TY  - EJOU
AU  - Jawarneh, Sana 

TI  - Enhanced Arithmetic Optimization Algorithm Guided by a Local Search for the Feature Selection Problem
T2  - Intelligent Automation \& Soft Computing

PY  - 2024
VL  - 39
IS  - 3
SN  - 2326-005X

AB  - High-dimensional datasets present significant challenges for classification tasks. Dimensionality reduction, a crucial aspect of data preprocessing, has gained substantial attention due to its ability to improve classification performance. However, identifying the optimal features within high-dimensional datasets remains a computationally demanding task, necessitating the use of efficient algorithms. This paper introduces the Arithmetic Optimization Algorithm (AOA), a novel approach for finding the optimal feature subset. AOA is specifically modified to address feature selection problems based on a transfer function. Additionally, two enhancements are incorporated into the AOA algorithm to overcome limitations such as limited precision, slow convergence, and susceptibility to local optima. The first enhancement proposes a new method for selecting solutions to be improved during the search process. This method effectively improves the original algorithm’s accuracy and convergence speed. The second enhancement introduces a local search with neighborhood strategies (AOA_NBH) during the AOA exploitation phase. AOA_NBH explores the vast search space, aiding the algorithm in escaping local optima. Our results demonstrate that incorporating neighborhood methods enhances the output and achieves significant improvement over state-of-the-art methods.
KW  - Arithmetic optimization algorithm; classification; feature selection problem; optimization

DO  - 10.32604/iasc.2024.047126