Modified Filter Based Feature Selection Technique for Dermatology Dataset Using Beetle Swarm Optimization

INTRODUCTION: Skin cancer is an emerging disease all over the world which causes a huge mortality. To detect skin at early stage, computer aided systems designed. The most crucial step in it feature selection process because of its greater impact on classification performance. Various algorithms were designed previously to find relevant features from set attributes. Yet, there arise challenges selecting appropriate datasets related prediction.OBJECTIVES: design hybrid algorithm for subspace dermatology datasets.METHODS: by integrating Latent Semantic Index (LSI) along with correlation-based Feature Selection (CFS). achieve optimal subset, beetle swarm optimization used.RESULTS: Statistical metrics such as accuracy, specificity, recall, F1 score and MCC are calculated.CONCLUSION: accuracy sensitivity value obtained 95% 92%.