Feature subset selection Filter–Wrapper based on low quality data

Integration of graph clustering with ant colony optimization for feature selection

“…Dimensionality reduction methods provide a way of understanding the data better, improving prediction performance and reducing the computation time in pattern recognition applications. As a general rule, for a classification problem with D dimensions and C classes, a minimum of 10 Â D Â C training samples are required [9]. While it is practically impossible to acquire the required number of training samples, reducing features reduces the size of the training sample required and consequently helps to improve the overall performance of the classification algorithm.…”

A graph theoretic approach for unsupervised feature selection

“…Accordingly machine learning methods often deal with samples consisting of thousands of features. In high-dimensional data, typically many features are irrelevant and/or redundant for a given learning task, having harmful consequences in terms of performance and/or computational cost (Cadenas et al, 2013;MonirulKabir et al, 2011;Unler et al, 2011). Moreover, a large number of features require a large storage space.…”

“…The feature selection methods can be classified into four categories including filter, wrapper, embedded, and hybrid models (Cadenas et al, 2013;Hu et al, 2015;Saeys et al, 2007;Song et al, 2013). In the filter-based methods each feature is ranked without consideration of any learning algorithms based on its discriminating power between different classes.…”

Handling Sparse Data Sets by Applying Contrast Set Mining in Feature Selection

“…If the data are not normally distributed, an exponential relationship between d and N will be assumed and the number of samples that are required may be as plentiful as: (5) where D steps is the discrete number of steps per feature. The next step is to quantify if the number of samples is sufficient to model the data accurately by defining a ratio between the actual number of samples and the minimum number of samples that are required.…”

“…Main idea of feature selection is to choose a subset of features by eliminating those with little predictive information. Benefits of feature selection include reducing dimensionality, removing irrelevant and redundant features, facilitating data understanding, reducing the amount of data for learning, improving predictive accuracy of algorithms, and increasing interpretability of models [2]- [5]. In this study, a contrast set mining based feature selection techniques are proposed.…”