If you use the matlab code here, please cite our paper below: References: Jie Gui, Zhenan Sun, Shuiwang Ji, DachengTao, Tieniu Tan, "Feature Selection Based on Structured Sparsity: AComprehensive Study", IEEE Transactions on Neural Networks and Learning Systems, 2017. J. Gui, P. Li, "Multi-View Feature Selection for Heterogeneous Face Recognition", IEEE International Conference on Data Mining (ICDM, 11.08% acceptance rate), 2018.

ATTN: This package is free for academic usage. You can run it at your own risk. For other purposes, please contact Jie Gui(guijie@ustc.edu).

Feature Selection Toolbox

Introduction

This repository contains a collection of MATLAB implementations for various feature selection algorithms. These algorithms are designed to help in selecting the most relevant features from high-dimensional datasets, which is a crucial step in machine learning and data mining tasks. The implementations are based on research papers and aim to provide efficient and effective solutions for feature selection problems.

Features

• Multiple feature selection algorithms implemented in MATLAB
• Code structure that facilitates easy integration into existing MATLAB projects
• Documentation and references for understanding the underlying methodologies
• Academic usage focus with proper citation guidelines

Getting Started

Prerequisites

• MATLAB installed on your system (the package was developed with MATLAB)
• Basic understanding of MATLAB scripting and data structures
• Knowledge of feature selection concepts and machine learning fundamentals

Installation

1. Clone this repository to your local machine:

   git clone https://github.com/Tarasom123/Feature-selection.git
   

2. Open MATLAB and navigate to the project directory.

Usage

1. Choose the feature selection algorithm that suits your problem based on the documentation and references provided.
2. Prepare your dataset in a format compatible with the selected algorithm.
3. Run the corresponding MATLAB script or function for the chosen algorithm.
4. Analyze the selected features and integrate them into your machine learning pipeline.

File Structure

• MATLAB implementation files for different feature selection algorithms
• Documentation and reference files
• Example datasets and usage demonstrations

License

This package is free for academic usage. You can run it at your own risk. For other purposes, please contact Jie Gui (guijie@ustc.edu).

References

If you use the MATLAB code in this repository, please cite the following papers:

• Jie Gui, Zhenan Sun, Shuiwang Ji, Dacheng Tao, Tieniu Tan, "Feature Selection Based on Structured Sparsity: A Comprehensive Study", IEEE Transactions on Neural Networks and Learning Systems, 2017.
• J. Gui, P. Li, "Multi-View Feature Selection for Heterogeneous Face Recognition", IEEE International Conference on Data Mining (ICDM, 11.08% acceptance rate), 2018

Acknowledgments

• The authors of the research papers on which these implementations are based
• The open-source community for providing valuable tools and resources
• Contributors and collaborators who helped in developing and testing these feature selection algorithms