다. 첫째, 전체 모델의 설계과정에서 전역적인 모델로써 선형회귀에 의해 데이터의 선형부분을 구축한다. 다음으로, 모델링 오차는 오차가 존재하는 국부적인 공간에서 RBFN에 의해 보상되어진다. 여기서, 오차의 분포로부터 RBFN을 설계하기 위해 컨텍스트 기반 퍼지 클러스터링(CFC: Context-based Fuzzy Clustering)를 통해 정보입자의 형태로 구축되어진다. 실험은 자동차 mpg 연료소비량 예측과 부동산 가격예측문제를 통해 제안된 방법의 우수성을 증명한다.

In order to navigate the mobile robots safely in unknown environments, many researches have been studied to devise navigational algorithms for the mobile robots. In this paper, we propose a navigational algorithm that consists of an obstacle-avoidance behavior module, a goal-approach behavior module and a radial basis function network(RBFN) supervisor. In the obstacle-avoidance behavior module and goal-approach behavior module, the fuzzy-artificial immune networks are used to select a proper steering angle which makes the autonomous mobile robot(AMR) avoid obstacles and approach the given goal. The RBFN supervisor is employed to combine the obstacle-avoidance behavior and goal-approach behavior for reliable and smooth motion. The outputs of the RBFN are proper combinational weights for the behavior modules and velocity to steer the AMR appropriately. Some simulations and experiments have been conducted to confirm the validity of the proposed navigational algorithm.

본 논문에서는 새로이 제안된 자기 구조화하는(Self-structuring) 새로운 Radial-Basis Function Network(RBFN)에 대해서 실험적인 검증을 했다. 이 자기 구조화하는 새로운 RBFN은 기존의 RBFN과 비교해서 여러 장점이 있다. Lyapunov 이론에 기초해서 새로운 학습 규칙을 선정하였기 때문에 시스템의 안정도를 보장할 수 있다. 그리고, 자기 구조화의 과정 즉, 생성과 병합을 통해 은닉층에서 적정수의 뉴런을 결정할 수 있다. 기존의 RBFN과 성능을 비교하기 위하여, 실제 비선형 시스템인 2축 암로봇에 대해 실험한 결과를 보였다. 결과적으로, 우리는 실험결과를 통해 자기 구조화하는 RBFN의 효율적인 구조와 시스템에 대한 안정도를 보장함을 볼 수 있다.

This paper reports the suitability of a domain decomposition technique for the hybrid simulation of dilute polymer solution flows using Eulerian Brownian dynamics and Radial Basis Function Networks (RBFN) based methods. The Brownian Configuration Fields (BCF) and RBFN method incorporates the features of the BCF scheme (which render both closed form constitutive equations and a particle tracking process unnecessary) and a mesh-less method (which eliminates element-based discretisation of domains). However, when dealing with large scale problems, there appear several difficulties: the high computational time associated with the Stochastic Simulation Technique (SST), and the ill-condition of the system matrix associated with the RBFN. One way to overcome these disadvantages is to use parallel domain decomposition (DD) techniques. This approach makes the BCF-RBFN method more suitable for large scale problems.

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields; however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an adaptive tracking control for robot manipulators using the radial basis function network (RBFN) that is e. kind of neural networks. Adaptation laws for parameters of the RBFN are developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Filtered tracking errors between actual outputs and desired outputs are discussed in the sense of the uniformly ultimately boundedness(UUB). Additionally, it is also shown that parameters of the RBFN are bounded. Experimental results for a SCARA-type robot manipulator show that the proposed adaptive tracking controller is adaptable to the environment changes and is more robust than the conventional PID controller and the neuro-controller based on the multilayer perceptron.

Currently, the radial basis function network (RBFN) and various other neural networks are employed to classify gases using chemical sensors arrays, and their performance is steadily improving. In particular, the identification performance of the RBFN algorithm is being improved by optimizing parameters such as the center, width, and weight, and improved algorithms such as the radial basis function network-stochastic gradient (RBFN-SG) and radial basis function network-normalized stochastic gradient (RBFN-NSG) have been announced. In this study, we optimized the number of centers, which is one of the parameters of the RBFN-NSG algorithm, and observed the change in the identification performance. For the experiment, repeated measurement data of 8 samples were used, and the elbow method was applied to determine the optimal number of centers for each sample of input data. The experiment was carried out in two cases(the only one center per sample and the optimal number of centers obtained by elbow method), and the experimental results were compared using the mean square error (MSE). From the results of the experiments, we observed that the case having an optimal number of centers, obtained using the elbow method, showed a better identification performance than that without any optimization.