Abstract
Filter-based feature selection methods such as information gain, Gini index, and gain ratio are commonly used in machine learning. It is often assumed that these methods select the most accurate features, but we show this is not true. In this thesis, we study cases when these feature selection metrics and accuracy show “misorderings”: given a pair of features F1 and F2, where F1 has a higher accuracy than F2, the feature selection value is higher for F2 than F1. We first study the frequency of misorderings in randomly-produced synthetic data. Secondly, we study the potential for misordering as two key parameters of the features in a dataset are varied. Finally, we study misorderings in real data and show that misorderings are also prevalent there. Based on our results, we observe that different metrics exhibit different misordering rates, and imposing redundancy-elimination criteria may have the side effect of reducing misordering.
ABSTRACT
Invitro determination of bacteriocidal...
ABSTRACT
The study examined teenage pregnancy and the awareness of dangers of teenage pregnancy employed by Tee...
Abstract
This study is on the impact of Nigeria pidgin on the written on English of senior secondary school students. Th...
ABSTRACT
This Is a study on problems of retirement in the enugu state civil service: a case study of Enugu State Univers...
Statement of Problem
Th...
Background of the study
Nigeria's foreign policy, like that of most other countries, has had achiev...
ABSTRACT
THE IMPACT OF COST-BENEFIT ANALYSIS ON BUSINESS STRATEGIES
This study investigates the impact of cost-benefit analysis...
Abstract
This study is on the assessment of SIWES relevance to business education programme objectives. The total popula...
ABSTRACT The uptake of phenol from simulated aqueous solution using agricultural wastes as adsorbents is the focus of this research work. The agric...
BACKGROUND OF THE STUDY
Housing has been widely regarded as one of the most basic requirements of human life and is a si...