Show simple item record

dc.contributor.authorDriscoll, Sonny
dc.date.accessioned2017-08-17T10:57:33Z
dc.date.available2017-08-17T10:57:33Z
dc.date.issued2017-04
dc.identifier.urihttp://hdl.handle.net/10369/8743
dc.description.abstractThe research contained in this paper consists of the full analysis of various machine learning techniques and their underlying algorithmic and mathematical principles. Further discussed is both the optimisation of the algorithms and their application to datasets. The technical development aspect of this paper consists of the application of Python programming scripts to dynamically prepare a genome DNA dataset from an opportunistic pathogen organism, the “Pseudomonas aeruginosa ”. Results are derived from further Python technical development by creating Decision Trees, Random Forests, Neural Networks and Support Vector Machines, to analyse the newly created datasets. Accuracies and detailed metrics are then further analysed and prepared. Further improvements and a basis for further research is then recommended based on the experience acquired from the conduction of the experiments contained in this paper.en_US
dc.language.isoenen_US
dc.publisherCardiff Metropolitan Universityen_US
dc.subjectDNA genome sequence, machine learning techniques, algorithmic, mathematical principles, datasets, Python, pathogen organism, Pseudomonas aeruginosaen_US
dc.titlePredicting the next character in a DNA genome sequence using data analysis and machine learning techniquesen_US
dc.typeDissertationen_US
rioxxterms.versionAOen_US


Files in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record