The processing of continuous data streams in non-stationary environments has gained increasing attention. However, supervised online learning is often limited by label availability. Furthermore, it is crucial to develop a stable and high-performance online method in non-stationary environments. To tackle these issues, we propose a dynamic chunk-based active learning framework (DCAL). This framework includes a dynamic dual-stage query strategy and an enhanced active learning model. Specifically, the proposed query strategy, referred to as DyDQS, evaluates sample value comprehensively by considering local density, uncertainty, and dynamic imbalance ratio. This approach selects samples that are both representative and uncertain, while also enhancing the likelihood of selecting minority class samples. Additionally, we introduce an enhanced active learning model, named eBLS-W, which is based on the broad learning system (BLS). We redesign the update rule of BLS and equip it with a kernel mapping to improve its robustness and performance, enabling it to better handle non-stationary environments. The effectiveness of the DyDQS, eBLS-W, and DCAL was validated through experiments on synthetic datasets with drift and real-world datasets. The results demonstrate that our approach outperforms other advanced methods in terms of robustness and accuracy.

In the field of online learning, handling imbalanced data streams with concept drift has become a substantial challenge. Research interest in the combined challenges of concept drift and class imbalance is steadily growing. When dealing with concept drift, existing methods usually adopt active detection or passive adaptation to deal with concept drift. However, a single adaptation method is relatively limited in dealing with joint concept drift. This paper introduces a novel hybrid ensemble framework (HEF-IDS) specifically designed to tackle drifting data streams while effectively accommodating class imbalance. The framework integrates an active detection module and a passive adaptation module. In the passive adaptation module, we use a hybrid sampling strategy to balance data chunks, construct a sub-ensemble classifier for each balanced chunk, and combine it with a weighted voting scheme to deal with the class imbalance and adapt to the latest concept. In the process of active detection, we design a new sample selection mechanism that stores the most informative samples in the buffer, and uses these samples for training when drift is detected to prevent catastrophic forgetting. Comparative results on artificial and real-world datasets show that the proposed HEF-IDS is superior to other advanced online classification methods.

In the current era of big data, securing computer networks and preventing cyberattacks have become a major challenge. In this regard, we present a novel approach for addressing the imbalanced problem of network traffic data. Specifically, the proposed method MC-OCBLS, leverages the maximum correntropy criterion (MCC) to develop a one-class broad learning system. The robustness of the one-class classification model is enhanced by maximizing the correlation entropy. Moreover, considering the limited generalization capability of individual models, we propose the boosting ensemble model SMC-OCBLS, which assigns higher weights to misclassified samples and classifiers with lower error rates. To increase the variety of classifiers in the ensemble framework, feature columns are randomly disrupted during training to construct different feature spaces. Training multiple hybrid classifiers using various feature spaces further enhances the accuracy and generalizability of the model. The experimental results demonstrate the superiority of the proposed model over other advanced approaches.

Feature selection is a highly regarded research area in the field of data mining, as it significantly enhances the efficiency and performance of high-dimensional data analysis by eliminating redundant and irrelevant features. Despite the ease of data acquisition, labeling data remains a laborious and expensive task. To leverage the abundance of unlabeled data, researchers have proposed various feature selection methods that operate with limited labels, including semi-supervised feature selection and unsupervised feature selection. However, a comprehensive review encompassing a thorough overview of feature selection algorithms with limited labels is lacking. To bridge this gap, this paper conducts a comprehensive exploration of feature selection methods specifically tailored to limited-label scenarios. These methods are systematically classified into two primary categories: semi-supervised and unsupervised feature selection. Additionally, by introducing a novel taxonomy and discussing future challenges, this survey aims to provide researchers with a comprehensive and in-depth understanding of feature selection in limited-label scenarios. Moreover, it aims to offer valuable insights that can guide further research and development in this domain.