TGT: A Novel Adversarial Guided Oversampling Technique for Handling Imbalanced Datasets

Egyptian Informatics Journal

Ayman El-Kilany¹  Ayat Mahmoud²  Farid Ali³  Sherif Mazen⁴ 

[1] Corresponding author.;Faculty of Computer Sciences, October University for Modern Sciences and Arts Cairo, Egypt;Information Systems Department, Faculty of Computers and Artificial Intelligence, Cairo University, Cairo, Egypt;Information Technology Department, Faculty of Computers and Artificial Intelligence, Beni-suef University, Egypt;

关键词: Imbalance;    Oversampling;    Classification;   

DOI  :  

来源: DOAJ

【 摘 要 】

With the volume of data increasing exponentially, there is a growing interest in helping people to benefit from their data regardless of its poor quality. One of the major data quality problems is the imbalanced distribution of different categories existing in the data. Such problem would affect the performance of any possible of analysis and mining on the data. For instance, data with an imbalanced distribution has a negative effect on the performance achieved by most traditional classification techniques. This paper proposes TGT (Train Generate Test), a novel oversampling technique for handling imbalanced datasets problem. Using different learning strategies, TGT guarantees that the generated synthetic samples reside in minority regions. TGT showed a high improvement in performance of different classification techniques when was experimented with five imbalanced datasets of different types.

【 授权许可】

Unknown