With the development of deep neural networks (DNNs), classifying streaming data with
concept drifts based on DNNs is becoming more and more effective. However, the …

In a streaming environment, the characteristics and labels of instances may change over
time, forming concept drifts. Previous studies on data stream learning generally assume that …

Abstract Concept drifts and class imbalance are two primary challenges in supervised data
stream classification, whereas their co-occurrence presents a more complicated learning …

Recent artificial intelligence (AI) technologies show remarkable evolution in various
academic fields and industries. However, in the real world, dynamic data lead to principal …

Reference vector adjustment approaches pose a considerable potential to strengthen the
capability of decomposition-based evolutionary many-objective algorithms in handling many …

The restricted training pattern in the standard BP requires end-to-end error propagation,
causing large memory costs and prohibiting model parallelization. Existing local training …

Uncertain changes in data streams present challenges for machine learning models to
dynamically adapt and uphold performance in real-time. Particularly, classification boundary …

Evolving concepts and imbalanced data deteriorate the learning performance of classifiers
in data streams. The performance is further affected when both issues co-exist. This paper …

Abstract Concept drifts and class imbalance are two major challenges in supervised data
stream classification, whereas their co-occurrence complicates the learning problem further …