Hybrid salp swarm and grey wolf optimizer algorithm based ensemble approach for breast cancer diagnosis

In the world, cancer is listed as the second leading cause of death. Breast cancer is one of the types that affects women more often than men, and because it has a high mortality rate, the early detection for breast cancer is crucial. The demand for early breast cancer diagnosis and detection has led to a number of creative research avenues in recent years. But even if artificial intelligence techniques have improved in precision, their exactness still has to be increased to allow for their inevitable implementation in practical applications. This paper provides a Salp Swarm and Grey Wolf Optimization-based technique for diagnosing breast cancer that is inspired by nature. Data analysis for breast cancer was done using both SVM and KNN algorithms. For the purpose of diagnosis, we made use of the Wisconsin Breast Cancer Dataset (WBCD). The study also describes the proposed model's actual implementation in the field of computational biology, together with its characteristics, assessments, evaluations, and conclusions. Specificity, precision, F1-score, recall, and accuracy were some of the metrics used to evaluate how well the approach in question performed. When used on the WBCD-dataset, the proposed SSA-GWO model had an accuracy of 99.42%. The outcomes of the actual applications demonstrate the suggested hybrid algorithm's applicability to difficult situations involving unidentified search spaces.