Paweł Teisseyre

TL;DR: Novel DNA models for prediction offreckles that can be used in forensic investigations are presented and significance of pigmentation genes and sex in predictive DNA analysis of freckles is emphasized.

TL;DR: Numerical experiments indicate that the proposed random subset method with a new weighting scheme behaves promisingly when its prediction errors are compared with errors of penalty-based methods such as the lasso and it has much smaller false discovery rate than the other methods considered.

TL;DR: An algorithm CCnet is proposed which is a combination of classifier chains and elastic-net regularization and it is shown that the feature selection is stable with respect to the order of fitting the models in the chain.

TL;DR: An experimental framework in which the features are observed with measurement errors and the costs depend on the quality of the features, which can be recommended in a situation when one wants to balance low costs and high prediction performance.

TL;DR: This work proposes stopping rules which are based on distribution of approximation of conditional mutual information given that all relevant features have been already selected and shows that the distribution is approximately chi square with appropriate number of degrees of freedom provided features are discretized into moderate number of bins.