Type-1 diabetes risk prediction using multiple kernel learning
Department of Computer Science
Master of Science
Roshan, Usman W.
Wang, Jason T. L.
Diabetes risk prediction
Multiple kernal learning
This thesis presents an analysis of multiple kernel learning (MKL) for type-1 diabetes risk prediction. MKL combines different models and representation of data to find a linear combination of these representations of the data. MKL has been successfully been implemented in image detection, splice site detection, ribosomal and membrane protein prediction, etc. In this thesis, this method was applied for Genome-wide association study (GWAS) for classifying cases and controls.
This thesis has shown that combined kernel does not perform better than the individual kernels and that MKL does not select the best model for this problem. Also, the effect of normalization on MKL as well as risk prediction has also been analyzed.
njit-etd2010-054 (41 pages ~ 1,383 KB pdf)
Please complete this Feedback Form to inform us about your experience using this website. It will assist us in better serving your information needs in the future. Thank You!
Created December 5, 2011