Narrow Results

This paper proposes a recurrent neural network of fuzzy units, which may be used for approximating a hetero-associative mapping and also for pattern classification. Since classification is concerned with set membership, and objects generally belong to sets to various degrees, a fuzzy network seems a natural for doing classification. In the network proposed here each fuzzy unit defines a fuzzy set. The fuzzy unit in the network determines the degree to which the input vector to the unit lies in that fuzzy set. The fuzzy unit may be compared to a perceptron in which case the input vector is compared to the weighting vector associated with the unit by taking the dot product. The resulting membership value in case of the fuzzy unit is compared to a threshold. Training of a fuzzy unit is based on an algorithm for solving linear inequalities similar to the method used for Ho-Kashyap recording. Training of the whole network is done by training each unit separately. The training algorithm is tested by trying the algorithm out on representations of letters of the alphabet with their noisy versions. The results obtained by the simulation are very promising.

In this study, we are concerned with the concept of fuzzy logic networks and their use to logic-based classification of ECG signals. The networks under discussion are treated as homogeneous architectures consisting of OR/AND neurons introduced by Hirota and Pedrycz. Regarded as generic processing units, OR/AND neurons are neurofuzzy constructs that exhibit well-defined logic characteristics come with a high level of parametric flexibility and exhibit significant interpretation abilities. The composite logic nature of the logic neurons becomes instrumental in covering a broad spectrum of characteristics between plain and and or logic descriptors (connectives). From the functional standpoint, the developed network realizes a logic approximation of multidimensional mappings between unit hypercubes, that is, transformations from [0,1]ⁿ to [0,1]^m. The way in which the structure of the network has been formed leads directly to the logic characterization of ECG signals by aggregating logically selected inputs with the use of and and or operators. The design of the logic description consists of two main development phases that is (a) structural optimization which is focused on the identification of the most “descriptive” (discriminating) features (inputs) and (b) ensuing parametric refinement of the logic description that is realized by adjusting the connections (weights) of fuzzy neurons of the structure. The design is carried out in the framework of genetic optimization and genetic algorithms, in particular. The experimental part of the study concerns illustrative synthetic data and a series of QRS complexes coming from the MIT-BIH database.