WestminsterResearch

A machine learning investigation of a beta-carotenoid dataset

Revett, Kenneth (2008) A machine learning investigation of a beta-carotenoid dataset. In: Bello, R. and Falcón, R. and Pedrycz, W. and Kacprzyk, J., (eds.) Granular computing: at the junction of rough sets and fuzzy sets. Studies in fuzziness and soft computing (224). Springer, Berlin / Heidelberg, pp. 211-227. ISBN 9783540769729

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1007/978-3-540-76973-6_14

Abstract

Numerous reports have implicated a diet and/or conditions where levels of carotene/retinol are below minimal daily requirements may pre-dispose individuals to an increased susceptibility to various types of cancer. This study investigates dietary and other factors that may influence plasma levels of these anti-oxidants. A rough sets approach is employed on a clinical dataset to determine the attributes and their values are associated with plamsa levels of carotene/retinol. The resulting classifier produced an accuracy of approximately 90% for both beta-carotene and retinol. The results from this study indicate that age, smoking, and dietary intake of these endogenous anti-oxidants is predictive of plasma levels.

Item Type:Book Section
Research Community:University of Westminster > Electronics and Computer Science, School of
ID Code:7195
Deposited On:12 Jan 2010 14:39
Last Modified:12 Jan 2010 14:39

Repository Staff Only: item control page