Neuro-Classification of Currency Fatigue Levels Based on Acoustic Cepstrum Patterns
Masaru Teranishi*, sigeru Omatu** and Toshihisa Kosaka***
*Department of Electrical Engineering, Nara National College of Technology 22 Yata-cho, Yamatokoriyama, Nara 639-1080, Japan
**Department of Computer and Systems Sciences, College of Engineering, Osaka Prefecture University Gakuencho, Sakai, Osaka 599-8531, Japan
***Glory Ltd. 1-3-1 Shimoteno, Himeji 670-8567, Japan
This paper proposes a new method to classify currencies into different fatigue levels. Acoustic cepstrum patterns obtained from an acoustic signal generated by a currency passing through a banking machine are used for classification. The acoustic cepstrum patterns are fed to a competitive neural network with the Learning Vector Quantization (LVQ) algorithm, and classified the currency into three fatigue levels. The experimental results show that the proposed method is useful for classification of fatigue levels of currencies, and the LVQ algorithm performs a good classification.