Document Type : Research Paper

Authors

• Negin Bagherpour ¹
• Behrang Ebrahimi ²

¹ Department of Engineering Sciences, University of Tehran

² University Of Tehran

Abstract

Feature selection is a critical step in machine learning, especially when dealing with high-dimensional and incomplete data. Traditional methods often struggle with missing values, which are common in real-world applications. This paper introduces Neural Network Feature Selection (NNFS), a novel deep learning-based approach that effectively identifies important features even in the presence of missing data. We provide a variety of comparisons to evaluate the suggested algorithm over existing methods. We demonstrate the accuracy, speed and sensitivity to missed data. According to numerical results, the proposed algorithm outperforms existing methods especially for medium size datasets. Both random and real tests are presented to make the results more realistic.

Keywords

• feature selection
• high dimension
• medium dimension
• incomplete data
• neural network