University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Identification of dental bacteria using statistical and neural approaches

Yong, CK, Lim, CM, Plumbley, M, Beighton, D and Davidson, R (2002) Identification of dental bacteria using statistical and neural approaches In: 9th International Conference on Neural Information Processing (ICONIP '02), 18 - 22 November 2002.

Full text not available from this repository.


This paper is devoted to enhancing rapid decision-making and identification of lactobacilli from dental plaque using statistical and neural network methods. Current techniques of identification such as clustering and principal component analysis are discussed with respect to the field of bacterial taxonomy. Decision-making using multilayer perceptron neural network and Kohonen self-organizing feature map is highlighted. Simulation work and corresponding results are presented with main emphasis on neural network convergence and identification capability using resubstitution, leave-one-out and cross validation techniques. Rapid analyses on two separate sets of bacterial data from dental plaque revealed accuracy of more than 90% in the identification process. The risk of misdiagnosis was estimated at 14% worst case. Test with unknown strains yields close correlation to cluster dendograms. The use of the AXEON VindAX simulator indicated close correlations of the results. The paper concludes that artificial neural networks are suitable for use in the rapid identification of dental bacteria.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Surrey research (other units)
Authors :
Yong, CK
Lim, CM
Beighton, D
Davidson, R
Date : 2002
DOI : 10.1109/ICONIP.2002.1198129
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:36
Last Modified : 23 Jan 2020 18:42

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800