Binary Sand Cat Swarm Optimization Algorithm for Wrapper Feature Selection on Biological Data

In large datasets, irrelevant, redundant, and noisy attributes are often present. These can have a negative impact on the classification model accuracy. Therefore, feature selection is an effective pre-processing step intended to enhance performance by choosing small number of relevant or significant features. It important note that due NP-hard characteristics selection, search agent become trapped in local optima, which extremely costly terms time complexity. To solve these problems, efficient global method needed. Sand cat swarm optimization (SCSO) newly introduced metaheuristic algorithm solves algorithms. Nevertheless, SCSO recommended for continuous problems. bSCSO binary version proposed here analysis solution discrete problems such as wrapper biological data. was evaluated ten well-known datasets determine effectiveness algorithm. Moreover, compared four recent algorithms had better efficiency. A findings demonstrated superiority approach both high prediction accuracy sizes.