Unsupervised adaptive resonance theory neural networks for control chart pattern recognition

This paper describes the use of unsupervised adaptive resonance theory ART2 neural networks for recognizing patterns in statistical process control ch arts. To improve the classification accuracy, three schemes are proposed. T he first scheme involves using information on changes between consecutive p oints in a pattern. The second scheme modifies the ART2 vigilance parameter during training. The third scheme merges class neurons representing the sa me class after training. The paper gives results which demonstrate the impr ovements achieved.