Multi-class Classification of Imbalanced Intelligent Data using Deep Neural Network

Abstract

In recent years, studies in the field of deep learning have made significant progress. These studies have focusedmore on datasets with balanced classification, and less research has been done on imbalanced datasets, whichare of great importance in the real world and present significant challenges for classification. This articlestudies the problem of classifying imbalanced data, introduces dynamic sampling for deep neural networks,investigates the imbalanced multiclass problem, and proposes a dynamic sampling method for deep learning.In our proposed method, all samples are fed to the current deep neural network for each training iteration,and the accuracy, precision, and mean error of the deep neural network are estimated. The proposed methoddynamically selects informative data for training the deep neural network. Comprehensive experiments wereconducted to evaluate and understand its strengths and weaknesses. The results of 13 imbalanced multiclassdatasets show that the proposed method outperforms other methods, such as initial sampling techniques,active learning, cost-sensitive learning, and reinforcement learning.