Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer

Feature selection is critical in fields like data mining and pattern classification, as it eliminates irrelevant data and enhances the quality of highly dimensional datasets. This study explores the effectiveness of the Q-learning embedded sine cosine algorithm (QLESCA) for feature selection in industrial casting defect detection using the VGG19 model. QLESCA’s performance is compared to other optimization algorithms, with experimental results showing that QLESCA outperforms the other algorithms in terms of classification metrics. The best accuracy achieved by QLESCA is 97.0359%, with an average fitness value of − 0.99124. The proposed method provides a promising approach to improve the accuracy and reliability of industrial casting defect detection systems, which is essential for product quality and safety. Our findings suggest that using powerful optimization algorithms like QLESCA is crucial for obtaining the best subsets of information in feature selection and achieving optimal performance in classification tasks.