Addax Optimization Algorithm with Convolutional Neural Network for Rheumatoid Arthritis classification

The Rheumatoid Arthritis (RA) is a very common autoimmune disease that causes significant morbidity and mortality, therefore early diagnosis treatment is important. The RA is an autoimmune illness that affects the musculoskeletal system causing systemic, inflammatory and chronic effects, it becomes decreases physical function causing articular damage and fatigue. This paper proposed Addax Optimization Algorithm (AOA) with Convolutional Neural Network (CNN) for classification, which is efficiently achieve better accuracy. Initially data obtained from the RA dataset and pre-processing involved the min-max normalization is uniformly the feature vector. The combination of AOA is designed to optimize hyper parameters efficiently which is significantly reduce the high dimensionality and better accuracy in classifying of RA. The classification utilized CNN technique capturing complex patterns in image data effective for analysis the RA image and adaptive approach helps to find the best solution by using optimization approach. The performance of proposed method is evaluated with various metrics such as accuracy, precision, recall and $\mathbf{f 1}$-score metrics on RA dataset.