Journal of Intelligent & Fuzzy Systems - Volume 4, issue 3

Article Type: Other

DOI: 10.3233/IFS-1996-4307

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. I-I, 1996

Authors: Zurada, Jozef | Graham, James H. | Karwowski, Waldemar

Article Type: Research Article

Abstract: This article concerns the use of a neural system in a previously unreported, but highly significant, application in robotics safety. It presents a neural network based decision unit for a real-time robot safety system. The decision unit occupies a high level position in the sensory processing hierarchy, using information from signal processing and detection at lower levels. The developed neural network accepts the following input: a map containing potential collision zones encoded as belief values into grids, the magnitude of a robot's velocity vector, and the robot's steering angle. The neural network decision is based on computation of the scalar …product of two vectors, the virtual repulsive force vector generated by the obstacle and the robot's velocity vector; it produces one of the following safety decisions: move as intended, slow down, or emergency stop. The effectiveness of this approach is verified by computer simulation. The response time of the neural network measured on the state of the art personal computer is 6 msec, and the correctness of the safety decisions exceeds 90%. Show more

DOI: 10.3233/IFS-1996-4301

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. 177-191, 1996

Authors: Shih, Ming-Chang | Lee, Kuo-Chan

Article Type: Research Article

Abstract: The purpose of this article is to design a neurofuzzy controller with a hybrid learning algorithm and to control the position of a hydraulic servocylinder with an IBM compatible microcomputer. The structure of the neurofuzzy controller is based on the bell-shaped membership function and the Mamdani fuzzy reasoning rules. According to the training data and the hybrid neural network learning, the minimum fuzzy reasoning rules and the optimized membership function can be found automatically. The effects of different design parameters and the load disturbance are also studied experimentally.

DOI: 10.3233/IFS-1996-4302

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. 193-206, 1996

Authors: Newcomb, Robert W. | de Figueiredo, Rui J.P.

Article Type: Research Article

Abstract: A generic two-layer feed forward functional neural network is proposed that processes functions rather than point evaluations of functions. Specifically, the network receives n functions as inputs and delivers m real values as outputs. Its architecture is derived using the nonlinear system identification techniques of Zyla and de Figueiredo. As such, neurons are represented by Volterra functions in Fock space, which is a reproducing kernel Hilbert space, with synaptic weights that are functions themselves. The main advantage is that this functional network can be used in the modeling of real-world (continuous-time parameter) nonlinear systems, capturing the dynamics presented in them, …as well as in the simulation of their behavior in a computer-based environment. Show more

DOI: 10.3233/IFS-1996-4303

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. 207-213, 1996

Authors: Thawonmas, Ruck | Abe, Shigeo

Article Type: Research Article

Abstract: In this article we propose a method for extracting fuzzy rules based on box-shaped regions (hyperboxes) that are defined for approximating class regions. In the proposed method, partition of hyperboxes is performed to achieve high accuracy in approximating the class regions. Excessive partition is prevented by the terminating criterion discussed. Each overlap between partitioned hyperboxes of different classes is resolved, if necessary, in a recursive fashion by means of defining new hyperboxes. Fuzzy rules are extracted based on the defined hyperboxes. We describe a mechanism for inference of these fuzzy rules. We show empirically that the proposed method has higher …generalization ability for the iris data and Japanese hiragana data on Japanese license plates than either that of a fuzzy rule extraction method without partition of hyperboxes or multilayered neural networks. Show more

DOI: 10.3233/IFS-1996-4304

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. 215-226, 1996

Authors: Foo, Shou King | Saratchandran, P. | Sundararajan, N.

Article Type: Research Article

Abstract: This article investigates optimal and suboptimal pattern allocation schemes when training-set parallelism is used as the paradigm to map a backpropagation neural network on a heterogeneous array of processors. In earlier work, it was shown that finding the optimal allocation of patterns to minimize the time for a training epoch for such a mapping leads to a mixed integer programming problem. Because the solution to the mixed integer programming requires prohibitively large computing time, several suboptimal allocation methods that are computationally less demanding are discussed and their performance compared with the optimal solution for the NETTALK benchmark problem. The processor …network used for mapping the neural network is a heterogeneous array of transputers connected in a pipelined ring topology. Show more

DOI: 10.3233/IFS-1996-4305

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. 227-234, 1996

Authors: Guo, Lei | Guo, Baolong

Article Type: Research Article

Abstract: Neural networks can be viewed as open constraint satisfaction networks. According to the consideration, neural networks (NNs) have to obey an inherent logical theory that consists of two-state decisions, weak constraints, rule type and strength, and identity and contradiction. This article presents the underlying frame of the theory that indicates that the essential reason why an NN is changing its states is the existence of superior contradiction inside the network, and that the process by which an NN seeks a solution corresponds to eliminating the superior contradiction. Different from general constraint satisfaction networks, the solutions found by NNs may contain …inferior contradiction but not the superior contradiction. Accordingly, the constraints in NNs are weak or flexible. The ability of a general NN is insufficient for its application to constraint satisfaction problems. Show more

DOI: 10.3233/IFS-1996-4306

Citation: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 3, pp. 235-242, 1996