In this paper, we present a methodology for automatic diagnosis of systems characterized by continuous signals. For each condition considered, the methodology requires the development of an alphabet of signal primitives, and a set of hierarchical fuzzy automatons (HFAs). Each alphabet is adaptively obtained by training an adaptive resonance theory (ART2) architecture with signal segments from a particular condition. Then, the original signal is transformed into a string of vectors of primitives, where each vector of primitives replaces a signal segment in the original signal. The string, in turn, is presented to the HFA characterizing that particular condition. Each set of HFA consists of a main automaton identifying the entire signal, and several sub-automata each identifying a particular significant structure in the signal. A transition in the main automaton occurs (i.e., the main automaton moves from one state to another) if the corresponding subautomaton recognizes a token where a token is a portion of the string of vectors of signal primitives with a significant structure. The fuzziness in automaton operation adds flexibility to the operation of the automaton, enabling the processing of imperfect input, allowing for toleration measurement noise and other ambiguities. The methodology is applied to the problem of automatic electrocardiogram diagnosis.

A methodology for automated diagnosis of systems characterized by continuous signals is presented. The methodology requires the definition and construction of several fuzzy automatons each capable of identifying a particular condition. When the diagnostic system is in operation, the time sampled system measurements are presented to all automatons simultaneously. The fuzziness in automaton operation enables input processing from several perspectives, consistent with the operation of the automatons, allowing for toleration of measurement noise and other ambiguities. The methodology is applied to the problem of automatic electrocardiogram diagnosis.

This paper presents progress on a new and novel testing approach for detecting interconnection deletion faults in electronic implementations of artificial neural networks (ANNs). The testing approach is based on an unusual transient behavior manifested by faulted ANNs showing better apparent performance than fault-free ANNs, when neurons are operated with low activation function gains. The result presented in this paper improves on prior results by requiring fewer test patterns.

A means for analyzing the faulty behavior of neural networks is presented. Using an analogy between statistical physics and neural networks, a method for assessing the performance of a synchronous neural network model in the presence of faults is developed. Analytical predictions are computed using the statistical physics analogy and compared with the simulated behavior for two neuron models. An example of the analytical technique applied to an autoassociative memory is described.>