Show simple item record

dc.contributor.advisorMwambi, Henry Godwell.
dc.contributor.advisorOmolo, Bernard.
dc.creatorMohammed, Mohanad Mohammed Adam.
dc.date.accessioned2020-02-14T08:15:57Z
dc.date.available2020-02-14T08:15:57Z
dc.date.created2018
dc.date.issued2018
dc.identifier.urihttps://researchspace.ukzn.ac.za/handle/10413/16920
dc.descriptionMasters Degree. University of KwaZulu-Natal, Pietermaritzburg.en_US
dc.description.abstractCancer is among the leading causes of death in both developed and developing countries. Through gene expression profiling of tumors, the accuracy of cancer classification has been enhanced, leading to correct diagnoses and the application of effective therapies. Here, we discuss a comparative review of the binary class predictive ability of seven classification methods (support vector machines, with the radial basis kernel (SVM(RK)), linear kernel (SVM(LK)) and the polynomial kernel (SVM(PK)), artificial neural networks (ANN), random forests (RF), k-nearest neighbor (KNN), and naive Bayes (NB)), using publicly-available gene expression data from cancer research. Results indicate that NB outperformed the other methods in terms of the accuracy, sensitivity, specificity, kappa coefficient, area under the curve (AUC), and balanced error rate (BER) of the binary classifier. Thus, overall the Naive Bayes (NB) approach turned out to be the best classifier with our datasets.en_US
dc.language.isoenen_US
dc.subject.otherCancer.en_US
dc.subject.otherGene expression.en_US
dc.subject.otherNaive Bayes.en_US
dc.subject.otherTumours.en_US
dc.subject.otherCancer classification.en_US
dc.subject.otherMicroarray data.en_US
dc.titleA comparison of cancer classification methods based on microarray data.en_US
dc.typeThesisen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record