A Dynamic Pattern Classifier for Complex Information Systems Based on Fuzzy Petri Nets

Aiming at the problem of pattern recognition for the complex information systems with many dynamic fault types, a dynamic pattern classifier is constructed based on fuzzy Petri nets for the fault classification of complex information systems. fuzzy Petri net is a machine-learning algorithm that has been successfully used in pattern recognition for cluster analysis. In this paper, the dynamic recognition classifier is constructed based on two types of learning. The static aspect of the learning is ensured by classifiers or systems of classifiers, while the dynamic aspect is translated by the learning of the planning of the various states by fuzzy Petri nets. Finally, the practical recognition process is given in an illustrative example of a synthetic data set. The results show that the method is effective and reasonable through approving.