Optimized Support Vector Machine using Sparrow Search Optimization for Osteoporosis Disease Diagnosis

Osteoporosis might potentially reduce fracture risk and enhance quality of life if detected early. A prominent intelligence technique for diagnosing osteoporosis is support vector machines (SVMs), and choosing the right SVM parameter is essential for precise model classification. This research study optimizes the kernel function parameter and penalty factor of SVM using the new and extremely efficient sparrow search algorithm (SSA) based on partial opposition-based learning (POBL) called POSSA called POSSA-SVM osteoporosis disease detection model. In comparison to the variants and conventional models, experiments demonstrate that the POSSA-SVM diagnostic model efficiently increases the accuracy of osteoporosis disease diagnosis. It also claims a strong optimization ability and a rapid convergence time.