Performance Degradation of Multi-class Classification Model Due to Continuous Evolving Data Streams

Palli, Abdul Sattar; Jaafar, Jafreezal; Hashmani, Manzoor Ahmed

doi:10.1007/978-3-030-70713-2_63

Cited by 1 publication

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detecting and classifying time-changing concepts is very challenging for the classifier in the context of concept drift. A lack of predictability in the occurrence of concept drift results in a lack of capacity to train the classifier with such data, which in turn has an impact on performance (Karbasi, 2020;Palli et al, 2021). On the other hand, due to the class imbalance, it is very difficult for the classifier to learn tiny class events in cases of skew data or infrequent or uneven class distribution (Korycki & Krawczyk, 2021;Taha et al, 2021).…”

Section: Class Imbalance Scenariosmentioning

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

Section: Class Imbalance Scenariosmentioning

confidence: 99%