Skip to content

fafsari/IVI_FuzzyKNN-Imbalanced

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 

Repository files navigation

Interval-Valued Fuzzy and Intuitionistic Fuzzy K-Nearest Neighbor (IVF-IFKNN) for Imbalanced Data Classification

This repository contains the implementation of the methods presented in the paper:
Interval–valued fuzzy and intuitionistic fuzzy–KNN for imbalanced data classification by Saeed Zeraatkar and Fatemeh Afsari.

Published in Expert Systems with Applications, this paper introduces advanced fuzzy-based approaches for effectively classifying imbalanced datasets, leveraging interval-valued and intuitionistic fuzzy K-Nearest Neighbor (IVF-IFKNN) methods.


Features

  • Interval-Valued Fuzzy KNN (IVF-KNN): Enhances the traditional KNN algorithm with interval-valued fuzzy logic to improve classification performance in imbalanced datasets.
  • Intuitionistic Fuzzy KNN (IF-KNN): Incorporates intuitionistic fuzzy sets to manage uncertainty and imprecision effectively.
  • Imbalance Handling: Tailored to mitigate the effects of class imbalance, improving average AUC.

Repository Structure

  • src/: Contains the main implementation of IVF-KNN and IF-KNN methods.
  • data/: Example datasets used for testing and evaluation.
  • results/: Output files and performance metrics from experiments.
  • README.md: This file.

Installation

To run the code, ensure you have the following installed:

  • Python 3.8 or later
  • Required Python libraries (install via requirements.txt):
    pip install -r requirements.txt  

Usage

  1. Clone the Repository

    git clone https://github.com/fafsari/IVI_FuzzyKNN-Imbalanced.git  
    cd IVI_FuzzyKNN-Imbalanced 
  2. Prepare Your Dataset
    Add your dataset in the data/ directory. Ensure it is in a compatible format (e.g., CSV).

  3. Run the Algorithm

    python src/run_main.py   

Results

The proposed IVF-IFKNN methods demonstrate superior performance over traditional KNN on benchmark datasets, particularly in handling class imbalance. For detailed results, refer to the results/ directory or the published paper.


Citation

If you use this repository in your research, please cite the original paper:

@article{saeed2021interval,
  title={Interval-valued fuzzy and intuitionistic fuzzy-KNN for imbalanced data classification [J]},
  author={Saeed, Zeraatkar and Fatemeh, Afsari},
  journal={Expert Systems With Applications},
  volume={2021},
  number={184},
  year={2021}
}  

Acknowledgments

This repository is maintained by the corresponding author of the paper. Special thanks to the open-source community for providing tools and libraries that supported the implementation and experiments.


License

This code is licensed under the MIT License.


About

SMOTE-IPF based on Interval-valued Intuitionistic Fuzzy KNN

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages