Unsupervised probabilistic feature selection using ant colony optimization

Feature Selection with a Local Search Strategy Based on the Forest Optimization Algorithm

“…While choosing features, it will consider the classification performance. Differently, on the other hand, UPFS [Dadaneh, Markid and Zakerolhosseini (2016)] and ANFS [Luo, Nie, Chang et al (2018)] are belong to unsupervised method. The labels of the dataset are masked while using these two methods.…”

“…Hou et al first combined the embedding learning and feature ranking together, and proposed joint embedding learning and sparse regression (JELSR) to perform feature selection [Hou, Nie, Li et al (2014)]. Dadaneh proposed unsupervised probabilistic feature selection using ant colony optimization (UPFS) [Dadaneh, Markid and Zakerolhosseini (2016)]. They utilized the inter-feature information that showed the similarity between the features that led the algorithm to decreased redundancy in the final set.…”

“…At the same time, our algorithm is compared with other feature selection methods. It includes feature selection using forest optimization algorithm based on contribution degree(FSFOACD) [Ma, Jia, Zhou et al (2018)], feature selection based on ant colony optimization unsupervised probability algorithm (UPFS) [Dadaneh, Markid and Zakerolhosseini (2016)], feature selection based on supervised rough sets (ANFS) [Luo, Nie, Chang et al (2018)] and the feature selection of a novel initialization and update mechanism of particle swarm optimization (PSO(4-2)) [Tran, Xue and Zhang (2014b)].…”

“…In order to verifying the effectiveness of our algorithm, 10 widely-used datasets from UCI are selected and three classifiers respectively from support vector machine (SVM) [Aburomman and Reaz (2016)], decision tree (DT) [Shirani, Habibi, Besalatpour et al (2015)] and k-nearest neighbor (KNN) [Benmahamed, Teguar and Boubakeur (2018)]. There are 4 feature selection methods are selected for comparison, including UPFS [Dadaneh, Markid and Zakerolhosseini (2016)], ANFS [Luo, Nie, Chang et al (2018)], PSO(4-2) [Tran, Xue and Zhang (2014b)] and FSFOACD [Ma, Jia, Zhou et al (2018)]. The experiments show that most of the results are superior to previous feature selection algorithms we selected.…”

Cluster Based Symbolic Representation for Skewed Text Categorization

“…A number of works can be traced in recent years addressing the problem of text classification through feature selection. Feature selection algorithms such as chisquare, information gain, and mutual information (Yang and Pedersen., 1997) though seem to be powerful techniques for text data, a number of novel feature selection algorithms based on genetic algorithm (Bharti and Singh., 2016;Ghareb et al, 2016), ant colony optimization (Dadaneh et al, 2016;Moradi and Gholampour., 2016;Uysal., 2016;Meena et al, 2012), Bayesian principle Zhang et al, 2016;Feng et al, 2012;Fenga et al, 2015;Sarkar et al, 2014), clustering of features (Bharti and Singh., 2015), global information gain (Shang et al, 2013), adaptive keyword (Tasci and Gungor., 2013), global ranking (Pinheiro et al, 2012;Pinheiro et al, 2015) are proposed.…”