Fast Neuro-Classification of New and Used Bills Using Spectral Patterns of Acoustic Data

Dongshik Kang, Sigeru Omatu and Michifumi Yoshioka

College of Engineering, Osaka Prefecture University 1-1 Gakuen-cho, Sakai, Osaka 599-8531, Japan

Received:

October 5, 1998

Accepted:

February 20, 1999

Published:

January 20, 2000

Keywords:

Adaptive digital filter, LVQ algorithm, IA algorithm, Transaction machine

Abstract

An advanced neuro-classification of new and used bills using the spectral patterns is proposed. An acoustic spectral pattern is obtained from the output of the two-stage adaptive digital filters (ADFs) for time-series acoustic data. The acoustic spectral patterns are fed to a competitive neural network, and classified into some categories which show worn-out degrees of the bill. The proposed method is based on extension of an ADF, an individual adaptation (IA) algorithm, and a learning vector quantization (LVQ) algorithm. The experimental results show that the proposed method is useful to classify new and used bills.

Cite this article as:

D. Kang, S. Omatu, and M. Yoshioka, “Fast Neuro-Classification of New and Used Bills Using Spectral Patterns of Acoustic Data,” J. Adv. Comput. Intell. Intell. Inform., Vol.4 No.1, pp. 12-17, 2000.

Data files:

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.