Published Articles >> Table of Contents >> Abstract

International Conference on Information Technology: Coding and Computing   p. 0512
The Investigation of Mercury Presence in Human Blood: An Extrapolation from Animal Data Using Neural Networks
Ray R. Hashemi, University of Arkansas at Little Rock and National Center for Toxicological Research
Mahmood Bahar, Teacher Training University
Alexander A. Tyler, University College Cork
John Young, National Center for Toxicological Research

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ITCC.2002.1000440
Send link to a friend

Abstract
In this research effort a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also investigated the effect of different data representations (As-is, Category, Simple binary, Thermometer, and Flag) on the model performance. In addition, we used the Rough Sets methodology to identify the redundant independent variables and then examined the proposed extrapolation model performance for a reduced set of independent variables. Moreover, a quality measure was introduced that revealed that the proposed extrapolation model performed extremely well for the Thermometer data representation.
Back to Top Additional Information
Citation:  Ray R. Hashemi, Mahmood Bahar, Alexander A. Tyler, John Young, "The Investigation of Mercury Presence in Human Blood: An Extrapolation from Animal Data Using Neural Networks," itcc, p. 0512,  International Conference on Information Technology: Coding and Computing,  2002