Classification of Imbalanced leukocytes Dataset using ANN-based Deep Learning

Nowadays, classification of imbalanced data is a major challenge in the machine learning (ML) algorithms, especially medical analysis, In this paper, deep algorithm which advance artificial neural network (ANN) used for classifying five white blood cells (WBCs). Different preprocessing image techniques and algorithms are applied to isolate WBCs segment nucleus cytoplasm. Geometric, statistical color features extracted, principal component analysis technique select optimal features. The process has been repeated several times tune parameters find best pattrens match through training until achieve accuracy. Multi-class results show high accuracy more than 94% types WBCs. We evaluate model using geometric mean, Cohen's Kappa, Receiver operating characteristic curve, Root mean squared error, relative absolute error cross-validation techniques. achieves can conduct multi-class datasets terms above-mentioned metrics.