A partial labeling framework for multi-class imbalanced streaming data

Arabmakki, Elaheh; Kantardzic, Mehmed; Sethi, Tegjyot Singh

doi:10.1109/ijcnn.2017.7965964

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It analyzes the data distribution from the perspectives of time and space, and presents a self-adaptive dual weighting strategy, which includes the weights built on the class imbalance ratio at the time level and the weights based on the probability density of samples at the space level. In addition, the RLS-Multi (Reduced Labeled Samples-Multiple class) [105] approach was proposed, where it uses DWM (Dynamic Weighted Majority) in an ensemble voting. It handles well for classification with multiple class imbalanced in conjunction with partially labeled (namely label missing) data stream.…”

Section: ) Pt Based Multi-label Data Stream Methodsmentioning

confidence: 99%

“…And in [117], based on a basic generator, there is another multi-label stream data generation framework. And a common method is introduced in [105], [116], [120], which models concept drifts by creating a new multi-label data stream with shuffling labels. Contrary to the aforementioned methods, authors in [35] consider two categories of label dependencies from the angle of probability, namely conditional dependence and unconditional dependence.…”

Section: Synthetic Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Multi-Label Data Stream Classification

Xiu-lin

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Nowadays, many real-world applications of our daily life generate massive volume of streaming data at a higher speed than ever before, to name a few, Web clicking data streams, sensor network data and credit transaction streams. Contrary to traditional data mining using static datasets, there are several challenges for data stream mining, for instance, finite memory, one-pass and timely reaction. In this survey, we provide a comprehensive review of existing multi-label streams mining algorithms and categorize these methods based on different perspectives, which mainly focus on the multi-label data stream classification. We first briefly summarize existing multi-label and data stream classification algorithms and discuss their merits and demerits. Secondly, we identify mining constraints on classification for multi-label streaming data, and present a comprehensive study in algorithms for multi-label data stream classification. Finally, several challenges and open issues in multi-label data stream classification are discussed, which are worthwhile to be pursued by the researchers in the future. INDEX TERMS Data stream mining, multi-label data, multi-label classification.

show abstract

Section: ) Pt Based Multi-label Data Stream Methodsmentioning

confidence: 99%

Section: Synthetic Datasetsmentioning

confidence: 99%

A Survey on Multi-Label Data Stream Classification

Xiu-lin

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Among the studies analysed in this work, 65.71 percent use an ensemble approach to adapt to the new concept. An ensemble-based approach is consisting of multiple trained classifiers (Arabmakki et al, 2017;Khandekar & Shrinath, 2022;Palli et al, 2023;Vafaie et al, 2020;Vasantha et al, 2019) when it receives a drift signal, the ensemble-based approach creates a new classifier and trains it on the latest data and adds it to the ensemble. It removes the classifier with poor performance.…”

Section: Ensemble Approachmentioning

confidence: 99%

Online Machine Learning from Non-stationary Data Streams in the Presence of Concept Drift and Class Imbalance: A Systematic Review

Palli,

Jaafar,

Gilal

et al. 2024

JICT

View full text Add to dashboard Cite

In IoT environment applications generate continuous non-stationary data streams with in-built problems of concept drift and class imbalance which cause classifier performance degradation. The imbalanced data affects the classifier during concept detection and concept adaptation. In general, for concept detection, a separate mechanism is added in parallel with the classifier to detect the concept drift called a drift detector. For concept adaptation, the classifier updates itself or trains a new classifier to replace the older one. In case, the data stream faces a class imbalance issue, the classifier may not properly adapt to the latest concept. In this survey, we study how the existing work addresses the issues of class imbalance and concept drift while learning from nonstationarydata streams. We further highlight the limitation of existing work and challenges caused by other factors of class imbalance alongwith concept drift in data stream classification. Results of our survey found that, out of 1110 studies, by using our inclusion and exclusion criteria, we were able to narrow the pool of articles down to 35 that directly addressed our study objectives. The study found that issues such as multiple concept drift types, dynamic class imbalance ratio, and multi-class imbalance in presence of concept drift are still open for further research. We also observed that, while major research efforts have been dedicated to resolving concept drift and class imbalance, not much attention has been given to with-in-class imbalance, rear examples, and borderline instances when they exist with concept drift in multi-class data. This paper concludes with some suggested future directions.

show abstract