Grey wolf optimization and enhanced stochastic fractal search algorithm for exoplanet detection

Detection of Exoplanet had been an ‘intensely active’ exploration area within Astronomy where several attempts are made. In the proposed research work, exoplanet detection was done using a Kepler Dataset. Data pre-processing was carried out through Mean Imputation which was found to be the most common procedure of replacing missing value. For assessing Imputation Method’s performance, Normalized Root Mean Square Error was calculated. In feature selection method, a novel combination of Grey Wolf Optimizer (GWO) based on Enhanced Stochastic Fractal Search Algorithm (ESFSA) had been utilized, in a more advanced manner, for reducing the number of normalized input values to those which were highly beneficial. Lastly, after finding the best optimum values and delivering them to Random Forest (RF), the exoplanet got classified into 3 categories—False Positive, Not Detected as well as Candidate. The research work also showed the quantitative analysis of proposed GWO-based ESFSA with other feature selection methods and RF classifier with other existing classifiers. Overall comparative analysis of the proposed method with other related works (present in the literature) was also carried out. As observed, GWO-based ESFSA provided outstanding results—99.74% of recall, 99.80% of specificity, 99.81% of accuracy, 99.98% of sensitivity, 98.84% of precision and 97.21% of F1-score, and proved its superiority over existing methods. © 2023, The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature.