Doctoral Degrees (Computer Science)

Permanent URI for this collection

https://scholar.sun.ac.za/handle/10019.1/96338

Browse

Browsing Doctoral Degrees (Computer Science) by browse.metadata.advisor "Malan, Katherine Mary"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Landscape aware algorithm selection for feature selection
    (Stellenbosch : Stellenbosch University, 2023-10) Mostert, Werner; Engelbrecht, Andries Petrus; Malan, Katherine Mary; Stellenbosch University. Faculty of Science. Dept. of Mathematical Sciences. Computer Science Division.
    ENGLISH ABSTRACT: Feature selection is commonly applied as a pre-processing technique for machine learning to reduce the dimensionality of a problem by removing redundant and irrelevant features. Another desirable outcome of feature selection lies in the potential performance improvement of predictive models. The development of new feature selection algorithms are common within the field, however, relatively little research has historically been done to better understand the feature selection problem from a theoretical perspective. Researchers and practitioners in the field often rely on a trial-and-error strategy to decide on which feature selection algorithm to use for a specific instance of a machine learning problem. This thesis contributes towards a better understanding of the complex feature selection problem by investigating the link between feature selection problem characteristics and the performance of feature selection algorithms. A variety of fitness landscape analysis techniques are used to gain insights into the structure of the feature selection fitness landscape. Performance complementarity for feature selection algorithms is empirically shown, emphasising the potential value of automated algorithm selection for feature selection algorithms. Towards the realisation of a landscape aware algorithm selector for feature selection, a novel performance metric for feature selection algorithms is presented. The baseline fitness improvement (BFI) performance metric is unbiased and can be used for comparative analysis across feature selection problem instances. The insights obtained via landscape analysis are used with other meta-features of datasets and the BFI performance measure to develop a new landscape aware algorithm selector for feature selection. The landscape aware algorithm selector provides a human-interpretable predictive model of the best feature selection algorithm for a specific dataset and classification problem.