DCGAN for Handling Imbalanced Malaria Dataset based on Over-Sampling Technique and using CNN

Class imbalance problem as a significant research problem has been recognized in classification In recent years, where by using the number of approach to rebalancing distributions of class such as; under-sampling or over-sampling for learning datasets to improve accuracy of classification, that give good performance. Many algorithms have been developed for classification, such as Back Propagation (BP) neural networks, decision tree, Bayesian networks etc., and have been used repeatedly in many fields. In this paper, to rebalancing distributions of class for imbalanced Malaria dataset to detect infected and uninfected people by equal percentage we proposed approach Deep Convolutional Generative Adversarial Network (DCGAN) based on the O.S. technique, which are generate the synthetic samples for the minority class for imbalanced Malaria dataset and achieve a balance ratio between classes of majority and minority 100% for imbalanced Malaria dataset. As well as used Deep Learning, applied by using Convolutional Neural Network (CNN). The goal of CNN is to prove the validity of the proposed approach by firstly, will be train the imbalanced Malaria dataset and results are tested before using proposed approach. Secondly, will be training balanced Malaria dataset and results are tested after using proposed approach and comparison between them.