Journal of Intelligent & Fuzzy Systems - Volume 5, issue 2

Authors: Myung, Hyun | Kim, Jong-Hwan

Article Type: Research Article

Abstract: In this article, a time-varying two-phase optimization neural network is proposed for the constrained time-varying optimization problem, which takes advantage of both the two-phase neural network and the time-varying programming neural network. Considering the training of a neural network as a time-varying optimization problem, the proposed algorithm is applied to the multilayer neural network training for the system identification or function learning and the model reference neurocontrol. Moreover, the neural network training with the constrained weights is also considered. The effectiveness of the proposed scheme is demonstrated by computer simulations.

DOI: 10.3233/IFS-1997-5201

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 2, pp. 85-101, 1997

Authors: Karayiannis, Nicolaos B.

Article Type: Research Article

Abstract: This article introduces three families of fuzzy partition entropies and investigates their relationship with Bezdek's partition entropy. Bezdek's partition entropy is interpreted as the limit of partition entropies of order a, partition entropies of order β, and R-norm partition entropies introduced in this study. The proposed partition entropies are used to formulate clustering as a constrained minimization problem. This formulation results in entropy constrained fuzzy clustering algorithms as the proposed partition entropies approach Bezdek's partition entropy. The algorithms resulting from the proposed formulation allow the transition from a maximally fuzzy to crisp partitions according to a procedure that resembles an …“annealing” process. More-over, entropy constrained algorithms satisfy a basic requirement for clustering algorithms; they are invariant under uniform scaling of the feature vectors. Show more

DOI: 10.3233/IFS-1997-5202

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 2, pp. 103-111, 1997

Authors: Ding, Hong | Gupta, Madan M.

Article Type: Research Article

Abstract: An important class of current fuzzy neural networks, called fuzzy set neural networks (FSNNs), is one in which all the inputs, synaptic weights, and outputs may be vectors of fuzzy sets. One of the most difficult tasks in the development of these FSNNs is the lack of efficient learning algorithms. In this article we employ genetic algorithms (GAs) techniques to design a FSNN. We first study the parameterization of the synaptic weights to be learned in an FSNN, and then the evolutionary learning procedure is discussed in each genetic cycle. Some simulation results on the application of a FSNN to …the problem of backing a truck are presented. Finally, the self-organizing space during reproduction of genes in GAs is studied. Show more

DOI: 10.3233/IFS-1997-5203

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 2, pp. 113-127, 1997

Authors: Al-Alawi, Raida

Article Type: Research Article

Abstract: This article presents a digital associative memory (DAM) with pyramids of probabilistic logic nodes used as the basic processing element. The DAM can be applied to various pattern recognition systems or image classifiers. A reward/penalty error back propagation algorithm used to train the model will be described. Computer simulations are done to evaluate the performance of the model by training the network on associating a number of patterns from each class of the numerals 0–9 with their prototype model. The effect of the size of the training set on the convergence of the training algorithm is investigated.

DOI: 10.3233/IFS-1997-5204

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 2, pp. 129-137, 1997

Authors: Balazinski, M. | Czogala, E. | Sadowski, T.

Article Type: Research Article

Abstract: This article recalls the idea of neural controllers with application to the control of mechanical systems. Basic structures of such controllers are suggested, and the results of simulations comparing their performance to that of conventional and fuzzy logic controllers are shown. The experiments indicate that the performance of the proposed neural controllers is satisfactory.

DOI: 10.3233/IFS-1997-5205

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 2, pp. 139-153, 1997

Authors: Jang, Wook-Jin | Byun, Joonbum | Hambaba, Mohamed L.

Article Type: Research Article

Abstract: An asynchronous transfer mode (ATM) network is a high-speed multimedia network that handles various kinds of traffic with different bit rates and different qualities of services (QoS). To maintain QoS for each traffic source and to avoid a possible congestion problem, an ATM network requires highly sophisticated and flexible controllers to insure that the demanding performance can be achieved under unexpected changes in traffic conditions. In this article we propose an intelligent architecture using neural networks for traffic congestion control in an ATM network. The congestion control using neural networks is suitable for an ATM because neural networks can learn …the offered traffic characteristics and the dynamic changes of the traffic. The proposed mechanism is based on the adaptive prediction of the future value of the offered traffic and the flow rate for each traffic source. At every given time slot, the controllers in the proposed architecture predict whether the congestion will happen or not and regulate the volume of input traffic for each traffic source before the congestion happens, maintaining the user-required QoS for each traffic source based on the predefined rules. Consequently, the mechanism guarantees the QoS for each traffic source and efficiently prevents congestion. Show more

DOI: 10.3233/IFS-1997-5206

Citation: Journal of Intelligent and Fuzzy Systems, vol. 5, no. 2, pp. 155-165, 1997