Automated White Blood Cell Disease Recognition Using Lightweight Deep Learning

White blood cells (WBC) are immune system cells, which is why they also known as cells. They protect the human body from a variety of dangerous diseases and outside invaders. The majority WBCs come red bone marrow, although some other important organs in body. Because manual diagnosis disorders difficult, it necessary to design computerized technique. Researchers have introduced various automated strategies recent years, but still face several obstacles, such imbalanced datasets, incorrect feature selection, deep model selection. We proposed an learning approach for classifying white this paper. data augmentation initially used increase size dataset. Then, Darknet-53 pre-trained fine-tuned according nature chosen On model, transfer used, features engineering done on global average pooling layer. retrieved characteristics subsequently improved with specified number iterations using hybrid reformed binary grey wolf optimization Following that, machine classifiers classify selected best final classification. experiment was carried out dataset increased imaging resulted accuracy over 99%.