• Steel and Composite Structures
• /
• v.18 no.3
• /
• pp.547-563
• /
• 2015

Deflection in a beam of a composite frame is a serviceability design criterion. This paper presents a methodology for rapid prediction of long-term mid-span deflections of beams in composite frames subjected to service load. Neural networks have been developed to predict the inelastic mid-span deflections in beams of frames (typically for 20 years, considering cracking, and time effects, i.e., creep and shrinkage in concrete) from the elastic moments and elastic mid-span deflections (neglecting cracking, and time effects). These models can be used for frames with any number of bays and stories. The training, validating, and testing data sets for the neural networks are generated using a hybrid analytical-numerical procedure of analysis. Multilayered feed-forward networks have been developed using sigmoid function as an activation function and the back propagation-learning algorithm for training. The proposed neural networks are validated for an example frame of different number of spans and stories and the errors are shown to be small. Sensitivity studies are carried out using the developed neural networks. These studies show the influence of variations of input parameters on the output parameter. The neural networks can be used in every day design as they enable rapid prediction of inelastic mid-span deflections with reasonable accuracy for practical purposes and require computational effort which is a fraction of that required for the available methods.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.235-241
• /
• 2000

This article suggests integrated neural network models for the interest rate forecasting using change point detection. The basic concept of proposed model is to obtain intervals divided by change point, to identify them as change-point groups, and to involve them in interest rate forecasting. the proposed models consist of three stages. The first stage is to detect successive change points in interest rate dataset. The second stage is to forecast change-point group with data mining classifiers. The final stage is to forecast the desired output with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. This article is then to examine the predictability of integrated neural network models for interest rate forecasting using change-point detection.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.2
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence 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 AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• The Journal of Information Technology and Database
• /
• v.2 no.2
• /
• pp.71-85
• /
• 1995

Many research results conducted by neural network researchers have claimed that the classification accuracy of neural networks is superior to, or at least equal to that of conventional methods. However, in series of neural network classifications, it was found that the classification accuracy strongly depends on the characteristics of training data set. Even though there are many research reports that the classification accuracy of neural networks can be different, depending on the composition and architecture of the networks, training algorithm, and test data set, very few research addressed the problem of classification accuracy when the basic assumption of data monotonicity is violated, In this research, development project of automated credit evaluation system is described. The finding was that arrangement of training data is critical to successful implementation of neural training to maintain monotonicity of the data set, for enhancing classification accuracy of neural networks.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.09a
• /
• pp.334-343
• /
• 1995

In recent years, neural networks have been developed as an alternative to traditional statistical techniques. In this study, a neural network model was compared to traditional forecasting models in terms of their capabilities to forecast passenger traffic for flights between U.S. and Korea. The results show that the forecasting ability of the neural networks was superior to the traditional models. In terms of accuracy, the performance of the neural networks was quite encouraging. Using mean absolute deviation, the neural network performed best. The new technique is easy to learn and apply with commercial neural network software. Therefore, airline decision makers should benefit from using neural networks in forecasting passenger loads.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.2
• /
• pp.209-214
• /
• 1998

In this paper, we are dealing with the problem of controlling unknown nonlinear dynamical system by using neural networks. A novel error self-recurrent(ESR) neural model is presented to perform black-box identification. Through the various outcome of the experiment, a new neural network is seen to be considerably faster than the BP algorithm and has advantages of being less affected by poor initial weights and learning rate. These characteristics make it flexible to design the controller in real-time based on neural networks model. In addition, we design an adaptive PID controller that Keyser suggested by using ESR neural networks, and present a method on the implementation of adaptive controller based on neural network for practical applications. We obtained good results in the case of robot manipulator experiment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.531-531
• /
• 2000

The challenge is to control unstable nonlinear dynamic systems using only sparse feedback from the environment concerning its performance. The design of such controllers can be achieved by evolving neural networks. An evolutionary approach to train neural networks in realtime is proposed. Evolutionary strategies adapt the weights of neural networks and the threshold values of neuron's synapses. The proposed method has been successfully implemented for pole balancing problem.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.378-388
• /
• 2000

In this paper, we propose Fuzzy Polynomial Neural Networks(FPNN) based on Polynomial Neural Networks(PNN) and Fuzzy Neural Networks(FNN) for model identification of complex and nonlinear systems. The proposed FPNN is generated from the mutually combined structure of both FNN and PNN. The one and the other are considered as the premise part and consequence part of FPNN structure respectively. As the consequence part of FPNN, 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. FPNN is available effectively for multi-input variables and high-order polynomial according to the combination of FNN with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. As the premise part of FPNN, FNN 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. And we use two kinds of FNN structure according to the division method of fuzzy space of input variables. One is basic FNN structure and uses fuzzy input space divided by each separated input variable, the other is modified FNN structure and uses fuzzy input space divided by mutually combined input variables. In order to evaluate the performance of proposed models, we use the nonlinear function and traffic route choice process. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously. And also performance index related to the approximation and prediction capabilities of model is evaluated and discussed.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.5
• /
• pp.46-55
• /
• 2000

This paper presents a direct adaptive control of robot system using chaotic neural networks and PD controller. The chaotic neural networks have robust nonlinear dynamic characteristics because of the sufficient nonlinearity in neuron itself, and the additional self-feedback and inter-connecting weights between neurons in same layer. Since the structure and the learning method are not appropriate for applying in control system, this neural networks have not been applied. In this paper, a modified chaotic neural networks is presented for dynamic control system. To evaluate the performance of the proposed neural networks, these networks are applied to the trajectory control of the three-axis PUMA robot. The structure of controller consists of PD controller and chaotic neural networks in parallel for conforming the stability in initial learning phase. Therefore, the chaotic neural network controller acts as a compensating controller of PD controller.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.562-567
• /
• 1998

This paper examined the relations among the multidimensional linear interpolation(MDI) and fuzzy reasoning , and neural networks, and showed that an showed that an MDI is a special form of Tsukamoto's fuzzy reasoning and regularization networks in the perspective of fuzzy reasoning and neural networks, respectively. For this purposes, we proposed a special Tsukamoto's membership (STM) systemand triangular basis function (TBF) networks, Also we verified the condition when our proposed TBF becomes a well-known radial basis function (RBF).