• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.316-319
• /
• 2006

Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1999.05a
• /
• pp.74-74
• /
• 1999

• Journal of Environmental Impact Assessment
• /
• v.14 no.4
• /
• pp.157-164
• /
• 2005

Existing models that predict of Daily water supply include statistical models and neural network model. The neural network model was more effective than the statistical models. Only neural network model, which predict of Daily water supply, is focused on estimation of the operational control. Neural network model takes long learning time and gets into local minimum. This study proposes Neuro Genetic hybrid model which a combination of genetic algorithm and neural network. Hybrid model makes up for neural network's shortcomings. In this study, the amount of supply, the mean temperature and the population of the area supplied with water are use for neural network's learning patterns for prediction. RMSE(Root Mean Square Error) is used for a MOE(Measure Of Effectiveness). The comparison of the two models showed that the predicting capability of Hybrid model is more effective than that of neural network model. The proposed hybrid model is able to predict of Daily water, thus it can apply real time estimation of operational control of water works and water drain pipes. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 11.81% and the average error was lower than 1.76%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.395-400
• /
• 2000

In this paper, we propose a new neuro-fuzzy controller based on reinforcement learning. The proposed system is composed of neuro-fuzzy controller which decides the behaviors of an agent, and dynamic recurrent neural networks(DRNNs) which criticise the result of the behaviors. Neuro-fuzzy controller is learned by reinforcement learning. Also, DRNNs are evolved by genetic algorithms and make internal reinforcement signal based on external reinforcement signal from environments and internal states. This output(internal reinforcement signal) is used as a teaching signal of neuro-fuzzy controller and keeps the controller on learning. The proposed system will be applied to controller optimization and adaptation with unknown environment. In order to verifY the effectiveness of the proposed system, it is applied to collision avoidance of an autonomous mobile robot on computer simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.123.2-123
• /
• 2001

It is difficult to determine the feeding rate of coagulant in the water treatment plant, due to nonlinearity, multivariables and slow response characteristics, etc. To deal with this difficulty, the neuro-fuzzy system and the genetic-fuzzy system were used in determining the feeding rate of the coagulant. The fuzzy system is excellently robust in multi-variables and nonlinear problems. Therefore it uses basic algorithm, but it is difficult to construct of the fuzzy parameter such as the rule table and the membership function, Therefore we made the neuro-fuzzy system and the genetic-fuzzy system with the fusion of learning algorithms and compared the performance of the two fuzzy systems. To apply these algorithms, we made the rule table, membership function from the actual operation data of the water treatment plant. We determined optimized feeding rate of coagulant using the fuzzy operation, and also compared ...

• Journal of the Korean Institute of Intelligent Systems
• /
• v.4 no.1
• /
• pp.35-49
• /
• 1994

It is well known that, for nominimum phase systems, a conventional linear controller of PID type or an adaptive controller of this structure shows limitation in achieving a satisfactory performance under tight specifications. In this paper, we combine a neuro-controller with a PI-controller with off-line learning capability provided by the Genetic Algorithm to propose a novel neuro-controller to control nonminimum phase systems effectively. The simulation results show that our proposed model is more efficient with faster rising time and less undershoot effect when the performances of the proposed controller and a conventional form are compared.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.1
• /
• pp.23-34
• /
• 2002

This paper proposes a new neuro-fuzzy system that is fast trained by evolution strategy and describes application results of the proposed system to nonlinear system identification to show its usefulness. As training methods of neuro-fuzzy systems, modified error back-propagation algorithms and genetic algorithms have been used so far. However, the former has some drawbacks such as long training time, falling to local optimum, and experimental selecting of learning rates and the latter has difficulty in precise searching solutions because genetic algorithms represents solutions as genotype individuals. The evolution strategy we used can do precise search because its individuals are represented as phenotype real values, it seldom falls into a local optimum, and its training speed is faster than error back-propagation algorithms. We apply our neuro-fuzzy systems to nonlinear system identification. It was found from experiments that training speed is fast and the training results were considerably good.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.772-777
• /
• 1993

This paper presents a neuro-fuzzy modelling method that determines chemicals dosing model based on historical operation data for effective water quality control in water treatment system and calculates automatically the amount of optimum chemicals dosing against the changes of raw water qualities and flow rate. The structure identification in the modelling by means of neuro-fuzzy reasing is performed by Genetic Algorithm(GA) and Complex Method in which the numbers of hidden layer and its hidden nodes, learning rate and connection pattern between input layer and output layer are identified. The learning network is implemented utilizing Back Propagation(BP) algorithm. The effectiveness of the proposed modelling scheme and the feasibility of the acquired neuro-fuzzy network is evaluated through computer simulation for chemicals dosing control in water treatment system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.83-86
• /
• 2001

In this paper, it study about the image filter applied the hybrid fuzzy membership function to the neuro-fuzzy system. Here, this system applys the genetic algorithm in order to obtain the optimal image as the iteration carry for making the data value in the error. It is removed the included noise in an image using the proposed image filter and compared the proposed image filter performance with the other filters using MATLAB. And it is found that the proposed filter performance is superior to the other filters which has the similar structure through the images. To show the superior ability, it is compared with MSE and SNR for images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.372-372
• /
• 2000

In this paper, we propose Neuro Fuzzy Polynomial Networks(NFPN) based on Polynomial Neural Network(PNN) and Neuro-Fuzzy(NF) for model identification of complex and nonlinear systems. The proposed NFPN is generated from the mutually combined structure of both NF and PNN. The one and the other are considered as the premise part and consequence part of NFPN structure respectively. As the premise part of NFPN, NF uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. As the consequence part of NFPN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. NFPN is available effectively for multi-input variables and high-order polynomial according to the combination of NF with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. In order to evaluate the performance of proposed models, we use the nonlinear function. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously.