Online Class Imbalance Learning and its Applications in Fault Detection

Although class imbalance learning and online learning have been extensively studied in the literature separately, online class imbalance learning that considers the challenges of both ̄elds has not drawn much attention. It deals with data streams having very skewed class distributions, such as fault diagnosis of real-time control monitoring systems and intrusion detection in computer networks. To ̄ll in this research gap and contribute to a wide range of real-world applications, this paper ̄rst formulates online class imbalance learning problems. Based on the problem formulation, a new online learning algorithm, sampling-based online bagging (SOB), is proposed to tackle class imbalance adaptively. Then, we study how SOB and other state-ofthe-art methods can bene ̄t a class of fault detection data under various scenarios and analyze their performance in depth. Through extensive experiments, we ̄nd that SOB can balance the performance between classes very well across di®erent data domains and produce stableG-mean when learning constantly imbalanced data streams, but it is sensitive to sudden changes in class imbalance, in which case SOB's predecessor undersampling-based online bagging (UOB) is more robust.