Neuro-classification of fatigued bill based on tensional acoustic signal

In the practical use of automated teller machines (ATM's), dealing with much fatigued bills causes serious trouble. To avoid this problem, rapid development of automatic classification methods that can be implemented on banking machines is desired. We propose a new automatic classification method of fatigued bill based on acoustic signal feature of a banking machine. Feeding a bill to a banking machine, a typical acoustic signal is emitted in the transportation part of the machine by tensioning the slackness of the bill transportation. The proposed method focuses on the fact that the tensional acoustic signal features differ in fatigue level of the bill, and uses spectral information of the tensional acoustic signal as the feature for classification of fatigued bill. The proposed method also uses the self organizing map (SOM) type neural network as the classifier to get high classification performance. Simulation results by using real tensional acoustic signal show the effectiveness of the proposed method.