A hybrid particle swarm optimization with multi-objective clustering for dermatologic diseases diagnosis

Abstract Effective and personalized treatment relies heavily on skin disease categorization. In the stratification of disorders, it is crucial to identify subtypes illnesses provide an efficient therapy. To attain this aim, researchers have focused their attention cluster algorithms for disorders in recent decades. But, real-world drawbacks, including experimental noises, a large number dimensions, poor ability comprehend. Cluster algorithms, particular, determine quality clusters using single internal evaluation operation majority cases. A assessment procedure difficult design robust all datasets, which problem. The multi-objective particle swarm obtained high sensitivity existing work, but not able anticipate kinds classes. An optimized distance parameter K -means clustering determined hybrid moth flame optimization. Multi-objective guided by two value indices, misclassification rate neural network classification rate. Hybrid PSO will solve problem optimal clustering. On dermatological dataset from UCI repository, MATLAB R2020a be used evaluate proposed method. This followed method’s performance indices.