|Chapter title||A machine learning investigation of a beta-carotenoid dataset|
|Editors||Bello, R., Falcón, R., Pedrycz, W. and Kacprzyk, J.|
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.
|Book title||Granular computing: at the junction of rough sets and fuzzy sets|
|Place of publication||Berlin / Heidelberg|
|Series||Studies in fuzziness and soft computing|
|Digital Object Identifier (DOI)||https://doi.org/10.1007/978-3-540-76973-6_14|
|Journal citation||(224), pp. 211-227|