Authors: Melvin Mokhtari, Alireza Basiri
Published in: Expert Systems with Applications, September 2024
Paper can be found:
Code and data can also be accessed:
- Locally in this GitHub repository
Rule OPtimized Aggregation Classifier (ROPAC) is a novel rule-based classifier that is introduced in two variants, ROPAC-L and ROPAC-M, to expand search space exploration and achieve better classification accuracy. This algorithm was evaluated on 50 diverse datasets, comparing accuracy with 15 famous algorithms, including ForestPA, LMT, MLP of Neural Networks, Random Forest, Optimized Forest, SPAARC, RACER, Bootstrap Aggregation (Bagging), C4.5, PART, the JRip implementation of RIPPER, SMO in SVM, Decision Tree (CART), IBk implementation of KNN, and Naïve Bayes. The experiments confirmed ROPAC-L as the most accurate, leading classifier.
If you found this work helpful, please star🌟 this repository and cite📑 our paper. Thank you for your support!
Mokhtari, M., & Basiri, A. (2024). ROPAC: Rule OPtimized Aggregation Classifier. Expert Systems with Applications, 123897.
@Article{Mokhtari2024,
author = {Mokhtari, Melvin and Basiri, Alireza},
title = {ROPAC: Rule OPtimized Aggregation Classifier},
year = {2024},
month = {9},
day = {15},
journal = {Expert Systems with Applications},
volume = {250},
doi = {https://doi.org/10.1016/j.eswa.2024.123897},
url = {https://www.sciencedirect.com/science/article/pii/S0957417424007632},
publisher = {Elsevier Ltd},
issn = {09574174},
coden = {ESAPE},
language = {English},
abbrev_source_title = {Expert Sys Appl},
type = {Article}
}If you have any questions about this repository, wish to request a feature or make a contribution, please open a GitHub issue, or feel free to contact melvmok@gmail.com.