SETL: a transfer learning based dynamic ensemble classifier;
concept drift detection in streaming data

doi:10.1007/s10586-023-04149-w

SETL: a transfer learning based dynamic ensemble classifier; concept drift detection in streaming data

2023-10-09

1

PRE

AI

DOI：10.1007/s10586-023-04149-w

Original

Original request for help

Save

Abstract

En 中文

Concept drift is one of the most prominent issues in streaming data that machine learning models need to address. Most of the research in the field of concept drift targets updating the prediction model; recovery from concept drift. A little ef; t has been put into the development of a learning system that can learn drifting concepts with minimal overhead. In this paper, a dynamic ensemble classifier is designed to detect and adapt the concept drifts in streaming data. Thereupon, a novel approach- Selective Ensemble using Transfer Learning (SETL) is proposed that has the ability to adapt the new concept of data. It employs a transfer learning and a weighted majority voting scheme to enable resource optimization. It also overcomes the issues, such as negative transfer and overfitting that may occur during the process of transfer learning. The experiments are per; med using real-world open-source datasets. The results indicate that SETL outper; ms existing state-of-the-art algorithms; most of the datasets in terms of per; mance metrics such as Accuracy, F1-score, Kappa measure, precision and recall.

Keywords:

Incremental learning

Transfer learning

Concept drift

Abrupt drift

Gradual drift

Streaming data

SETL: a transfer learning based dynamic ensemble classifier; concept drift detection in streaming data

Abstract

Journal

Organization