Browsing Natural and Agricultural Sciences by Supervisor "Kanfer, F.H.J. (Frans)"

Browsing Natural and Agricultural Sciences by Supervisor "Kanfer, F.H.J. (Frans)"

Sort by: Order: Results:

  • A spatial variant of the Gaussian mixture of regressions model 
    Delport, Marion (University of Pretoria, 2017)
    In this study the nite mixture of multivariate Gaussian distributions is discussed in detail including the derivation of maximum likelihood estimators, a discussion on identi ability of mixture components as well as a ...
  • Adaboost and its application using classification trees 
    Vithal, Nishay (University of Pretoria, 2013)
    This mini-dissertation seeks to provide the reader with an understanding of one of the most popular boosting methods in use today called Adaboost and its first extension Adaboost.M1. Boosting, as the name suggests, is an ...
  • Clustering time-course data using P-splines and mixed effects mixture models 
    Bredenkamp, Deidre (University of Pretoria, 2022)
    In the field of biology, gene expressions are evaluated over time to study complicated biological processes and genetic supervisory networks. Because the process is continuous, time-course gene-expression data may ...
  • Data Compression and Quantization 
    Du Toit, Benjamin David (University of Pretoria, 2014)
    Data Compression Due to limitations in data storage and bandwidth, data of all types has often required compression. This need has spawned many different methods of compressing data. In certain situations the fidelity of ...
  • LASSO - simultaneous shrinkage and selection via the L1 norm 
    Kirkland, Lisa-Ann (University of Pretoria, 2014)
    Two major purposes of regression models are explanation and prediction of scientific phenomena. Explanation is obtained by producing interpretable models through variable selection, while prediction accuracy is optimised ...
  • Minimum sample size for estimating the Bayes error at a predetermined level 
    Potgieter, Ryno (University of Pretoria, 2013)
    Determining the correct sample size is of utmost importance in study design. Large samples yield classifiers or parameters with more precision and conversely, samples that are too small yield unreliable results. Fixed ...
  • A mixed model approach to conjoint analysis 
    Cronje, Tanita (University of Pretoria, 2014-05)
    In this decision-driven era, it has become vital for modelers to efficiently model consumer choices and preferences (from a marketing perspective for instance). Conjoint analysis is a known method which has been used to ...
  • Penalized feature selection in model-based clustering 
    Potgieter, Luandrie (University of Pretoria, 2022)
    Cluster analysis is a popular unsupervised statistical method used to group observations into clusters. Identifying latent segments and groupings in the data aids in the understanding of natural phenomena. The data driven ...
  • Robust mixture regression using mean-shift penalisation 
    Wessels, Anika (University of Pretoria, 2021)
    The purpose of finite mixture regression (FMR) is to model the relationship between a response and feature variables in the presence of latent groups in the population. The different regression structures are quantified ...
  • Robust parameter estimation of finite mixture models with self-paced learning 
    Kleynhans, Andre Ruben (University of Pretoria, 2022)
    Self-paced learning (SPL) is a training strategy that mitigates the impact of non-typical observations. SPL introduces observations in a meaningful order by considering the likelihood for each observation. The proposed ...
  • Semi-parametric mixtures of partially linear models 
    Du Randt, Ruan Jean (University of Pretoria, 2022)
    This mini-dissertation considers semi-parametric finite mixtures of partially linear models with Gaussian errors and focuses on the estimation procedure for such models. The semi-parametric structure allows for flexible ...
  • Semi-parametric mixtures of quantile regressions 
    Gouws, Divan (University of Pretoria, 2023)
    Mixtures of quantile regressions are explored through the lens of a kernel density based EM-type algorithm and a newly proposed CEM-type algorithm. This allows the simultaneous clustering and modeling of conditional ...
  • Structuring of breeding objectives in the pork supply chain in South Africa 
    Visser, Daniel Pieter (University of Pretoria, 2006-01-14)
    Pig production is a techno-scientific internationalized business that is continuously exposed to change and risk. Changes in the Agri-Business are inter alia caused by changes in globalization, information technology, ...
  • The Suitability of test-day models for genetic evaluation of dairy cattle in South Africa 
    Mostert, Bernice Euodia (University of Pretoria, 2007-05-30)
    In this study the possibility to change to test-day models for genetic evaluation of production traits and somatic cell score of South African dairy breeds (i.e. Ayrshires, Guernseys, Holsteins and Jerseys) was investigated. ...