Feature selection and pattern recognition for different types of skin disease in human body using the rough set method

Disease analysis is one of the applications of data mining. The rough set is knowledge and information based method to help human decision-making, learning, and activity. Many researchers have put forward their findings in the study of skin diseases, but the feature selection and the pattern recognition of different types of skin disease by taking a standard set of the large platform (taking as parameters) have not been seen yet using the rough set method. We use histopathological skin data samples to exhibits strategy for multi-source, multi-methodology, and multi-scale data frameworks. This realistic evaluation strategy shows that the system performance accuracy of the pattern for six types of skin disease (psoriasis, Seborrhoeic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris) is 96.62% in the rough set method. Therefore, in this paper, we deal with the feature selection and pattern recognition for different types of skin disease in uncertain conditions through information knowledge and data-intensive computer-based solutions using the rough set.