P Zhou, P Li, S Zhao, X Wu - IEEE Transactions on Neural …, 2020 - ieeexplore.ieee.org
… of positive interaction and negative interaction, we present a new streaming featureselection method that can guarantee the selected features relevant to the class and interact with …
H Wang, SH Lo, T Zheng, I Hu - Bioinformatics, 2012 - academic.oup.com
… novel featureselection method incorporating variable interaction. … be significantly reduced by considering interactions. Secondly, a … In summary, interaction-based methods may lead to …
L Wang, S Jiang, S Jiang - Expert Systems with Applications, 2021 - Elsevier
… an interactive and relevance-based featureselection method… interactivefeatures, and then put forward a featureselection … basis of measuring feature relevance and featureinteraction. …
J Brank, M Grobelnik, N Milic-Frayling… - Workshop on Text …, 2002 - researchgate.net
… In this paper we explore effects of various featureselection … for featureselection in order to obtain the feature space for … Experiments show that featureselection based on the linear …
… featureselection methods that are computationally efficient, yet sensitive to complex patterns of association, eg interactions, so that informative features … style featureselection algorithms …
X Lin, C Li, W Ren, X Luo, Y Qi - Computational biology and chemistry, 2019 - Elsevier
… feature relevance and featureinteraction to measure the feature importance and proposes a new featureselection algorithm based on interaction gain and the recursive feature …
… In this paper, four filter methods for featureselection are applied over a synthetic data set … regarding the number of features and samples, the level of noise and the interaction between …
… , we find that featureselection based on the labeled training set has little effect. But our experiments on human subjects indicate that human feedback on feature relevance can identify a …