DSpace
 

KNUSTSpace >
Theses / Dissertations >
College of Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/8561

Title: A multigene genetic programming model for thyroid disorder detection
Authors: Oheneba-Osei, Nyame Fidelis
Issue Date: 8-Apr-2016
Abstract: Two common diseases of the thyroid gland, which releases thyroid hormones for regulating the rate of the bodys metabolism, are hyperthyroidism and hypothyroidism. The classi cation of these thyroid diseases is one of the considerable tasks. Before a patient is classi ed as being normal (thyroid gland is functioning well) or su ering from hyperthyroidism or hypothyroidism, there are a lot of information and tests conducted on the patient by existing models and these are costly in terms of time and money. This research is conducted to enhance the detection of thyroid disorder based on attributes collected from patients. A mathematical model is developed using Multigene Symbolic Regression Genetic Programming technique. A statistical test is conducted to ascertain the goodness of t of the model. The test result showed that the model is good and is even able to reduce the number of attributes used to classify a patient as Normal, Hyperthyroidism and Hypothyroidism.
Description: A project report submitted to the Department Of Mathematics, Kwame Nkrumah University of Science and Technology, Kumasi, in partial fulfillment of the requirements for the degree of Master of Philosophy In Applied Mathematics, 2015
URI: http://hdl.handle.net/123456789/8561
Appears in Collections:College of Science

Files in This Item:

File Description SizeFormat
thesis.pdf1.4 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback