• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2519-2521
• /
• 2003

In this paper, we propose Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) architecture for optimal model identification and discuss a comprehensive design methodology supporting its development. It is shown that this network exhibits a dynamic structure as the number of its layers as well as the number of nodes in each layer of the SOFPNN are not predetermined (as this is the case in a popular topology of a multilayer perceptron). As the form of the conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership function are studied and the number of the premise input variables used in the rules depends on that of the inputs of its node in each layer. We introduce two kinds of SOFPNN architectures, that is, the basic and modified one with both the generic and the advanced type. The superiority and effectiveness of the proposed SOFPNN architecture is demonstrated through nonlinear function numerical example.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.5
• /
• pp.502-508
• /
• 2012

Heliostat, as a concentrator to reflect the incident solar energy to the receiver, is the most important system in the tower-type solar thermal power plant since it determines the efficiency and ultimately the overall performance of solar thermal power plant. Thus, a good sun tracking ability as well as a good optical property of it are required. Heliostat sun tracking system uses usually an open loop control system. Thus the sun tracking error caused by heliostat's geometrical error, optical error and computational error cannot be compensated. Recently use of sun tracking error model to compensate the sun tracking error has been proposed, where the error model is obtained from the measured ones. This work is a development of heliostat sun tracking error measurement and compensation method using BCS (Beam Characterization System). We first developed an image processing system to measure the sun tracking error optically. Then the measured error is modeled in linear polynomial form and neural network form trained by the extended Kalman filter respectively. Finally error models are used to compensate the sun tracking error. We also developed the necessary image processing algorithms so that the heliostat optical properties such as maximum heat flux intensity, heat flux distribution and total reflected heat energy could be analyzed. Experimentally obtained data shows that the heliostat sun tracking accuracy could be dramatically improved using either linear polynomial type error model or neural network type error model. Neural network type error model is somewhat better in improving the sun tracking performance. Nevertheless, since the difference between two error models in compensation of sun tracking error is small, a linear error model is preferred in actual implementation due to its simplicity.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.5
• /
• pp.463-468
• /
• 2010

An obstacle avoidance method for a mobile robot is proposed in this paper. Our research was focused on the obstacles that can be found indoors since a robot is usually used within a building. It is necessary that the robot maintain the desired direction after successfully avoiding the obstacles to achieve a good autonomous navigation performance for the specified project mission. Sensors such as laser, ultrasound, and PSD (Position Sensitive Detector) can be used to detect and analyze the obstacles. A PSD sensor was used to detect and measure the height and width of the obstacles on the floor. The PSD sensor was carefully calibrated before measuring the obstacles to achieve better accuracy. Data obtained from the repeated experiments were used to plot an error graph which was fitted to a polynomial curve. The polynomial equation was used to navigate the robot. We also obtained a direction-error model of the robot after avoiding the obstacles. The prototypes for the obstacle and direction-error were modeled using a neural network whose inputs are the obstacle height, robot speed, direction of the wheels, and the error in direction. A mobile robot operated by a notebook computer was setup and the proposed algorithm was used to navigate the robot and avoid the obstacles. The results showed that our algorithm performed very well during the experiments.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1567-1577
• /
• 2020

Urban land cover classification is role in urban planning and management. So, it's important to improve classification accuracy on urban location. In this paper, machine learning model, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are proposed for urban land cover classification based on high resolution satellite imagery (KOMPSAT-3A). Satellite image was trained based on 25 m rectangle grid to create training data, and training models used for classifying test area. During the validation process, we presented confusion matrix for each result with 250 Ground Truth Points (GTP). Of the four SVM kernels and the two activation functions ANN, the SVM Polynomial kernel model had the highest accuracy of 86%. In the process of comparing the SVM and ANN using GTP, the SVM model was more effective than the ANN model for KOMPSAT-3A classification. Among the four classes (building, road, vegetation, and bare-soil), building class showed the lowest classification accuracy due to the shadow caused by the high rise building.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.52-58
• /
• 2005

We have developed a Group Method of Data Handling (GMDH) type algorithm for designing multi-layered neural networks. The algorithm is general enough that it will accept any number of inputs and any sized training set. Each neuron of the resulting network is a function of two of the inputs to the layer. The equation for each of the neurons is a quadratic polynomial. Several forms of the equation are tested for each neuron to make sure that only the best equation of two inputs is kept. All possible combinations of two inputs to each layer are also tested. By carefully testing each resulting neuron, we have developed an algorithm to keep only the best neurons at each level. The algorithm's goal is to create as accurate a network as possible while minimizing the size of the network. Software was developed to train and simulate networks using our algorithm. Several applications were modeled using our software, and the result was that our algorithm succeeded in developing small, accurate, multi-layer networks.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.18-31
• /
• 2002

In this study, we introduce a concept of advanced neurofuzzy polynomial networks(ANFPN), a hybrid modeling architecture combining neurofuzzy networks(NFN) and polynomial neural networks(PNN). These networks are highly nonlinear rule-based models. The development of the ANFPN dwells on the technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks and genetic algorithms. NFN contributes to the formation of the premise part of the rule-based structure of the ANFPN. The consequence part of the ANFPN is designed using PNN. At the premise part of the ANFPN, NFN uses both the simplified fuzzy inference and error back-propagation learning rule. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. As the consequence structure of ANFPN, PNN is a flexible network architecture whose structure(topology) is developed through learning. In particular, the number of layers and nodes of the PNN are not fixed in advance but is generated in a dynamic way. In this study, we introduce two kinds of ANFPN architectures, namely the basic and the modified one. Here the basic and the modified architecture depend on the number of input variables and the order of polynomial in each layer of PNN structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the ANFPN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed ANFPN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.307-310
• /
• 2004

In this study, a new architecture and comprehensive design methodology of genetically optimized Multi-layer Fuzzy Neural Networks (gMFNN) are introduced and a series of numeric experiments are carried out. The gMFNN architecture results from a synergistic usage of the hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN), FNN contributes to the formation of the premise part of the overall network structure of the gMFNN. The consequence part of the gMFNN is designed using PNN.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.114-117
• /
• 2000

In this paper, Fuzzy Self-organizing Neural Networks(FSONN) based on Fuzzy Neural Networks(FNN) is proposed to overcome some problems, such as the conflict between ovefitting and good generation, and low reliability. The proposed FSONN consists of FNN and SONN. Here, FNN is used as the premise part of FSONN and SONN is the consequnt part of FSONN. The FUN plays the preceding role of FSONN. For the fuzzy reasoning and learning method in FNN, Simplified fuzzy reasoning and backpropagation learning rule are utilized. The number of layers and the number of nodes in each layers of SONN that is based on the GMDH method are not predetermined, unlike in the case of the popular multi layer perceptron structure and can be generated. Also the partial descriptions of nodes can use various forms such as linear, modified quadratic, cubic, high-order polynomial and so on. In this paper, the optimal design procedure of the proposed FSONN is shown in each step and performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• Journal of Power Electronics
• /
• v.19 no.3
• /
• pp.771-783
• /
• 2019

Due to nonlinear-synthetic uncertainty including the total unknown nonlinear load torque, the total parameter variation and the fixed load torque, a synchronous reluctance motor (SynRM) driving a continuously variable transmission (CVT) system causes a lot of nonlinear effects. Linear control methods make it hard to achieve good control performance. To increase the control performance and reduce the influence of nonlinear time-synthetic uncertainty, an admixed recurrent Gegenbauer orthogonal polynomials neural network (ARGOPNN) with a modified particle swarm optimization (MPSO) control system is proposed to achieve better control performance. The ARGOPNN with a MPSO control system is composed of an observer controller, a recurrent Gegenbauer orthogonal polynomial neural network (RGOPNN) controller and a remunerated controller. To insure the stability of the control system, the RGOPNN controller with an adaptive law and the remunerated controller with a reckoned law are derived according to the Lyapunov stability theorem. In addition, the two learning rates of the weights in the RGOPNN are regulating by using the MPSO algorithm to enhance convergence. Finally, three types of experimental results with comparative studies are presented to confirm the usefulness of the proposed ARGOPNN with a MPSO control system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.12
• /
• pp.2352-2360
• /
• 2011

In this paper, we introduce a comprehensive design methodology of Radial Basis Function Neural Networks (RBFNN) that is based on mechanism of clustering and optimization algorithm. We can divide some clusters based on similarity of input dataset by using clustering algorithm. As a result, the number of clusters is equal to the number of nodes in the hidden layer. Moreover, the centers of each cluster are used into the centers of each receptive field in the hidden layer. In this study, we have applied Fuzzy-C Means(FCM) and K-Means(KM) clustering algorithm, respectively and compared between them. The weight connections of model are expanded into the type of polynomial functions such as linear and quadratic. In this reason, the output of model consists of relation between input and output. In order to get the optimal structure and better performance, Particle Swarm Optimization(PSO) is used. We can obtain optimized parameters such as both the number of clusters and the polynomial order of weights connection through structural optimization as well as the widths of receptive fields through parametric optimization. To evaluate the performance of proposed model, NXT equipment offered by National Instrument(NI) is exploited. The situation awareness system-related intelligent model was built up by the experimental dataset of distance information measured between object and diverse sensor such as sound sensor, light sensor, and ultrasonic sensor of NXT equipment.