Classification of bill fatigue levels by feature-selected acoustic energy pattern using competitive neural network

This paper proposes a new method to classify bills into different fatigue levels. Feature-selected acoustic energy patterns obtained from an acoustic signal generated by a bill passing through a banking machine are used for classification. The feature-selected acoustic energy patterns are fed to a competitive neural network with the learning vector quantization algorithm, and classified the bill into three fatigue levels. Furthermore, the selection of features in an acoustic energy pattern is performed to improve classification performance. We introduce a genetic algorithm to obtain the optimal feature selection. The experimental results show that the proposed method is useful for classification of fatigue levels of bills, and the classification performances are improved by selecting feature with genetic algorithm.